"Misclassification of the Dependent Variable in Binary Choice Models: Evidence from Five Latin American Countries"

Misclassification of the dependent variable in binary choice models can result in inconsistency of the parameter estimates. I estimate probit models that treat misclassification probabilities as estimable parameters for three labor market outcomes: formal sector employment, pension contribution and job change. I use Living Standards Measurement Study data from Nicaragua, Peru, Brazil, Guatemala, and Panama. I find that there is significant misclassification in eleven of the sixteen cases that I investigate. If misclassification is present, but is ignored, estimates of the probit parameters and their standard errors are biased toward zero. In most cases, predicted probabilities of the outcomes are significantly affected by misclassification of the dependent variable. Even a moderate degree of misclassification can have substantial effects on the estimated parameters and on many of the predictions.