Generalized two-parameter estimators in the multinomial logit regression model: methods, simulation and application

In this article, we propose generalized two-parameter (GTP) estimators and an algorithm for the estimation of shrinkage parameters to combat multicollinearity in multinomial logit regression model. addition, mean squared error properties are derived. A simulation study is conducted investigate performance proposed different sample sizes, degrees multicollinearity, number explanatory variables. Swedish football league dataset analyzed show benefits GTP over traditional maximum likelihood estimator (MLE). The empirical results article revealed that have a smaller than MLE can be recommended practitioners.