>Date: Mon, 12 Mar 2007 15:35:18 -0700 >From: John Gerlach <[EMAIL PROTECTED]> >Subject: Re: Dealing with non-normal, ordinal data for 2-way ANOVA with interactions
>My short answer is that for controlled blocked factorial experiments where = >interactions are important and where you have planned contrasts - since you= >designed it you should know what the important questions are - I'm not awa= >re of any tool except ANOVA that will suffice. Am I missing something here?? ANOVA is linear regression...linear regression is GLM (generalised linear modelling)....if you can set up your explanatory variables in an ANOVA context (for interactions with planned contrasts), you can do the same in a logistic regression context, and for ordinal data. The only thing that is changing is the exact interpretation of the parameters if you swap families, but that shouldn't be a problem? We all seem to agree that the logistic regression (or better: its extension to ordinal data) is a better approach for your ordinal data. If your GLM software crashed for your data, then there is something wrong with your data or model, not with the software (provided it is decent software like SAS or R). >up a design and a response variable. That said, you should use the correct = >statistical tool but, where you have choices, ANOVA seems to be the most ef= >ficient. What is your definition of "efficient"? I haven't seen many examples for which all the assumptions of linear regression/ANOVA were met. My belief is that everything in ecology is heterogeneous....hence the only thing I do is mixed modelling (or GLS). Heterogeneity is part of the nature of the data, and should be taken into account....not hidden behind a transformation. Chapter 5 in Pinheiro and Bates gives a good intro. As to one of the other respondents to this posting.....6-8 weeks ago there was a posting on the statistical newsgroup allstat that summarised 10-20 replies on the significance of main terms if the interaction is also significant. It is not that trivial. I don't have good email access this week, hence can't provide the URL for the summary posting on allstat ; just google on "allstat significance main terms" Alain Dr. Alain F. Zuur First author of: Analysing Ecological Data (2007). Zuur, AF, Ieno, EN and Smith, GM. Springer. 680 p. URL: www.springer.com/0-387-45967-7 Analysing Ecological data using GLMM and GAMM in R. (2008). Zuur, AF, Ieno, EN, Walker, N and Smith, GM Springer. Other books: http://www.brodgar.com/books.htm Statistical consultancy, courses, data analysis and software Highland Statistics Ltd. 6 Laverock road UK - AB41 6FN Newburgh Tel: 0044 1358 788177 Email: [EMAIL PROTECTED] URL: www.highstat.com URL: www.brodgar.com
