In practices, it is not easy to make such decision. One example is
size of social ties in social network study. It is very common to use
OLS thought it is count variable rather than normal. I think AIC is
suggestive as well.
Ronggui
2009/8/2 Alain Zuur :
>
>
>
> Mark Na wrote:
>>
>> Dear R-helper
Mark Na wrote:
>
> Dear R-helpers,
> I would like to compare the fit of two models, one of which I fit using
> lm()
> and the other using glm(family=poisson). The latter doesn't provide
> r-squared, so I wonder how to go about comparing these
> models (they have the same formula).
>
> Thanks v
Mark Na gmail.com> writes:
>
> Dear R-helpers,
> I would like to compare the fit of two models, one of which I fit using lm()
> and the other using glm(family=poisson). The latter doesn't provide
> r-squared, so I wonder how to go about comparing these
> models (they have the same formula).
>
>
i don't understand how you can fit a poisson model with lm() function.
otherwise, how could you compare lm() with glm(...family=poisson)?
On Fri, Jul 31, 2009 at 7:41 PM, Mark Na wrote:
> Dear R-helpers,
> I would like to compare the fit of two models, one of which I fit using lm()
> and the other
Dear R-helpers,
I would like to compare the fit of two models, one of which I fit using lm()
and the other using glm(family=poisson). The latter doesn't provide
r-squared, so I wonder how to go about comparing these
models (they have the same formula).
Thanks very much,
Mark Na
[[alterna
5 matches
Mail list logo