A note on a reformulation of the KHB method
The Karlson–Holm–Breen (KHB) method has rapidly become popular as a way of separating the impact of confounding from rescaling when comparing conditional and unconditional parameter estimates in nonlinear probability models such as the logit and probit. In this note, we show that the same estimates...
| المؤلفون الرئيسيون: | , , |
|---|---|
| التنسيق: | Journal article |
| منشور في: |
SAGE Publications
2018
|
| _version_ | 1826266750462722048 |
|---|---|
| author | Breen, R Karlson, K Holm, A |
| author_facet | Breen, R Karlson, K Holm, A |
| author_sort | Breen, R |
| collection | OXFORD |
| description | The Karlson–Holm–Breen (KHB) method has rapidly become popular as a way of separating the impact of confounding from rescaling when comparing conditional and unconditional parameter estimates in nonlinear probability models such as the logit and probit. In this note, we show that the same estimates can be obtained in a somewhat different way to that advanced by Karlson, Holm, and Breen in their original article and implemented in the user-written Stata command khb. While the KHB method and this revised KHB method both work by holding constant the residual variance of the model, the revised method makes comparisons across multiple nested models easier than the original method. |
| first_indexed | 2024-03-06T20:43:42Z |
| format | Journal article |
| id | oxford-uuid:3522f94e-dd91-4d35-bc5c-446d8379e8e3 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T20:43:42Z |
| publishDate | 2018 |
| publisher | SAGE Publications |
| record_format | dspace |
| spelling | oxford-uuid:3522f94e-dd91-4d35-bc5c-446d8379e8e32022-03-26T13:30:14ZA note on a reformulation of the KHB methodJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:3522f94e-dd91-4d35-bc5c-446d8379e8e3Symplectic Elements at OxfordSAGE Publications2018Breen, RKarlson, KHolm, AThe Karlson–Holm–Breen (KHB) method has rapidly become popular as a way of separating the impact of confounding from rescaling when comparing conditional and unconditional parameter estimates in nonlinear probability models such as the logit and probit. In this note, we show that the same estimates can be obtained in a somewhat different way to that advanced by Karlson, Holm, and Breen in their original article and implemented in the user-written Stata command khb. While the KHB method and this revised KHB method both work by holding constant the residual variance of the model, the revised method makes comparisons across multiple nested models easier than the original method. |
| spellingShingle | Breen, R Karlson, K Holm, A A note on a reformulation of the KHB method |
| title | A note on a reformulation of the KHB method |
| title_full | A note on a reformulation of the KHB method |
| title_fullStr | A note on a reformulation of the KHB method |
| title_full_unstemmed | A note on a reformulation of the KHB method |
| title_short | A note on a reformulation of the KHB method |
| title_sort | note on a reformulation of the khb method |
| work_keys_str_mv | AT breenr anoteonareformulationofthekhbmethod AT karlsonk anoteonareformulationofthekhbmethod AT holma anoteonareformulationofthekhbmethod AT breenr noteonareformulationofthekhbmethod AT karlsonk noteonareformulationofthekhbmethod AT holma noteonareformulationofthekhbmethod |