The article presents a statistical model for analyzing data when the observed dependent variable is in ordinal form. This model is an extension of the dichotomous probit model and assumes that the ordinal nature of the data is due to limitations in data collection. It considers a linear effect of each independent variable and break points between categories for the dependent variable. Maximum likelihood estimators are used to find parameters, and a measure of goodness of fit is defined. The model is demonstrated by analyzing Congressional voting on the 1965 Medicare Bill.