Simulation power analysis

Question

How do you perform a power analysis for linear mixed model using R? I measure area of five groups of plants across time. Each group of plants grow under two treatments. I have 12 replicates for each plant. I have fitted a lme with plant group and treatment as fix effects and the replicates as random effect. How can I go from that to the actual calculation? I have found tools for ANOVAs and MANOVAs but not for lme. Thanks.

possible duplicate of [Simulation of Logistic Regression Power Analysis - Designed Experiments](http://stats.stackexchange.com/questions/35940/simulation-of-logistic-regression-power-analysis-designed-experiments) — gung - Reinstate Monica, Feb 27 '14 at 15:10

score 4 · Answer 1 · edited Mar 13 '14 at 13:08

This is one way to perform power analysis using lmer. I have created a simulated data set using different functions. Here I report how I could perform the actual simulation.

library(lme4)
library(lmerTest)

simulateFixedEffect <- function(model, ecotype, time, id, B){
  Tvalue=rep(0, B)
  set.seed(781)
  for(b in 1:B){
    s1 <- drop(simulate(model))
    ms <- lmer(s1$sim_1 ~ ecotype * time + (time | id))
    Tvalue[b] <- anova(ms)[[6]][3]
  }
  return(Tvalue)   
}

plotValue <- function(Fvalue, alpha=0.05){
  mean(Fvalue > alpha)
  hist(Fvalue, 30, prob=T, xlab="", ylab="", main="")
  x <- seq(0, 15, 0.1)
  lines(x, df(x,1,80), col="red")
  grid()
}

time <- (subdata$time)
    gclass <- as.factor(subdata$gclass)
id <- subdata$id
    growth <- subdata$growth

m1 <- lmer(growth ~ gclass * time + (time | id))
Tvalue <- simulateFixedEffect(m1,gclass, time, id, 10)

Simulation power analysis

1 Answers1