Measuring Income in Surveys

"Income Measures in Cross-National Surveys: Problems and Solutions" (with Grigore Pop-Eleches)

Comparable household income measures are crucial for most social science analyses of cross-national public opinion survey data. However, income questions in many cross-national surveys suffer from comparability and interpretability limitations that have not been adequately addressed by the existing literature. In this article, we examine the income measure in one major survey, the World Values Survey (WVS), arguing that a variety of problems arise when drawing inferences - descriptive or causal, individual or aggregate - using the standard 10-category measure. We then propose and implement a number of corrections to these potential biases and present a series of diagnostics that confirm the importance of our proposed corrections. We conclude by documenting some of the same challenges in the income measures used in other cross-national surveys. The accompanying data set can be merged with the WVS to make better use of the income measure.

"Measuring Subjective and Objective Income in Cross-National Surveys" (with Grigore Pop-Eleches)

This paper examines the impact of two similar, but conceptually distinct measures of income. We first describe the theoretical underpinnings of these two measures, arguing that both are valid measures, but that they ultimately differ in what they are trying to measure. In some theoretical frameworks, subjective income mediates the impact of objective income on some variables, in others, they should act separately. We then examine the impact of objective and subjective income measures on the same dependent variables. We show that while it is true that some attitudes are correlated with both forms of income to a similar degree, it is not the case that this makes them interchangeable for most research purposes.

A draft and data will be posted here soon.