On group comparisons with logistic regression models
<p>It is widely believed that regression models for binary responses are problematic if we want to compare estimated coefficients from models for different groups or with different explanatory variables. This concern has two forms. The first arises if the binary model is treated as an estimat...
| Главные авторы: | , |
|---|---|
| Формат: | Journal article |
| Опубликовано: |
SAGE Publications
2018
|
| _version_ | 1826286717204692992 |
|---|---|
| author | Kuha, J Mills, C |
| author_facet | Kuha, J Mills, C |
| author_sort | Kuha, J |
| collection | OXFORD |
| description | <p>It is widely believed that regression models for binary responses are problematic if we want to compare estimated coefficients from models for different groups or with different explanatory variables. This concern has two forms. The first arises if the binary model is treated as an estimate of a model for an unobserved continuous response, and the second when models are compared between groups which have different distributions of other causes of the binary response. We argue that these concerns are usually misplaced. The first of them is only relevant if the unobserved continuous response is really the subject of substantive interest. If it is, the problem should be addressed through better measurement of this response. The second concern refers to a situation which is unavoidable but unproblematic, in that causal effects and descriptive associations are inherently group-dependent and can be compared as long as they are correctly estimated. </p> |
| first_indexed | 2024-03-07T01:47:53Z |
| format | Journal article |
| id | oxford-uuid:9909efa6-e588-46fa-a0ba-6204a309ce10 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T01:47:53Z |
| publishDate | 2018 |
| publisher | SAGE Publications |
| record_format | dspace |
| spelling | oxford-uuid:9909efa6-e588-46fa-a0ba-6204a309ce102022-03-27T00:11:28ZOn group comparisons with logistic regression modelsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:9909efa6-e588-46fa-a0ba-6204a309ce10Symplectic Elements at OxfordSAGE Publications2018Kuha, JMills, C <p>It is widely believed that regression models for binary responses are problematic if we want to compare estimated coefficients from models for different groups or with different explanatory variables. This concern has two forms. The first arises if the binary model is treated as an estimate of a model for an unobserved continuous response, and the second when models are compared between groups which have different distributions of other causes of the binary response. We argue that these concerns are usually misplaced. The first of them is only relevant if the unobserved continuous response is really the subject of substantive interest. If it is, the problem should be addressed through better measurement of this response. The second concern refers to a situation which is unavoidable but unproblematic, in that causal effects and descriptive associations are inherently group-dependent and can be compared as long as they are correctly estimated. </p> |
| spellingShingle | Kuha, J Mills, C On group comparisons with logistic regression models |
| title | On group comparisons with logistic regression models |
| title_full | On group comparisons with logistic regression models |
| title_fullStr | On group comparisons with logistic regression models |
| title_full_unstemmed | On group comparisons with logistic regression models |
| title_short | On group comparisons with logistic regression models |
| title_sort | on group comparisons with logistic regression models |
| work_keys_str_mv | AT kuhaj ongroupcomparisonswithlogisticregressionmodels AT millsc ongroupcomparisonswithlogisticregressionmodels |