CASEN survey: statistical and methodological misleads in key public policy in Chile

Discussing statistical error and research design problems and the organizational implications of delivering “good news” at all cost.

This case can be used on basic courses of Public Policy, Marketing Research and Quantitative Methods.

MIDEPLAN on July 2012 showed the results of the CASEN (Caracterización Socio-Económica or Socio-Economical Characterization) survey of 2011. The results showed that poverty was lowered by 0.6 per cent and was greatly highlighted by the media. Opposition coalition and academics started to ask questions about statistical error, which was not yet known. It was revealed that the government asked Comisión Económica para América Latina y el Caribe (CEPAL), a public organization dependent on the United Nations (UN) that was helping Chile to manage the CASEN survey, to review the results and incorporate a variable “y11,” but academics questioned it due to comparability reasons. The statistical error was revealed and it was 0.8 per cent. On October 2012, CEPAL decided to stop helping Chilean institutions.

The key analysis and conclusions which should arise as a result of teaching this case are: The relevance of the statistical error as a key component of research to evaluate data; the importance of fully implementing research design and accuracy of every step to reach valid results; analyze and discuss organizational implications of delivering “good news” at all cost.

Teaching Notes are available for educators only. Please contact your library to gain login details or email pfarias@unegocios.cl to request teaching notes.