When presented with a binary classification problem, a common strategy is to try probit or logistic regression first. If the resulting model is not satisfactory then you can try a neural model and use ...

This paper develops new econometric methods to infer hospital quality in a model with discrete dependent variables and non-random selection. Mortality rates in patient discharge records are widely ...

The Clark approximation, in which the maximum of two normally distributed random variables is approximated by a third normally distributed random variable, forms the basis of a relatively inexpensive ...

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 ...