Desktop productivity for business analysts and programmers

Question about proc logistic and correlation between input vars

Reply
Frequent Contributor
Posts: 90

Question about proc logistic and correlation between input vars


Hi,

I have a question about proc logistic.
I am creating a regresion logistic model with proc logistic.

All the vars included in the model have dependencies with the target table.
Using proc freq or proc discrim I can see that there is a dependency

 

When I am exploring the vars, I find that there are vars highly correlated.
The vars rango_ant and rango_edad hace a correlation about 0.9

Do I have to exclude one of them from my model?

 

This is my model:

proc logistic data=test outmodel=modelo1 plots(only)=roc;
class cod_posicion nivel_sal rango_edad rango_ant rango_eval;
model baja = rango_edad rango_ant nivel_sal rango_eval cod_posicion ;
quit;

 

Do I have tu use cross effects?. Like this:

 

proc logistic data=test outmodel=modelo1 plots(only)=roc;
class cod_posicion nivel_sal rango_edad rango_ant rango_eval;
model baja = rango_edad rango_ant nivel_sal rango_eval cod_posicion rango_edad*rango_ant ;
quit;

 

proc logistic data=test outmodel=modelo1 plots(only)=roc;
class cod_posicion nivel_sal rango_edad rango_ant rango_eval;
model baja = rango_edad rango_ant nivel_sal rango_eval cod_posicion rango_edad*rango_ant ;
quit;

 

I don't know the effect of correlation in logistic regresion.
Can anybody help me?, any help will be greatly appreciated

 

Thanks in advance

Trusted Advisor
Posts: 1,059

Re: Question about proc logistic and correlation between input vars

I suggest you post this in one of the Analytics communities. It really doesn't have anything to do with Enterprise Guide.

 

Tom

Frequent Contributor
Posts: 90

Re: Question about proc logistic and correlation between input vars

Ok, but proc logistic is a task of E.G.
Trusted Advisor
Posts: 1,059

Re: Question about proc logistic and correlation between input vars

Technically, SAS EG has a task called "Logistic Regression". This task runs PROC LOGISTIC to do the calculations.

 

It's a little confusing, but here's how I'd describe the dividing line. If I had questions about the meanings of the variable roles or about some of the task options, I'd post under Enterprise Guide. But if a question pertains to the underlying PROC LOGISTIC code, as yours does, I think it's a better fit in the Analytics community. I'm an IT guy, and I monitor the EG community for technical questions about using the product, but I don't have the statistical methodology chops to answer questions like yours. Those guys are in the Analytics community.

 

Tom

Ask a Question
Discussion stats
  • 3 replies
  • 92 views
  • 0 likes
  • 2 in conversation