Contrast coding
good summary
http://www.lrdc.pitt.edu/maplelab/slides/Simple_Main_Effects_Fraundorf.pdf
https://gyazo.com/2171ec13f186a7da6523fb8a801ab3a3
https://gyazo.com/a03b4e8919b2be35507ccb6fde3dc2f5
https://gyazo.com/9034c1eaa27f64a6bc681838b2b8464e
https://gyazo.com/2e89966952bea25e7061db4f8eceb76f
Dummy coding
Intercept = the refernece level of the variable with the reference levels of the other variables (only one group)
Effect coding
Intercept = the reference level of the variable with the grand mean (e.g., -0.5 vs. 0.5) of the other variables (ignoring the effects of other variable)
https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/
https://gyazo.com/93a2c5fa47f039e2604dead77e0fc282
Helmart
this type of coding is useful in situations where the levels of the categorical variable are ordered say, from lowest to highest, or smallest to largest, etc.
https://gyazo.com/f0c3fbdf59ef974aa9da706ffd8e3ed5
https://gyazo.com/5ae9d8a7324164632918517212215525
https://gyazo.com/122e0089e000664d262dae6840798898
https://gyazo.com/bebcd0292f0020959739f4948b4f7f6e
Orthgonoal
This type of coding system should be used only with an ordinal variable in which the levels are equally spaced.
Repeated
This type of coding may be useful with either a nominal or an ordinal variable.
table:Interaction (Typical contrast?)
Contrast Level 1 = 0.80 Level 2 = -.20 Level 3 = -.20 Level 4 = -.20 Level 5 = -.20
Level 1 = -0.5 4/5 X -1/2 = -4/10 -1/5 X -1/2 = 1/10 -1/5 X -1/2 = 1/10 -1/5 X -1/2 = 1/10 -1/5 X -1/2 = 1/10
Level 2 = 0.5 4/5 X 1/2 = 4/10 -1/5 X 1/2 = -1/10 -1/5 X 1/2 = -1/10 -1/5 X 1/2 = -1/10 -1/5 X 1/2 = -1/10
https://gyazo.com/b3147fe929cee4521d698d4570229d33