[R-sig-ME] p values absent in lmer output
Luciano La Sala
lucianolasala at yahoo.com.ar
Thu Apr 16 05:58:02 CEST 2009
Dear R-mixed-models experts,
I am running R version 2.8.1 on Windows Vista. I am studying factors which influence egg morphometrics in a seagull population. My dataset consists of: “Year” (0,1), “HatchingOrder” (HO) (1, 2, 3) and “ClutchSize” (1, 2, 3) as independent variables, and “Egg measurements” (I run models for max. breadth, length and volume) as dependent variable (continuous). I included “NestID” as a random effect.
I specified my model as follows:
model <- lmer(EggVolume~HO+Year+ClutchSize+(1|NestID),Data)
summary(model)
(See output below)
At this point, my main questions are:
1. Is my model correctly built?
2. Why don’t I get p values for t?
3. If I simplify my model to: lmer (EggVolume ~ HO+ (1|NestID), Data)
.... I still don't get any p values. How is that possible? Is there any way to compute p values for the fixed effects?
Linear mixed model fit by REML
Formula: EggVol ~ HatchingOrder1 + EggVol + Year1 + ClutchSize + (1 | NestID)
Data: Data
AIC BIC logLik deviance REMLdev
1441 1469 -712.3 1431 1425
Random effects:
Groups Name Variance Std.Dev.
NestID (Intercept) 21.9883 4.6892
Residual 7.9196 2.8142
Number of obs: 248, groups: NestID, 120
Fixed effects:
Estimate Std. Error t value
(Intercept) 77.060 1.124 68.54
HatchingOrder1Second -2.227 0.443 -5.03
HatchingOrder1Third -5.945 0.544 -10.93
Year2006 -2.504 0.969 -2.58
ClutchSizeTwo-eggs 2.101 1.349 1.56
ClutchSizeThree-eggs 5.869 1.243 4.72
Correlation of Fixed Effects:
(Intr) HtcO1S HtcO1T Y12006 CltchSzTw-
HtchngOrd1S -0.004
HtchngOrd1T -0.018 0.407
Year12006 -0.460 0.008 0.038
CltchSzTw-g -0.598 -0.153 -0.067 -0.129
CltchSzThr- -0.734 -0.177 -0.216 0.046 0.616
Thank you very much in advance!
Luciano
Yahoo! Cocina
Recetas prácticas y comida saludable
http://ar.mujer.yahoo.com/cocina/
More information about the R-sig-mixed-models
mailing list