Working Paper: NBER ID: w14458
Authors: Richard V. Burkhauser; Shuaizhang Feng; Jeff Larrimore
Abstract: Using the Census Bureau's internal March Current Population Surveys (CPS) file, we construct and make available variances and cell means for all topcoded income values in the public-use version of these data. We then provide a procedure that allows researchers with access only to the public-use March CPS data to take advantage of this added information when imputing its topcoded income values. As an example of its value we show how our new procedure improves on existing imputation methods in the labor earnings inequality literature.
Keywords: Labor Earnings; Inequality; Imputation
JEL Codes: C8; D31; J3
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Traditional methods of imputing topcoded earnings in the CPS (C80) | Significant understatements of labor earnings variance (J31) |
| Significant understatements of labor earnings variance (J31) | Affects the measurement of income inequality (D31) |
| Proposed method integrating cell means and variances in a Stoppa distribution framework (C46) | More accurately reflects the distribution of labor earnings (J31) |
| Proposed method (C59) | Log variance estimates closer to those observed in internal data (C51) |
| Proposed method (C59) | Log variance of labor earnings greater than that observed when using cell means alone (J39) |
| Proposed method (C59) | Log variance of labor earnings less than that estimated under the Pareto distribution assumption (J79) |