Marissa Isidro

IFS, Massey University

Intercensal updating of small area estimates

The main objective of my research has been to develop a feasible and theoretically sound intercensal updating method for small area estimates of poverty statistics in third world countries. My proposed method is called Extended Structure PREserving Estimation (ESPREE) method, this approach is an extension of the classical small area estimation technique called structure preserving estimation (SPREE) method – an approach to small area estimation based on a categorical data analysis framework. ESPREE is structured within a generalized linear model (GLM) framework and uses information from the most recent survey and pseudo-census (replicated sets of the census data) data to generate updated small area estimates.

The World Bank in collaboration with the National Statistical Coordination Board in the Philippines has conducted an intercensal updating project using a methodology based on the widely implemented small area estimation methodology for poverty measures in third world countries called ELL (Elbers, Lanjouw and Lanjouw). The estimates generated from the ELL and the ESPREE updating methods were compared and substantial differences were observed not only at the small area level (municipality) but also at higher levels of aggregation e.g., provincial and regional levels. The ESPREE method seemed to work better than the ELL updating method in that the ESPREE method generated unbiased estimates. An in-country validation exercise was conducted allowing for better assessment of acceptability and consistency of the estimates generated with the available indicators at the municipal level as well as with the expert opinion of key informants.