This paper uses latent class analysis (LCA) to estimate the amount of underreporting on the BLS Consumer Expenditure Quarterly Survey (CEQ). Specifically, it models underreporting in a given commodity category by those reporting a purchase of any item within that category. This work builds on previous research by these authors using LCA to model the extent of erroneous nonreports and estimate the amount of underreporting from nonreporters. It also builds on research by Tucker (1992) that models patterns of consumer expenditure reporting based on microlevel, procedural indicators. Data from the CEQ for 1996 to 2003 are used in the analysis. A series of LCA models are used to evaluate observed expenditure reporting patterns. Model covariates include characteristics of the interview, the respondent, and the household. Best-fitting models are determined from statistical and subjective diagnostics developed by the authors. Diagnostic tools developed in previous research are expanded, and issues related to correlated classification errors are discussed. Finally, weighted estimates of the amount of underreported expenditures are produced.