Jinovo/language-conditioned-psychometric-harmonization-model
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

import(stage1): validate YRBS 2021 and 2023 layouts

Browse Source
This commit is contained in:
Jinotech
2026-09-20 09:04:42 +12:00
parent 64e05f42d0
commit a6df01da7e
13 changed files with 488 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files
research/stage1/audit_yrbs_primary_outcome_sources.py
+9 -9
View File
@@ -106,7 +106,7 @@ def build_audit() -> dict:
source_files.setdefault(relative, {"role": role, "sha256": sha256(path)})
full_path = PACKAGE / "full_by_year" / f"yrbs_{year}_full.parquet"
full_schema = set(pq.ParquetFile(full_path).schema_arrow.names) if year <= 2019 else set()
full_schema = set(pq.ParquetFile(full_path).schema_arrow.names) if full_path.exists() else set()
for offset, construct in enumerate(CONSTRUCTS):
official_variable = f"q{data_start + offset}"
questionnaire_number = questionnaire_start + offset
@@ -118,7 +118,7 @@ def build_audit() -> dict:
if data_start != questionnaire_start:
questionnaire_data_number_differences.add(year)
if year <= 2019:
if full_path.exists():
if official_variable not in full_schema:
raise AssertionError(f"{year} full table lacks {official_variable}")
official_counts = value_counts(full_path, official_variable)
@@ -130,8 +130,8 @@ def build_audit() -> dict:
else:
official_counts = None
previous_counts = None
code_domain_status = "not_tested_quarantined"
data_status = "quarantined_pending_import_layout_validation"
code_domain_status = "not_tested_missing_import"
data_status = "missing_import"
items.append(
{
@@ -177,8 +177,8 @@ def build_audit() -> dict:
"summary": {
"years_reviewed": 17,
"items_reviewed": len(items),
"years_available_in_full_tables": 15,
"years_quarantined": 2,
"years_available_in_full_tables": len({item["year"] for item in items if item["data_status"] == "available_full_table"}),
"years_quarantined": len({item["year"] for item in items if item["data_status"] != "available_full_table"}),
"previous_mapping_mismatch_years": sorted(mismatch_years),
"previous_mapping_mismatch_items": sum(item["mapping_status"] != "verified" for item in items),
"questionnaire_data_number_difference_years": sorted(questionnaire_data_number_differences),
@@ -188,7 +188,7 @@ def build_audit() -> dict:
"decision": {
"registry_action": "replace prior YRBS primary-outcome variable mappings with this direct-source crosswalk",
"data_action": "use verified data-user-guide variables from annual full tables; do not infer data columns from printed questionnaire numbers",
"quarantine": "retain 2021 and 2023 as metadata-only until their imports and layouts are independently validated",
"quarantine": "2021 and 2023 released from layout quarantine after independent official-SAS import validation; item review remains provisional",
"gate_1": "in_progress",
},
}
@@ -232,11 +232,11 @@ def render_markdown(audit: dict) -> str:
"",
"## Gate 1 decision",
"",
"Gate 1 remains **in progress**. The 51 YRBS primary-outcome source records now have a direct-source crosswalk and clean response options, but 2021/2023 respondent imports remain quarantined, missing reasons require a conservative rule, and two actual human reviewers have not yet signed the primary outcomes.",
"Gate 1 remains **in progress**. The 51 YRBS primary-outcome source records have a direct-source crosswalk, clean response options, and validated 1991-2023 full tables. Missing reasons still require the conservative rule, and two actual human reviewers have not yet signed the primary outcomes.",
"",
"## Reproduction",
"",
"Run `research/stage1/audit_yrbs_primary_outcome_sources.py` in the project Python environment. It verifies source hashes, checks the 1991-2019 annual Parquet schemas, and compares official versus previous mappings.",
"Run `research/stage1/import_yrbs_2021_2023.py` first, then `research/stage1/audit_yrbs_primary_outcome_sources.py`. The scripts validate official layouts, verify source hashes, check all 1991-2023 annual Parquet schemas, and compare official versus previous mappings.",
"",
]
return "\n".join(lines)
research/stage1/build_primary_outcome_package.py
+4 -6
View File
@@ -219,7 +219,7 @@ def build() -> dict[str, int]:
"response_type": source["response_type"], "language": source["language"],
"questionnaire_version": f"YRBS national questionnaire {year}",
"data_availability": source["data_status"],
"analysis_eligibility": "quarantined_pending_import_layout_validation" if year in {"2021", "2023"} else "provisional_pipeline_development_only",
"analysis_eligibility": "provisional_pipeline_development_only",
"source_file": source["questionnaire_source_file"], "source_url": "",
"page_or_section": f"{source['questionnaire_page_or_section']}; data guide {source['data_guide_page_or_section']}",
"reviewer_1": "", "reviewer_2": "", "review_status": "provisional",
@@ -238,9 +238,7 @@ def build() -> dict[str, int]:
})
for year in sorted({str(r["year"]) for r in yrbs_rows}):
if year in {"2021", "2023"}:
status = "quarantined_pending_import_layout_validation"
elif year in {"2017", "2019"}:
if year in {"2017", "2019"}:
status = "provisional_design_incomplete"
else:
status = "provisional"
@@ -253,7 +251,7 @@ def build() -> dict[str, int]:
"namespace_rule": "prefix PSU and stratum with survey year before pooling",
"design_source": next(r["data_guide_source_file"] for r in yrbs_rows if str(r["year"]) == year),
"design_status": status,
"notes": "2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.",
"notes": "2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.",
})
# NSDUH: four youth-module years. Attempt is documented but unavailable locally.
@@ -432,7 +430,7 @@ Generated from the direct-source registry and audits by `build_primary_outcome_p
- source conflicts or evidence gaps: {conflicts}
- human reviewers recorded: 0
The package does not satisfy Gate 1 by itself. Two actual human reviewers must independently sign every primary-outcome item; `responses_long.parquet` is not yet built; YRBS 2021/2023 remain quarantined; NSDUH youth attempt is absent from local public-use microdata; and several design and administered-language fields remain provisional.
The package does not satisfy Gate 1 by itself. Two actual human reviewers must independently sign every primary-outcome item; `responses_long.parquet` is not yet built; NSDUH youth attempt is absent from local public-use microdata; and several design and administered-language fields remain provisional.
"""
(STAGE1 / "primary_outcome_package.md").write_text(text, encoding="utf-8")
research/stage1/import_yrbs_2021_2023.py
+152
View File
@@ -0,0 +1,152 @@
"""Validate CDC fixed-width layouts and import quarantined YRBS 2021/2023 files."""
from __future__ import annotations
import hashlib
import json
import re
from collections import Counter
from pathlib import Path
import pyarrow as pa
import pyarrow.parquet as pq
ROOT = Path(__file__).resolve().parents[2]
SOURCE = ROOT / "Dataset" / "YRBS_National_1991_2023"
OUT = ROOT / "Dataset" / "可直接分析数据包_NSDUH_YRBS" / "YRBS" / "full_by_year"
STAGE1 = ROOT / "research" / "stage1"
YEARS = {
2021: {
"raw": SOURCE / "raw" / "YRBS_2021_National.dat",
"archive": SOURCE / "source_archive" / "2021_cdc_download" / "XXH2021_YRBS_Data.dat",
"sas": SOURCE / "source_archive" / "2021_cdc_download" / "2021XXH-SAS-Input-Program.sas",
"items": ("Q26", "Q27", "Q28"),
},
2023: {
"raw": SOURCE / "raw" / "XXH2023_YRBS_Data.dat",
"archive": SOURCE / "source_archive" / "2023_cdc_download" / "XXH2023_YRBS_Data.dat",
"sas": SOURCE / "source_archive" / "2023_cdc_download" / "2023XXH-SAS-Input-Program.sas",
"items": ("Q27", "Q28", "Q29"),
},
}
def sha256(path: Path) -> str:
digest = hashlib.sha256()
with path.open("rb") as handle:
for block in iter(lambda: handle.read(1024 * 1024), b""):
digest.update(block)
return digest.hexdigest()
def parse_layout(path: Path) -> list[dict[str, object]]:
text = path.read_text(encoding="utf-8-sig")
block = re.search(r"^\s*Input\s*$\s*(.*?);", text, flags=re.I | re.M | re.S)
if not block:
raise ValueError(f"No SAS Input block in {path}")
fields = []
pattern = re.compile(r"@(\d+)\s+([A-Za-z][A-Za-z0-9_]*)\s+(\$?)(\d+)(?:\.(\d+))?\.")
for start, name, character, width, decimals in pattern.findall(block.group(1)):
fields.append({
"start": int(start), "name": name.lower(), "width": int(width),
"character": bool(character), "decimals": int(decimals or 0),
})
if not fields:
raise ValueError(f"No fields parsed from {path}")
names = [str(field["name"]) for field in fields]
if len(names) != len(set(names)):
raise ValueError(f"Duplicate field names in {path}")
return fields
def convert(raw: str, character: bool, decimals: int):
value = raw.strip()
if not value or value == ".":
return None
if character:
return value
if decimals or "." in value:
return float(value)
return int(value)
def import_year(year: int, spec: dict[str, object]) -> dict[str, object]:
raw = spec["raw"]
archive = spec["archive"]
raw_hash = sha256(raw)
archive_hash = sha256(archive)
if raw_hash != archive_hash:
raise ValueError(f"{year}: raw file differs from CDC archive copy")
layout = parse_layout(spec["sas"])
columns = {str(field["name"]): [] for field in layout}
line_lengths = Counter()
with raw.open("r", encoding="ascii", newline="") as handle:
for source_row, line in enumerate(handle, start=1):
line = line.rstrip("\r\n")
line_lengths[len(line)] += 1
for field in layout:
start = int(field["start"]) - 1
width = int(field["width"])
columns[str(field["name"])].append(convert(line[start : start + width], bool(field["character"]), int(field["decimals"])))
if set(line_lengths) != {421}:
raise ValueError(f"{year}: unexpected record lengths {dict(line_lengths)}")
count = sum(line_lengths.values())
table_data = {"survey_year": [year] * count, "source_row": list(range(1, count + 1))}
table_data.update(columns)
table = pa.table(table_data)
output = OUT / f"yrbs_{year}_full.parquet"
pq.write_table(table, output, compression="zstd")
reread = pq.read_table(output)
if reread.num_rows != count or reread.num_columns != len(table_data):
raise ValueError(f"{year}: Parquet round-trip shape mismatch")
item_counts = {}
domains = {}
for item in spec["items"]:
values = columns[item.lower()]
counts = Counter("<missing>" if value is None else str(value) for value in values)
item_counts[item] = dict(sorted(counts.items()))
observed = {value for value in values if value is not None}
allowed = {"1", "2"} if item != spec["items"][2] else {"1", "2", "3", "4", "5"}
domains[item] = "passed" if {str(v) for v in observed} <= allowed else "failed"
design_nonmissing = {name: sum(value is not None for value in columns[name]) for name in ("weight", "stratum", "psu")}
return {
"year": year, "source_file": str(raw.relative_to(ROOT)).replace("\\", "/"),
"sas_layout": str(Path(spec["sas"]).relative_to(ROOT)).replace("\\", "/"),
"sha256": raw_hash, "archive_copy_identical": True, "record_length": 421,
"rows": count, "columns": len(table_data), "layout_fields": len(layout),
"output_file": str(output.relative_to(ROOT)).replace("\\", "/"),
"parquet_roundtrip": "passed", "primary_outcome_value_counts": item_counts,
"primary_outcome_domains": domains, "design_nonmissing": design_nonmissing,
"status": "import_validated",
}
def main() -> None:
results = [import_year(year, spec) for year, spec in YEARS.items()]
audit = {
"schema_version": "1.0", "generated_on": "2026-09-20",
"status": "passed_for_import; still provisional for human item review",
"method": "Official CDC SAS fixed-width Input positions; raw/archive SHA-256 identity; record-length, domain, design-field, and Parquet round-trip checks.",
"years": results,
"decision": "YRBS 2021 and 2023 respondent files are released from import-layout quarantine. Primary-outcome items remain provisional pending two human reviewers.",
}
(STAGE1 / "yrbs_2021_2023_import_audit.json").write_text(json.dumps(audit, indent=2, ensure_ascii=False) + "\n", encoding="utf-8")
lines = ["# YRBS 2021/2023 official-layout import audit", "", audit["decision"], ""]
for result in results:
lines.extend([
f"## {result['year']}", "",
f"- rows × columns: {result['rows']:,} × {result['columns']}",
f"- raw file identical to archived CDC download: yes (`{result['sha256']}`)",
f"- fixed record length: {result['record_length']} bytes for every row",
f"- design completeness: `{result['design_nonmissing']}`",
f"- primary outcome domains: `{result['primary_outcome_domains']}`",
f"- output: `{result['output_file']}`", "",
])
lines.extend(["## Boundary", "", "This resolves the import-layout quarantine only. It does not substitute for two actual human item reviewers or approve design-based variance estimation.", ""])
(STAGE1 / "yrbs_2021_2023_import_audit.md").write_text("\n".join(lines), encoding="utf-8")
print(json.dumps(audit, indent=2, ensure_ascii=False))
if __name__ == "__main__":
main()
research/stage1/item_bank.csv
+6 -6
View File
@@ -65,12 +65,12 @@ YRBS::2017::Q28,YRBS::suicide_attempt::past_12_months,YRBS::2017,YRBS_NATIONAL::
YRBS::2019::Q26,YRBS::suicide_ideation::past_12_months,YRBS::2019,YRBS_NATIONAL::2019,YRBS,United States,2019,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q26,"During the past 12 months, did you ever seriously consider attempting suicide?",suicide_ideation,past 12 months,binary,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2019,available_full_table,provisional_pipeline_development_only,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2019_YRBS-National-HS-Questionnaire.pdf,,page 8; data guide pages 27-28,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2019::Q27,YRBS::suicide_plan::past_12_months,YRBS::2019,YRBS_NATIONAL::2019,YRBS,United States,2019,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q27,"During the past 12 months, did you make a plan about how you would attempt suicide?",suicide_plan,past 12 months,binary,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2019,available_full_table,provisional_pipeline_development_only,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2019_YRBS-National-HS-Questionnaire.pdf,,page 8; data guide pages 27-28,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2019::Q28,YRBS::suicide_attempt::past_12_months,YRBS::2019,YRBS_NATIONAL::2019,YRBS,United States,2019,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q28,"During the past 12 months, how many times did you actually attempt suicide?",suicide_attempt,past 12 months,ordinal_frequency,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2019,available_full_table,provisional_pipeline_development_only,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2019_YRBS-National-HS-Questionnaire.pdf,,page 8; data guide pages 27-28,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2021::Q26,YRBS::suicide_ideation::past_12_months,YRBS::2021,YRBS_NATIONAL::2021,YRBS,United States,2021,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q26,"During the past 12 months, did you ever seriously consider attempting suicide?",suicide_ideation,past 12 months,binary,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2021,quarantined_pending_import_layout_validation,quarantined_pending_import_layout_validation,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2021-YRBS-National-HS-Questionnaire.pdf,,page 8; data guide page 28,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2021::Q27,YRBS::suicide_plan::past_12_months,YRBS::2021,YRBS_NATIONAL::2021,YRBS,United States,2021,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q27,"During the past 12 months, did you make a plan about how you would attempt suicide?",suicide_plan,past 12 months,binary,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2021,quarantined_pending_import_layout_validation,quarantined_pending_import_layout_validation,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2021-YRBS-National-HS-Questionnaire.pdf,,page 8; data guide page 28,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2021::Q28,YRBS::suicide_attempt::past_12_months,YRBS::2021,YRBS_NATIONAL::2021,YRBS,United States,2021,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q28,"During the past 12 months, how many times did you actually attempt suicide?",suicide_attempt,past 12 months,ordinal_frequency,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2021,quarantined_pending_import_layout_validation,quarantined_pending_import_layout_validation,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2021-YRBS-National-HS-Questionnaire.pdf,,page 8; data guide page 28,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2023::Q27,YRBS::suicide_ideation::past_12_months,YRBS::2023,YRBS_NATIONAL::2023,YRBS,United States,2023,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q27,"During the past 12 months, did you ever seriously consider attempting suicide?",suicide_ideation,past 12 months,binary,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2023,quarantined_pending_import_layout_validation,quarantined_pending_import_layout_validation,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2023_YRBS_National_HS_Questionnaire.pdf,,page 9; data guide page 29,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2023::Q28,YRBS::suicide_plan::past_12_months,YRBS::2023,YRBS_NATIONAL::2023,YRBS,United States,2023,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q28,"During the past 12 months, did you make a plan about how you would attempt suicide?",suicide_plan,past 12 months,binary,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2023,quarantined_pending_import_layout_validation,quarantined_pending_import_layout_validation,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2023_YRBS_National_HS_Questionnaire.pdf,,page 9; data guide page 29,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2023::Q29,YRBS::suicide_attempt::past_12_months,YRBS::2023,YRBS_NATIONAL::2023,YRBS,United States,2023,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q29,"During the past 12 months, how many times did you actually attempt suicide?",suicide_attempt,past 12 months,ordinal_frequency,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2023,quarantined_pending_import_layout_validation,quarantined_pending_import_layout_validation,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2023_YRBS_National_HS_Questionnaire.pdf,,page 9; data guide page 29,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2021::Q26,YRBS::suicide_ideation::past_12_months,YRBS::2021,YRBS_NATIONAL::2021,YRBS,United States,2021,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q26,"During the past 12 months, did you ever seriously consider attempting suicide?",suicide_ideation,past 12 months,binary,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2021,available_full_table,provisional_pipeline_development_only,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2021-YRBS-National-HS-Questionnaire.pdf,,page 8; data guide page 28,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2021::Q27,YRBS::suicide_plan::past_12_months,YRBS::2021,YRBS_NATIONAL::2021,YRBS,United States,2021,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q27,"During the past 12 months, did you make a plan about how you would attempt suicide?",suicide_plan,past 12 months,binary,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2021,available_full_table,provisional_pipeline_development_only,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2021-YRBS-National-HS-Questionnaire.pdf,,page 8; data guide page 28,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2021::Q28,YRBS::suicide_attempt::past_12_months,YRBS::2021,YRBS_NATIONAL::2021,YRBS,United States,2021,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q28,"During the past 12 months, how many times did you actually attempt suicide?",suicide_attempt,past 12 months,ordinal_frequency,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2021,available_full_table,provisional_pipeline_development_only,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2021-YRBS-National-HS-Questionnaire.pdf,,page 8; data guide page 28,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2023::Q27,YRBS::suicide_ideation::past_12_months,YRBS::2023,YRBS_NATIONAL::2023,YRBS,United States,2023,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q27,"During the past 12 months, did you ever seriously consider attempting suicide?",suicide_ideation,past 12 months,binary,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2023,available_full_table,provisional_pipeline_development_only,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2023_YRBS_National_HS_Questionnaire.pdf,,page 9; data guide page 29,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2023::Q28,YRBS::suicide_plan::past_12_months,YRBS::2023,YRBS_NATIONAL::2023,YRBS,United States,2023,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q28,"During the past 12 months, did you make a plan about how you would attempt suicide?",suicide_plan,past 12 months,binary,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2023,available_full_table,provisional_pipeline_development_only,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2023_YRBS_National_HS_Questionnaire.pdf,,page 9; data guide page 29,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
YRBS::2023::Q29,YRBS::suicide_attempt::past_12_months,YRBS::2023,YRBS_NATIONAL::2023,YRBS,United States,2023,national,students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review,Q29,"During the past 12 months, how many times did you actually attempt suicide?",suicide_attempt,past 12 months,ordinal_frequency,English questionnaire source; actual accommodation/language coverage not established by this audit,YRBS national questionnaire 2023,available_full_table,provisional_pipeline_development_only,Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2023_YRBS_National_HS_Questionnaire.pdf,,page 9; data guide page 29,,,provisional,blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
NSDUH::2021::YUSUITHK,NSDUH::suicide_ideation::past_12_months,NSDUH::2021,NSDUH_YOUTH::2021,NSDUH,United States,2021,national household survey youth module,adolescents aged 12-17; final eligibility and skip logic require annual guide sign-off,YUSUITHK,"The next few questions are about thoughts of suicide. At any time in the past 12 months, that is from [DATEFILL] up to and including today, did you seriously think about trying to kill yourself ?",suicide_ideation,past 12 months,categorical_binary_with_explicit_uncertainty,English source metadata; administered-language/accommodation coverage not established,NSDUH 2021 youth module,available_in_local_public_use_table,provisional_pipeline_development_only,Dataset/可直接分析数据包_NSDUH_YRBS/NSDUH/nsduh_complete_variable_dictionary.csv,https://datatools.samhsa.gov/api/surveys/NSDUH-2021-DS0001/?format=json,YUSUITHK,,,provisional,Keep 'not sure' and refusal/nonresponse distinct until skip and missing rules are verified.
NSDUH::2021::YUSUIPLN,NSDUH::suicide_plan::past_12_months,NSDUH::2021,NSDUH_YOUTH::2021,NSDUH,United States,2021,national household survey youth module,adolescents aged 12-17; final eligibility and skip logic require annual guide sign-off,YUSUIPLN,"During the past 12 months, did you make any plans to kill yourself?",suicide_plan,past 12 months,categorical_binary_with_explicit_uncertainty,English source metadata; administered-language/accommodation coverage not established,NSDUH 2021 youth module,available_in_local_public_use_table,provisional_pipeline_development_only,Dataset/可直接分析数据包_NSDUH_YRBS/NSDUH/nsduh_complete_variable_dictionary.csv,https://datatools.samhsa.gov/api/surveys/NSDUH-2021-DS0001/?format=json,YUSUIPLN,,,provisional,Keep 'not sure' and refusal/nonresponse distinct until skip and missing rules are verified.
NSDUH::2022::YUSUITHK,NSDUH::suicide_ideation::past_12_months,NSDUH::2022,NSDUH_YOUTH::2022,NSDUH,United States,2022,national household survey youth module,adolescents aged 12-17; final eligibility and skip logic require annual guide sign-off,YUSUITHK,"Note: Beginning in 2022, questions YSUI01, YCOV9, YSUI02, YCOV10, YSUI03, YCOV11, YSUI04, and YSUI05 were moved from the youth mental health service utilization section to the youth experiences section. The next few questions are about thoughts of suicide. You can answer “I’m not sure” or “I don’t want to answer” to any question. At any time in the past 12 months, that is from [DATEFILL] up to and including today, did you seriously think about trying to kill yourself?",suicide_ideation,past 12 months,categorical_binary_with_explicit_uncertainty,English source metadata; administered-language/accommodation coverage not established,NSDUH 2022 youth module,available_in_local_public_use_table,provisional_pipeline_development_only,Dataset/可直接分析数据包_NSDUH_YRBS/NSDUH/nsduh_complete_variable_dictionary.csv,https://datatools.samhsa.gov/api/surveys/NSDUH-2022-DS0001/?format=json,YUSUITHK,,,provisional,Keep 'not sure' and refusal/nonresponse distinct until skip and missing rules are verified.
1 item_version_id item_family_id survey_id component_id survey country year scope population source_variable question_text construct time_window response_type language questionnaire_version data_availability analysis_eligibility source_file source_url page_or_section reviewer_1 reviewer_2 review_status notes
65 YRBS::2019::Q26 YRBS::suicide_ideation::past_12_months YRBS::2019 YRBS_NATIONAL::2019 YRBS United States 2019 national students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review Q26 During the past 12 months, did you ever seriously consider attempting suicide? suicide_ideation past 12 months binary English questionnaire source; actual accommodation/language coverage not established by this audit YRBS national questionnaire 2019 available_full_table provisional_pipeline_development_only Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2019_YRBS-National-HS-Questionnaire.pdf page 8; data guide pages 27-28 provisional blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
66 YRBS::2019::Q27 YRBS::suicide_plan::past_12_months YRBS::2019 YRBS_NATIONAL::2019 YRBS United States 2019 national students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review Q27 During the past 12 months, did you make a plan about how you would attempt suicide? suicide_plan past 12 months binary English questionnaire source; actual accommodation/language coverage not established by this audit YRBS national questionnaire 2019 available_full_table provisional_pipeline_development_only Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2019_YRBS-National-HS-Questionnaire.pdf page 8; data guide pages 27-28 provisional blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
67 YRBS::2019::Q28 YRBS::suicide_attempt::past_12_months YRBS::2019 YRBS_NATIONAL::2019 YRBS United States 2019 national students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review Q28 During the past 12 months, how many times did you actually attempt suicide? suicide_attempt past 12 months ordinal_frequency English questionnaire source; actual accommodation/language coverage not established by this audit YRBS national questionnaire 2019 available_full_table provisional_pipeline_development_only Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2019_YRBS-National-HS-Questionnaire.pdf page 8; data guide pages 27-28 provisional blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
68 YRBS::2021::Q26 YRBS::suicide_ideation::past_12_months YRBS::2021 YRBS_NATIONAL::2021 YRBS United States 2021 national students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review Q26 During the past 12 months, did you ever seriously consider attempting suicide? suicide_ideation past 12 months binary English questionnaire source; actual accommodation/language coverage not established by this audit YRBS national questionnaire 2021 quarantined_pending_import_layout_validation available_full_table quarantined_pending_import_layout_validation provisional_pipeline_development_only Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2021-YRBS-National-HS-Questionnaire.pdf page 8; data guide page 28 provisional blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
69 YRBS::2021::Q27 YRBS::suicide_plan::past_12_months YRBS::2021 YRBS_NATIONAL::2021 YRBS United States 2021 national students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review Q27 During the past 12 months, did you make a plan about how you would attempt suicide? suicide_plan past 12 months binary English questionnaire source; actual accommodation/language coverage not established by this audit YRBS national questionnaire 2021 quarantined_pending_import_layout_validation available_full_table quarantined_pending_import_layout_validation provisional_pipeline_development_only Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2021-YRBS-National-HS-Questionnaire.pdf page 8; data guide page 28 provisional blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
70 YRBS::2021::Q28 YRBS::suicide_attempt::past_12_months YRBS::2021 YRBS_NATIONAL::2021 YRBS United States 2021 national students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review Q28 During the past 12 months, how many times did you actually attempt suicide? suicide_attempt past 12 months ordinal_frequency English questionnaire source; actual accommodation/language coverage not established by this audit YRBS national questionnaire 2021 quarantined_pending_import_layout_validation available_full_table quarantined_pending_import_layout_validation provisional_pipeline_development_only Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2021-YRBS-National-HS-Questionnaire.pdf page 8; data guide page 28 provisional blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
71 YRBS::2023::Q27 YRBS::suicide_ideation::past_12_months YRBS::2023 YRBS_NATIONAL::2023 YRBS United States 2023 national students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review Q27 During the past 12 months, did you ever seriously consider attempting suicide? suicide_ideation past 12 months binary English questionnaire source; actual accommodation/language coverage not established by this audit YRBS national questionnaire 2023 quarantined_pending_import_layout_validation available_full_table quarantined_pending_import_layout_validation provisional_pipeline_development_only Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2023_YRBS_National_HS_Questionnaire.pdf page 9; data guide page 29 provisional blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
72 YRBS::2023::Q28 YRBS::suicide_plan::past_12_months YRBS::2023 YRBS_NATIONAL::2023 YRBS United States 2023 national students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review Q28 During the past 12 months, did you make a plan about how you would attempt suicide? suicide_plan past 12 months binary English questionnaire source; actual accommodation/language coverage not established by this audit YRBS national questionnaire 2023 quarantined_pending_import_layout_validation available_full_table quarantined_pending_import_layout_validation provisional_pipeline_development_only Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2023_YRBS_National_HS_Questionnaire.pdf page 9; data guide page 29 provisional blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
73 YRBS::2023::Q29 YRBS::suicide_attempt::past_12_months YRBS::2023 YRBS_NATIONAL::2023 YRBS United States 2023 national students in grades 9-12 attending public and private schools in the United States; detailed eligibility remains subject to annual design review Q29 During the past 12 months, how many times did you actually attempt suicide? suicide_attempt past 12 months ordinal_frequency English questionnaire source; actual accommodation/language coverage not established by this audit YRBS national questionnaire 2023 quarantined_pending_import_layout_validation available_full_table quarantined_pending_import_layout_validation provisional_pipeline_development_only Dataset/YRBS_National_1991_2023/documentation/Questionnaire/2023_YRBS_National_HS_Questionnaire.pdf page 9; data guide page 29 provisional blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason
74 NSDUH::2021::YUSUITHK NSDUH::suicide_ideation::past_12_months NSDUH::2021 NSDUH_YOUTH::2021 NSDUH United States 2021 national household survey youth module adolescents aged 12-17; final eligibility and skip logic require annual guide sign-off YUSUITHK The next few questions are about thoughts of suicide. At any time in the past 12 months, that is from [DATEFILL] up to and including today, did you seriously think about trying to kill yourself ? suicide_ideation past 12 months categorical_binary_with_explicit_uncertainty English source metadata; administered-language/accommodation coverage not established NSDUH 2021 youth module available_in_local_public_use_table provisional_pipeline_development_only Dataset/可直接分析数据包_NSDUH_YRBS/NSDUH/nsduh_complete_variable_dictionary.csv https://datatools.samhsa.gov/api/surveys/NSDUH-2021-DS0001/?format=json YUSUITHK provisional Keep 'not sure' and refusal/nonresponse distinct until skip and missing rules are verified.
75 NSDUH::2021::YUSUIPLN NSDUH::suicide_plan::past_12_months NSDUH::2021 NSDUH_YOUTH::2021 NSDUH United States 2021 national household survey youth module adolescents aged 12-17; final eligibility and skip logic require annual guide sign-off YUSUIPLN During the past 12 months, did you make any plans to kill yourself? suicide_plan past 12 months categorical_binary_with_explicit_uncertainty English source metadata; administered-language/accommodation coverage not established NSDUH 2021 youth module available_in_local_public_use_table provisional_pipeline_development_only Dataset/可直接分析数据包_NSDUH_YRBS/NSDUH/nsduh_complete_variable_dictionary.csv https://datatools.samhsa.gov/api/surveys/NSDUH-2021-DS0001/?format=json YUSUIPLN provisional Keep 'not sure' and refusal/nonresponse distinct until skip and missing rules are verified.
76 NSDUH::2022::YUSUITHK NSDUH::suicide_ideation::past_12_months NSDUH::2022 NSDUH_YOUTH::2022 NSDUH United States 2022 national household survey youth module adolescents aged 12-17; final eligibility and skip logic require annual guide sign-off YUSUITHK Note: Beginning in 2022, questions YSUI01, YCOV9, YSUI02, YCOV10, YSUI03, YCOV11, YSUI04, and YSUI05 were moved from the youth mental health service utilization section to the youth experiences section. The next few questions are about thoughts of suicide. You can answer “I’m not sure” or “I don’t want to answer” to any question. At any time in the past 12 months, that is from [DATEFILL] up to and including today, did you seriously think about trying to kill yourself? suicide_ideation past 12 months categorical_binary_with_explicit_uncertainty English source metadata; administered-language/accommodation coverage not established NSDUH 2022 youth module available_in_local_public_use_table provisional_pipeline_development_only Dataset/可直接分析数据包_NSDUH_YRBS/NSDUH/nsduh_complete_variable_dictionary.csv https://datatools.samhsa.gov/api/surveys/NSDUH-2022-DS0001/?format=json YUSUITHK provisional Keep 'not sure' and refusal/nonresponse distinct until skip and missing rules are verified.
research/stage1/primary_outcome_package.md
+1 -1
View File
@@ -10,4 +10,4 @@ Generated from the direct-source registry and audits by `build_primary_outcome_p
- source conflicts or evidence gaps: 32
- human reviewers recorded: 0
The package does not satisfy Gate 1 by itself. Two actual human reviewers must independently sign every primary-outcome item; `responses_long.parquet` is not yet built; YRBS 2021/2023 remain quarantined; NSDUH youth attempt is absent from local public-use microdata; and several design and administered-language fields remain provisional.
The package does not satisfy Gate 1 by itself. Two actual human reviewers must independently sign every primary-outcome item; `responses_long.parquet` is not yet built; NSDUH youth attempt is absent from local public-use microdata; and several design and administered-language fields remain provisional.
research/stage1/primary_outcome_registry.json
+6 -6
View File
@@ -1513,7 +1513,7 @@
"previous_registry_variable": "Q28",
"mapping_status": "verified",
"present_in_local_data": false,
"data_status": "quarantined_pending_import_layout_validation",
"data_status": "available_full_table",
"source_verification_status": "direct_questionnaire_and_data_user_guide_reviewed",
"review_status": "provisional",
"reviewer_1": null,
@@ -1543,7 +1543,7 @@
"previous_registry_variable": "Q26",
"mapping_status": "verified",
"present_in_local_data": false,
"data_status": "quarantined_pending_import_layout_validation",
"data_status": "available_full_table",
"source_verification_status": "direct_questionnaire_and_data_user_guide_reviewed",
"review_status": "provisional",
"reviewer_1": null,
@@ -1573,7 +1573,7 @@
"previous_registry_variable": "Q27",
"mapping_status": "verified",
"present_in_local_data": false,
"data_status": "quarantined_pending_import_layout_validation",
"data_status": "available_full_table",
"source_verification_status": "direct_questionnaire_and_data_user_guide_reviewed",
"review_status": "provisional",
"reviewer_1": null,
@@ -1606,7 +1606,7 @@
"previous_registry_variable": "Q29",
"mapping_status": "verified",
"present_in_local_data": false,
"data_status": "quarantined_pending_import_layout_validation",
"data_status": "available_full_table",
"source_verification_status": "direct_questionnaire_and_data_user_guide_reviewed",
"review_status": "provisional",
"reviewer_1": null,
@@ -1636,7 +1636,7 @@
"previous_registry_variable": "Q27",
"mapping_status": "verified",
"present_in_local_data": false,
"data_status": "quarantined_pending_import_layout_validation",
"data_status": "available_full_table",
"source_verification_status": "direct_questionnaire_and_data_user_guide_reviewed",
"review_status": "provisional",
"reviewer_1": null,
@@ -1666,7 +1666,7 @@
"previous_registry_variable": "Q28",
"mapping_status": "verified",
"present_in_local_data": false,
"data_status": "quarantined_pending_import_layout_validation",
"data_status": "available_full_table",
"source_verification_status": "direct_questionnaire_and_data_user_guide_reviewed",
"review_status": "provisional",
"reviewer_1": null,
research/stage1/survey_design.csv
+17 -17
View File
@@ -6,23 +6,23 @@ GSHS::JAM_2023_GSHS_v01,JAM_2023_GSHS_v01::jam_st_cath_2023,GSHS,Jamaica,2023,sc
GSHS::MNG_2023_GSHS_v01,MNG_2023_GSHS_v01::mng2023,GSHS,Mongolia,2023,school-attending students; exact sampled ages/grades remain pending component source review,sample_weight,sampling_psu,sampling_stratum,pending official component design review,prefix PSU and stratum with component_id before pooling,Dataset/GSHS-全球学生健康调查数据/GSHS/Questionnaire/GSHS Per Country/Mongolia 2023/Mongolia-GSHS-Questionnaire-ENGLISH.docx,provisional,Canonical fields are present; observed full GSHS table has 20 missing values in each design field overall. Component-specific design validity remains to be reviewed.
GSHS::SLB_2023_GSHS_v01,SLB_2023_GSHS_v01::slb_2023,GSHS,Solomon Islands,2023,school-going adolescents aged 13-17 years; Form 1-Form 6; all students in selected classes eligible,sample_weight,sampling_psu,sampling_stratum,pending official component design review,prefix PSU and stratum with component_id before pooling,https://extranet.who.int/ncdsmicrodata/index.php/catalog/992,provisional,Canonical fields are present; observed full GSHS table has 20 missing values in each design field overall. Component-specific design validity remains to be reviewed.
GSHS::WLF_2023_GSHS_v01,WLF_2023_GSHS_v01::wlf_2023,GSHS,Wallis and Futuna,2023,school-attending students; exact sampled ages/grades remain pending component source review,sample_weight,sampling_psu,sampling_stratum,pending official component design review,prefix PSU and stratum with component_id before pooling,Dataset/GSHS-全球学生健康调查数据/GSHS/Questionnaire/GSHS Per Country/Wallis and Futuna 2023/Wallis and Futuna - GSHS Questionnaire - Final - French.docx,provisional,Canonical fields are present; observed full GSHS table has 20 missing values in each design field overall. Component-specific design validity remains to be reviewed.
YRBS::1991,YRBS_NATIONAL::1991,YRBS,United States,1991,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1991_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::1993,YRBS_NATIONAL::1993,YRBS,United States,1993,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1993_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::1995,YRBS_NATIONAL::1995,YRBS,United States,1995,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1995_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::1997,YRBS_NATIONAL::1997,YRBS,United States,1997,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1997_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::1999,YRBS_NATIONAL::1999,YRBS,United States,1999,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1999_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::2001,YRBS_NATIONAL::2001,YRBS,United States,2001,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2001_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::2003,YRBS_NATIONAL::2003,YRBS,United States,2003,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2003_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::2005,YRBS_NATIONAL::2005,YRBS,United States,2005,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2005_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::2007,YRBS_NATIONAL::2007,YRBS,United States,2007,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2007_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::2009,YRBS_NATIONAL::2009,YRBS,United States,2009,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2009_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::2011,YRBS_NATIONAL::2011,YRBS,United States,2011,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2011_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::2013,YRBS_NATIONAL::2013,YRBS,United States,2013,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2013_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::2015,YRBS_NATIONAL::2015,YRBS,United States,2015,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/2015_yrbs-data-users_guide_smy_combined.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::2017,YRBS_NATIONAL::2017,YRBS,United States,2017,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/2017_YRBS_Data_Users_Guide.pdf,provisional_design_incomplete,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::2019,YRBS_NATIONAL::2019,YRBS,United States,2019,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/2019_National_YRBS_Data_Users_Guide.pdf,provisional_design_incomplete,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::2021,YRBS_NATIONAL::2021,YRBS,United States,2021,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/2021_YRBS_Data_Users_Guide_508.pdf,quarantined_pending_import_layout_validation,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::2023,YRBS_NATIONAL::2023,YRBS,United States,2023,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/2023_National_YRBS_Data_Users_Guide508.pdf,quarantined_pending_import_layout_validation,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined.
YRBS::1991,YRBS_NATIONAL::1991,YRBS,United States,1991,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1991_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::1993,YRBS_NATIONAL::1993,YRBS,United States,1993,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1993_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::1995,YRBS_NATIONAL::1995,YRBS,United States,1995,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1995_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::1997,YRBS_NATIONAL::1997,YRBS,United States,1997,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1997_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::1999,YRBS_NATIONAL::1999,YRBS,United States,1999,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1999_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::2001,YRBS_NATIONAL::2001,YRBS,United States,2001,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2001_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::2003,YRBS_NATIONAL::2003,YRBS,United States,2003,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2003_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::2005,YRBS_NATIONAL::2005,YRBS,United States,2005,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2005_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::2007,YRBS_NATIONAL::2007,YRBS,United States,2007,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2007_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::2009,YRBS_NATIONAL::2009,YRBS,United States,2009,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2009_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::2011,YRBS_NATIONAL::2011,YRBS,United States,2011,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2011_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::2013,YRBS_NATIONAL::2013,YRBS,United States,2013,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2013_National_User_Guide.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::2015,YRBS_NATIONAL::2015,YRBS,United States,2015,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/2015_yrbs-data-users_guide_smy_combined.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::2017,YRBS_NATIONAL::2017,YRBS,United States,2017,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/2017_YRBS_Data_Users_Guide.pdf,provisional_design_incomplete,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::2019,YRBS_NATIONAL::2019,YRBS,United States,2019,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/2019_National_YRBS_Data_Users_Guide.pdf,provisional_design_incomplete,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::2021,YRBS_NATIONAL::2021,YRBS,United States,2021,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/2021_YRBS_Data_Users_Guide_508.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
YRBS::2023,YRBS_NATIONAL::2023,YRBS,United States,2023,students in grades 9-12 attending public and private schools in the United States,weight,psu,stratum,Taylor linearization candidate; annual official design confirmation pending,prefix PSU and stratum with survey year before pooling,Dataset/YRBS_National_1991_2023/documentation/UserGuide/2023_National_YRBS_Data_Users_Guide508.pdf,provisional,2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
NSDUH::2021,NSDUH_YOUTH::2021,NSDUH,United States,2021,adolescents aged 12-17,ANALWT2_C (year-specific C1-C4 mapping unresolved),VEREP,VESTR_C,pending official combined-file guide review,prefix variance units with survey year before pooling,Dataset/可直接分析数据包_NSDUH_YRBS/README.md; official annual/combined-file guide pending,provisional_weight_mapping_unresolved,All four ANALWT2_C1-C4 fields are positive in every local year; do not select a weight by suffix without the official year-specific mapping.
NSDUH::2022,NSDUH_YOUTH::2022,NSDUH,United States,2022,adolescents aged 12-17,ANALWT2_C (year-specific C1-C4 mapping unresolved),VEREP,VESTR_C,pending official combined-file guide review,prefix variance units with survey year before pooling,Dataset/可直接分析数据包_NSDUH_YRBS/README.md; official annual/combined-file guide pending,provisional_weight_mapping_unresolved,All four ANALWT2_C1-C4 fields are positive in every local year; do not select a weight by suffix without the official year-specific mapping.
NSDUH::2023,NSDUH_YOUTH::2023,NSDUH,United States,2023,adolescents aged 12-17,ANALWT2_C (year-specific C1-C4 mapping unresolved),VEREP,VESTR_C,pending official combined-file guide review,prefix variance units with survey year before pooling,Dataset/可直接分析数据包_NSDUH_YRBS/README.md; official annual/combined-file guide pending,provisional_weight_mapping_unresolved,All four ANALWT2_C1-C4 fields are positive in every local year; do not select a weight by suffix without the official year-specific mapping.
1 survey_id component_id survey country year population weight_field psu_field stratum_field variance_method namespace_rule design_source design_status notes
6 GSHS::MNG_2023_GSHS_v01 MNG_2023_GSHS_v01::mng2023 GSHS Mongolia 2023 school-attending students; exact sampled ages/grades remain pending component source review sample_weight sampling_psu sampling_stratum pending official component design review prefix PSU and stratum with component_id before pooling Dataset/GSHS-全球学生健康调查数据/GSHS/Questionnaire/GSHS Per Country/Mongolia 2023/Mongolia-GSHS-Questionnaire-ENGLISH.docx provisional Canonical fields are present; observed full GSHS table has 20 missing values in each design field overall. Component-specific design validity remains to be reviewed.
7 GSHS::SLB_2023_GSHS_v01 SLB_2023_GSHS_v01::slb_2023 GSHS Solomon Islands 2023 school-going adolescents aged 13-17 years; Form 1-Form 6; all students in selected classes eligible sample_weight sampling_psu sampling_stratum pending official component design review prefix PSU and stratum with component_id before pooling https://extranet.who.int/ncdsmicrodata/index.php/catalog/992 provisional Canonical fields are present; observed full GSHS table has 20 missing values in each design field overall. Component-specific design validity remains to be reviewed.
8 GSHS::WLF_2023_GSHS_v01 WLF_2023_GSHS_v01::wlf_2023 GSHS Wallis and Futuna 2023 school-attending students; exact sampled ages/grades remain pending component source review sample_weight sampling_psu sampling_stratum pending official component design review prefix PSU and stratum with component_id before pooling Dataset/GSHS-全球学生健康调查数据/GSHS/Questionnaire/GSHS Per Country/Wallis and Futuna 2023/Wallis and Futuna - GSHS Questionnaire - Final - French.docx provisional Canonical fields are present; observed full GSHS table has 20 missing values in each design field overall. Component-specific design validity remains to be reviewed.
9 YRBS::1991 YRBS_NATIONAL::1991 YRBS United States 1991 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1991_National_User_Guide.pdf provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
10 YRBS::1993 YRBS_NATIONAL::1993 YRBS United States 1993 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1993_National_User_Guide.pdf provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
11 YRBS::1995 YRBS_NATIONAL::1995 YRBS United States 1995 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1995_National_User_Guide.pdf provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
12 YRBS::1997 YRBS_NATIONAL::1997 YRBS United States 1997 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1997_National_User_Guide.pdf provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
13 YRBS::1999 YRBS_NATIONAL::1999 YRBS United States 1999 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_1999_National_User_Guide.pdf provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
14 YRBS::2001 YRBS_NATIONAL::2001 YRBS United States 2001 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2001_National_User_Guide.pdf provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
15 YRBS::2003 YRBS_NATIONAL::2003 YRBS United States 2003 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2003_National_User_Guide.pdf provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
16 YRBS::2005 YRBS_NATIONAL::2005 YRBS United States 2005 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2005_National_User_Guide.pdf provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
17 YRBS::2007 YRBS_NATIONAL::2007 YRBS United States 2007 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2007_National_User_Guide.pdf provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
18 YRBS::2009 YRBS_NATIONAL::2009 YRBS United States 2009 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2009_National_User_Guide.pdf provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
19 YRBS::2011 YRBS_NATIONAL::2011 YRBS United States 2011 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2011_National_User_Guide.pdf provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
20 YRBS::2013 YRBS_NATIONAL::2013 YRBS United States 2013 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/YRBS_2013_National_User_Guide.pdf provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
21 YRBS::2015 YRBS_NATIONAL::2015 YRBS United States 2015 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/2015_yrbs-data-users_guide_smy_combined.pdf provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
22 YRBS::2017 YRBS_NATIONAL::2017 YRBS United States 2017 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/2017_YRBS_Data_Users_Guide.pdf provisional_design_incomplete 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
23 YRBS::2019 YRBS_NATIONAL::2019 YRBS United States 2019 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/2019_National_YRBS_Data_Users_Guide.pdf provisional_design_incomplete 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
24 YRBS::2021 YRBS_NATIONAL::2021 YRBS United States 2021 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/2021_YRBS_Data_Users_Guide_508.pdf quarantined_pending_import_layout_validation provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
25 YRBS::2023 YRBS_NATIONAL::2023 YRBS United States 2023 students in grades 9-12 attending public and private schools in the United States weight psu stratum Taylor linearization candidate; annual official design confirmation pending prefix PSU and stratum with survey year before pooling Dataset/YRBS_National_1991_2023/documentation/UserGuide/2023_National_YRBS_Data_Users_Guide508.pdf quarantined_pending_import_layout_validation provisional 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 imports are quarantined. 2017/2019 local PSU and stratum fields are entirely missing and weights are partial; 1997 has one row missing all three design fields; 2021/2023 official-layout imports have complete design fields.
26 NSDUH::2021 NSDUH_YOUTH::2021 NSDUH United States 2021 adolescents aged 12-17 ANALWT2_C (year-specific C1-C4 mapping unresolved) VEREP VESTR_C pending official combined-file guide review prefix variance units with survey year before pooling Dataset/可直接分析数据包_NSDUH_YRBS/README.md; official annual/combined-file guide pending provisional_weight_mapping_unresolved All four ANALWT2_C1-C4 fields are positive in every local year; do not select a weight by suffix without the official year-specific mapping.
27 NSDUH::2022 NSDUH_YOUTH::2022 NSDUH United States 2022 adolescents aged 12-17 ANALWT2_C (year-specific C1-C4 mapping unresolved) VEREP VESTR_C pending official combined-file guide review prefix variance units with survey year before pooling Dataset/可直接分析数据包_NSDUH_YRBS/README.md; official annual/combined-file guide pending provisional_weight_mapping_unresolved All four ANALWT2_C1-C4 fields are positive in every local year; do not select a weight by suffix without the official year-specific mapping.
28 NSDUH::2023 NSDUH_YOUTH::2023 NSDUH United States 2023 adolescents aged 12-17 ANALWT2_C (year-specific C1-C4 mapping unresolved) VEREP VESTR_C pending official combined-file guide review prefix variance units with survey year before pooling Dataset/可直接分析数据包_NSDUH_YRBS/README.md; official annual/combined-file guide pending provisional_weight_mapping_unresolved All four ANALWT2_C1-C4 fields are positive in every local year; do not select a weight by suffix without the official year-specific mapping.
research/stage1/yrbs_2021_2023_import_audit.json
+97
View File
@@ -0,0 +1,97 @@
{
"schema_version": "1.0",
"generated_on": "2026-09-20",
"status": "passed_for_import; still provisional for human item review",
"method": "Official CDC SAS fixed-width Input positions; raw/archive SHA-256 identity; record-length, domain, design-field, and Parquet round-trip checks.",
"years": [
{
"year": 2021,
"source_file": "Dataset/YRBS_National_1991_2023/raw/YRBS_2021_National.dat",
"sas_layout": "Dataset/YRBS_National_1991_2023/source_archive/2021_cdc_download/2021XXH-SAS-Input-Program.sas",
"sha256": "0a8605d7843fba9cb50e7c0c4094089b0ce2793a9988506971fdae3d9f2a04ae",
"archive_copy_identical": true,
"record_length": 421,
"rows": 17232,
"columns": 239,
"layout_fields": 237,
"output_file": "Dataset/可直接分析数据包_NSDUH_YRBS/YRBS/full_by_year/yrbs_2021_full.parquet",
"parquet_roundtrip": "passed",
"primary_outcome_value_counts": {
"Q26": {
"1": 3593,
"2": 13334,
"<missing>": 305
},
"Q27": {
"1": 2801,
"2": 13520,
"<missing>": 911
},
"Q28": {
"1": 13820,
"2": 993,
"3": 525,
"4": 114,
"5": 121,
"<missing>": 1659
}
},
"primary_outcome_domains": {
"Q26": "passed",
"Q27": "passed",
"Q28": "passed"
},
"design_nonmissing": {
"weight": 17232,
"stratum": 17232,
"psu": 17232
},
"status": "import_validated"
},
{
"year": 2023,
"source_file": "Dataset/YRBS_National_1991_2023/raw/XXH2023_YRBS_Data.dat",
"sas_layout": "Dataset/YRBS_National_1991_2023/source_archive/2023_cdc_download/2023XXH-SAS-Input-Program.sas",
"sha256": "0a83cba11dc8a0cdf0043aacf0b80478f86cf93a91a8ecb81a276518e486241a",
"archive_copy_identical": true,
"record_length": 421,
"rows": 20103,
"columns": 252,
"layout_fields": 250,
"output_file": "Dataset/可直接分析数据包_NSDUH_YRBS/YRBS/full_by_year/yrbs_2023_full.parquet",
"parquet_roundtrip": "passed",
"primary_outcome_value_counts": {
"Q27": {
"1": 4214,
"2": 15453,
"<missing>": 436
},
"Q28": {
"1": 3212,
"2": 15154,
"<missing>": 1737
},
"Q29": {
"1": 17341,
"2": 1109,
"3": 630,
"4": 100,
"5": 156,
"<missing>": 767
}
},
"primary_outcome_domains": {
"Q27": "passed",
"Q28": "passed",
"Q29": "passed"
},
"design_nonmissing": {
"weight": 20103,
"stratum": 20103,
"psu": 20103
},
"status": "import_validated"
}
],
"decision": "YRBS 2021 and 2023 respondent files are released from import-layout quarantine. Primary-outcome items remain provisional pending two human reviewers."
}
research/stage1/yrbs_2021_2023_import_audit.md
+25
View File
@@ -0,0 +1,25 @@
# YRBS 2021/2023 official-layout import audit
YRBS 2021 and 2023 respondent files are released from import-layout quarantine. Primary-outcome items remain provisional pending two human reviewers.
## 2021
- rows × columns: 17,232 × 239
- raw file identical to archived CDC download: yes (`0a8605d7843fba9cb50e7c0c4094089b0ce2793a9988506971fdae3d9f2a04ae`)
- fixed record length: 421 bytes for every row
- design completeness: `{'weight': 17232, 'stratum': 17232, 'psu': 17232}`
- primary outcome domains: `{'Q26': 'passed', 'Q27': 'passed', 'Q28': 'passed'}`
- output: `Dataset/可直接分析数据包_NSDUH_YRBS/YRBS/full_by_year/yrbs_2021_full.parquet`
## 2023
- rows × columns: 20,103 × 252
- raw file identical to archived CDC download: yes (`0a83cba11dc8a0cdf0043aacf0b80478f86cf93a91a8ecb81a276518e486241a`)
- fixed record length: 421 bytes for every row
- design completeness: `{'weight': 20103, 'stratum': 20103, 'psu': 20103}`
- primary outcome domains: `{'Q27': 'passed', 'Q28': 'passed', 'Q29': 'passed'}`
- output: `Dataset/可直接分析数据包_NSDUH_YRBS/YRBS/full_by_year/yrbs_2023_full.parquet`
## Boundary
This resolves the import-layout quarantine only. It does not substitute for two actual human item reviewers or approve design-based variance estimation.
research/stage1/yrbs_primary_outcome_source_audit.json
+87 -27
View File
@@ -148,8 +148,8 @@
"summary": {
"years_reviewed": 17,
"items_reviewed": 51,
"years_available_in_full_tables": 15,
"years_quarantined": 2,
"years_available_in_full_tables": 17,
"years_quarantined": 0,
"previous_mapping_mismatch_years": [
1995,
2001,
@@ -2090,10 +2090,18 @@
"questionnaire_page_or_section": "page 8",
"data_guide_source_file": "Dataset/YRBS_National_1991_2023/documentation/UserGuide/2021_YRBS_Data_Users_Guide_508.pdf",
"data_guide_page_or_section": "page 28",
"data_status": "quarantined_pending_import_layout_validation",
"official_value_counts": null,
"previous_mapped_value_counts": null,
"code_domain_status": "not_tested_quarantined",
"data_status": "available_full_table",
"official_value_counts": {
"1": 3593,
"2": 13334,
"<missing>": 305
},
"previous_mapped_value_counts": {
"1": 3593,
"2": 13334,
"<missing>": 305
},
"code_domain_status": "passed",
"missing_rule_status": "blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason",
"review_status": "provisional",
"reviewer_1": null,
@@ -2121,10 +2129,18 @@
"questionnaire_page_or_section": "page 8",
"data_guide_source_file": "Dataset/YRBS_National_1991_2023/documentation/UserGuide/2021_YRBS_Data_Users_Guide_508.pdf",
"data_guide_page_or_section": "page 28",
"data_status": "quarantined_pending_import_layout_validation",
"official_value_counts": null,
"previous_mapped_value_counts": null,
"code_domain_status": "not_tested_quarantined",
"data_status": "available_full_table",
"official_value_counts": {
"1": 2801,
"2": 13520,
"<missing>": 911
},
"previous_mapped_value_counts": {
"1": 2801,
"2": 13520,
"<missing>": 911
},
"code_domain_status": "passed",
"missing_rule_status": "blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason",
"review_status": "provisional",
"reviewer_1": null,
@@ -2155,10 +2171,24 @@
"questionnaire_page_or_section": "page 8",
"data_guide_source_file": "Dataset/YRBS_National_1991_2023/documentation/UserGuide/2021_YRBS_Data_Users_Guide_508.pdf",
"data_guide_page_or_section": "page 28",
"data_status": "quarantined_pending_import_layout_validation",
"official_value_counts": null,
"previous_mapped_value_counts": null,
"code_domain_status": "not_tested_quarantined",
"data_status": "available_full_table",
"official_value_counts": {
"1": 13820,
"2": 993,
"3": 525,
"4": 114,
"5": 121,
"<missing>": 1659
},
"previous_mapped_value_counts": {
"1": 13820,
"2": 993,
"3": 525,
"4": 114,
"5": 121,
"<missing>": 1659
},
"code_domain_status": "passed",
"missing_rule_status": "blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason",
"review_status": "provisional",
"reviewer_1": null,
@@ -2186,10 +2216,18 @@
"questionnaire_page_or_section": "page 9",
"data_guide_source_file": "Dataset/YRBS_National_1991_2023/documentation/UserGuide/2023_National_YRBS_Data_Users_Guide508.pdf",
"data_guide_page_or_section": "page 29",
"data_status": "quarantined_pending_import_layout_validation",
"official_value_counts": null,
"previous_mapped_value_counts": null,
"code_domain_status": "not_tested_quarantined",
"data_status": "available_full_table",
"official_value_counts": {
"1": 4214,
"2": 15453,
"<missing>": 436
},
"previous_mapped_value_counts": {
"1": 4214,
"2": 15453,
"<missing>": 436
},
"code_domain_status": "passed",
"missing_rule_status": "blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason",
"review_status": "provisional",
"reviewer_1": null,
@@ -2217,10 +2255,18 @@
"questionnaire_page_or_section": "page 9",
"data_guide_source_file": "Dataset/YRBS_National_1991_2023/documentation/UserGuide/2023_National_YRBS_Data_Users_Guide508.pdf",
"data_guide_page_or_section": "page 29",
"data_status": "quarantined_pending_import_layout_validation",
"official_value_counts": null,
"previous_mapped_value_counts": null,
"code_domain_status": "not_tested_quarantined",
"data_status": "available_full_table",
"official_value_counts": {
"1": 3212,
"2": 15154,
"<missing>": 1737
},
"previous_mapped_value_counts": {
"1": 3212,
"2": 15154,
"<missing>": 1737
},
"code_domain_status": "passed",
"missing_rule_status": "blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason",
"review_status": "provisional",
"reviewer_1": null,
@@ -2251,10 +2297,24 @@
"questionnaire_page_or_section": "page 9",
"data_guide_source_file": "Dataset/YRBS_National_1991_2023/documentation/UserGuide/2023_National_YRBS_Data_Users_Guide508.pdf",
"data_guide_page_or_section": "page 29",
"data_status": "quarantined_pending_import_layout_validation",
"official_value_counts": null,
"previous_mapped_value_counts": null,
"code_domain_status": "not_tested_quarantined",
"data_status": "available_full_table",
"official_value_counts": {
"1": 17341,
"2": 1109,
"3": 630,
"4": 100,
"5": 156,
"<missing>": 767
},
"previous_mapped_value_counts": {
"1": 17341,
"2": 1109,
"3": 630,
"4": 100,
"5": 156,
"<missing>": 767
},
"code_domain_status": "passed",
"missing_rule_status": "blank/null retained as unresolved missing; annual guide reports Missing but does not distinguish reason",
"review_status": "provisional",
"reviewer_1": null,
@@ -2264,7 +2324,7 @@
"decision": {
"registry_action": "replace prior YRBS primary-outcome variable mappings with this direct-source crosswalk",
"data_action": "use verified data-user-guide variables from annual full tables; do not infer data columns from printed questionnaire numbers",
"quarantine": "retain 2021 and 2023 as metadata-only until their imports and layouts are independently validated",
"quarantine": "2021 and 2023 released from layout quarantine after independent official-SAS import validation; item review remains provisional",
"gate_1": "in_progress"
}
}
research/stage1/yrbs_primary_outcome_source_audit.md
+4 -4
View File
@@ -27,8 +27,8 @@ The previous registry mapped 21 items in 7 years to the wrong data variable: 199
| 2015 | `Q27/Q28/Q29` | 27/28/29 | Q27/Q28/Q29 (verified) | available_full_table |
| 2017 | `Q26/Q27/Q28` | 27/28/29 | Q26/Q27/Q28 (verified) | available_full_table |
| 2019 | `Q26/Q27/Q28` | 26/27/28 | Q26/Q27/Q28 (verified) | available_full_table |
| 2021 | `Q26/Q27/Q28` | 26/27/28 | Q26/Q27/Q28 (verified) | quarantined_pending_import_layout_validation |
| 2023 | `Q27/Q28/Q29` | 31/32/33 | Q27/Q28/Q29 (verified) | quarantined_pending_import_layout_validation |
| 2021 | `Q26/Q27/Q28` | 26/27/28 | Q26/Q27/Q28 (verified) | available_full_table |
| 2023 | `Q27/Q28/Q29` | 31/32/33 | Q27/Q28/Q29 (verified) | available_full_table |
## Source interpretation
@@ -39,8 +39,8 @@ The previous registry mapped 21 items in 7 years to the wrong data variable: 199
## Gate 1 decision
Gate 1 remains **in progress**. The 51 YRBS primary-outcome source records now have a direct-source crosswalk and clean response options, but 2021/2023 respondent imports remain quarantined, missing reasons require a conservative rule, and two actual human reviewers have not yet signed the primary outcomes.
Gate 1 remains **in progress**. The 51 YRBS primary-outcome source records have a direct-source crosswalk, clean response options, and validated 1991-2023 full tables. Missing reasons still require the conservative rule, and two actual human reviewers have not yet signed the primary outcomes.
## Reproduction
Run `research/stage1/audit_yrbs_primary_outcome_sources.py` in the project Python environment. It verifies source hashes, checks the 1991-2019 annual Parquet schemas, and compares official versus previous mappings.
Run `research/stage1/import_yrbs_2021_2023.py` first, then `research/stage1/audit_yrbs_primary_outcome_sources.py`. The scripts validate official layouts, verify source hashes, check all 1991-2023 annual Parquet schemas, and compare official versus previous mappings.