Title: A comparison of preliminary test, stein-type and penalty estimators in gamma regression models
Authors: Akram Mahmoudi - Jönköping International Business School (Sweden) [presenting]
Reza Arabi Belaghi - Tabriz University (Iran)
Saumen Mandal - University of Manitoba (Canada)
Abstract: Some estimators are proposed based on the preliminary test and Stein-type strategies to estimate unknown parameters in a Gamma regression model. These proposed estimators are considered when it is suspected that the parameters may be restricted to a subspace of the parameter space. Also, two penalty estimators such as LASSO and ridge regression are presented. Comprehensive Monte-Carlo simulation experiments are conducted. Then, comparisons are made based on simulated relative efficiency to clarify the performance of the proposed estimators. Practitioners are recommended to use the positive-part Stein-type estimator since its performance is robust irrespective of the reliability of the subspace information. A real data on prostate cancer is considered to illustrate the performance of the proposed estimators.