This might be a long shot, but I thought I'd give ResearchGate a chance to prove itself.
I'm having trouble trying to conduct an ANCOVA in R when one of my variables is a time-dependent covariate. For simplicity sake, let's say I have variables Y, A, B, and X, where Y is my dependent variable, A is a between subjects factor with two levels, B is a within-subjects factor with 6 levels, and X is a continuous variable I want to add as a covariate and is measured at all levels of A and B.
Any help on how to conduct this in R using either lm(), lmer(), aov(), ezANOVA(), or something similar would be very helpful.
Thanks!
You could try with the package 'afex', which is quite similar to 'ez' and has the argument 'covariate'. HTH
http://cran.r-project.org/web/packages/afex/afex.pdf
I'll check that one out. Do you know how it handles time-dependency in covariates? The 'ez' package also has arguments for 'within_covariates' and 'between_covariates' but I'm not convinced that it can handle time-dependency.
Mixed-factors as in a between subjects factor crossed with a within-subjects factor (http://en.wikipedia.org/wiki/Mixed-design_analysis_of_variance).
X is a covariate that is measured within-subjects (like the DV) at each condition of B (the within-subjects factor). X is time-dependent (i.e. time-varying) in that it is not stable across repeated measurements.
We ended up doing something different with it. From my investigation, however, I can tell you that the solution will involve a multilevel modeling approach where observation time is included as a higher order variable in the regression model. Beyond that, I'm not yet expert enough to really provide an adequate answer for you.
However, if you're unfamiliar with multilevel data structure and regression techniques (like I was!), I can recommend the book Data Analysis Using Regression and Multilevel/Hierarchical Models by Andrew Gelman and Jennifer Hill as a starting point. it has been a great resource.
Good luck!
Although it's an old post, I think it would be interesting to supplement it with the following SPSS approach (check out Model 5): https://stats.idre.ucla.edu/spss/faq/how-can-i-do-repeated-measures-anova-with-covariates-in-spss/. Maybe you could have avoided the multilevel modeling approach with this one.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Modeling
- Analyses of Variance
- ANOVA