Good Thinking: The Foundations of Probability and Its Applications

by Irving John Good

These sparkling essays by a gifted thinker offer philosophical views on the roots of statistical interference. A pioneer in the early development of computing, Irving J. Good made fundamental contributions to the theory of Bayesian inference and was a key member of the team that broke the German Enigma code during World War II. Good maintains that a grasp of probability is essential to answering both practical and philosophical questions. This compilation of his most accessible works concentrates on philosophical rather than mathematical subjects, ranging from rational decisions, randomness, and the nature of probability to operational research, artificial intelligence, cognitive psychology, and chess.
These twenty-three self-contained articles represent the author's work in a variety of fields but are unified by a consistently rational approach. Five closely related sections explore Bayesian rationality; probability; corroboration, hypothesis testing, and simplicity; information and surprise; and causality and explanation. A comprehensive index, abundant references, and a bibliography refer readers to classic and modern literature. Good's thought-provoking observations and memorable examples provide scientists, mathematicians, and historians of science with a coherent view of probability and its applications.

Genres: Science, Philosophy, Mathematics

352 pages, Paperback

First published December 1, 1983

Reviews

[Gwern · Rating 2 out of 5]

Moved to gwern.net.

[Nils Lid Hjort · Rating 5 out of 5]

Den uforlignelige I.J. Good, venn og medforfatter av den fiktive J.I. Doog den gang han ikke fikk lov til å skrive "we" i en artikkel han hadde skrevet, tilhører de ytterst interessante, originale, fritttenkende probabilister, statistikere, maskinlærere, datavitenskapspersoner, Bayesianere, tja, kanskje man skal føye til "tallknusere" også.

Han vant annen verdenskrig (vel, sammen med Alan Turing); han har funnet på den moderne datamaskin; han har forutsett og satt navn på og problematisert The Singularity; han har skrevet en artikkel om trykkfeil i egne publikasjoner; han har beregnet en lower bound for the number of different Bayesian statisticians (det er, eller burde være, minst 46656 ulike Baeysianere); han har slitt ut ti sekretærer og muligens fridd til den ellevte; han har skrevet The Botryology of Botryology; &c., &c.

Dette er altså en samling av hans vidtfavnende og bredspektrede artikler.

Les også David Banks' intervju med ham i Statistical Science, 1996. Jeg må maile ham og spørre om en bestemt Good-referanse jeg ikke fant frem idag.

PS: Kanskje I.J. Good ville likt den følgende idiosynkratiske selvutleverende fotnote: Jeg kikket altså på denne boken, på Goodreads, og fomlet en anelse med mine fingre, mens jeg så etter mulige reviews. Plutselig & uplanlagt og vips-vops hadde GR klassifisert meg som "Wanting to read" denne boken. Jeg finner ingen av-knapp på GR, der jeg kunne ha skyndet meg å undo dette. Jeg vil i grunnen ikke ha noen "want to read"-bøker her, og dessuten vil jeg si noe om hver bok jeg merker av. Antallet bøker under MyBooks skal presist matche antallet bøker jeg har lagt inn et review om. Altså måtte jeg, uforvarende & unplanlagt, forfatte dette review, i den proverbiale fulle fart. For jeg har altså lest boken!

[Daniel · Rating 4 out of 5]

This collection of scientific papers is a challenging but useful discussion on statistical methods, probability, randomness, logic and decision-making. Much of the book centers around Bayesian statistical methods and when and why to use them, as well as "philosophy of science"-type discussions on when a scientist should--or sometimes must--apply subjective judgments to scientific problems.

It will help enormously if you've had a semester or two of statistics to really get at the meat of this book. If not, scroll down a few... [see the rest on my book review site.]