Re: Goodness of fit measures for a distribution
- From: "Unknown" <noone@xxxxxxxxxxx>
- Date: Thu, 7 Apr 2005 13:55:14 +0100
"Glen" <glenbarnett@xxxxxxxxxxxxx> wrote in message
> I suspect that you actually have no need for a "best" fit at all.
> Perhaps you should think more carefully about what it is you
> ultimately wish to achieve.
>
> Glen
Hi,
what I am trying to do is to determine which univariate model is the most
appropriate and valid for my data. Of course such a requirement can be
interpreted in many ways.
Since I am not really a statistician, I thought of using goodness of fit
measures and graphical interpretations to accomplish the above requirement.
I guess this comes from the analogous example of curve fitting, where given
some data you can fit a parametric model to it that minimises some error
metric and best describes the behaviour of the data.
If you know of a more appropriate way please let me know.
V.Z.
.
- Follow-Ups:
- Re: Goodness of fit measures for a distribution
- From: Reef Fish
- Re: Goodness of fit measures for a distribution
- References:
- Goodness of fit measures for a distribution
- From: Unknown
- Re: Goodness of fit measures for a distribution
- From: Glen
- Goodness of fit measures for a distribution
- Prev by Date: Re: Is this binomial distribution?
- Next by Date: Re: Metropolis-Hastings f90 code anyone?
- Previous by thread: Re: Goodness of fit measures for a distribution
- Next by thread: Re: Goodness of fit measures for a distribution
- Index(es):
Relevant Pages
|