Analisis estadistico de la eleccion presidencial de 2006. Fraude o errors aleatorios?

In: Política y gobierno

Abstract

This paper tests some of the main fraud allegations of the 2006 presidential election in Mexico with the evidence from a statistical analysis of precinct-level data. First, I analyze the data flow from the quick count, the preliminary results (PREP) & the official district tally (computo distrital). Secondly, I analyze the size & distribution of errors in the polling-station acts & the partial recount. Lastly, I consider atypical precincts & the role of party representatives. My main conclusion is that, since most fraud allegations are not supported by the evidence, the presidential election outcome is statistically reliable. Adapted from the source document.