[R] ANOVA test to decide whether to use multiple linear regression or linear mixed effects model

[Lucy McMahon]

R-help:


I am trying to decide between using a multiple linear regression or a linear mixed effects model for my data:


model1 <- lm (responsevariable ~ predictor1 + predictor2 + predictor3 + predictor4, data= data)

model2 <- lme (responsevariable ~ predictor1 + predictor2 + predictor3 + predictor4, random = ~1 | site, data= data)


anova (model1, model2)


but I keep getting the following error code:

Error in anova.lmlist (object, ...):

    models were not all fitted to the same size of dataset


Any advice would be appreciated, thanks.



	[[alternative HTML version deleted]]