I loose a lot of cases with missing value in this analysis!   I want to analyze correlation among my biomarkers, varA varB varC varD, controlling for varE.  My code is; proc corr;    var varA varB varC varD;    partial varE; run;   I have N=1500 in my data set, in which cases have at least one biomarker.  However, varA has 300 missing cases, varB has 500 missing cases, varC has 150 missing cases, and varE has 500 missing cases.  Some missing cases are overlapped but the others are not overlapped.  When I use the above code, there are only N=50.   How can I calculate, for example, a correlation between varA and varB controlling for varE using all available cases with varA, varB and varE data? I actually have 50 biomarker variables in the correlation analysis.  It is too much to type all pair-wise analyses (1225 pairs) by hand!   Thank you in advance for your help!   Sincerely, Rcore ... View more

This message occurs when I use an output data set (SpearmanCorr) in proc corr. I would like to remove these notes; 15354:NOTE: Invalid numeric data, '<.0001' , at line 101090 column 212. 15355:NOTE: Invalid numeric data, '_' , at line 101090 column 11. My code looks like this; ods output SpearmanCorr=mycorrpvalue; proc corr spearman data=mydata ; var myvariable; run; data new; set mycorrpvalue; if myvariable='<.0001' then myvariable=0.0001; if myvariable='_' then myvariable=.; if 0<myvariable<0.001 then newvar=0.001; else newvar=.; run; This is because the data set mycorrpvalue contains numbers and characters, '<.0001' and '_'. How can I totally replace these characters with number? Sincerely, Nish ... View more