Programming the statistical procedures from SAS

LR model identifies a predictor as significant, but OR=1

Accepted Solution Solved
Reply
New Contributor
Posts: 3
Accepted Solution

LR model identifies a predictor as significant, but OR=1

I performed a logistic regression with stepwise selection, and a variable that was retained has on OR point estimate of 1.000, with 95% Wald CLs of 1.000-1.001.  Is this likely a glitch, or are the "true" point estimate and lower CL just a titch above 1 and victims of rounding (e.g., lower CL 1.00001, point estimate 1.00008)?

 

The code:

PROC LOGISTIC DATA=train;

    CLASS landcover (REF='11') / PARAM=REF;

    MODEL case (EVENT='1')=landcover water_pct temperature precipitation / SELECTION=STEPWISE;

RUN;

 


Accepted Solutions
Solution
‎10-10-2016 11:54 AM
SAS Super FREQ
Posts: 3,306

Re: LR model identifies a predictor as significant, but OR=1

Because the variable was selected, I would guess the CI is [1 + epsilon, 1.001].  You can use the ODS OUTPUT statement to see the full precision of the estimates:

 

ods output OddsRatios=OR;

PROC LOGISTIC ...;
RUN;

proc print data=OR; 
format LowerCL UpperCL 16.14;
run;

View solution in original post


All Replies
Solution
‎10-10-2016 11:54 AM
SAS Super FREQ
Posts: 3,306

Re: LR model identifies a predictor as significant, but OR=1

Because the variable was selected, I would guess the CI is [1 + epsilon, 1.001].  You can use the ODS OUTPUT statement to see the full precision of the estimates:

 

ods output OddsRatios=OR;

PROC LOGISTIC ...;
RUN;

proc print data=OR; 
format LowerCL UpperCL 16.14;
run;
☑ This topic is SOLVED.

Need further help from the community? Please ask a new question.

Discussion stats
  • 1 reply
  • 106 views
  • 0 likes
  • 2 in conversation