Toggle Side Panel
Close search
Back to Module

Propensity Scores

0% Complete
0/0 Steps
  1. Getting Started
  2. Background
    1 Topic
  3. Introduction to Propensity Scores
    2 Topics
    |
    2 Quizzes
  4. Estimating and Assessing the Propensity Score
    4 Topics
  5. Applying the Propensity Score
    5 Topics
  6. High-Dimensional Propensity Scores
    2 Topics
  7. Applying the High-Dimensional Propensity Score
    3 Topics
  8. References
  9. Additional Resources

Participants 174

Show more
Section Progress
0% Complete

Step 2: Trimming the cohort

Next, trim the areas of no-overlap in the cohort. First try doing this on your own using the simulated data sets.

Reveal example code below if you need a hint or want to check your work.

Example code (click to reveal)

proc sort data=ps_out;
  by exposure;
run;

proc univariate data=ps_out noprint;
  var ps;
  by exposure;
  output out=ps_range min=min max=max;
run;

data _null_;
  set ps_range;
    if exposure=1 then do;
    call symput("min_exposed",min);
    call symput("max_exposed",max);
  end;
    else do;
    call symput("min_unexposed",min);
    call symput("max_unexposed",max);
  end;
run;

data ps_trim;
  set ps_out;
  if ps >= max(&min_exposed,&min_unexposed) and ps <= min(&max_exposed,&max_unexposed);
run;