Comparing Cross-Survey Micro Imputation and Macro Projection Techniques: Poverty in Post Revolution Tunisia


  • Jose Cuesta Georgetown University
  • Gabriel Lara Ibarra World Bank


Tunisia was showcased for a long time as an example of poverty reduction achievement and pro-poor growth. Yet, after halving its poverty rates a revolution took the world by surprise early in 2011 and since then nothing is known about its poverty levels. To fill that gap, this analysis develops and compares multiple cross-survey micro imputations (using household budgetary and labor force surveys) with macro poverty projections (based on sector GDP, unemployment and inflation). Results from both techniques are robust: poverty in post revolution Tunisia first increased in 2011 to then decrease in 2012. The magnitude of this swing oscillates between 1 and 2.3 percent points and accrues mostly from urban areas. Methods using readily available macro administrative data provide estimates of poverty levels and trends very close to those provided by analytically more sophisticated and data demanding micro imputation techniques. These findings for Tunisia provide relevant insights in data deprived contexts with serious deficiencies in the frequency and accessibility of welfare statistics.