Not signed in

Want to take part in these discussions? Sign in if you have an account, or apply for one below

• Forgot your password?
• Apply for membership

1. • CommentRowNumber1.
   • CommentAuthorzskoda
   • CommentTimeAug 20th 2014
   • PermaLink
   Author: zskoda
   Format: MarkdownItex[[statistic]], [[statistics]] and [[parastatistics]]

   statistic, statistics and parastatistics

2. • CommentRowNumber2.
   • CommentAuthorUrs
   • CommentTimeAug 20th 2014
   • PermaLink
   Author: Urs
   Format: MarkdownItexI have added a minimum cross-link between _parastatics_ and the existing _[[braid group statistics]]_

   I have added a minimum cross-link between parastatics and the existing braid group statistics

3. • CommentRowNumber3.
   • CommentAuthorTobyBartels
   • CommentTimeAug 22nd 2014
   • PermaLink
   Author: TobyBartels
   Format: MarkdownItexWhat does this mean? >[A statistic is] a function of a sample where the function itself is independent of the sample's distribution. This may come from Wikipedia, but the explanation there (‘the function can be stated before realization of the data’) does not help. Since the sample is the input to the function, if the function depends on the distribution of the sample, then we just write that dependence into the definition of the function, and now we have a function that's independent of the sample's distribution. More formally, if we have a function $f_S$ for each sample $S$, so that the value of the statistic at $S$ is $f_S(S)$, then we define $g(S) \coloneqq f_S(S)$, and now $g$ does not depend on the distribution of $S$. So it seems that, mathematically, all that a statistic is, is simply a function from the set of all samples (to, say, the set of real numbers). Is this correct? Can we just say that?

   What does this mean?

   [A statistic is] a function of a sample where the function itself is independent of the sample’s distribution.

   This may come from Wikipedia, but the explanation there (‘the function can be stated before realization of the data’) does not help.

   Since the sample is the input to the function, if the function depends on the distribution of the sample, then we just write that dependence into the definition of the function, and now we have a function that’s independent of the sample’s distribution.

   More formally, if we have a function $f_S$ for each sample $S$, so that the value of the statistic at $S$ is $f_S(S)$, then we define $g(S) \coloneqq f_S(S)$, and now $g$ does not depend on the distribution of $S$.

   So it seems that, mathematically, all that a statistic is, is simply a function from the set of all samples (to, say, the set of real numbers). Is this correct? Can we just say that?