Reparametrized generalized gamma partially linear regression with application to breast cancer data

We construct a new partially linear regression based on a reparametrized generalized gamma distribution with two systematic components that can be easily interpreted. Its parameters are estimated by penalized maximum likelihood. For different parameter settings, sample sizes, and censoring percentages, some simulations are performed to examine the accuracy of the maximum likelihood estimators, and the empirical distribution of the residuals compared with the standard normal distribution. The methodology is applied to breast cancer data in the city of João Pessoa in the state of Paraíba in Brazil.