In the video link I have attached, a particular Friedman's test is implemented for a comparison of several treatments against a control. I am not sure if this implementation is well known. My knowledge is that Friedman compares several treatments in an all-to-all fashion. Also, I do not know if this tests maintains the Type I error constant.
This proposed test would be a non-parametric version of a Dunnett's test, with repeated measures.
Particularly, I wanted to know:
- Are there open source references about this test? the video has a website reference (http://appliednonparametricstatistic.blogspot.com), and there is a cited book there called "Applied Nonparametric Statistics" by Wayne A. Daniel http://www.amazon.com/Applied-Nonparametric-Statistics-Wayne-Daniel/dp/0534381944. I guess that more explanations about publications could be there. Any guiding content with more references would be useful.
- Is the Type I error controlled by using this test on a comparison of a higher number of treatments against a control?