Search

This paper presents a discussion regarding regression models, especially those belonging to the location class. Our main motivation is that, with simple distributions having simple interpretations, in some cases, one gets better results than the ones obtained with overly complex distributions. For instance, with the reverse Gumbel (RG) distribution, it is possible to explain response variables by making use of the generalized additive models for location, scale, and shape (GAMLSS) framework, which allows the fitting of several parameters (characteristics) of the probabilistic distributions, like mean, mode, variance, and others. Three real data applications are used to compare several location models against the RG under the GAMLSS framework. The intention is to show that the use of a simple distribution (e.g., RG) based on a more sophisticated regression structure may be preferable than using a more complex location model.

Renal insufficiency is a serious medical and public health problem worldwide. Recently, although many surveys have been developed to identify factors related to the lifetime of patients with renal insufficiency, controversial results from several studies suggest that researches should be conducted by region. Thus, in this study we aim to predict and identify factors associated with the lifetime of patients with chronic renal failure (CRF) in the metropolitan area of Maringá, Paraná State, Brazil, based on the generalized additive models for location, scale and shape (GAMLSS) framework. Data used in this study were collected from the Maringá Kidney Institute and comprehends 177 patients (classified with CRF and mostly being treated under the Brazilian Unified National Health System) enrolled in a hemodialysis program from 1978 up to 2010. By using this approach, we concluded that in other regions, gender, kidney transplant indicator, antibodies to hepatitis B and antibodies to hepatitis C are significant factors that affect the expected lifetime.