Dealing with missing value in panel analysis

[Marcello91]

Hi everybody, I'm a new user and I would like to have suggestions to solve a matter. I have to do a panel analysis with numerical data. When running the "proc panel" I get this message as result:

"ERROR: Not enough observations with non-missing model variables for model statement  in cross
       section ID=CS"

I have some missing values in the dataset. Do you perhaps know how to deal with them? 

It would be really helpful! Thanks in advance.

[DartRodrigo]

Hi,

I found a link to this. I think it will help you.

PROC PANEL - MISSING VALUES

Hope this helps 

Att

[Marcello91]

Thank you very much!! But I already found that link and I don't know how to apply the OUTPUT statement with the proc panel. Do you have suggestions please?? Thanks in advance

[Marcello91]

I-ve just tried the output statement in the proc freq like this

proc freq data=Lib1;
TABLES N_Patents  Stringency Turnover GERD EPE_Exp CO2 GDP Tertiary / missprint;
   title 'MISSPRINT Option';
run;


proc freq data=Lib1;
TABLES N_Patents  Stringency Turnover GERD EPE_Exp CO2 GDP Tertiary / missing;
   title 'MISSING Option';
run;

But when trying to run the proc panel I get the same error statement as above.