eCite Digital Repository

Be wary of using Poisson regression to estimate risk and relative risk


Zhu, C and Blizzard, L and Stankovich, J and Wills, K and Hosmer, DW, Be wary of using Poisson regression to estimate risk and relative risk, Biostatistics and Biometrics Open Access Journal, 4, (5) Article 555649. ISSN 2573-2633 (2018) [Refereed Article]


Copyright Statement

Copyright All rights are reserved by Blizzard L. Licensed under Creative Commons Attribution 4.0 International (CC BY 4.0)

Official URL:

DOI: doi:10.19080/BBOAJ.2018.04.555649


Fitting a log binomial model to binary outcome data makes it possible to estimate risk and relative risk for follow-up data, and prevalence and prevalence ratios for cross-sectional data. However, the fitting algorithm may fail to converge when the maximum likelihood solution is on the boundary of the allowable parameter space. Some authorities recommend switching to Poisson regression with robust standard errors to approximate the coefficients of the log binomial model in those circumstances. This solves the problem of non-convergence, but results in errors in the coefficient estimates that may be substantial particularly when the maximum fitted value is large. The paradox is that the circumstances in which the modified Poisson approach is needed to overcome estimation problems are the same circumstances when the error in using it is greatest. We recommend that practitioners should be wary of using modified Poisson regression to approximate risk and relative risk.

Item Details

Item Type:Refereed Article
Keywords:relative risk, log binomial model, Poisson regression, boundary point
Research Division:Mathematical Sciences
Research Group:Statistics
Research Field:Biostatistics
Objective Division:Health
Objective Group:Public health (excl. specific population health)
Objective Field:Public health (excl. specific population health) not elsewhere classified
UTAS Author:Zhu, C (Mr Chao Zhu)
UTAS Author:Blizzard, L (Professor Leigh Blizzard)
UTAS Author:Stankovich, J (Dr Jim Stankovich)
UTAS Author:Wills, K (Dr Karen Wills)
ID Code:135470
Year Published:2018
Deposited By:Menzies Institute for Medical Research
Deposited On:2019-10-23
Last Modified:2020-12-18
Downloads:19 View Download Statistics

Repository Staff Only: item control page