# Loading the dataset that has been reset into a long version
load("/Users/levibrackman/data.test.RData")
# Creating a new variable that is the mean of all positive purpose Life
# Satisfaction questions
data.test$LS <- apply(data.test[, c("LS1", "LS2", "LS3", "LS4", "LS5")], 1,
mean, na.rm = TRUE)
For lme to work GROUP and ID need to be seen as factors
data.test$GROUP <- as.factor(data.test$GROUP)
data.test$ID <- as.factor(data.test$ID)
# Load the psych package
library(psych)
Describe the LS variable by the GROUP variable
describeBy(data.test$LS, group = data.test$GROUP)
## group: 0
## vars n mean sd median trimmed mad min max range skew kurtosis se
## 1 1 80 4.49 1.34 4.6 4.58 1.19 1.4 7 5.6 -0.52 -0.22 0.15
## --------------------------------------------------------
## group: 1
## vars n mean sd median trimmed mad min max range skew kurtosis se
## 1 1 70 4.89 1.24 5.2 5 1.04 1.6 6.8 5.2 -0.73 -0.12 0.15
## --------------------------------------------------------
## group: 2
## vars n mean sd median trimmed mad min max range skew kurtosis se
## 1 1 5 4.88 1.1 5 4.88 0.89 3.4 6.4 3 0.03 -1.61 0.49
Create a plot that visualizes LS variable by the GROUP variable
library(ggplot2)
##
## Attaching package: 'ggplot2'
##
## The following object is masked from 'package:psych':
##
## %+%
qplot(GROUP, LS, data = data.test, geom = "boxplot")
# Load the nlme package
library(nlme)
with(data.test, boxplot(LS ~ wave + GROUP))
Graphing the Two-Way Interaction.
# Load the nlme package
library(nlme)
I am not sure if I am doing this right
baseline <- lme(LS ~ 1, random = ~1 | ID/GROUP/wave, data = data.test, method = "ML")
LSModel <- lme(LS ~ GROUP, random = ~1 | ID/GROUP/wave, data = data.test, method = "ML")
LS2Model <- lme(LS ~ GROUP + wave, random = ~1 | ID/GROUP/wave, data = data.test,
method = "ML")
fullModel <- lme(LS ~ GROUP * wave, random = ~1 | ID/GROUP/wave, data = data.test,
method = "ML")
We again the significance of our models by comparing them from the baseline model using the anova() function.
anova(baseline, LSModel, LS2Model, fullModel)
## Model df AIC BIC logLik Test L.Ratio p-value
## baseline 1 5 483.1 498.3 -236.6
## LSModel 2 7 485.2 506.5 -235.6 1 vs 2 1.893 0.3881
## LS2Model 3 8 481.9 506.3 -233.0 2 vs 3 5.306 0.0212
## fullModel 4 10 482.0 512.4 -231.0 3 vs 4 3.953 0.1385
summary(fullModel)
## Warning: NaNs produced
## Linear mixed-effects model fit by maximum likelihood
## Data: data.test
## AIC BIC logLik
## 482 512.4 -231
##
## Random effects:
## Formula: ~1 | ID
## (Intercept)
## StdDev: 0.0002606
##
## Formula: ~1 | GROUP %in% ID
## (Intercept)
## StdDev: 1.081
##
## Formula: ~1 | wave %in% GROUP %in% ID
## (Intercept) Residual
## StdDev: 2.347e-05 0.6467
##
## Fixed effects: LS ~ GROUP * wave
## Value Std.Error DF t-value p-value
## (Intercept) 4.316 0.2837 89 15.210 0.0000
## GROUP1 -0.113 0.4133 0 -0.274 NaN
## GROUP2 -0.894 1.1561 89 -0.774 0.4411
## wave 0.089 0.1565 59 0.567 0.5728
## GROUP1:wave 0.347 0.2365 59 1.468 0.1475
## GROUP2:wave 1.023 0.6636 59 1.542 0.1284
## Correlation:
## (Intr) GROUP1 GROUP2 wave GROUP1:
## GROUP1 -0.687
## GROUP2 -0.245 0.169
## wave -0.769 0.528 0.189
## GROUP1:wave 0.509 -0.778 -0.125 -0.662
## GROUP2:wave 0.181 -0.125 -0.776 -0.236 0.156
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -3.05070 -0.38595 0.01563 0.35921 2.46085
##
## Number of Observations: 155
## Number of Groups:
## ID GROUP %in% ID wave %in% GROUP %in% ID
## 91 92 154