Abstract
Error in survey data originates from failure to contact the sample and from false answers to verifiable questions. These errors may be systematic and associated with uncooperative or unreliable respondents. Zabel modeled attrition in the Survey of Income and Program Participation and found systematic demographic and design effects. Bollinger and David modeled response error and identified correlations to income per capita. In this analysis, we link missing interviews in a panel and response error through a trivariate probit analysis. Robustness of the correlation between attrition and response error is examined by comparing variants of the model. The joint model of response error and attrition becomes the first stage of a pseudolikelihood estimate of a model of food-stamp participation. The model is significantly different from naive probit on the survey data.
| Original language | English |
|---|---|
| Pages (from-to) | 129-141 |
| Number of pages | 13 |
| Journal | Journal of Business and Economic Statistics |
| Volume | 19 |
| Issue number | 2 |
| DOIs | |
| State | Published - Apr 2001 |
Bibliographical note
Funding Information:We gratefully acknowledge support from the National Science Foundation, grants SBR-9511935 and SBR-952174. We thank the Census Bureau for indispensable assistance and particularly Ket Mnriqs.aPartuicipants in a variety of seminars contributed substantially to our understanding of the problem. We also thank two anonymous referees for valuable suggestions. The work could not havbeencemoletedpwithout the assistance of Joseph Hendrickson. The views expressed here are those of the authors and do not represent viewoftseh Census Bureau. The authors are solely responsible for errrs.o
Keywords
- Measurement error
- Multivariate probit
- Psuedolikelihood
ASJC Scopus subject areas
- Statistics and Probability
- Social Sciences (miscellaneous)
- Economics and Econometrics
- Statistics, Probability and Uncertainty