Stephen Paul King (stephenk1@home.com)
Fri, 07 May 1999 15:04:41 GMT
On Fri, 07 May 1999 14:53:03 +0200, Axel Hutt <hutt@cns.mpg.de> wrote:
>Stephen Paul King wrote:
>
>> Hi all,
>>
>> I have assembled a link page on Fisher information and have a
>> definition: "The Fisher Information about a parameter is defined to
>> be \theta the expectation of the second derivative of the
>> loglikelihood."
>> http://members.home.net/stephenk1/Outlaw/fisherinfo.html
>> But I am still needing an intuitive grasp of that it means. :)
>
>Hi Stephen,
>
>IMO it is just a definition denoting the reciprocal proportional factor
>to to the maximum-likelihood estimation of e.g. model parameters.
>
>In my bool, I read
>
>Fisher information I=\int_D 1/p(e) (dp(e)/de)^2 de
>
>with p(e) denoting the probability density of the noise e,
>D={ e | p(e) > 0 } set of all allowed e.
>
>I hope it will help.
>
>Greetings
>
>
>Axl
>
This archive was generated by hypermail 2.0b3 on Sun Oct 17 1999 - 22:10:31 JST