Latent Class Analysis of Measurement Error in the Consumer Expenditure Survey (GTP) Survey

Brian J. Meekins and Clyde Tucker


Previous research by Tucker et al. (2010), working with the Consumer Expenditure Survey (CE), explores the factor structure of measurement error indicators such as: interview length, extent and type of records used, the monthly reporting patterns, item missing , attempt information, and panel response behavior in a latent class model. Findings from this research, using cases from 2005 to 2009, yielded models with slightly poorer fit and less efficacy in predicting household expenditure than models using earlier data. While a number of recent revisions have been made to the CE that may have resulted in less measurement error overall, the differences in model fit and efficacy are worthy of investigation. In current research we add the use of the information booklet as an indicator of error.