Misclassification in binary choice (binomial response) models occurs when t
he dependent variable is measured with error, that is, when an actual "one"
response is sometimes recorded as a zero and vice versa. This paper shows
that binary response models with misclassification are semiparametrically i
dentified, even when the probabilities of misclassification depend in unkno
wn ways on model covariates and the distribution of the errors is unknown.