Re: Goodness of fit measures for a distribution

In article <d343js$h3g$1@xxxxxxxxxxxxxxxxxxx>,
Unknown <noone@xxxxxxxxxxx> wrote:


>> Well, it's one I would go for. It's time to trot out the well known
>> G.E.P. Box quote: "All models are wrong, but some are useful". This
>> suggests that "best" is not a good criterion (because it'll never be right
>> anyway, and there are an infinite number of models you could try). I
>> suppose the criterion used in practice is "good enough". And we try to
>> discourage people from putting a number on that as well.

>> Bob


>Yes, and I guess that would explain the fact why there are over 100
>distributions out there when one could have "good enough" results with the
>Normal distribution right?

Whether the normal distribution gives good enough results
depends on the problem. For regression, under mild conditions,
assuming normality is of little importance. For deciding
what is an outlier, it is of great importance. For being
confident about the tails, or in setting up an IQ scale,
it is of very great importance.




--
This address is for information only. I do not claim that these views
are those of the Statistics Department or of Purdue University.
Herman Rubin, Department of Statistics, Purdue University
hrubin@xxxxxxxxxxxxxxx Phone: (765)494-6054 FAX: (765)494-0558
.

Relevant Pages

  • Re: Computational complexity of finding MLEs?
    ... >compute derivatives and iterate several times. ... >estimating mean of the Normal distribution) for cases where Newton-type ... are those of the Statistics Department or of Purdue University. ... Herman Rubin, Department of Statistics, Purdue University ...
    (sci.stat.math)
  • Re: Questions: the central limit theorem when n is a random variable.
    ... > The central limit theorem: ... > Does Sapproaches Normal distribution? ... are those of the Statistics Department or of Purdue University. ... Herman Rubin, Department of Statistics, Purdue University ...
    (sci.stat.math)
  • Re: Derivation as de Moivre did of the normal distribution
    ... >Does anybody know the derivation of the normal distribution as was ... Just as the sum is an approximation ... are those of the Statistics Department or of Purdue University. ... Herman Rubin, Department of Statistics, Purdue University ...
    (sci.math)
  • Re: Great physicist rejected by anti-semitic M.I.T.
    ... thing some 30 years before Koufax. ... the importance of RH and YK across. ... are those of the Statistics Department or of Purdue University. ... Herman Rubin, Department of Statistics, Purdue University ...
    (soc.culture.jewish.moderated)
  • Misuse of statistics
    ... The use of the normal distribution as a model for ... are those of the Statistics Department or of Purdue University. ... Herman Rubin, Department of Statistics, Purdue University ...
    (misc.health.diabetes)