Working Paper: NBER ID: w10338
Authors: Orazio Attanasio; Erich Battistin; Hidehiko Ichimura
Abstract: This paper considers data quality issues for the analysis of consumption inequality exploiting two complementary datasets from the Consumer Expenditure Survey for the United States. The Interview sample follows survey households over four calendar quarters and consists of retrospectively collected information about monthly expenditures on durable and non-durable goods. The Diary sample interviews household for two consecutive weeks and includes detailed information about frequently purchased items (food, personal cares and household supplies). Most reliable information from each sample is exploited to derive a correction for the measurement error affecting observed measures of consumption inequality in the two surveys. We find that consumption inequality, as measured by the standard deviation of log non-durable consumption, has increased by roughly 5% points during the 1990s.
Keywords: No keywords provided
JEL Codes: E21; E26
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| consumption inequality (measured by standard deviation of log nondurable consumption) (D31) | increased by approximately 5 points during the 1990s (C80) |
| diary sample (DS) (C80) | substantial increase in consumption inequality (F61) |
| interview sample (IS) (C83) | relatively flat consumption inequality (D31) |
| wage inequality (J31) | increases (O42) |
| consumption inequality (D31) | does not follow the same trajectory as wage inequality (J79) |
| consumption measures (E20) | provide a different perspective on economic well-being (P46) |