.png){kind=icon}
.png){kind=icon}
Return
Robust logistic regression for ordered and unordered responses
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ecosta.2023.05.004.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multinomial regression models and cumulative, adjacent-categories and continuation-ratio models are applied in many fields to analyze unordered or ordered responses with respect to subjects' profiles. They are typically fitted by maximum likelihood estimators, which unfortunately are sensitive to anomalous data. In order to cope with these data robust M type estimators can be applied. They exploit the properties of the logistic link function and are based on a weighted likelihood approach. The M estimators can be easily implemented numerically, provide reliable inference when data are contaminated and lead to an accurate model specification. Inference based on the M estimators is illustrated in three case studies related to risk attitude in financial investments, diabetes in non-obese adult patients and intensity of chronic pain in aging people. (c) 2023 EcoSta Econometrics and Statistics. Published by Elsevier B.V. All rights reserved.
Keywords:
Anomalous data
Logistic link function
Nominal response model
Ordinal response models
Robustness
Journal
E
IF:
2.5
Papers:
31
Citations:
0
