How is Type Error computed in proc GLM ?

[Mathis1]

Hello, I would like to know how the type error given by the output of Proc GLM is computed. I initially thought  it was SQRT((p(1-p)/n)) but it's obviously not. 

Thank you for your help 

[Mathis1]

I must precise, i was referring to standard error for each modality of a categorical variable. 

[PaigeMiller]

It is calculated as the standard error of the mean of the Y variable, at a given level of the X variable. Formulas are available in most textbooks, and probably on the internet as well.

By the way, can you fix the title on your original post, because there is no such thing as "Type Error", could you please use the words that SAS uses on the output?

[Rick_SAS · Accepted solution]

If you are asking about the standard error of the parameter estimate, that (and other formulas) are available in the doc section "Parameter Estimates and Associated Statistics."