Stat Computing > SAS > FAQ

SAS FAQ 
How do I analyze survey data with a probability proportional to size sampling design?

This example is taken from Levy and Lemeshow's Sampling of Populations.

Page 353 cluster sampling with unequal probabilities:   probability proportional to size sampling
This example uses the hospslct data set.
NOTE:  The data step creating hspslct2 is necessary to create the weight variable, w2star.

data hspslct2;
  set hospslct;
  /*n is 50*/
  /*N_i is admiss*/
  /* X is 7087, the total number of life-threatening conditions across all the hospitals*/
  /*X_i is tl, the total number of life-threatening conditions for each hospital*/
  if hospno = 2 then  tl = 785; 
  if hospno = 5 then  tl = 3404; 
  if hospno = 9 then  tl = 778; 
  w2star = (admiss/50)*(7087/tl);
run;

proc surveymeans data = hspslct2 n = 4672 mean sum;
  weight w2star;
  cluster drawing;
  var lifethrt dxdead;
run;

The SURVEYMEANS Procedure

            Data Summary

Number of Clusters                 5
Number of Observations            50
Sum of Weights            51344.9973

                               Statistics

                               Std Error
Variable            Mean         of Mean             Sum         Std Dev
------------------------------------------------------------------------
LIFETHRT        0.121904        0.021404     6259.175814     1276.638273
DXDEAD          0.034287        0.022991     1760.471466     1078.465840
------------------------------------------------------------------------

UCLA Researchers are invited to our Statistical Consulting Services
We recommend others to our list of Other Resources for Statistical Computing Help
These pages are Copyrighted (c) by UCLA Academic Technology Services