[R-sig-eco] Post Hoc tests GLM (B.-Markus Clarin)

[Highland Statistics Ltd]

>
> Today's Topics:
>
>     1. Re: Post Hoc tests GLM (B.-Markus Clarin)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Mon, 14 Oct 2013 10:13:57 +0200
> From: "B.-Markus Clarin" <b.markus.clarin at gmail.com>
> To: Javier Atalah <Javier.Atalah at cawthron.org.nz>
> Cc: "r-sig-ecology at r-project.org" <r-sig-ecology at r-project.org>
> Subject: Re: [R-sig-eco] Post Hoc tests GLM
> Message-ID:
> 	<CA+r--qRK3kpHvtYT+RJCRH3LtTk6eHP9mWF8tgzbNQUaPxrbOw at mail.gmail.com>
> Content-Type: text/plain
>
> Dear Luis and Javier,
>
> I am having a bit trouble understanding the model structure that was posted
> in the original question:
>
> glm(formula = Frec ~ Group+ Hour:Category, family = poisson)
>
> I am an ecologist and I recall from all courses on statistical modelling,
> that if I find an interaction term significant, I HAVE to retain the
> related main effects as well, even if they have no significant effect by
> themselves.

Never say 'you have to..' in statistics. See:

The Hierarchy Principle in Designed Industrial Experiments

Douglas C. Montgomery, Raymond H. Myers, Walter H. Carter, Jr. and G. 
Geoffrey Vining
Qual. Reliab. Engng. Int. 2005; 21:197–201


Alain Zuur

>

-- 
Dr. Alain F. Zuur
First author of:

1. Analysing Ecological Data (2007)
2. Mixed effects models and extensions in ecology with R (2009)
3. A Beginner's Guide to R (2009)
4. Zero Inflated Models and GLMM with R (2012)
5. A Beginner's Guide to GAM (2012)
6. A Beginner's Guide to GLM and GLMM (2013)

Highland Statistics Ltd.
6 Laverock road
UK - AB41 6FN Newburgh
Tel: 0044 1358 788177
Email: highstat at highstat.com
URL: www.highstat.com
URL: www.brodgar.com