Since ANCOVA is essentially regression with some additional assumptions, we can still construct an ANCOVA-like solution using regression even when the homogeneity of slopes assumption is violated. This assumption is violated when there is a significant interaction between the covariate and the independent variable.
Topics
References
Seltman, H. J. (2018) Experimental design and analysis
https://stat.cmu.edu/~hseltman/309/Book/PrefTOC.pdf
PennState (2024) Unequal slopes model: salary example
https://online.stat.psu.edu/stat502/lesson/9/9.5
Dear Charles,
first of all, thank you for your great work! Which alternatives are there, if the assumptions of an ANCOVA are not met? You mention that it is possible, but i can’t perveive a suggestion of an alternative. I hope i don’t oversee something on this page…
Thank you very much,
Severin
Dear Severin,
You need to click on the Basic Concepts link among the Topics on this webpage.
Charles