Poststratification Weights Output Data Set

If you specify the OUTPSWGT= option in the POSTSTRATA statement, PROC SURVEYMEANS stores the poststratification weights in an output data set. The OUTPSWGT= output data set contains all observations from the DATA= input data set that are valid (used in the analysis). (A valid observation is an observation that has a positive value of the WEIGHT variable. Valid observations must also have nonmissing values of the STRATA and CLUSTER variables, unless you specify the MISSING option. See the section Data and Sample Design Summary for more information about valid observations.)

For VARMETHOD=TAYLOR, the OUTPSWGT= data set contains the following variables:

  • all variables in the DATA= input data set

  • _PSWt_, which contains poststratification weights

For VARMETHOD=BRR and VARMETHOD=JACKKNIFE, the OUTPSWGT= option is the same OUTWEIGHTS= method-option that you specify in the PROC SURVEYMEANS statement, except that it also contains the variable _PSWt_, which contains poststratification weights for the full sample. The replication weights, adjusted for poststratification, are stored in the OUTWEIGHTS= data set. See the section Replicate Weights Output Data Set for the contents of the OUTWEIGHTS= data set.

However, if you also specify an OUTWEIGHTS= method-option in the PROC SURVEYMEANS statement and use a different data set name, the data set in OUTPSWGT= option is ignored.

If you provide your own replicate weights by using a REPWEIGHTS statement for VARMETHOD=BRR or VARMETHOD=JACKKNIFE, the poststratification replicate weights replace the original replicate weights in the OUTPSWGT= data set.