On some beta ridge regression estimators: method, simulation and application

The classic statistical method for modelling the rates and proportions is beta regression model (BRM). standard maximum likelihood estimator (MLE) used to estimate coefficients of BRM. However, this MLE very sensitive when regressors are linearly correlated. Therefore, study introduces a new ridge (BRR) as remedy problem instability MLE. We mean squared error properties BRR analytically then based on derived MSE, we suggest some estimators shrinkage parameter. also median (SE) performance criterion, which can be achieve strong evidence in favour proposed Monte Carlo simulation study. appraised through simulation. Finally, an empirical application show advantages estimator.