[R] mixed models lmer function help!!
Shelby Leonard
shelby_leonard26 at yahoo.com
Mon Jun 19 18:29:30 CEST 2017
Hi,I have tumor growth curve data for a bunch of different mice in various groups. I want to compare the growth curves of the different groups to see if timing of drug delivery changed tumor growth.I am trying to run a mixed models with repeated measures over time with each mouse as a random effect with linear and quadratic terms for time.This took me a long time to figure out and I just wanted to make sure I did it correctly and I am interpreting it correctly. This is the code I ran
Rtumor<-lmer(volume~Group+Time+(1|Subject), data=Rtumor)summary(Rtumor)Rtumor.null=lmer(volume~Time+(1|Subject), data=Rtumor, REML=FALSE)Rtumor.full=lmer(volume~Group+Time+(1|Subject), data=Rtumor, REML=FALSE)anova(Rtumor.null,Rtumor.full)
Here is my output Rtumor<-lmer(volume~Group+Time+(1|Subject), data=Rtumor)> summary(Rtumor)Linear mixed model fit by REML ['lmerMod']Formula: volume ~ Group + Time + (1 | Subject) Data: Rtumor
REML criterion at convergence: 1541.2
Scaled residuals: Min 1Q Median 3Q Max -1.8006 -0.6348 -0.0658 0.3903 4.7551
Random effects: Groups Name Variance Std.Dev. Subject (Intercept) 3.197e-09 5.654e-05 Residual 3.348e+05 5.786e+02Number of obs: 101, groups: Subject, 11
Fixed effects: Estimate Std. Error t value(Intercept) -495.520 303.619 -1.632Group 24.350 115.615 0.211Time 79.653 7.886 10.101
Correlation of Fixed Effects: (Intr) Group Group -0.933 Time -0.300 -0.007
> Rtumor.null=lmer(volume~Time+(1|Subject), data=Rtumor, REML=FALSE)> Rtumor.full=lmer(volume~Group+Time+(1|Subject), data=Rtumor, REML=FALSE)> anova(Rtumor.null,Rtumor.full)Data: RtumorModels:Rtumor.null: volume ~ Time + (1 | Subject)Rtumor.full: volume ~ Group + Time + (1 | Subject) Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)Rtumor.null 4 1576.5 1586.9 -784.24 1568.5 Rtumor.full 5 1578.4 1591.5 -784.22 1568.4 0.0457 1 0.8307There were 50 or more warnings (use warnings() to see the first 50)
My questions are1) Did I do this correctly?2) Do I still need to run it again with quadratic terms for time?, If so, how do I do this?3) If I am understanding these results correctly, they say There is no difference between these groups on volume growth curves
[[alternative HTML version deleted]]
More information about the R-help
mailing list