When outcome variables are not measured on a continuous scale, special models and estimation procedures are needed to take the scale of the outcome variables into account. Mplus has special estimation procedures for binary, ordered categorical (ordinal), unordered categorical (nominal), and count dependent variables. For binary and ordered categorical outcome variables, both weighted least squares and maximum likelihood estimators are available. With weighted least squares, probit regressions are estimated. With maximum likelihood, logistic regressions are estimated. Logistic regression for ordered categorical outcomes uses the proportional odds specification.