The Crisscross Method to Evaluate Data Quality in Fertility Surveys

Bruno D. Schoumaker, Université Catholique de Louvain

In this paper, I use the crisscross method (Schmertmann, 2002)- an indirect method of fertility estimation based on cohort parity increments – as a tool to evaluate data quality in birth histories. The method is used (1) to evaluate if the birth histories are affected by data quality problems, and (2) to help identify the type of data quality problems (omissions of recent births, displacements of births, differences in sample implementation). Simulated birth histories and birth histories from Demographic and Health Surveys conducted since the 1980s are used.