Reparameterized extended Maxwell regression: Properties, estimation and application

We propose a reparameterized regression for the median of an extended Maxwell distribution that can be used when the response variable has a positive support. We obtain some structural properties of the distribution. The parameter estimates are obtained by maximum likelihood and Bayesian methods. Some influence measures and quantile residuals are defined. Several Monte Carlo simulations are reported for inference purposes. The new regression is applied to an experimental data set.

Automated summary

We propose a reparameterized regression for estimating the median of an extended Maxwell distribution with positive support. We investigate the structural properties of the distribution and estimate the parameters using maximum likelihood and Bayesian methods. Influence measures and quantile residuals are defined, and Monte Carlo simulations are conducted for inference purposes. The new regression is also applied to an experimental data set.