Missing observations in regression: a conditional approach
This note presents an alternative to multiple imputation and other approaches to regression analysis in the presence of missing covariate data. Our recommendation, based on factorial and fractional factorial arrangements, is more faithful to ancillarity considerations of regression analysis and invo...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Royal Society
2023-02-01
|
| Series: | Royal Society Open Science |
| Subjects: | |
| Online Access: | https://royalsocietypublishing.org/doi/10.1098/rsos.220267 |
| _version_ | 1797858603138285568 |
|---|---|
| author | H. S. Battey D. R. Cox |
| author_facet | H. S. Battey D. R. Cox |
| author_sort | H. S. Battey |
| collection | DOAJ |
| description | This note presents an alternative to multiple imputation and other approaches to regression analysis in the presence of missing covariate data. Our recommendation, based on factorial and fractional factorial arrangements, is more faithful to ancillarity considerations of regression analysis and involves assessing the sensitivity of inference on each regression parameter to missingness in each of the explanatory variables. The ideas are illustrated on a medical example concerned with the success of hematopoietic stem cell transplantation in children, and on a sociological example concerned with socio-economic inequalities in educational attainment. |
| first_indexed | 2024-04-09T21:16:00Z |
| format | Article |
| id | doaj.art-28d4614a4a924eff889c4d293de6521d |
| institution | Directory Open Access Journal |
| issn | 2054-5703 |
| language | English |
| last_indexed | 2024-04-09T21:16:00Z |
| publishDate | 2023-02-01 |
| publisher | The Royal Society |
| record_format | Article |
| series | Royal Society Open Science |
| spelling | doaj.art-28d4614a4a924eff889c4d293de6521d2023-03-28T08:51:00ZengThe Royal SocietyRoyal Society Open Science2054-57032023-02-0110210.1098/rsos.220267Missing observations in regression: a conditional approachH. S. Battey0D. R. Cox1Department of Mathematics, Imperial College London, London SW7 2AZ, UKNuffield College, University of Oxford, Oxford OX1 1NF, UKThis note presents an alternative to multiple imputation and other approaches to regression analysis in the presence of missing covariate data. Our recommendation, based on factorial and fractional factorial arrangements, is more faithful to ancillarity considerations of regression analysis and involves assessing the sensitivity of inference on each regression parameter to missingness in each of the explanatory variables. The ideas are illustrated on a medical example concerned with the success of hematopoietic stem cell transplantation in children, and on a sociological example concerned with socio-economic inequalities in educational attainment.https://royalsocietypublishing.org/doi/10.1098/rsos.220267ancillarityEM algorithmfractional factorialHadamard matrixmissing dataregression |
| spellingShingle | H. S. Battey D. R. Cox Missing observations in regression: a conditional approach Royal Society Open Science ancillarity EM algorithm fractional factorial Hadamard matrix missing data regression |
| title | Missing observations in regression: a conditional approach |
| title_full | Missing observations in regression: a conditional approach |
| title_fullStr | Missing observations in regression: a conditional approach |
| title_full_unstemmed | Missing observations in regression: a conditional approach |
| title_short | Missing observations in regression: a conditional approach |
| title_sort | missing observations in regression a conditional approach |
| topic | ancillarity EM algorithm fractional factorial Hadamard matrix missing data regression |
| url | https://royalsocietypublishing.org/doi/10.1098/rsos.220267 |
| work_keys_str_mv | AT hsbattey missingobservationsinregressionaconditionalapproach AT drcox missingobservationsinregressionaconditionalapproach |