Factors associated with: problems of using exploratory multivariable regression to identify causal risk factors
Lewer and colleagues explain why risk factors for a health outcome should not be studied by putting several candidate independent variables (exposures) into a multivariable regression model and identifying which are statistically significant after mutual adjustment.
Authors
- Thomas D. Brothers (ORCID: https://orcid.org/0000-0002-5570-5556)
- Elizabeth O’Nions (ORCID: https://orcid.org/0000-0003-4427-0910)
- John Pickavance (ORCID: https://orcid.org/0000-0002-5259-5291)
- Dan Lewer (ORCID: https://orcid.org/0000-0003-3698-7196)
Institutions
- Dalhousie University (CA)
- University of Bradford (GB)
- University College London (GB)
Publication Details
- Journal
- BMJ Medicine
- Published
- 2025-10-01
- DOI
- https://doi.org/10.1136/bmjmed-2025-001375
- Citations
- 2
- Primary Topic
- Statistical Methods in Epidemiology
- Type
- article
- Field-Weighted Citation Impact
- 5.26