A class of residuals for outlier identification in zero adjusted regression models
| Autor: | Denise Aparecida Botter, Gustavo H. A. Pereira, Juliana Scudilio, Mônica Carneiro Sandoval, Manoel Santos-Neto |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Statistics and Probability
Class (set theory) 021103 operations research 0211 other engineering and technologies Zero (complex analysis) Regression analysis Articles 02 engineering and technology Interval (mathematics) 01 natural sciences 010104 statistics & probability Identification (information) DIAGNÓSTICO Mathematics::K-Theory and Homology Diagnostic analysis Outlier Statistics 0101 mathematics Statistics Probability and Uncertainty Positive real numbers Mathematics |
| Zdroj: | Repositório Institucional da USP (Biblioteca Digital da Produção Intelectual) Universidade de São Paulo (USP) instacron:USP J Appl Stat |
| ISSN: | 1360-0532 0266-4763 |
| DOI: | 10.1080/02664763.2019.1696759 |
| Popis: | Zero adjusted regression models are used to fit variables that are discrete at zero and continuous at some interval of the positive real numbers. Diagnostic analysis in these models is usually performed using the randomized quantile residual, which is useful for checking the overall adequacy of a zero adjusted regression model. However, it may fail to identify some outliers. In this work, we introduce a class of residuals for outlier identification in zero adjusted regression models. Monte Carlo simulation studies and two applications suggest that one of the residuals of the class introduced here has good properties and detects outliers that are not identified by the randomized quantile residual. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|