Journal of Political Economy · 1986 · 213 citations · 0 references
Social SciencesEconomicsCensus AnalysisLabor EconomicsPopulation StudiesCensus Data AnalysisDemographic AnalysisIncome DistributionMissing Data ComputationMissing Data ImputationMissing Data MethodsActual IncomeCensus ImputationData ImputationImputation Of EarningsImputed Income AssessmentMissing Data In Surveys
A growing share of respondents in key microdata sets refuse to report income, prompting the Census Bureau to impute missing values. The study evaluates the Census Bureau’s imputation method and questions its validity. The hot‑deck imputation matches nonrespondents to demographically similar donors, relying on event commonality rather than informative regressors. The method underestimates income for some occupations and likely underestimates average incomes due to an invalid assumption about reporting propensities.
In the most frequently used microdata sets, over a quarter of all respondents now refuse to answer some questions about their incomes. The Census Bureau has dealt with this problem, which has been increasing in severity over time, by imputing incomes of non-respondents. Their imputation procedure, called the "hot deck," essentially matches nonrespondents with demographically similar donors. In this paper we evaluate the census imputation methodology and raise some questions. First, the census procedure is tied to commonality of events in the population rather than the more appropriate informational content of regressors. Clearly, the census procedure severely understates income in certain occupations. Because it is based on the apparently invalid assumption that income does not affect reporting propensities, it most likely understates average incomes as well.