Warning with betareg
On 31/10/2012 11:00, r-sig-ecology-request at r-project.org wrote:
Send R-sig-ecology mailing list submissions to r-sig-ecology at r-project.org To subscribe or unsubscribe via the World Wide Web, visit
https://stat.ethz.ch/mailman/listinfo/r-sig-ecology or, via email, send a message with subject or body 'help' to r-sig-ecology-request at r-project.org You can reach the person managing the list at r-sig-ecology-owner at r-project.org When replying, please edit your Subject line so it is more specific than "Re: Contents of R-sig-ecology digest..." Today's Topics: 1. Warning with betareg (leanne heisler) ---------------------------------------------------------------------- Message: 1 Date: Tue, 30 Oct 2012 12:59:09 -0500 From: leanne heisler <leanneheisler at hotmail.com> To: <r-sig-ecology at r-project.org> Subject: [R-sig-eco] Warning with betareg Message-ID: <COL120-W73FF7F07D1F61C5A4DC17AE620 at phx.gbl> Content-Type: text/plain; charset="iso-8859-1" Dear List, I am looking for weather patterns affecting the composition of rodent communities. I have the proportions of species (DM,MV,SBV,OBPM,HM,NGM) and shrews (SHREW) from 2004 to 2011 and am using the betareg package and AIC model selection to identify which weather variables of the current year (PREC,GDD,SNOW) and/or previous year (PREC_T,, GDD_T,,SNOW_T)) are the best predictors of change in the relative abundance (% community) of each species.
I am not sure about the cause of the error....but you shouldn't do a regression type analysis with so few observations. General recommendation is to have 15-25 observations per covariate. Eight observations doesn't bring you that far. And certainly not 3 covariates with 8 observations! Alain
ab
X DM MV SBV SHREW OBPM HM NGM PREC GDD SNOW PREC_T1 GDD_T1 SNOW_T1 1 2004 0.2583 0.1301 0.5685 0.0215 0.00291 0.00101 0.01761 301.53 1572.14 4.67 258.06 1747.26 10.00 2 2005 0.2539 0.1258 0.5448 0.0478 0.00541 0.00461 0.01771 373.70 1564.48 18.33 301.53 1572.14 4.67 3 2006 0.3595 0.1131 0.4088 0.0474 0.02551 0.01091 0.03471 235.60 1884.40 11.33 373.70 1564.48 18.33 4 2007 0.4839 0.3441 0.0968 0.0753 0.00001 0.00001 0.00001 290.44 1753.85 34.00 235.60 1884.40 11.33 5 2008 0.4632 0.2436 0.2309 0.0326 0.00001 0.00851 0.02121 294.70 1631.28 23.00 290.44 1753.85 34.00 6 2009 0.2600 0.3102 0.3744 0.0482 0.00211 0.00051 0.00471 257.45 1697.45 38.67 294.70 1631.28 23.00 7 2010 0.7219 0.0888 0.0947 0.0592 0.00001 0.00591 0.02961 386.45 1459.83 33.00 257.45 1697.45 38.67 8 2011 0.3204 0.4611 0.1222 0.0463 0.04811 0.00191 0.00001 214.30 1662.87 72.00 386.45 1459.83 33.00 I have successfully modeled all species up to OBPM, but have run into a warning message that I haven't been able to decipher (below).
library(betareg) betareg <- betareg(OBPM ~ GDD_T,, data=ab)
Error in while (testhalf & stepFactor < ))) { :
missing value where TRUE/FALSE needed
In addition: Warning message:
In sqrt(wpp) : NaNs produced
I'm sure this is something simple, but if anyone could help me with this it would be greatly appreciated.
Thank you in advance,
---------------
Leanne Heisler
Graduate Student
Department of Biology
University of Regina
Canada
------------------------------
_______________________________________________ R-sig-ecology mailing list R-sig-ecology at r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-ecology End of R-sig-ecology Digest, Vol 55, Issue 12 *********************************************
Dr. Alain F. Zuur First author of: 1. Analysing Ecological Data (2007). Zuur, AF, Ieno, EN and Smith, GM. Springer. 680 p. URL: www.springer.com/0-387-45967-7 2. Mixed effects models and extensions in ecology with R. (2009). Zuur, AF, Ieno, EN, Walker, N, Saveliev, AA, and Smith, GM. Springer. http://www.springer.com/life+sci/ecology/book/978-0-387-87457-9 3. A Beginner's Guide to R (2009). Zuur, AF, Ieno, EN, Meesters, EHWG. Springer http://www.springer.com/statistics/computational/book/978-0-387-93836-3 4. Zero Inflated Models and Generalized Linear Mixed Models with R. (2012) Zuur, Saveliev, Ieno. http://www.highstat.com/book4.htm Other books: http://www.highstat.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: highstat at highstat.com URL: www.highstat.com URL: www.brodgar.com