-
Notifications
You must be signed in to change notification settings - Fork 2
Home
This page answers some of the most typical questions asked by users of the R-package "phia". Many of these answers are actually repetitions or expansions on the information that is given in the vignette that comes with the package. If you have a question that is not answered in this page, please check first that vignette.
Some users have doubts that are not that much related to how the package works, but are rather general questions on statistics or model fitting. Those questions will not be answered in these FAQ, since there are many available resources on the web with excellent introductions to statistics, which readers are encouraged to look into.
- [[What is the meaning of the column "Value" in the tables returned by
testInteractions?|Maths-behind-phia-functions#what-is-the-meaning-of-the-column-value-in-the-tables-returned-by-testinteractions]] - [[How does
testInteractionstest pairwise comparisons: by Scheffé's method, Tukey's...?|Maths-behind-phia-functions#how-does-testinteractions-test-pairwise-comparisons-by-scheffés-method-tukeys]] - Why do I obtain p-values from a Chi-squared distribution instead of an F distribution?
- Can I analyse with "phia" models fitted by other methods (GAM, RLM...)?
- I would like to test differences between factor levels, but in different combinations to those given by
testInteractions. - The p-values reported by
testInteractionsare all very close to 1, although according to the ANOVA there were significant differences and interactions.
- What does the column "SE of link" mean in the tables of
interactionMeans? - How can I interpret the values of adjusted means and interactions of a GLM
If you think that you found a bug, please file an issue with the description of your problem, ideally copying a minimal reproducible example. Or if you don't feel like setting up a GitHub account for it, try submitting your issues through Git Reports. And if you are an advanced user and have any code suggestion for improving the package, please feel free to fork this repository and send a pull request with your proposed changes!