Classical ordinal logit and probit models are used in studies where the dependent variable is categorical and ordinal. In order to use these models, the assumption of parallel slopes must be met. If this assumption is not met, the generalized ones of the ordinal logit and ordinal probit models, which are more flexible in terms of assumptions, or the multinomial logit model can be used. The aim of this study is to discuss in detail the ordered logit and ordered probit models, which are developed when the dependent variable category is more than two. For this purpose, a sample data set was taken and first of all, the assumption of parallel slopes was investigated. While the validity of the models was tested with the likelihood ratio test statistic, AIC and BIC and deviation statistics were used for the goodness of fit test. The results show that there are no significant differences between the models and there are no strict rules for choosing the probit model or the logit model.