Repeated Measures for LOT
#Loading the dataset that has been reset into a long version
data.test4 <- read.csv("/Volumes/TOSHIBA EXT/Dropbox/ADULT STUDY/adult_study011615.csv")
# Load the psych package
library(psych)Creating a new variable that is the mean of all positive purpose LOT questions
items <- grep("LOTR[0-9]", names(data.test4), value=TRUE)
scaleKey <- c(1, 1, -1, 1, 1, 1, -1, 1, -1, 1)
data.test4[,items] <- apply(data.test4[,items],2, as.numeric)
data.test4$LOT <- scoreItems(scaleKey, items = data.test4[, items])$score
library(reshape2); library(car)## Warning: package 'car' was built under R version 3.1.2##
## Attaching package: 'car'
##
## The following object is masked from 'package:psych':
##
## logitdata <- data.test4[,c("ID", "GROUP", "wave", "LOT")]
data <- dcast(data, ID + GROUP ~ wave, mean, value.var = "LOT")
data[,3:5] <- apply(data[,3:5],2,function(x) recode(x, "NaN = NA") )Create new data set with ID Group basline LOT and wave so that we have Baseline, time 1 and 2 to compare to
data2 <- as.data.frame(mapply(c,data[,1:4], data[,c(1:3,5)]))
data2$wave <- rep(1:2, each=89)
names(data2) <- c("ID", "GROUP", "BASELINE", "LOT", "WAVE")Drop the cases where participants did not complete the intervention completely
#data2 <- data2[-c(which(data2$GROUP ==2)),]Intention to treat model (ITT) where we keep the cases who dropped out and did not complete the study (http://en.wikipedia.org/wiki/Intention-to-treat_analysis).
data2[which(data2$GROUP ==2), "GROUP"] <- 1For lme to work GROUP and ID need to be seen as factors
data2$GROUP <-as.factor(data2$GROUP)
data2$ID <-as.factor(data2$ID)Describe the LOT variable by the GROUP variable
describeBy(data2[,3:4], group = data2$GROUP)## group: 0
## vars n mean sd median trimmed mad min max range skew kurtosis
## BASELINE 1 86 2.44 0.79 2.5 2.39 0.89 1.1 4.3 3.2 0.43 -0.47
## LOT 2 59 2.19 0.80 2.1 2.11 0.74 1.1 4.2 3.1 0.86 -0.17
## se
## BASELINE 0.09
## LOT 0.10
## --------------------------------------------------------
## group: 1
## vars n mean sd median trimmed mad min max range skew kurtosis
## BASELINE 1 88 2.38 0.72 2.30 2.35 0.82 1.1 4 2.9 0.37 -0.69
## LOT 2 54 1.94 0.57 1.85 1.88 0.52 1.1 4 2.9 1.22 1.97
## se
## BASELINE 0.08
## LOT 0.08Create a plot that visualizes LOT variable by the GROUP variable
library(ggplot2)##
## Attaching package: 'ggplot2'
##
## The following object is masked from 'package:psych':
##
## %+%Take a look at the residuals
residual <- lm(LOT ~ BASELINE, data=data2)$residualPlot the residuals to see that they are random
plot(density(residual))# A density plot
qqnorm(residual) # A quantile normal plot to checking normality
qqline(residual)
Checking the different between intervention and control groups residuals. This allows us to control for individual unsystematic differences.
data2$residual <- NA
sel1 <- which(!is.na(data2$LOT))
sel2 <- which(!is.na(data2$BASELINE))
data2$residual[intersect(sel1,sel2)] <- residual
qplot(GROUP, LOT, data=data2, geom="boxplot")## Warning: Removed 65 rows containing non-finite values (stat_boxplot).
Plot of the difference between intervention and control groups.
qplot(GROUP, residual, data=data2, geom="boxplot")## Warning: Removed 69 rows containing non-finite values (stat_boxplot).
Two way repeated measures ======================================================== Graphing the Two-Way Interaction. Both LOT and the Residuals
# Load the nlme package
library(nlme)
with(data2, boxplot(LOT ~ WAVE + GROUP))
with(data2, boxplot(residual ~ WAVE + GROUP))
Comparing Basline to Wave 2 and 3 by Group.
fullModel <- lme(LOT ~ GROUP * WAVE + BASELINE, random = ~1 | ID, data = data2, method = "ML", na.action = "na.omit")Explanation of significance:
We asses the significance of our models by comparing them from the baseline model using the anova() function.
(Intercept): Where everything is 0
GROUP1: Is there a difference between group. If it is significant than there is a difference and the treatment had an effect.
WAVE: Asseses whether the effects gets bigger beteen time 2 and 3 (does not have to be significant)
BASELINE: Should not be significant. If it is then it shows that there is a difference between groups before the treatment.
GROUP1:WAVE: If this is significant then it means that the effect was either fleeting or it happened after the treatment i.e. between time 2 and 3.
summary(fullModel)## Linear mixed-effects model fit by maximum likelihood
## Data: data2
## AIC BIC logLik
## 217.5 236.3 -101.7
##
## Random effects:
## Formula: ~1 | ID
## (Intercept) Residual
## StdDev: 0.3869 0.5005
##
## Fixed effects: LOT ~ GROUP * WAVE + BASELINE
## Value Std.Error DF t-value p-value
## (Intercept) 1.2002 0.3123 66 3.843 0.0003
## GROUP1 0.0477 0.3245 66 0.147 0.8837
## WAVE 0.0637 0.1436 38 0.443 0.6600
## BASELINE 0.3966 0.0910 66 4.357 0.0000
## GROUP1:WAVE -0.1890 0.2103 38 -0.899 0.3745
## Correlation:
## (Intr) GROUP1 WAVE BASELI
## GROUP1 -0.513
## WAVE -0.668 0.614
## BASELINE -0.711 0.052 0.047
## GROUP1:WAVE 0.457 -0.903 -0.683 -0.032
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -1.91498 -0.48795 -0.09516 0.38488 2.66042
##
## Number of Observations: 109
## Number of Groups: 69Table with P-values
| Value | Std.Error | DF | t-value | p-value | |
|---|---|---|---|---|---|
| (Intercept) | 1.2002 | 0.3123 | 66.0000 | 3.8433 | 0.0003 |
| GROUP1 | 0.0477 | 0.3245 | 66.0000 | 0.1469 | 0.8837 |
| WAVE | 0.0637 | 0.1436 | 38.0000 | 0.4434 | 0.6600 |
| BASELINE | 0.3966 | 0.0910 | 66.0000 | 4.3570 | 0.0000 |
| GROUP1:WAVE | -0.1890 | 0.2103 | 38.0000 | -0.8986 | 0.3745 |
``` Table with confidence intervals
| est. | lower | upper | |
|---|---|---|---|
| (Intercept) | 1.2002 | 0.5912 | 1.8092 |
| GROUP1 | 0.0477 | -0.5852 | 0.6805 |
| WAVE | 0.0637 | -0.2203 | 0.3476 |
| BASELINE | 0.3966 | 0.2191 | 0.5741 |
| GROUP1:WAVE | -0.1890 | -0.6048 | 0.2269 |