Interpretation of coefficients in segmented regression for interrupted time series analyses
Two common parametrizations of segmented regression represent the same model but have different interpretations of a key coefficient. Researchers employing either parametrization should exercise caution when interpreting coefficients and calculating intervention effects.
Authors
- Catherine M. Crespi (ORCID: https://orcid.org/0000-0002-6150-2181)
- Gaole Song (ORCID: https://orcid.org/0000-0002-6163-6817)
- Narissa J. Nonzee (ORCID: https://orcid.org/0000-0002-7431-3371)
- Kimlin Ashing (ORCID: https://orcid.org/0000-0002-6209-508X)
- Haonan Zhang (ORCID: https://orcid.org/0000-0002-1590-8842)
- Yongzhe Wang (ORCID: https://orcid.org/0000-0002-4014-6958)
Institutions
- University of Washington (US)
- City of Hope (US)
Publication Details
- Journal
- BMC Medical Research Methodology
- Published
- 2025-04-16
- DOI
- https://doi.org/10.1186/s12874-025-02556-8
- Citations
- 1
- Primary Topic
- Mental Health Research Topics
- Type
- article
- Field-Weighted Citation Impact
- 2.12
Funders
- National Institutes of Health
- National Cancer Institute