Probit ("probability unit") regression is a classical machine learning technique that can be used for binary classification -- predicting an outcome that can only be one of two discrete values. For ...

Equicorrelated binary observations are modelled using a multivariate probit regression model. Log likelihood derivatives are reduced to simple linear combinations of equicorrelated multivariate normal ...

Probit regression is very similar to logistic regression and the two techniques typically give similar results. Probit regression tends to be used most often with finance and economics data, but both ...