01-04-2017 11:14 AM
My question is more about statistics methods.
Say, I have variables A and B to predict variable C that is a count.
A balance between A and B is supposed to be positively associated with C, which has been tested and proved.
Now, my research takes a closer look at this equation. In particular, in the context of a balance between A and B, A may have four different dimensions. These dimensions are not mutually exclusive. In other words, two or more dimensions of A may happen at the same time. I want to test how each dimension of A impacts C, and how A's dimensions interactively impact C, contigent on a balance between A and B.
It seems that I'm stuck with too many interactions. Do you wise people have better ideas on how to test this, apparently in SAS? Thank you!
01-05-2017 02:09 PM - edited 01-05-2017 02:09 PM
Could you explain what you mean by "balance" and "dimensions"? Are A and B discrete (categorical) variables?
In the ANOVA setting, "balance" refers to the number of observations in each level of a categorical variable. For example, if a study has 50 males and 50 females, then the SEX variable is balanced.
When you say "dimension," do you mean the number of levels of a categorical variable? Please give an example of data where "two or more dimensions of A may happen at the same time."