Working Paper: NBER ID: w19589
Authors: John Sabelhaus; David Johnson; Stephen Ash; David Swanson; Thesia Garner; John Greenlees; Steve Henderson
Abstract: Aggregate under-reporting of household spending in the Consumer Expenditure Survey (CE) can result from two fundamental types of measurement errors: higher-income households (who presumably spend more than average) are under-represented in the CE estimation sample, or there is systematic under-reporting of spending by at least some CE survey respondents. Using a new data set linking CE units to zip-code level average Adjusted Gross Income (AGI), we show that the very highest-income households are less likely to respond to the survey when they are sampled, but unit non-response rates are not associated with income over most of the income distribution. Although increasing representation at the high end of the income distribution could in principle significantly raise aggregate CE spending, the low reported average propensity to spend for higher-income respondent households could account for at least as much of the aggregate shortfall in total spending.
Keywords: Consumer Expenditure Survey; Income Representation; Household Spending; Measurement Error
JEL Codes: C83; D12
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| lower response rates (C83) | underrepresentation of high-income households (R20) |
| underrepresentation of high-income households (R20) | shortfall in reported aggregate spending (H62) |
| low reported average propensity to spend for higher-income respondents (D12) | aggregate shortfall in total spending (H62) |
| underreporting of spending among higher-income households (D12) | underestimation of expenditures relative to other income groups (H59) |
| higher-income families (I24) | lower response rates (C83) |
| higher AGI (Q19) | higher nonresponse probability (C83) |