Attrition in longitudinal household survey data | some tests for three developing-country samples

Longitudinal household data can have considerable advantages over much more widely used cross-sectional data. The collection of longitudinal data, however, may be difficult and expensive. One problem that has concerned many analysts is that sample attrition may make the interpretation of estimates problematic. Such attrition may be particularly severe in areas where there is considerable mobility because of migration between rural and urban areas. Many analysts share the intuition that attrition is likely to be selective on characteristics such as schooling and that high attrition is likely to bias estimates made from longitudinal data. This paper considers the extent of and implications of attrition for three longitudinal household surveys from Bolivia, Kenya, and South Africa that report very high per-year attrition rates between survey rounds. Our estimates indicate that (1) the means for a number of critical outcome and family background variables differ significantly between attritors and nonattritors; (2) a number of family background variables are significant predictors of attrition; but (3) nevertheless, the coefficient estimates for “standard” family background variables in regressions and probit equations for the majority of the outcome variables considered in all three data sets are not affected significantly by attrition. Therefore, attrition apparently is not a general problem for obtaining consistent estimates of the coefficients of interest for most of these outcomes. These results, which are very similar to results for developed economies, suggest that for these outcome variables—despite suggestions of systematic attrition from univariate comparisons between attritors and nonattritors, multivariate estimates of behavioral relations of interest may not be biased due to attrition.

Non-PR

IFPRI1; MP-17

FCND