Meaning of residual/standard error of residuals in Proc Reg

CheerfulChu — Fri, 21 Jul 2017 21:21:48 GMT

Dear Experts

I have two questions:

https://support.sas.com/documentation/cdl/en/statug/63033/HTML/default/viewer.htm#statug_reg_sect039.htm

what is the square bracket in STDR means? What does the STDR means? Is it same as ri / sqrt( 1/(n-1) * sum ri^2 ) where ri is the ith residual computed as yi - yi hat.

Q2.

proc reg data=work.cfs0x1 noprint;

model &alpname = &regvars/noint;

weight glswgt;

output out=&tmp_ds p=pred_alpha_x stdr=stdr_alpha_x;

run;

data work.cfs0x1;

merge work.cfs0x1(in=in_1)

&tmp_ds(in=in_2);

&alpname = (&alpname - pred_alpha_x) / stdr_alpha_x;

run;

Do you know what is the meaning for calculating &alpname = (&alpname - pred_alpha_x) / stdr_alpha_x ? I read that people called it regression neutralization. I dont see how it really does.

Re: Meaning of residual/standard error of residuals in Proc Reg

Reeza — Fri, 21 Jul 2017 22:52:48 GMT

I'm not sure what you mean by the square bracket. Can you please highlight it here:

http://documentation.sas.com/?docsetId=statug&docsetVersion=14.2&docsetTarget=statug_reg_details25.htm&locale=en

Note that I'm using the latest documentation since the old one did not render properly in my browser.

I think if you follow the chain of links it leads you to a detailed page with explanation of the statistics, I just don't have time to go down that rabbit hole right now.

topic Re: Meaning of residual/standard error of residuals in Proc Reg in Statistical Procedures

Meaning of residual/standard error of residuals in Proc Reg

Re: Meaning of residual/standard error of residuals in Proc Reg