Re: [boost] [math] Empirical distribution function

Subject: Re: [boost] [math] Empirical distribution function
From: er (er.ci.2020_at_[hidden])
Date: 2011-06-15 06:26:48

On 6/15/11 6:19 AM, er wrote:
> On 6/15/11 4:30 AM, John Maddock wrote:
>>> I guess you mean the ECDF under assumption of independent trials? I
>>> developed one as a Boost.Accumulator here:
>>>
>>> https://svn.boost.org/svn/boost/sandbox/statistics/non_parametric/boost/statistics/detail/non_parametric/
>>>
>>>
>>>
>>> While it's been a while I haven't touched these directories, I'd be
>>> happy to do some maintenance & a proper doc/test suite.
>>
>> Nod, this looks more like an accumulator than a distribution - in the
>> sense that you can only calculate properties from a set of values?
>>
>> John.
>> __________________________
>
>
> It is the ECDF assuming independent sampling (I think identically need
> not even be assumed) and derived quantities (such as Kolmogorov Smirnov
> statistic) :
>
> F(x) = count of samples below x
>
> The fact that it's an accummulator is just a convenience : the
> distribution is updated each time a sample is passed to the acc.
>
> I'm doing maintenance work right not, whether or not this matches the
> need of the Denis. It shouldn't take too much time (days).
>
> _______________________________________________
> Unsubscribe & other changes:
> http://lists.boost.org/mailman/listinfo.cgi/boost
>

Perhaps you are thinking about offering an interface identical to 
boost's statistical distribution's (not accumulator), as [math] would 
suggest.

Just a thought : it shouldn't be too hard to specify a wrapper around an 
accumulator with this interface, but perhaps there already exists things 
like that (haven't checked in a while)...