I am trying to understand how I can calculate effect sizes for GEE analyses of longitudinal data. Is it correct that the Exp(B) can be used as an odds ratio, an estimate of the effect size of each model parameter? If so, how can I interpret that with continuous variables?
Cohen's f2 can be used to calculate the effect size of all of the predictors in the model: f2 = R2/(1-R2). See Cohen (1992) for reference and values matching different effect sizes (small, medium, large). Extracting the local effect sizes for particular predictors of interest is somewhat tricky, but I've found Selya and colleagues' (2012) article helpful even if you don't use SAS.
Cohen, J. (1992). A power primer. Psychological Bulletin, 112(1), 155–159. https://doi.org/10.1037/0033-2909.112.1.155
Selya, A. S., Rose, J. S., Dierker, L. C., Hedeker, D., & Mermelstein, R. J. (2012). A practical guide to calculating Cohen’s f2, a measure of local effect size, from PROC MIXED. Frontiers in Psychology, 3(APR). https://doi.org/10.3389/fpsyg.2012.00111
- Badges
- Science topic
- Similar topics
- Psychology