Adjusting for covariates in correlation test

[cardinal]

Hi,

I wonder if it is possible to adjust for covariates when we use PROC CORR (correlation test) in SAS.

Thanks!

 

[hlsmith]

You can likely do a partial correlation.

What is the purpose of doing this andwhy would it be preferred over multiple linear regression?

 

[cardinal]

Thanks for your reply.

I am going to report some spearman correlations statistics. I know age and BMI influences my reported correlations, so I want to adjust for these two.

 

[hlsmith]

This seems to work, I tried it and added spearman in the top line:

[FONT=Courier New][SIZE=2][COLOR=#000080][FONT=Courier New][SIZE=2][COLOR=#000080][FONT=Courier New][SIZE=2][COLOR=#000080][B]proc[/B][/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][B][FONT=Courier New][SIZE=2][COLOR=#000080][FONT=Courier New][SIZE=2][COLOR=#000080][FONT=Courier New][SIZE=2][COLOR=#000080]corr[/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][/B][FONT=Courier New][SIZE=2][COLOR=#0000ff][FONT=Courier New][SIZE=2][COLOR=#0000ff][FONT=Courier New][SIZE=2][COLOR=#0000ff]data[/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][FONT=Courier New][SIZE=2][FONT=Courier New][SIZE=2]=cf_combo_2 [/SIZE][/FONT][/SIZE][/FONT][FONT=Courier New][SIZE=2][COLOR=#0000ff][FONT=Courier New][SIZE=2][COLOR=#0000ff][FONT=Courier New][SIZE=2][COLOR=#0000ff]spearman[/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][FONT=Courier New][SIZE=2][FONT=Courier New][SIZE=2] plots=scatter([/SIZE][/FONT][/SIZE][/FONT][FONT=Courier New][SIZE=2][COLOR=#0000ff][FONT=Courier New][SIZE=2][COLOR=#0000ff][FONT=Courier New][SIZE=2][COLOR=#0000ff]alpha[/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][FONT=Courier New][SIZE=2][FONT=Courier New][SIZE=2]=[/SIZE][/FONT][/SIZE][/FONT][B][FONT=Courier New][SIZE=2][COLOR=#008080][FONT=Courier New][SIZE=2][COLOR=#008080][FONT=Courier New][SIZE=2][COLOR=#008080].20[/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][/B][B][FONT=Courier New][SIZE=2][COLOR=#008080][FONT=Courier New][SIZE=2][COLOR=#008080][FONT=Courier New][SIZE=2][COLOR=#008080].30[/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][/COLOR][/SIZE][/FONT][/B][FONT=Courier New][SIZE=2][FONT=Courier New][SIZE=2]);[/SIZE][/FONT][/SIZE][/FONT]

See link for description, image part may be irrelevant and based on Pearson. So I am not saying this IS the answer, you may need to double check to make sure it is really doing what I am presuming it is. You could run it with and with out the partial syntax part and see if you get the same results given the partial variable is truly correlated with the variables.


http://support.sas.com/documentatio...fault/viewer.htm#procstat_corr_examples12.htm

 

[cardinal]

I have another question. I appreciate your help in advance.

I would like to look at the correlation of a hormone level (continuous variable) and a genotype activity (categorical variable with the following levels:COMT-low, COMT-high, and COMT-intermediate). How should I do this in SAS?
PS I have done the polyserial correlation but that doesn't make sense to me!