Comparison between Highly Complex Location Models and GAMLSS
| Autor: | Lucas Augusto Vieira, Thiago G. Ramires, Luiz Ricardo Nakamura, Carlos Eduardo Pereira, Ana Julia Righetto, Renan J. Carvalho |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
distributional regression
Computer science Science QC1-999 regression models General Physics and Astronomy Astrophysics beyond mean regression 01 natural sciences Article smoothing functions 010104 statistics & probability 03 medical and health sciences Gumbel distribution Applied mathematics 0101 mathematics 030304 developmental biology 0303 health sciences parsimony principle Location model Physics Generalized additive model Probabilistic logic Mode (statistics) Regression analysis Variance (accounting) Regression QB460-466 MODELOS LINEARES GENERALIZADOS |
| Zdroj: | Entropy, Vol 23, Iss 469, p 469 (2021) Entropy Volume 23 Issue 4 Repositório Institucional da USP (Biblioteca Digital da Produção Intelectual) Universidade de São Paulo (USP) instacron:USP |
| ISSN: | 1099-4300 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |