Gradient Boosting to Address Statistical Problems Arising from Non-Linkage of Census Bureau Datasets
June 2024
Working Paper Number:
CES-24-27
Abstract
This article introduces the twangRDC package, which contains functions to address non-linkage in US Census Bureau datasets. The Census Bureau's Person Identification Validation System facilitates data linkage by assigning unique person identifiers to federal, third party, decennial census, and survey data. Not all records in these datasets can be linked to the reference file and as such not all records will be assigned an identifier. This article is a tutorial for using the twangRDC to generate nonresponse weights to account for non-linkage of person records across US Census Bureau datasets.
Document Tags and Keywords
Keywords
Keywords are automatically generated using KeyBERT, a powerful and innovative
keyword extraction tool that utilizes BERT embeddings to ensure high-quality and contextually relevant
keywords.
By analyzing the content of working papers, KeyBERT identifies terms and phrases that capture the essence of the
text, highlighting the most significant topics and trends. This approach not only enhances searchability but
provides connections that go beyond potentially domain-specific author-defined keywords.
:
estimating,
data,
census data,
microdata,
survey,
record,
matching,
race,
census bureau,
records census,
sampling,
census survey,
datasets,
identifier,
assessed,
census linked,
census records,
linkage
Tags
Tags are automatically generated using a pretrained language model from spaCy, which excels at
several tasks, including entity tagging.
The model is able to label words and phrases by part-of-speech,
including "organizations." By filtering for frequent words and phrases labeled as "organizations", papers are
identified to contain references to specific institutions, datasets, and other organizations.
:
Social Security,
Protected Identification Key,
Person Validation System,
Census Bureau Person Identification Validation System,
Personally Identifiable Information
Similar Working Papers
Similarity between working papers are determined by an unsupervised neural
network model
know as Doc2Vec.
Doc2Vec is a model that represents entire documents as fixed-length vectors, allowing for the
capture of semantic meaning in a way that relates to the context of words within the document. The model learns to
associate a unique vector with each document while simultaneously learning word vectors, enabling tasks such as
document classification, clustering, and similarity detection by preserving the order and structure of words. The
document vectors are compared using cosine similarity/distance to determine the most similar working papers.
Papers identified with 🔥 are in the top 20% of similarity.
The 10 most similar working papers to the working paper 'Gradient Boosting to Address Statistical Problems Arising from Non-Linkage of Census Bureau Datasets' are listed below in order of similarity.
-
Working PaperThe Person Identification Validation System (PVS): Applying the Center for Administrative Records Research and Applications' (CARRA) Record Linkage Software
July 2014
Working Paper Number:
carra-2014-01
The Census Bureau's Person Identification Validation System (PVS) assigns unique person identifiers to federal, commercial, census, and survey data to facilitate linkages across and within files. PVS uses probabilistic matching to assign a unique Census Bureau identifier for each person. The PVS matches incoming files to reference files created with data from the Social Security Administration (SSA) Numerical Identification file, and SSA data with addresses obtained from federal files. This paper describes the PVS methodology from editing input data to creating the final file.View Full Paper PDF
-
Working PaperSYNTHETIC DATA FOR SMALL AREA ESTIMATION IN THE AMERICAN COMMUNITY SURVEY
April 2013
Working Paper Number:
CES-13-19
Small area estimates provide a critical source of information used to study local populations. Statistical agencies regularly collect data from small areas but are prevented from releasing detailed geographical identifiers in public-use data sets due to disclosure concerns. Alternative data dissemination methods used in practice include releasing summary/aggregate tables, suppressing detailed geographic information in public-use data sets, and accessing restricted data via Research Data Centers. This research examines an alternative method for disseminating microdata that contains more geographical details than are currently being released in public-use data files. Specifically, the method replaces the observed survey values with imputed, or synthetic, values simulated from a hierarchical Bayesian model. Confidentiality protection is enhanced because no actual values are released. The method is demonstrated using restricted data from the 2005-2009 American Community Survey. The analytic validity of the synthetic data is assessed by comparing small area estimates obtained from the synthetic data with those obtained from the observed data.View Full Paper PDF
-
Working PaperPerson Matching in Historical Files using the Census Bureau's Person Validation System
September 2014
Working Paper Number:
carra-2014-11
The recent release of the 1940 Census manuscripts enables the creation of longitudinal data spanning the whole of the twentieth century. Linked historical and contemporary data would allow unprecedented analyses of the causes and consequences of health, demographic, and economic change. The Census Bureau is uniquely equipped to provide high quality linkages of person records across datasets. This paper summarizes the linkage techniques employed by the Census Bureau and discusses utilization of these techniques to append protected identification keys to the 1940 Census.View Full Paper PDF
-
Working PaperThe Privacy-Protected Gridded Environmental Impacts Frame
December 2024
Working Paper Number:
CES-24-74
This paper introduces the Gridded Environmental Impacts Frame (Gridded EIF), a novel privacy-protected dataset derived from the U.S. Census Bureau's confidential Environmental Impacts Frame (EIF) microdata infrastructure. The EIF combines comprehensive administrative records and survey data on the U.S. population with high-resolution geospatial information on environmental hazards. While access to the EIF is restricted due to the confidential nature of the underlying data, the Gridded EIF offers a broader research community the opportunity to glean insights from the data while preserving confidentiality. We describe the data and privacy protection process, and offer guidance on appropriate usage, presenting practical applications.View Full Paper PDF
-
Working PaperEstimating Record Linkage False Match Rate for the Person Identification Validation System
July 2014
Working Paper Number:
carra-2014-02
The Census Bureau Person Identification Validation System (PVS) assigns unique person identifiers to federal, commercial, census, and survey data to facilitate linkages across files. PVS uses probabilistic matching to assign a unique Census Bureau identifier for each person. This paper presents a method to measure the false match rate in PVS following the approach of Belin and Rubin (1995). The Belin and Rubin methodology requires truth data to estimate a mixture model. The parameters from the mixture model are used to obtain point estimates of the false match rate for each of the PVS search modules. The truth data requirement is satisfied by the unique access the Census Bureau has to high quality name, date of birth, address and Social Security (SSN) data. Truth data are quickly created for the Belin and Rubin model and do not involve a clerical review process. These truth data are used to create estimates for the Belin and Rubin parameters, making the approach more feasible. Both observed and modeled false match rates are computed for all search modules in federal administrative records data and commercial data.View Full Paper PDF
-
Working PaperThe Design of Sampling Strata for the National Household Food Acquisition and Purchase Survey
February 2025
Working Paper Number:
CES-25-13
The National Household Food Acquisition and Purchase Survey (FoodAPS), sponsored by the United States Department of Agriculture's (USDA) Economic Research Service (ERS) and Food and Nutrition Service (FNS), examines the food purchasing behavior of various subgroups of the U.S. population. These subgroups include participants in the Supplemental Nutrition Assistance Program (SNAP) and the Special Supplemental Nutrition Program for Women, Infants, and Children (WIC), as well as households who are eligible for but don't participate in these programs. Participants in these social protection programs constitute small proportions of the U.S. population; obtaining an adequate number of such participants in a survey would be challenging absent stratified sampling to target SNAP and WIC participating households. This document describes how the U.S. Census Bureau (which is planning to conduct future versions of the FoodAPS survey on behalf of USDA) created sampling strata to flag the FoodAPS targeted subpopulations using machine learning applications in linked survey and administrative data. We describe the data, modeling techniques, and how well the sampling flags target low-income households and households receiving WIC and SNAP benefits. We additionally situate these efforts in the nascent literature on the use of big data and machine learning for the improvement of survey efficiency.View Full Paper PDF
-
Working PaperIncorporating Administrative Data in Survey Weights for the 2018-2022 Survey of Income and Program Participation
October 2024
Working Paper Number:
CES-24-58
Response rates to the Survey of Income and Program Participation (SIPP) have declined over time, raising the potential for nonresponse bias in survey estimates. A potential solution is to leverage administrative data from government agencies and third-party data providers when constructing survey weights. In this paper, we modify various parts of the SIPP weighting algorithm to incorporate such data. We create these new weights for the 2018 through 2022 SIPP panels and examine how the new weights affect survey estimates. Our results show that before weighting adjustments, SIPP respondents in these panels have higher socioeconomic status than the general population. Existing weighting procedures reduce many of these differences. Comparing SIPP estimates between the production weights and the administrative data-based weights yields changes that are not uniform across the joint income and program participation distribution. Unlike other Census Bureau household surveys, there is no large increase in nonresponse bias in SIPP due to the COVID-19 Pandemic. In summary, the magnitude and sign of nonresponse bias in SIPP is complicated, and the existing weighting procedures may change the sign of nonresponse bias for households with certain incomes and program benefit statuses.View Full Paper PDF
-
Working PaperUsing Small-Area Estimation (SAE) to Estimate Prevalence of Child Health Outcomes at the Census Regional-, State-, and County-Levels
November 2022
Working Paper Number:
CES-22-48
In this study, we implement small-area estimation to assess the prevalence of child health outcomes at the county, state, and regional levels, using national survey data.View Full Paper PDF
-
Working PaperA Simulated Reconstruction and Reidentification Attack on the 2010 U.S. Census
August 2025
Working Paper Number:
CES-25-57
For the last half-century, it has been a common and accepted practice for statistical agencies, including the United States Census Bureau, to adopt different strategies to protect the confidentiality of aggregate tabular data products from those used to protect the individual records contained in publicly released microdata products. This strategy was premised on the assumption that the aggregation used to generate tabular data products made the resulting statistics inherently less disclosive than the microdata from which they were tabulated. Consistent with this common assumption, the 2010 Census of Population and Housing in the U.S. used different disclosure limitation rules for its tabular and microdata publications. This paper demonstrates that, in the context of disclosure limitation for the 2010 Census, the assumption that tabular data are inherently less disclosive than their underlying microdata is fundamentally flawed. The 2010 Census published more than 150 billion aggregate statistics in 180 table sets. Most of these tables were published at the most detailed geographic level'individual census blocks, which can have populations as small as one person. Using only 34 of the published table sets, we reconstructed microdata records including five variables (census block, sex, age, race, and ethnicity) from the confidential 2010 Census person records. Using only published data, an attacker using our methods can verify that all records in 70% of all census blocks (97 million people) are perfectly reconstructed. We further confirm, through reidentification studies, that an attacker can, within census blocks with perfect reconstruction accuracy, correctly infer the actual census response on race and ethnicity for 3.4 million vulnerable population uniques (persons with race and ethnicity different from the modal person on the census block) with 95% accuracy. Having shown the vulnerabilities inherent to the disclosure limitation methods used for the 2010 Census, we proceed to demonstrate that the more robust disclosure limitation framework used for the 2020 Census publications defends against attacks that are based on reconstruction. Finally, we show that available alternatives to the 2020 Census Disclosure Avoidance System would either fail to protect confidentiality, or would overly degrade the statistics' utility for the primary statutory use case: redrawing the boundaries of all of the nation's legislative and voting districts in compliance with the 1965 Voting Rights Act.View Full Paper PDF
-
Working PaperEstimating the U.S. Citizen Voting-Age Population (CVAP) Using Blended Survey Data, Administrative Record Data, and Modeling: Technical Report
April 2023
Working Paper Number:
CES-23-21
This report develops a method using administrative records (AR) to fill in responses for nonresponding American Community Survey (ACS) housing units rather than adjusting survey weights to account for selection of a subset of nonresponding housing units for follow-up interviews and for nonresponse bias. The method also inserts AR and modeling in place of edits and imputations for ACS survey citizenship item nonresponses. We produce Citizen Voting-Age Population (CVAP) tabulations using this enhanced CVAP method and compare them to published estimates. The enhanced CVAP method produces a 0.74 percentage point lower citizen share, and it is 3.05 percentage points lower for voting-age Hispanics. The latter result can be partly explained by omissions of voting-age Hispanic noncitizens with unknown legal status from ACS household responses. Weight adjustments may be less effective at addressing nonresponse bias under those conditions.View Full Paper PDF
