Paper announcements

[David Wolpert]

	*** PAPER ANNOUNCEMENTS ***

The following two papers may be of interest to people in the
connectionist community. Both will appear in the proceedings of the
1995 conference on Maximum Entropy and Bayesian Methods. Retrieval
instructions are at the bottom of this post.






THE BOOTSTRAP IS INCONSISTENT WITH PROBABILITY THEORY

by D. H. Wolpert


Abstract: This paper proves that for no prior probability distribution
does the bootstrap (BS) distribution equal the predictive
distribution, for all Bernoulli trials of some fixed size. It then
proves that for no prior will the BS give the same first two moments
as the predictive distribution for all size trials. It ends with an
investigation of whether the BS can get the variance correct.





DETERMINING WHETHER TWO DATA SETS ARE FROM THE SAME DISTRIBUTION

by D. H. Wolpert


Abstract: This paper presents two Bayesian alternatives to the
chi-squared test for determining whether a pair of categorical data
sets were generated from the same underlying distribution. It then
discusses such alternatives for the Kolmogorov-Smirnov test, which is
often used when the data sets consist of real numbers.


============================================================

To retrieve these papers anonymous ftp to ftp.santafe.edu. The papers
are in pub/dhw_ftp, under the titles maxent.95.boot.ps.Z and
maxent.95.wv.ps.Z, respectively.