How Much of Observed Economic Mobility is Measurement Error? IV Methods to Reduce Measurement Error Bias, with an Application to Vietnam

Glewwe, Paul

Oxford University Press on behalf of the World Bank

关键词: autocorrelation;    covariance;    Econometrics;    economic growth;    equations;   

学科分类：社会科学、人文和艺术（综合）

来源: World Bank Open Knowledge Repository

【 摘 要 】

Research on economic growth and inequality inevitably raises issues concerning economic mobility because the relationship between long-run inequality and short-run inequality is mediated by income mobility; for a given level of short-run inequality, greater mobility implies lower long-run inequality. But empirical measures of both inequality and mobility tend to be biased upward due to measurement error in income and expenditure data collected from household surveys. This paper examines how to reduce or remove this bias using instrumental variable methods, and provides conditions that instrumental variables must satisfy to provide consistent estimates. This approach is applied to panel data from Vietnam. The results imply that at least 15 percent, and perhaps as much as 42 percent, of measured mobility is upward bias due to measurement error. The results also suggest that measurement error accounts for at least 12 percent of measured inequality.