Probability Theory As Extended Logic
Last Modified
7152010
Edwin T. Jaynes
was one of the first people to realize that
probability theory, as originated by Laplace, is
a generalization of Aristotelian logic that reduces to
deductive logic in the special case that our hypotheses are
either true or false.
This web site has been established to help promote this
interpretation of probability theory by
distributing articles, books
and related material.
As Ed Jaynes originated this interpretation of probability theory
we have a large selection of his articles, as well as articles by
a number of other people who use probability theory in this way:

E. T. Jaynes:
Jaynes' book on probability theory is now in its second printing.
The publisher, Cambridge, requested the version of the
book that was online be removed to avoid copyright problems.
Jaynes' book is available from
Amazon
here in the US
and from
Amazon in the UK.
We have a selection of Dr. Jaynes'
articles,
and the first three chapters from Jaynes' book on
probability theory are now online
as a pdf file or as a
postscript file.
A typed publication quality version of his unpublished book titled
"Probability Theory, With Applications in Science and Engineering"
that was being prepared for publication in the mid
1970's is available.
Additionally, a copy of his
music book,
a selection of his unpublished, works,
a selection of his book reviews,
and a tribute
to him are still available online.
Finally, the Washington University Library has posted a copy
of Jaynes' obituary that was published in
physics Today.

Phil Gregory:
We have two article
by Phil Gregory and Tom Loredo and several others by Phil.
These article are on the application
of probability theory to the problem of estimating the frequency
of oscillation of a nonsinusoidal signal in data that consists of
counts.
You can find out a bit more about Phil by visiting his
home
page at the University of British Columbia
and you can buy a copy of Phil's book from
Amazon.

Tom Loredo:
We have Tom Loredo's excellent
tutorial on probability theory. It was presented at the Dartmouth
meeting of the International Society for the study of Maximum Entropy
and Bayesian methods.
Other works by
Tom Loredo.

David MacKay:
We have three papers by David
MacKay. These papers cover a broad range of topics and we direct
you to the appropriate directory for more on them.
Other works by
David MacKay.

D. S. Sivia:
We have six papers by Dr. Devinder Sivia
on the application of Bayesian probability theory to spectral analysis,
analyzing quasielastic neutron scattering data, and extracting StructureFactor
amplitudes from powder diffraction data.
For more about D. S. Sivia visit his
home page.

Stephen Gull:
We have two papers by Steve Gull.
The first is a general survey of Bayesian methods with an application to
determining the expansion order in a polynomial expansion.
The second is on straightline fitting and is the article that spurred
Ed Jaynes' attempt on the same problem.

Rainer Fischer
runs the Bayesian data analysis group at the MaxPlankInstitut
and over the last few years, he and Volker Dose, has put together what is,
in my opinion, one of the finest Bayesian groups on earth.

G. Larry Bretthorst:
I have posted my
book,
"Bayesian Spectrum Analysis and Parameter Estimation."
The previous hyperlink will download a pdf version of my book.
A gzip compressed
postscript
version of my book is also available.
A selection of my
articles
is also available, these include two tutorials on probability theory.
A new version of the Bayesian Analysis Software with a Java based GUI
is available. See the Bayesian Analysis Software
home page
for an overview of the software, installation procedures.
For a description of the applications contained in the software see this
pakage list.
The user manual for the Bayesian Analysis Software, can be downloaded
here.
This version of the manual was placed online May 28, 2014.
This site is being maintained by:
Larry Bretthorst
Dept. Of Radiology
Washington University
St. Louis MO 63130
Phone: 314 3629994
All questions concerning this site should be directed to him.