An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-sig-ecology/attachments/20130508/da6167b4/attachment.pl>
population model with proportions as responses
3 messages · Milos Blagojevic, Mollie Brooks, Botta-Dukát Zoltán
An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-sig-ecology/attachments/20130508/9dfecb8b/attachment.pl>
Dear Milos,
It could be a problem that the predictors (forest_percent + meadow_percent + plowland_percent) are non-independent, but I don't know if it's a big problem. Maybe someone else could weigh in on that.
Such strong linear relationship between predictors (collinearity) is a big problem. If all predictor included, the model becomes ill-defined. I suggest including only two of them. Choose the pair of predictor that lead to most easily interpretable model (probably choosing the two extreme habitat is the best solution). Best wishes Zoltan
Botta-Duk?t Zolt?n -------------------------------- ?kol?giai ?s Botanikai Int?zet Magyar Tudom?nyos Akad?mia ?kol?giai Kutat?k?zpont -------------------------------- 2163. V?cr?t?t, Alkotm?ny u. 2-4. tel: +36 28 360122/157 fax: +36 28 360110 botta-dukat.zoltan at okologia.mta.hu www.okologia.mta.hu Zolt?n BOTTA-Duk?t -------------------------------- Institute of Ecology and Botany Hungarian Academy of Sciences Centre for Ecological Research -------------------------------- H-2163 V?cr?t?t, Alkom?ny u. 2-4. HUNGARY Phone: +36 28 360122/157 Fax..: +36 28 360110 botta-dukat.zoltan at okologia.mta.hu www.okologia.mta.hu