Programming the statistical procedures from SAS

Propensity Score - As covariate in logistic regression - Need help interpreting output

Reply
New Contributor
Posts: 2

Propensity Score - As covariate in logistic regression - Need help interpreting output

Hi All,

 

I am using proc logistic to estimate propensity scores with the code below:

proc logistic data=anh.anh_sample_sat2;
    model tri_both (event='1')=race age bmi parity_1 any_smoke any_diabetes_oshpd htn_disorder non_cchd_sbd;
    output out=anh.prop pred=ps;
    title "Estimation of propensity score from covariates";
run;

 

Both my outcome and all covariates are binary (0/1)

 

Here is the model without the pscore:

proc logistic data=anh.prop;
    model cchd (event='1')=tri_both race age bmi parity_1 any_smoke any_diabetes_oshpd htn_disorder non_cchd_sbd ps;
    title "Adding propensity score as covariate";
run;

 

and the model with the p-score added as a covariate:

proc logistic data=anh.prop;
    model cchd (event='1')=tri_both race age bmi parity_1 any_smoke any_diabetes_oshpd htn_disorder non_cchd_sbd;
    title "Without propensity score as covariate";
run;

 

 

When I add the p-score I get output that I do not know how to interpret (see bold text below). Can someone please help me understand this? Thank you in advance!!!

My outcome is rare (298/115,406) and again all variables are binary (0/1)

Odds Ratio Estimates

Effect

Point Estimate

95% Wald
Confidence Limits

tri_both

1.410

1.080

1.840

race

1.018

0.671

1.545

age

1.264

0.599

2.666

bmi

0.952

0.393

2.309

parity_1

0.823

0.218

3.107

any_smoke

0.289

<0.001

550.733

any_diabetes_OSHPD

0.706

0.006

86.076

HTN_disorder

0.502

<0.001

>999.999

non_cchd_sbd

7.540

0.576

98.620

ps

>999.999

<0.001

>999.999

SAS Super FREQ
Posts: 3,306

Re: Propensity Score - As covariate in logistic regression - Need help interpreting output

The interpretation is that the confidence intervals are noninformative. (That is, you aren't confident at all in the point estimate!) For practical purposes, the Wald confidence interval for the odds ratio is (0, infinity). This can happen in a contingency table if there is a cell count of zero. Your model is too complicated for me to guess what is going on, but there could be a degenerate relationship between the response variable and the ps variable.

 

It might be interesting to compare the Wald CIs to the profile-likelihood CIs. You can specify

... / CLODDS=BOTH;

on the MODEL statement and see what happens.

New Contributor
Posts: 2

Re: Propensity Score - As covariate in logistic regression - Need help interpreting output

Thank you for your reply! I did as you suggested and attached are my
results. I still don't know what they mean though.

##- Please type your reply above this line. Simple formatting, no
attachments. -##
Trusted Advisor
Posts: 1,195

Re: Propensity Score - As covariate in logistic regression - Need help interpreting output

What is the purpose of using posterior probabilites as a predictor in same logistic regression model that generated these probabilites? These results may be as a result of high association between predictived probabilties and observed respose.

 

 

 

Grand Advisor
Posts: 9,451

Re: Propensity Score - As covariate in logistic regression - Need help interpreting output

"Both my outcome and all covariates are binary (0/1)"

HoHo. That is not good for proc logistic . Since they are all category variables, your data more like a contingency table. 

So maybe you should use PROC CATMOD to build logistic model .

SAS Employee
Posts: 187

Re: Propensity Score - As covariate in logistic regression - Need help interpreting output

[ Edited ]

You might try a different approach.  You can match subjects 1 to 1 having similar propensity scores.  With the matched pairs data, you then need only fit a model with your predictor of primary interest omitting the other predictors (model cchd=tri_both; ) . 

SAS Employee
Posts: 187

Re: Propensity Score - As covariate in logistic regression - Need help interpreting output

[ Edited ]

Regarding the results that you show, I think you are essentially removing the effects of the secondary predictors twice by including both the propensity score and the predictors in the propensity score model.  If you don't do matching, then you should only need to fit the model with the primary predictor and the propensity score (model cchd=tri_both ps; ).  Notice that all of the secondary predictors are nonsignficant as well as the redundant propensity score.

Ask a Question
Discussion stats
  • 6 replies
  • 343 views
  • 4 likes
  • 5 in conversation