Note on optimal predictors of binary response

In a recent Economics Letters article, Terza [Terza, J.V., 2006. Optimal Discrete Prediction in Parametric Binary Response Models. Economics Letters 91, 72–75] shows that the optimal threshold is 1/2 for binary-response prediction under symmetric loss. We show that Terzaʹs result is in fact a special case of a more general and simpler result by Manski and Thompson [Manski, C.F., Thompson, T.S., 1989. Estimation of Best Predictors of Binary Response. Journal of Econometrics 40, 97–123].