In article <337a47b0.414296@netnews2.worldnet.att.net>, Gregory A. Light <greg.light@worldnet.att.net> wrote: >Are there any macros available to perform resampling techniques such >as bootstrapping or jackknifing?

There has been a macro to do leaving one out classification in a discriminant analysis for some time (it's shipped with the Advanced Statistics module). We added the feature to the DISCRIMINANT procedure for Release 7.5. Note that this is not specifically a jackknife, though it's often referred to that way. The true jackknife holds out each case, produces a solution and classifies all cases, while this leaving one out or U-method classifies only the held out case.

The CNLR procedure will produce bootstrapped estimates of standard errors for regression models. I don't know of any macros for bootstrapping, but I have some syntax that David Marso wrote to create a file with bootstrapped samples:

COMPUTE ID=$CASENUM . SAVE OUTFILE 'BOOTDATA.SAV'. INPUT PROGRAM . LOOP SAMP=1 to nsamples. LOOP V = 1 to ncases. COMPUTE ID=TRUNC(UNIFORM(ncases)) + 1. END CASE. LEAVE SAMP. END LOOP. END LOOP. END FILE. END INPUT PROGRAM . SORT CASES BY ID . MATCH FILES / FILE * / TABLE 'BOOTDATA.SAV' / BY ID . SORT CASES BY SAMP. SPLIT FILE BY SAMP.

-- ----------------------------------------------------------------------------- David Nichols Senior Support Statistician SPSS, Inc. Phone: (312) 329-3684 Internet: nichols@spss.com Fax: (312) 329-3668 -----------------------------------------------------------------------------