Using Survey-to-Survey Imputation to Fill Poverty Data Gaps at a Low Cost : Evidence from a Randomized Survey Experiment

Survey data on household consumption are often unavailable or incomparable over time in many low- and middle-income countries. Based on a unique randomized survey experiment implemented in Tanzania, this study offers new and rigorous evidence demonstrating that survey-to-survey imputation can fill consumption data gaps and provide low-cost and reliable poverty estimates. Basic imputation models featuring utility expenditures, together with a modest set of predictors on demographics, employment, household assets, and housing, yield accurate predictions. Imputation accuracy is robust to varying the survey questionnaire length, the choice of base surveys for estimating the imputation model, different poverty lines, and alternative (quarterly or monthly) Consumer Price Index deflators. The proposed approach to imputation also performs better than multiple imputation and a range of machine learning techniques. In the case of a target survey with modified (shortened or aggregated) food or non-food consumption modules, imputation models including food or non-food consumption as predictors do well only if the distributions of the predictors are standardized vis-a-vis the base survey. For the best-performing models to reach acceptable levels of accuracy, the minimum required sample size should be 1,000 for both the base and target surveys. The discussion expands on the implications of the findings for the design of future surveys