| Full text | |
| Author(s): |
Hashimoto, Elizabeth M.
[1]
;
Ortega, Edwin M. M.
[2]
;
Cordeiro, Gauss M.
[3]
;
Cancho, Vicente G.
[4]
;
Klauberg, Carine
[5]
Total Authors: 5
|
| Affiliation: | [1] UTFPR, Dept Acad Matemt, Apucarana - Brazil
[2] ESALQ USP, Dept Ciencias Exatas, Av PaduaDias 11, Caixa Postal 9, BR-13418900 Piracicaba, SP - Brazil
[3] Univ Fed Pernambuco, Dept Estat, Recife, PE - Brazil
[4] ICMC USP, Dept Matemat Aplicada & Estat, Sao Carlos, SP - Brazil
[5] US Forest Serv, USDA, Rocky Mt Stn, Forestry Sci Lab, Moscow, ID - USA
Total Affiliations: 5
|
| Document type: | Journal article |
| Source: | JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION; v. 89, n. 1, p. 52-70, JAN 2 2019. |
| Web of Science Citations: | 0 |
| Abstract | |
Zero-inflated data are more frequent when the data represent counts. However, there are practical situations in which continuous data contain an excess of zeros. In these cases, the zero-inflated Poisson, binomial or negative binomial models are not suitable. In order to reduce this gap, we propose the zero-spiked gamma-Weibull (ZSGW) model by mixing a distribution which is degenerate at zero with the gamma-Weibull distribution, which has positive support. The model attempts to estimate simultaneously the effects of explanatory variables on the response variable and the zero-spiked. We consider a frequentist analysis and a non-parametric bootstrap for estimating the parameters of the ZSGW regression model. We derive the appropriate matrices for assessing local influence on the model parameters. We illustrate the performance of the proposed regression model by means of a real data set (copaiba oil resin production) from a study carried out at the Department of Forest Science of the Luiz de Queiroz School of Agriculture, University of Sao Paulo. Based on the ZSGW regression model, we determine the explanatory variables that can influence the excess of zeros of the resin oil production and identify influential observations. We also prove empirically that the proposed regression model can be superior to the zero-adjusted inverse Gaussian regression model to fit zero-inflated positive continuous data. (AU) | |
| FAPESP's process: | 10/04496-2 - Gamma-G regression model in survival analysis |
| Grantee: | Elizabeth Mie Hashimoto |
| Support Opportunities: | Scholarships in Brazil - Doctorate |