Proceedings of the Joint Statistical Meetings 2023 Survey Research Methods Section
August 6 - August 10, 2023

50 years of NCVS data: What we’ve accomplished and where we are headed — Topic Contributed Papers
Organizer(s): Heather Brotsos Organizer, Bureau of Justice Statistics
Chair(s): Alex Piquero, Bureau of Justice Statistics

Adding a new mode: Can the NCVS be self-administered on the web? Findings from an initial test using a combined ABS and panel sample design. — David Cantor, Westat

Boosting the NCVS sample to produce direct state-level estimates: a first look at key indicators — Rachel Morgan, Bureau of Justice Statistics

Data collection and research using the National Crime Victimization Survey: An update on the NCVS projects and priorities. — Heather Brotsos, Bureau of Justice Statistics

Redesigning the NCVS Instrument: Lessons from a large-scale field test. — Jennifer Truman, Bureau of Justice Statistics

Research and development under the NCVS subnational program. — Alexandra Thompson, DOJ/OJP/Bureau of Justice Statistics

Formally Private Disclosure Limitation Methods for Establishment Data — Invited Paper Session
Organizer(s): Daniell Toth, US Bureau of Labor Statistics
Chair(s): Alex Piquero, Bureau of Justice Statistics
Discussant(s) : Stephen Cohen Discussant, NORC at The University of Chicago

Challenges in Formally Private Synthetic Data for Establishments — Daniel Kifer, Penn State University

Relating Legacy Methods to Formal Privacy and Leveraging Statistical Modeling in the Release of Formally Private Data. — Scott Holan, University of Missouri/U.S. Census Bureau

Valid Statistical Inference for Establishment Data Protected with Formally Private Methods — Aleksandra Slavkovic, Pennsylvania State University; Kaitlyn Dowden

SPEED 2: Survey Methods and Methods for Health Policy and Government, Part 1 — Contributed Speed
Chair(s): Aaron Hudson, Fred Hutchinson Cancer Center

Density forecast estimation for long-term energy market projections — Janice Lent, U.S. Energy Information Administration; Adebowale Sijuwade, U.S. Energy Information Administration; Caitlin Steiner, U.S. Energy Information Administration
Keywords: density forecast, energy projection, time series, exponential smoothing

A Comparison Study of Creating Synthetic Survey Data Using Different Approaches — Bill Cai, National Center for Health Statistics; Guangyu Zhang, National Center for Health Statistics; Yulei He, National Center for Health Statistics; Anna Oganian, National Center for Health Statistics
Keywords: RANDS during COVID-19, Synthetic Data, R Synthpop, SAS Proc MI, IVEware

Federated Targeted Learning — Rachael Phillips; Mark Van Der Laan, UC Berkeley
Keywords: federated learning, non-disclosive data analysis, multi-cohort studies, targeted learning, super ensemble machine learning, targeted maximum likelihood estimation

Predictive Model for All-Cause Mortality — Fei Han, The Hilltop Institute At UMBC; Morgan Henderson, The Hilltop Institute at UMBC; Leigh Goetschius, The Hilltop Institute at UMBC; Ian Stockwell, University of Maryland Baltimore County
Keywords: Predictive model, All-cause mortality, Hospice care, Ranking

A Latent Principal Stratification Method to Address Noncompliance in Cluster RCTs — Anthony Sisti, Brown University; Roee Gutman, Brown University
Keywords: Multilevel Noncompliance, Cluster Randomized Controlled Trial, Bayesian Statistics, Principal Stratification, Causal Inference

A Comparison of Single Imputation Methods for the Ohio Children's Opportunity Index — Krista Wurscher, Ohio Colleges of Medicine Government Resource Center
Keywords: Single Imputation, Most Similar Neighbors, Opportunity Index

The Augmented Synthetic Control Method in Public Health and Biomedical Research — Taylor Krajewski, University of North Carolina at Chapel Hill; Michael Hudgens, University of North Carolina at Chapel Hill
Keywords: causal inference, synthetic controls

ANOVA-based Constrained Randomization to Balance Covariate for a CRT with More Than Two Study Groups — Wen Wan; Nikita Thomas, University of Chicago - Chicago, IL; Elbert Huang, University of Chicago - Chicago, IL; Valerie Press, University of Chicago - Chicago, IL
Keywords: Constrained randomization, covariate balance, cluster randomized trial (CRT), imbalance score

WITHDRAWN Comparison of methods for analyzing proxy responses in patient-reported outcomes — Jennifer Scodes; Roee Gutman, Brown University
Keywords: patient-reported outcomes, proxy, item-response theory

Constructing Better "Confidence" Intervals for Proportions and Tests of Differences Among Them — Phillip Kott, RTI International
Keywords: Edgeworth Expansion, Third-Central Moment, Holm-Bonferroni, Variance Stratum

Generalized Estimating Equations for Interpretable Coefficients of Trends, Seasonality & Covariates — Harold Gomes, NIOSH, CDC; Kitty Hendricks, Division of Safety Research, National Institute for Occupational Safety and Health; Scott Hendricks, National Institute for Occupational Safety and Health (NIOSH)
Keywords: Evaluate Multiple Trends, Difference-in-Trends, Rate Ratio for Seasonality, Generalized Estimating Equations, Poisson or Negative Binomial Regression, National Electronic Injury Surveillance System (NEISS)

Evaluating the Hidiroglou-Berthelot Method for Survey Data Collected by the US EIA — Michael Winkler, Energy Information Administration; Pushpal Mukhopadhyay, U.S. Energy Information Administration; Orhan Yildiz, US Energy Information Administration; Preston McDowney, US Energy Information Administration; Caitlin Steiner, U.S. Energy Information Administration
Keywords: Statistical Editing, Ratio Edit, HB Method

Creating Compact Sampling Units Meeting Population Constraints for In-Person Surveys — Stephanie Zimmer, RTI International; Joe McMichael, RTI International; Taylor Lewis, RTI International
Keywords: multi-stage sampling, area sampling, frame

Outlier Detection for Administrative Data — John Bunker, RTI International; Dan Liao; Marcus Berzofsky, RTI International; Erica Smith, Bureau of Justice Statistics, US Department of Justice
Keywords: outlier detection, administrative data, crime data, weighting, imputation

Using propensity score estimation with survey weighted data to estimate population treatment effects — Lihua Li, Icahn School of Medicine At Mount Sinai; Chen Yang, Icahn School of Medicine at Mount Sinai; Meaghan Cuerden, London Health Sciences Centre; Bian Liu, Icahn School of Medicine at Mount Sinai; Madhu Mazumdar, Icahn School of Medicine At Mount Sinai; Melissa Aldridge, Icahn School of Medicine at Mount Sinai
Keywords: propensity score weighing (PSW), Covariate Balance Propensity Score (CBPS), Generalized Boosted Model (GBM), Classification and Regression Trees (CART), Random Forest, complex survey data

Propensity score weighting with survey weighted data when outcomes are binary — Chen Yang, Icahn School of Medicine at Mount Sinai; Meaghan Cuerden, London Health Sciences Centre; Wei Zhang, University of Arkansas At Little Rock; Melissa Aldridge, Icahn School of Medicine at Mount Sinai; Lihua Li, Icahn School of Medicine At Mount Sinai
Keywords: propensity score weighing (PSW), Covariate Balance Propensity Score (CBPS), Generalized Boosted Model (GBM), Classification and Regression Trees (CART), Random Forest, complex survey data

To Calibrate or Not to Calibrate: Disability Measurement & Calibration in a State Health Survey — Robert Ashmead, Ohio Colleges of Medicine Government Resource Center; Leyla Tosun, Ohio Colleges of Medicine Government Resource Center; Marcus Berzofsky, RTI International; Caroline Scruggs, RTI International
Keywords: survey sampling, calibration, disability, total survey error

Calibrating the Census' Low Response Score — Stanislav Kolenikov, NORC at The University of Chicago; Patrick Coyle, NORC at The University of Chicago; David Dutwin, SSRS / Social Science Research Solutions
Keywords: sampling design, low response score, survey nonresponse, address-based sampling

Recent Advances in Statistical Modeling and Machine Learning for Dependent Data in Official Statistics and Survey Methodology — Topic Contributed Papers
Organizer(s): Scott Holan, University of Missouri/U.S. Census Bureau
Chair(s): Scott Holan, University of Missouri/U.S. Census Bureau

A SOCIO-DEMOGRAPHIC LATENT SPACE APPROACH TO SPATIAL DATA WHEN GEOGRAPHY IS IMPORTANT BUT NOT ALL-IMPORTANT — Scott Holan, University of Missouri/U.S. Census Bureau; Michael Schweinberger, The Pennsylvania State University; Saikat Nandy, University of Missouri

Bayesian Unit-level Models for Longitudinal Survey Data under Informative Sampling with Application to the Household Pulse Survey — Paul Parker; Scott Holan, University of Missouri/U.S. Census Bureau; Daniel Vedensky, University of Missouri

Generating differentially private, tract-level synthetic data for births in Pennsylvania — Harrison Quick

SPEED 2: Survey Methods and Methods for Health Policy and Government, Part 2 — Contributed Posters

40 Years of the Survey of Consumer Finances: Building a community of use for evidence building
Chair(s): Arthur Kennickell, Stone Center, City University of New York
Dicsussant(s): Barry Johnson, Internal Revenue Service
Organizer(s): Arthur Kennickell Organizer, Stone Center, City University of New York

The Past, Present and Future of the Survey of Consumer Finances — Alice Volz, Federal Reserve Board

Data Collection Challenges and Preparing for the Future of the Survey of Consumer Finances — Catherine Haggerty, NORC at The University of Chicago
Keywords: RANDS during COVID-19, Synthetic Data, R Synthpop, SAS Proc MI, IVEware

Lessons from the SCF for future research on household finance — Pirmin Fessler

The Survey of Consumer Finances at Forty: Reflections of an Early User — Topic-Contributed Paper Session — Andrew Samwick, Dartmouth College

Missing Data: The Where, the How, and the Why — Invited Paper Session Chair(s): Matt Williams, RTI
Dicussant(s): Roderick Little, University of Michigan
Organizer(s): Sahar Zangeneh, RTI International

It's who is missing that matters: Can a nonignorable missingness mechanism explain bias in estimates of COVID-19 vaccine uptake? — Rebecca Andridge, The Ohio State University

Likelihood-Based Inference for the Finite Population Mean with Post-Stratification Information Under Non-Ignorable Non-Response — Sahar Zangeneh, RTI International

Modeling racial/ethnic differences in COVID-19 incidence with covariates subject to non-random missingness — Robert Trangucci

Mediation analysis with the mediator and outcome missing not at random — Fan Yang, Tsinghua University

Exploring auxiliary resources at early stages in the sampling process — Contributed Papers
Chair(s):Katherine Irimata, National Center for Health Statistics

Cost Reduction for Big Data Exploration and Pertinent Knowledge Extraction — Abdellatif Demnati, Independent Researcher
Keywords: Digital network, Job shop scheduling, Multiweights calibration, Poisson sampling, Sample size determination, Two-phase sampling

Examining SNAP Status of Dwelling Units Over Time In the FoodAPS Field Test — Elizabeth Petraglia, Westat; Robyn Ferg, Westat; Thomas Krenzke, Westat; Elina Page, Economic Research Service
Keywords: SNAP, FoodAPS, administrative data, survey data

Utility of Commercial Data for Sampling Population Subgroups: A Case of Health and Retirement Study — Chendi Zhao; Sunghee Lee, University of Michigan; Anqi Liu, University of Michigan, Ann Arbor; Brady West, Institute for Social Research; Paul Burton, University of Michigan; Raphael Nishimura, University of Michigan
Keywords: Area probability sampling, Population subgroups, Commercial data, Health and Retirement Study

Evaluating Three Ways to Handle Drop Points in Address-Based Sampling Frame Surveys — Taylor Lewis; Charlotte Looby, RTI International; Joseph McMichael, RTI International
Keywords: address-based sample, ABS, health survey, substitution

Designing a Probability Sample to Produce a Large Number of Key Estimates — Darryl Creel; Phillip Kott, RTI International
Keywords: probability proportional-to-size sampling, maximal Brewer selection

Medicare Advantage Encounter Data and Enhanced Estimation for a Changing Population of Beneficiaries — Nicholas Davis, NORC at The University of Chicago; Holly Cast, NORC at The University of Chicago; Michael Trierweiler, NORC at the University of Chicago
Keywords: Survey, Medicare, Claims, Encounter Data, Estimation, MCBS

Computational methods toward fully Bayesian optimal survey sample design — Jonathan Mendelson, Bureau of Labor Statistics; Michael Elliott, University of Michigan
Keywords: Survey, Medicare, Claims, Encounter Data, Estimation, MCBS

Hierarchical models for survey data — Contributed Papers
Chair(s):Akhil Vaish, RTI International

Accounting for dose uncertainty in dose-response curve estimation using hierarchical Bayes models — Andreea Erciulescu, Westat; Jean Opsomer, Westat
Keywords: community response, measurement error, noise level, supersonic aircraft

WITHDRAWN Small Area Estimation using Samplics, a Python Package for Survey Analysis — Mamadou Diallo, Samplics LLC
Keywords: Small area estimation, Empirical best prediction, Survey sampling, Python, Samplics

Mixture Model and Its Application — Yang Cheng, National Agricultural Statistics Service; Lu Chen, NISS; Gauri Datta, University of Georgia
Keywords: Mixture model, Small area estimation, Fay-Herriot model, Cash Rents Survey

Comparison of Measurement Error Models with Differentially Private Covariates — Kyle Irimata
Keywords: Small Area Estimation, Fay Herriot, Differential Privacy

WITHDRAWN Data Integration For Small Areas using Dirichlet Process — Yang Liu, Worcester Polytechnic Institute; Balgobin Nandram, Worcester Polytechnic Institute
Keywords: Big data, Covariate, Finite population mean, Dirichlet process, Small area, Selection bias

Comparison of Small Area Procedures based on Gamma Distributions Extending to Informative Sampling — Yanghyeon Cho; Emily Berg
Keywords: Small area, Informative sampling, Agricultural survey, Parametric bootstrap, Gamma distribution

Evaluating and addressing survey nonresponse — Contributed Papers
Chair(s):Daifeng Han, Westat

Measuring Nonresponse Bias in Pregnancy Risk Assessment Monitoring System (PRAMS), 2019 — Holly Shulman, CDC; Philip Hastings, Far Harbor; Joseph Pirozzolo, Far Harbor; Ruben Smith, Centers for Disease Control and Prevention (CDC); Lee Warner, CDC; Machell Town, Centers for Disease Control & Prevention
Keywords: nonresponse bias, response rates, PRAMS

Evaluating Nonresponse Bias Following COVID-Related Data Collection Changes in the MCBS — Holly Cast, NORC at The University of Chicago; Whitney Murphy, NORC at The University of Chicago; Nicholas Davis, NORC at The University of Chicago; Chrystine Tadler, NORC at The University of Chicago; Nathaniel Poland, NORC at the University of Chicago
Keywords: Nonresponse Bias Analysis, Bias, Response Rates, Weighting, Representativeness, Medicare

A Nonresponse Bias Analysis of the 2021 General Social Survey — Erin Tanenbaum, NORC at The University of Chicago; Brian Geistwhite; Brian Wells, NORC at the University of Chicago
Keywords: Nonresponse Bias Analysis, Response Rate, Hard-to-Reach Human Populations

The Use of Design Weights in Classification Trees for Survey Nonresponse Under a Cluster Design — Jennifer Kali, Westat; William Cecere, Westat; Michael Jones, Westat; Tien-Huan Lin, Westat
Keywords: classification trees, nonresponse bias, response propensities, design weights, survey weights

Propensity-Adjusted Raking with Applications to Current Population Survey Nonresponse — Justin McIllece, Bureau of Labor Statistics;
Keywords: Current Population Survey, CPS, nonresponse, raking, response propensity

Finding Better Weighting Adjustment Cells When Design Variables and Covariates are Limited — Amang Sukasih, RTI International
Keywords: Survey nonresponse, Subclassification, Matching, Simulation

Multiple imputation and synthetic data generation under unequal probability sampling — Hang Joon Kim, University of Cincinnati; Won Chang, University of Cincinnati; Ayat Almomani, University of Cincinnati
Keywords: Multiple imputation, Synthetic data, Survey weight, Informative sampling, Bayesian inference, Uncertainty adjustment

Cell Suppression Methods for Economic Census and Establishment Surveys — Topic-Contributed Paper Session
Chair(s): Yang Cheng, National Agricultural Statistics Service
Discussant(s): Saki Kinney, Discussant RTI International
Organizer(s): Yang Cheng, National Agricultural Statistics Service

Overview of Cell Suppression Methods — Ruiyi Zhang; Lu Chen, NISS; Yang Cheng, National Agricultural Statistics Service; Michael Jacobsen, USDA/NASS

Assessing the performance of the open-sourced linear programming solver in disclosure control problems — Haoluan Chen, Statistics Canada; Steven Thomas, Statistics Canada

IP Cell Suppression Algorithms for Econ Census Data — Bei Wang, US Census Bureau

Major Initiatives to Improve the U.S. Energy Information Administration's Statistical Disclosure Limitation Procedures — David Kinyon, Energy Information Administration

Modern Techniques in Robust Estimation for Handling Outliers and Influential Units — Invited Paper Session
Chair(s):David Haziza, University of Ottawa
Discussant(s): Emily Berg Discussant
Organizer(s): Sixia Chen

A Robust Nested Error Regression Model with High Dimensional Parameter for Discrete Outcomes in Unplanned Domain Prediction — Gaia Bertarelli, University of Venice

Triply robust estimation under missing at random — Jae-Kwang Kim, Iowa State University; Hengfang Wang, Iowa State University of Science and Technology; Youngjo Lee

Robust Imputation Procedures in the Presence of Influential Units in Surveys — Sixia Chen

Survey and data science — Contributed Papers
Chair(s):Victoria Landsman, Institute for Work and Health

"balance” - a Python package for balancing biased data samples — Tal Sarig, Meta; Roee Eilat, Meta; Tal Galili, Tel Aviv University; Steve Mandala, Meta
Keywords: Survey statistics, Survey weighting, Propensity score, Open-source software, Python

Orthogonal Projection of the Extended MLE on the Parameter Space of Partially Estimable Log-Linear Models — Yves Thibaudeau, US Census Bureau
Keywords: Extend MLE, Orthogonal Projections, Regularization

Predicting Census Survey Response Rates via Interpretable Nonparametric Additive Models — Emanuel Ben-David, US Census Bureau; Shibal Ibrahim, Massachusetts Institute of Technology; Rahul Mazumder, Massachusetts Institute of Technology; Peter Radchenko, University of Sydney

Design-based conformal prediction for survey sampling — Jerzy Wieczorek, Colby College
Keywords: Survey sampling, Conformal prediction, Machine learning, Cross validation, Predictive modeling

Advanced Methods of Using Auxiliary Information to Improve Inferences of Population Quantities — Invited Paper Session
Chair(s): Sixia Chen
Organizer(s): Lingxiao Wang, National Cancer Institute

Imputation calibration method for improving robustness and efficiency of relative risk estimation in the population using influence functions as auxiliary variables — Lingxiao Wang, National Cancer Institute; Yan Li, University of Maryland, College Park; Barry Graubard, National Cancer Institute; Hormuzd Katki, National Cancer Institute

Nonprobability follow-up sample analysis: an application to SARS-Cov-2 infection prevalence estimation — Yan Li, University of Maryland, College Park; Michael Fay, National Institute of Allergy and Infectious Diseases; Sally Hunsberger; Barry Graubard, National Cancer Institute

A Multiple Imputation Comparison Analysis Approach to Health Surveys Subject to Selection Bias — Yulei He, National Center for Health Statistics; Yan Li, University of Maryland, College Park; Guangyu Zhang, National Center for Health Statistics; Katherine Irimata, National Center for Health Statistics

The Implications of Weighting Adjustments for Sampling Variance Estimates — Raphael Nishimura, University of Michigan; Brady West, Institute for Social Research

Combining Economic Survey Data with Other Data Sources — Topic-Contributed Paper Session
Chair(s): Heng Chen, Bank of Canada
Organizer(s): Heng Chen, Bank of Canada; Christopher Henry, Bank of Canada; Angelika Welte, Bank of Canada

Incorporate Trip-chaining into Proximity Measurement: an Application of Mobile Data for Canadians Access to Cash — Hongyu Xiao

Using transaction records to improve survey-based estimates of transaction frequency — Marcin Hitczenko, Federal Reserve Bank of Atlanta

Cashless Society? Results and Comparisons from a US Survey — Kevin Foster, Federal Reserve Bank of Atlanta

Inferring merchant acceptance through consumer surveys — Joy Wu, Bank of Canada

Analyzing health survey data — Contributed Papers
Chair(s): Erin Tanenbaum, NORC at The University of Chicago

Topic modelling for automated other-specify upcoding in the National Household and Education Surveys — Rachel Carroll, American Institutes for Research; Sam Mabile, American Institutes for Research; Danielle Battle, American Institutes for Research
Keywords: Natural language processing, survey data, education, upcoding, survey methodology

Feeling of loneliness among the European elderly: changes during the Covid-19 waves — Omar Paccagnella, University of Padua; Maria Iannario, University of Naples Federico II; Cosmo Strozza, University of Southern Denmark
Keywords: Aging, COVID-19, CUSH model, loneliness, ordinal data, uncertainty

Estimation of age-conditional cause-specific probabilities of dying by categories of exposure — Victoria Landsman, Institute for Work and Health; Barry Graubard, National Cancer Institute
Keywords: survival analysis, competing risks, partitioned mortality, cause-specific mortality, complex survey data, combined cohort

Enhanced Inference for Finite Population Sampling-Based Prevalence Estimation with Misclassification — Lin Ge; Yuzi Zhang, Emory University, Rollins School of Public Health; Lance Waller, Emory University; Robert Lyles, Emory University
Keywords: random sampling, misclassification errors, bias-corrected prevalence estimation, variance enhancement, finite population correction (FPC)

Bayesian Mixture Modeling with Ranked Set Samples — Amirhossein Alvandi, University of Massachusetts Amherst; Armin Hatefi, Memorial University of Newfoundland
Keywords: Finite mixture models, Ranked set sampling, Bayesian estimation, Metropolis within Gibbs Sampling, misplacement porbability, Bone mineal density

WITHDRAWN Using Fixed Population Bayesian Methods for a Consumer Assessment of Healthcare Provider Survey — Kimberly Ault, RTI International; Daniel Barch, RTI International; Celia Eicheldinger, RTI International; Sara Zuckerbraun, RTI
Keywords: Bayesian methods, Binary data, Finite population methods, Survey weights, R software

A Novel Robust Ratio Estimator Applied to Covid-19 Data — Azaz Ahmed, National College of Business Administration and Economics Department of Statistics; Muhammad Hanif, National College of Business Administration and Economics Department of Statistics; Evrim Oral, LSUHSC School of Public Health
Keywords: Generalized least square estimator, modified maximum likelihood, robust ratio estimator, auxiliary variable, Covid-19

Field Survey Labor Challenges in the U.S. — Topic-Contributed Panel Session
Chair(s): Brad Edwards, Westat
Panelist(s): Grant Benson, University of Michigan Institute for Social Research; Jill Carle Panelist, Westat; Howard Speizer Panelist, RTI; James T. Christy, U.S. Census Bureau;
Organizer(s): Brad Edwards, Westat

Contributed Poster Presentations: Survey Research Methods Section — Contributed Posters
Chair(s): Jacob Bien, University of Southern California

WITHDRAWN A NEW UNRELATED QUESTION MODEL WITH UNKNOWN REPEATED TRIALS — Inderjit Grewal

WITHDRAWN Dynamic Time-to-Event Models for Future Call Attempts Required Until Interview or Refusal — Xinyu Zhang, University of Michigan
Keywords: Survey cost, Responsive survey design, Machine learning, Paradata

WITHDRAWN Equating Monitor Based to Self-Reported Physical Activity by Zero-Inflated Quantile Regression — Greg Welk, Iowa State University; Nicholas Lamoureux, University of Nebraska Kearney; Chengpeng Zeng; Zhengyuan Zhu, Iowa State University; Emily Berg; Dana Wolff-Hughes, National Cancer Institute; Richard Troiano, National Cancer Institute;
Keywords: Pyhsical Activity Surveillance, Zero-Inflated Quantile Regression, MIMS(Monitor Independent Movement Summary), GPAQ(Global Physical Activity Questionnaire)

WITHDRAWN Error Sources, Data Summaries and Data Cleaning from a World War I era Survey — Gerald Shoultz, Grand Valley State University
Keywords: Survey Error, Data Analysis, Demographics, Digital Humanities, Data Cleaning

WITHDRAWN Estimation of US County-level Average Unhealthy Days by Zero-Inflated Model and Hurdle model — Yan Wang, CDC; Xingyou Zhang, Bureau of Labor Statistics; Hua Lu; Susan Carlson, CDC; BENJAMIN LEE, Oak Ridge Institute for Science and Education; Magdalena Pankowska, Oak Ridge Institute for Science and Education; Kurt Greenlund, CDC
Keywords: Behavioral Risk Factor Surveillance System, hurdle model, small area estimation, unhealthy days, zero-inflated model

WITHDRAWN Extension of Ardah and Oral's two-stage RRT to the Polychotomous Case — Evrim Oral, LSUHSC School of Public Health; Tina Trosclair
Keywords: Randomized Response Tecnhnique, Ardah and Oral's RRT, Polychotomous Responses, Relative Efficiency

WITHDRAWN Uncertainty Estimation for U.S. Crime Estimates using the National Incident Based Reporting System — George Couzens, RTI International; Marcus Berzofsky, RTI International
Keywords: Bias Estimation, Uncertainty, Imputation, Copula

Sampling and evaluation strategies to improve coverage and response — Contributed Papers
Chair(s): Eric Rancourt, Statistics Canada

Asking Questions about Disabilities using Multiple Modes — Kathy Ott, USDA/National Agricultural Statistics Service; Struther VanHorn, USDA/National Agricultural Statistics Service Doug Kilburg, USDA/National Agricultural Statistics Service Carlos Coleman, United States Department of Agriculture
Keywords: disabilities, mode effects, behavior coding

A meta-analysis of web & mail mixed-mode survey experiments on response rates and web participation — Kristen Olson, University of Nebraska-Lincoln Jolene Smyth, University of Nebraska, Lincoln; Rebecca Medway, University of Maryland; Ting Yan, Westat
Keywords: Survey methodology, Mixed-mode surveys, Web survey, Mail survey, Response Rates, Nonresponse

A Second Chance at Response: A mode analysis from National Survey on Drug Use and Health — Lauren Warren; Peter Frechtel, RTI International; Sara Russell, RTI International; Jennifer Hoenig, SAMHSA; Douglas Richesson, SAMHSA; Tenecia Smith, SAMHSA
Keywords: Survey mode, Reliability, Measurement Error, Breakoff

An Assessment of the Effects of COVID-19 and Modes of Data Collection on Selected NSDUH Estimates — Akhil Vaish, RTI International; Kathryn Spagnola, RTI International; Douglas Richesson, SAMHSA; Tenecia Smith, SAMHSA; Jennifer Hoenig, SAMHSA
Keywords: Mode Effects (In-person vs. Web Mode), The National Survey on Drug Use and Health (NSDUH), COVID-19, Relative Risks, SUDAAN, Log-Binomial Regression Models

An Evaluation of Prepaid and Promised Incentive Experiment in a Mail Push-to-Web Survey — Daifeng Han, Westat; Tien-Huan Lin, Westat; J. Michael Brick, Westat; Sadeq Chowdhury, Agency for Healthcare Research and Quality; David Kashihara, Agency for Healthcare Research & Quality
Keywords: Address-based sample, Response rate, Survey cost, Prepaid incentive, Promised incentive, Mail push-to-Web

Does it Pay to Send Multiple Pre-Paid Incentives? Evidence from a Randomized Experiment — Andrew C. Chang, Board of Governors of the Federal Reserve System; Joanne W. Hsu, University of Michigan, Institute for Social Research, Survey Research Center; Eva Ma, Board of Governors of the Federal Reserve System; Kate Bachtell; Micah Sjoblom, NORC at The University of Chicago
Keywords: Incentives, response rates, experiment

A Hybrid Household and Respondent-Driven Sampling Strategy for Reaching Underrepresented Groups — Brian Kim, University of Maryland; Arianna Gard, University of Maryland
Keywords: Network Sampling, Survey error, Health, Minority, Adolescent

Using Machine Learning & Data Science Methods to Improve Model Assisted Estimation & Survey Design — Invited Paper Session
Chair(s): Katherine Thompson, US Census Bureau
Dicussant(s): Kelly McConville, Harvard University
Organizer(s): Morgan Earp, National Center for Health Statistics

Design Consistent Bayesian Tree Models — Daniell Toth, US Bureau of Labor Statistics

Treatment of Unit Nonresponse in Surveys Through Regression Trees — David Haziza, University of Ottawa

Machine Learning and Parametric Modeling Techniques for Informing Responsive Survey Design Strategies — Brady West, Institute for Social Research

Machine Learning for Model-Based Weighting Methods with Complex Nonresponse in the American Community Survey — Darcy Morris, U.S. Census Bureau; Joseph Kang, US Census Bureau; Patrick Joyce, US Census Bureau; Isaac Dompreh

Using Machine Learning for Nonresponse Adjustment in the National Health Interview Survey (NHIS) — Morgan Earp, National Center for Health Statistics; Benjamin Zablotsky, National Center for Health Statistics; Lindsey Black, National Center for Health Statistics; Jonaki Bose, NCHS; Matthew Bramlett, National Center for Health Statistics; James Dahlhamer, National Center for Health Statistics

Getting the Utility Out of Privatized Data — Topic-Contributed Paper Session
Chair(s): Michael Hawes
Organizer(s): Daniell Toth, US Bureau of Labor Statistics

Simulation-based, Finite-sample Inference for Privatized Data — Jordan Awan, Purdue University; Zhanyu Wang

Nonparametric Modeling of an Economic Measure Using Top-coded Household Expenditure Survey Data — Daniel Yang, Bureau of Labor Statistics

Zero-Concentrated Differential Privacy for Natural Exponential Families — Aratrika Mustafi, Pennsylvania State University; Soumya Mukherjee; Matthew Reimherr, Penn State; Aleksandra Slavkovic, Pennsylvania State University

Zero-Concentrated Differential Privacy for Natural Exponential Families — Aratrika Mustafi, Pennsylvania State University; Soumya Mukherjee; Matthew Reimherr, Penn State; Aleksandra Slavkovic, Pennsylvania State University

Traversing the Hypercube: An Efficient Algorithm for the Cell Suppression Problem — Elan Segarra, US Bureau of Labor Statistics

Weighting Adjustments — Contributed Papers
Chair(s): Evrim Oral, LSUHSC School of Public Health

Introducing Educational Attainment to the Poststratification Adjustment in the NSDUH — Devon Cribb, RTI International; P. Mae Cooper, SAMHSA; Rong Cai, SAMHSA; Jennifer Hoenig, SAMHSA; Kathryn Spagnola, RTI International; Patrick Chen, RTI International; Lanting Dai, RTI International
Keywords: NSDUH, Weighting, Poststratification Adjustment, Educational Attainment

On calibration to estimated totals in survey sampling — Takis Merkouris, Athens University of Economics & Business
Keywords: calibration estimator, regression estimator, survey data combination, survey errors, aligned estimates

2020 Decennial Census Effect on the NSDUH Substance Use and Mental Health Estimates — Kathryn Spagnola, RTI International; Neeraja Sathe, RTI International; Patrick Chen, RTI International; Devon Cribb, RTI International; Jennifer Hoenig, SAMHSA; Jingsheng Yan, SAMHSA; Rong Cai, SAMHSA
Keywords: 2020 population, census effect, NSDUH, weighting, substance use, mental health

Consistency of survey estimates through adjusted integer weights — Luca Sartore, National Institute of Statistical Sciences; Lu Chen, NISS
Keywords: Calibration, Weighting, Survey, Consistency, Estimation, Integer programming

Propensity score weighting in survey data with survival outcomes — Wei Zhang, University of Arkansas At Little Rock; Lihua Li, Icahn School of Medicine At Mount Sinai; Chen Yang, Icahn School of Medicine at Mount Sinai
Keywords: Survey data, propensity score weighting, provider-patient discussion

Comparison of Different Algorithms on Propensity Score Weighting with Survey Data:A Simulation Study — Bocheng Jing; Chen Yang, Icahn School of Medicine at Mount Sinai; John Boscardin, Division of Geriatrics, University of California, San Francisco; Lihua Li, Icahn School of Medicine At Mount Sinai
Keywords: Propensity Score Weighting, Survey Design, Machine Learning, Causal Inference

Identifying covariates to adjust for selection bias in national estimates of web-based panel surveys — Katherine Irimata, National Center for Health Statistics; Yan Li, University of Maryland, College Park; Yulei He, National Center for Health Statistics
Keywords: machine learning, mean estimation, National Health Interview Survey, Research and Development Survey, web surveys

Contributions to Inference from Survey Samples: In Honor of Professor Joe Sedransk — Invited Paper Session
Chair(s): Guofen Yan, University of Virginia
Dicussant(s): Balgobin Nandram, Worcester Polytechnic Institute
Organizer(s): Balgobin Nandram, Worcester Polytechnic Institute

Bivariate Hierarchical Bayesian Model for Combining Summary Measures and their Uncertainties from Multiple Sources — Qixuan Chen, Columbia University; Yujing Yao; Todd Ogden, Columbia University; Chubing Zeng

Hierarchical Bayesian Model for State-Level Cash Rental Rates — Lu Chen, NISS; Balgobin Nandram, Worcester Polytechnic Institute;

Adaptive cluster sampling as domain estimation — Glen Meeden, University of Minnesota

Implementing order constraints in survey data analysis — Jiayang Sun, George Mason University; Mary Meyer, Colorado State University; Zixiang Xu

The Bayesian and frequentist dialogue in survey sampling — Mary Thompson, University of Waterloo

Cryptocurrency Surveys: What data tells us?— Topic-Contributed Paper Session
Chair(s): Christopher Henry, Bank of Canada
Discussant(s): Marcel Voia
Organizer(s): Daniela Balutel, York University

Central bank digital currency, crypto assets, and cash demand: Evidence from Japan — Hiroshi Fujiki, Chuo University

Numeracy, Financial Literacy and Crypto-assets Ownership: Evidence from the United States — Aditi Routh, Federal Reserve Bank of Kansas City; Kevin Foster, Federal Reserve Bank of Atlanta

Private Digital Cryptoassets as Investment? Bitcoin Ownership and Use in Canada — Daniela Balutel, York University; Doina Rusu, Bank of Canada; Christopher Henry, Bank of Canada

Measurement of Sexual Orientation and Gender Identity in Federal Surveys — Topic-Contributed Paper Session
Chair(s): Kathy Ott, USDA/NASS
Organizer(s): Kathy Ott, USDA/National Agricultural Statistics Service; Struther VanHorn, USDA/National Agricultural Statistics Service

Behavior Coding of Sexual Orientation and Gender Identity Questions Administered by Telephone Interviewers — Struther VanHorn, USDA/National Agricultural Statistics Service; Doug Kilburg, USDA/National Agricultural Statistics Service; Kathy Ott, USDA/National Agricultural Statistics Service; Carlos Coleman, United States Department of Agriculture

Comparing Forced-Choice versus Select All that Apply Response Options in a 2-Step Gender Identity Question — Victoria Narine, Bureau of Labor Statistics; Robin Kaplan, Bureau of Labor Statistics; Rebecca Morrison, Bureau of Labor Statistics

Testing SOGI Questions in Spanish for Federal Surveys — Alicia Schoua-Glusberg, Research Support Services;

Updates on a Research Agenda for the Sexual Orientation and Gender Identity Questions on the Experimental Household Pulse Survey — Zachary Scherer

Various Mode Effects, Item Response Rates, and Response Analyses by Demographic Groups for a SOGI and Disability Study — Doug Kilburg, USDA/National Agricultural Statistics Service

Model-based estimation for survey data — Contributed Papers
Chair(s): Justin McIllece, Bureau of Labor Statistics

A Bayesian Model for a Binary Variable with Covariates and Survey Weights — Lingli Yang, Worcester Polytechnic Institute; Balgobin Nandram, Worcester Polytechnic Institute
Keywords: probability samples, covariates, sampling weights, outliers, selection bias

Evaluation of Bayesian Adjusted Global Fit Indices in Structural Equation Modeling: Small Sample Performance in the Presences of Missing Data — Jonathan Bishop; Kevin Gittner, Kennesaw State University; Chia-Lin Tsai, University of Northern Colorado
Keywords: Bayesian Structural Equation Modeling, Posterior predictive p-value performance, Bayesian adjusted global fit indices, Small sampling, Missing data

Evaluating Compliance and Churn in Metered Panel Data — Robert Petrin, Ipsos Public Affairs; Brittany Alexander; August Warren, Ipsos Public Affairs; Margie Strickland, Ipsos Public Affairs
Keywords: Probability Panel, Metering, Compliance, Failure Time Analysis, Attrition, Bayes

WITHDRAWN Using Auxiliary Information in Probability Survey Data to Improve Pseudo-Weighting in Non-Probability Samples: A Copula Model Approach — Tingyu Zhu, Oregon State University; Lan Xue, Oregon State University; Virginia Lesser, Oregon State University
Keywords: Inclusion probability, Ancillary variable, Panel sample, Sample likelihood, Pseudo likelihood

Efficacy of Model Based Estimation with Tax Applications — Hamid Ashtiani; Wendy Rotz, Grant Thornton, LLP
Keywords: Tax, Model-Based Estimation, Design-Based Estimation, All or Nothing, Horvitz-Thompson Estimator (Mean Per Unit, MPU), Difference Estimator (DIF)

Tuned Ratio Uniquely Discovered Estimator’s Adjusted Undercount (TRUDEAU) — Sarjinder Singh, Texas A&M University-Kingsville; Stephen Sedory, Texas A & M University - Kingsville
Keywords: Census, Ratio estimator, Correlation bias, DSE, PES, Capture-recapture

Using American Community Survey (ACS) Data in Federal Surveys: from Benchmarking to Machine Learning — Topic-Contributed Paper Session
Chair(s): Samson Adeshiyan, U.S. Energy Information Administration
Discussant(s): Robert Fay, Westat
Organizer(s): Janice Lent, U.S. Energy Information Administration

History of American Community Survey Use in Federal Surveys and Information Products — Mark Asiala, US Census Bureau;

Applying Balanced Sampling to the Current Population Survey — Timothy Trudell

Uses of American Community Survey Results in Conducting the Residential Energy Consumption Survey — James Berry; Grace Deng, U.S. Energy Information Administration; Matt Sanders, U.S. Energy Information Administration

Leveraging the American Community Survey and machine learning for spatial microsimulation — Karthik Akkiraju, Yale University Jared Creason, U.S. Environmental Protection Agency

Analyzing discrete data: challenges in the modern era of data science — Invited Paper Session
Chair(s): Dungang Liu, University of Cincinnati
Organizer(s): Dungang Liu, University of Cincinnati

Bayesian Semiparametric Joint Modeling of Longitudinal Data and Discrete Outcomes — Michael Pennell, The Ohio State University; Woobeen Lim, Food and Drug Administration; Michelle Naughton, The Ohio State University; Electra Paskett, The Ohio State University

Jeffreys-prior penalty in binomial-response generalized linear models — Ioannis Kosmidis, University of Warwick

New Residuals for Regression Models with Discrete Outcomes Based on Double Probability Integral Transform — Lu Yang, University of Minnesota

Rank Intraclass Correlation for Clustered Data — Chun Li, University of Southern California

Worldwide Statistics Without Borders: Innovative Project Collaborations to Inform Decisions and Drive Discovery — Topic-Contributed Panel Session
Chair(s): David Corliss, GM OnStar Insurance
Panelist(s): Michelle Vanchu-Orosco; David Whitford; Michiko Wolcott, Msight Analytics; Organizer(s): Michelle Vanchu-Orosco

Bayesian Estimation of Multilevel Modeling with Survey Data — Invited Panel Session
Chair(s): Sahar Zangeneh, RTI International
Panelist(s): Yajuan Si, University of Michigan; Matt Williams, RTI; Terrance Savitsky, US Bureau of Labor Statistics; Luis Leon Novelo, University of Texas-Health Science Center At Houston-School of Public Health;
Organizer(s): Yajuan Si, University of Michigan

(Hidden) Missing Data Problems in Practice — Topic-Contributed Paper Session
Chair(s): Hans Kiesl, Regensburg University of Applied Sciences
Organizer(s): Florian Meinfelder, Universitaet Bamberg

Multiple Imputation for Measurement Error Problems — Trivellore Raghunathan, University of Michigan

Imputation strategies for right-censored income information in longitudinal administrative data — Joerg Drechsler, Institute for Employment Research

An index for assessing selection bias in non-probability samples: A validation study and a real-world application — Sabine Zinn, DIW Berlin

WITHDRAWN Implicates as Instrumental Variables: An Approach for Estimation and Inference with Probabilistically Matched Data — Dhiren Patki, Federal Reserve Bank of Boston

Data Fusion and the Potential Outcome Framework: Finding the Right Nearest-Neighbor Method — Florian Meinfelder, Universitaet Bamberg

Transporting Clinical Trial Results to the Population — Invited Paper Session
Chair(s): Kean Ming Tan;
Organizer(s): Michael Elliott, University of Michigan

Efficient and robust transfer learning of optimal individualized treatment regime with right-censored survival data — Shu Yang, North Carolina State University, Department of Statistics; Pan Zhao, National Institute for Research in Digital Science and Technology

Examining subgroup-specific treatment effects in multi-source data: source-specific inference and transportability to an external population — Guanbo Wang, Harvard University; Alexander Levis, Carnegie Mellon University; Issa Dahabreh

Expanding the evidence-base for medically underserved populations by integrating evidence from RCTs and electronic health records — Rebecca Hubbard, University of Pennsylvania

Transportability of clinical trial inference to a target population using a 'doubly robust' estimator — Michael Elliott, University of Michigan; Orlagh Carroll, London School of Hygiene and Tropical Medicine

Paving paths forward for governmental data privacy protection, some recent advancements of methods and practice in synthetic data — Topic-Contributed Paper Session
Chair(s): Yajuan Si, University of Michigan
Organizer(s): Yulei He, National Center for Health Statistics; Terrance Savitsky, US Bureau of Labor Statistics

Modernizing data access to more disaggregated data through synthetic data: the UNECE HLG-MOS guide — Kenza Sallier, Statistics Canada; Kate Burnett-Isaacs, Statistics Canada

Understanding and Addressing Challenges for Deidentified Data in Government Applications — Christine Task, Knexus Research Corporation; Gary Howarth

Democratizing access to data for citizen science and open science through use of synthetic data and development of data access pathways for ethical synthetic data use — Amanda Purnell, Veterans Administration

Validation Study of Synthetic California Breast Cancer Registry Data Based on Real-world Analyses — Mandi Yu, National Cancer Institute

Privacy Preserving Techniques: Case Studies from the National Center for Health Statistics — Cordell Golden, National Center for Health Statistics (NCHS/CDC); Lisa Mirel

Model Transportation, Distribution Shift, and Data Integration — Invited Paper Session
Chair(s): Yang Ning, Cornell University
Organizer(s): Jiwei Zhao, University of Wisconsin-Madison

Regularized Continuous Label Shift Adaptation — Qinglong Tian

Extending inferences from a cluster randomized trial to a target population — Sarah Robertson

Integrating information from multiple external studies with reduced parameter sets to improve estimation of a generalized linear model — Jeremy Taylor, University of Michigan

Record Linkage Theory and Methods in Applications and Government Statistics — Invited Paper Session
Chair(s): Jeri Mulrow, Westat
Organizer(s): Michael Larsen, St. Michael's College

National Center for Health Statistics: Realizing the Power of Data through Linkages — Cordell Golden, National Center for Health Statistics (NCHS/CDC); Jessie Parker

Estimation of small area means with linked data — Abel Dasylva, Statistics Canada

Bayesian Record Linkage with Variables in One File — Gauri Kamat, Brown University

Non-independence of identifier agreements under a Fellegi-Sunter record linkage framework — Dean Resnick, NORC at The University of Chicago

An End-to-End Evaluation Framework for Entity Resolution Systems With Application to Inventor Name Disambiguation — Olivier Binette, Duke University

Student Paper Competition Award Winners- Government Statistics Section (GSS), Social Statistics Section (SSS), and Survey Research Methods Section (SRMS) — Topic-Contributed Paper Session
Chair(s): Michael Jadoo, Bureau of Labor Statistics
Organizer(s): Michael Jadoo, Bureau of Labor Statistics

Bayesian jackknife empirical likelihood-based inference for missing data and causal inference problems — Yuke Wang, Georgia State University

Causal Inference with Corrupted Data: Measurement Error, Missing Values, Discretization, and Differential Privacy — Rahul Singh, MIT

Optimal Conformal Prediction for Small Areas — Elizabeth Bersson, Duke University

Safe Policy Learning under Regression Discontinuity Designs with Multiple Cutoffs — Yi Zhang, Harvard University

Sensitivity Analysis for Survey Weights — Melody Huang, University of California, Berkeley

Capturing the Diversity of the United States Through Statistics: The Impact of Coverage — Invited Paper Session Chair(s): Stephen Blumberg
Organizer(s): Jennifer Parker, National Center for Health Statistics; Linda Young, USDA NASS

Combining data to assess broadband access for agricultural producers and their farms — Linda Young, USDA NASS

Providing data for timely health information for diverse populations — Jennifer Parker, National Center for Health Statistics

WITHDRAWN Counting all students: Addressing undercoverage and low response among private PK-12 schools — Gail Mulligan, National Center for Education Statistics

Challenges in equity analysis – hard to reach is hard to measure — Robert Sivinski, Office of Management and Budget

Obtaining informative estimates of rare characteristics: topics in sampling and estimation of rare or difficult to enumerate populations — Topic-Contributed Paper Session Chair(s): Rebecca Andridge, The Ohio State University
Organizer(s): Katherine Thompson, US Census Bureau

Predicting eligibility of a very rare household population to improve sample design — Joe McMichael, RTI International; William Andrews, NOAA Fisheries; Jamie Ridenhour, RTI International

Using Partially Synthetic Frames to Evaluate Alternative Sample Designs for Estimating a Rare Business Characteristic — Stephen Kaputa, US Census Bureau; Hang Joon Kim, University of Cincinnati; Katherine Thompson, US Census Bureau

AN APPLICATION OF ADAPTIVE CLUSTER SAMPLING TO SURVEYING INFORMAL BUSINESSES — David Francis, World Bank; Joshua Wimpey, IBRD World Bank

Neighborhood bootstrap for respondent-driven sampling — Mamadou Yauck, University of Quebec at Montreal

Empirical Best Prediction of Small Area Means Based on a Unit-level Gamma-Poisson Model — Emily Berg