Difference between revisions of "Amount of evidence"

From Lesswrongwiki
Jump to: navigation, search
(created stub)
 
(wrote page)
Line 1: Line 1:
 +
To a Bayesian, evidence is a quantitative concept. In principle, a hypothetical Bayesian superintelligence could say not only ''that'' the evidence supports a particular hypothesis, but by ''how much''. (In practice the true math is usually intractable.) The more complicated or ''a priori'' improbable a hypothesis is, the more evidence you need just to justify it, or even just [[Locate the hypothesis|single it out]] of the amongst the mass of competing theories.
 +
 +
We often find it convenient to express the '''amount of evidence''' in terms of logarithms of odds, ''decibels'' if we use the base-10 logarithm, ''bits'' if we use the base-2.
 +
 
==Main post==
 
==Main post==
  
 
* [http://lesswrong.com/lw/jn/how_much_evidence_does_it_take/ How Much Evidence Does It Take?]
 
* [http://lesswrong.com/lw/jn/how_much_evidence_does_it_take/ How Much Evidence Does It Take?]
  
{{stub}}
+
==See also==
 +
*[[Evidence]]
 +
*[[Bayesian probability]]
 +
 
 +
 
 +
[http://yudkowsky.net/rational/technical A Technical Explanation of Technical Explanation] by Eliezer Yudkowsky
 +
 
 
[[Category:Concepts]]
 
[[Category:Concepts]]

Revision as of 17:03, 21 October 2009

To a Bayesian, evidence is a quantitative concept. In principle, a hypothetical Bayesian superintelligence could say not only that the evidence supports a particular hypothesis, but by how much. (In practice the true math is usually intractable.) The more complicated or a priori improbable a hypothesis is, the more evidence you need just to justify it, or even just single it out of the amongst the mass of competing theories.

We often find it convenient to express the amount of evidence in terms of logarithms of odds, decibels if we use the base-10 logarithm, bits if we use the base-2.

Main post

See also


A Technical Explanation of Technical Explanation by Eliezer Yudkowsky