Loading the dataset
data.test4 <- read.csv("/Volumes/TOSHIBA EXT/Dropbox/ADULT STUDY/adult_study011615.csv")
# Load the psych package
library(psych)
items <- grep("APSI[0-8]", names(data.test4), value=TRUE)
scaleKey <- c(1, 1, 1, 1, 1, -1, 1, 1)
data.test4[,items] <- apply(data.test4[,items], 2, as.numeric)
data.test4$meanAPSI <- scoreItems(scaleKey, items = data.test4[, items], delete = FALSE)$score
library(reshape2); library(car); library(Amelia);library(mitools);library(nlme);library(predictmeans)
##
## Attaching package: 'car'
##
## The following object is masked from 'package:psych':
##
## logit
##
## Loading required package: Rcpp
## ##
## ## Amelia II: Multiple Imputation
## ## (Version 1.7.3, built: 2014-11-14)
## ## Copyright (C) 2005-2015 James Honaker, Gary King and Matthew Blackwell
## ## Refer to http://gking.harvard.edu/amelia/ for more information
## ##
## Loading required package: lme4
## Loading required package: Matrix
##
## Attaching package: 'lme4'
##
## The following object is masked from 'package:nlme':
##
## lmList
#Remove the meanAPSI and ID Group and wave from data.test4 and create a new #dataset with only those variables.
data <- data.test4[,c("ID", "GROUP", "wave", "meanAPSI")]
#Use dcast to cnage from long-format data to wide format data
data <- dcast(data, ID + GROUP ~ wave, mean, value.var = "meanAPSI")
# Changing all NaNs to NA
data[,3:5] <- apply(data[,3:5],2,function(x) recode(x, "NaN = NA") )
Unsing the mapply function we create a new data set with ID Group baseline meanAPSI and wave 2 and 3 of meanAPSI. So we have a Baseline, which is Time 1 (placed in column 3 one on top of the other) to compare to both Time 2 and 3 (placed in column 4 one on top of the other). In the next line of code we then create a separate column called “wave” which calls the first 89 (which compares Time 2 to Baseline) “wave 1” and then the second 89 we call “wave 2” which compares Time 3 to Baseline. In the third line of code we add names to the new columns of the dataset.
data2 <- as.data.frame(mapply(c,data[,1:4], data[,c(1:3,5)]))
data2$wave <- rep(1:2, each=89)
names(data2) <- c("ID", "GROUP", "BASELINE", "meanAPSI", "WAVE")
Intention to treat model (ITT) where we keep the cases who dropped out and did not complete the study (http://en.wikipedia.org/wiki/Intention-to-treat_analysis).
data2[which(data2$GROUP ==2), "GROUP"] <- 1
data2$GROUP <-as.factor(data2$GROUP)
data2$ID <-as.factor(data2$ID)
Imputing missing data
MI <- amelia(data2, 50, idvars = c("ID"), ords = "GROUP")
## -- Imputation 1 --
##
## 1 2 3 4 5 6 7 8 9 10 11
##
## -- Imputation 2 --
##
## 1 2 3 4 5 6 7
##
## -- Imputation 3 --
##
## 1 2 3 4 5 6 7
##
## -- Imputation 4 --
##
## 1 2 3 4 5 6 7 8 9
##
## -- Imputation 5 --
##
## 1 2 3 4 5 6 7 8 9 10 11
##
## -- Imputation 6 --
##
## 1 2 3 4 5 6 7 8 9 10
##
## -- Imputation 7 --
##
## 1 2 3 4 5 6 7 8 9 10
##
## -- Imputation 8 --
##
## 1 2 3 4 5 6 7
##
## -- Imputation 9 --
##
## 1 2 3 4 5 6 7
##
## -- Imputation 10 --
##
## 1 2 3 4 5 6 7 8 9
##
## -- Imputation 11 --
##
## 1 2 3 4 5 6 7
##
## -- Imputation 12 --
##
## 1 2 3 4 5 6 7 8 9 10
##
## -- Imputation 13 --
##
## 1 2 3 4 5 6 7 8 9 10
##
## -- Imputation 14 --
##
## 1 2 3 4 5 6 7 8
##
## -- Imputation 15 --
##
## 1 2 3 4 5 6 7 8 9 10
##
## -- Imputation 16 --
##
## 1 2 3 4 5 6 7 8 9 10
##
## -- Imputation 17 --
##
## 1 2 3 4 5 6 7 8 9
##
## -- Imputation 18 --
##
## 1 2 3 4 5 6 7 8 9 10
##
## -- Imputation 19 --
##
## 1 2 3 4 5 6 7
##
## -- Imputation 20 --
##
## 1 2 3 4 5 6 7 8 9 10 11 12
##
## -- Imputation 21 --
##
## 1 2 3 4 5 6 7 8 9 10
##
## -- Imputation 22 --
##
## 1 2 3 4 5 6 7 8
##
## -- Imputation 23 --
##
## 1 2 3 4 5 6 7 8 9 10 11
##
## -- Imputation 24 --
##
## 1 2 3 4 5 6 7 8
##
## -- Imputation 25 --
##
## 1 2 3 4 5 6 7 8 9 10 11 12 13
##
## -- Imputation 26 --
##
## 1 2 3 4 5 6 7 8 9
##
## -- Imputation 27 --
##
## 1 2 3 4 5 6 7 8
##
## -- Imputation 28 --
##
## 1 2 3 4 5 6 7 8 9 10 11 12
##
## -- Imputation 29 --
##
## 1 2 3 4 5 6
##
## -- Imputation 30 --
##
## 1 2 3 4 5 6 7 8 9 10 11
##
## -- Imputation 31 --
##
## 1 2 3 4 5 6 7 8 9
##
## -- Imputation 32 --
##
## 1 2 3 4 5 6
##
## -- Imputation 33 --
##
## 1 2 3 4 5 6
##
## -- Imputation 34 --
##
## 1 2 3 4 5 6 7 8
##
## -- Imputation 35 --
##
## 1 2 3 4 5 6 7 8
##
## -- Imputation 36 --
##
## 1 2 3 4 5 6 7 8 9
##
## -- Imputation 37 --
##
## 1 2 3 4 5 6 7 8 9 10
##
## -- Imputation 38 --
##
## 1 2 3 4 5 6 7 8 9
##
## -- Imputation 39 --
##
## 1 2 3 4 5 6 7
##
## -- Imputation 40 --
##
## 1 2 3 4 5 6 7 8 9
##
## -- Imputation 41 --
##
## 1 2 3 4 5 6 7 8
##
## -- Imputation 42 --
##
## 1 2 3 4 5 6 7 8 9 10
##
## -- Imputation 43 --
##
## 1 2 3 4 5 6 7
##
## -- Imputation 44 --
##
## 1 2 3 4 5 6 7
##
## -- Imputation 45 --
##
## 1 2 3 4 5 6 7
##
## -- Imputation 46 --
##
## 1 2 3 4 5 6 7 8 9
##
## -- Imputation 47 --
##
## 1 2 3 4 5 6 7
##
## -- Imputation 48 --
##
## 1 2 3 4 5 6 7 8 9 10 11 12
##
## -- Imputation 49 --
##
## 1 2 3 4 5 6 7
##
## -- Imputation 50 --
##
## 1 2 3 4 5 6
Creating new dataset with missing data imputed
data(MI$imputations)
## Warning in data(MI$imputations): data set 'MI$imputations' not found
allimplogreg<-lapply(MI$imputations,function(X) {lme(meanAPSI ~ GROUP * WAVE + BASELINE, random = ~1 | ID, data = X, method = "ML", na.action = "na.omit")})
betas<-MIextract(allimplogreg, fun=fixef)
vars<-MIextract(allimplogreg, fun=vcov)
summary(MIcombine(betas,vars))
## Multiple imputation results:
## MIcombine.default(betas, vars)
## results se (lower upper) missInfo
## (Intercept) 1.49703786 0.26605247 0.97422356 2.0198522 33 %
## GROUP1 0.45718563 0.20043036 0.06377612 0.8505951 24 %
## WAVE 0.08705878 0.09719714 -0.10406545 0.2781830 37 %
## BASELINE 0.60187205 0.05814329 0.48747338 0.7162707 40 %
## GROUP1:WAVE -0.04733202 0.12961342 -0.30196108 0.2072970 31 %
Check results with Imputations using Zelig
library("Zelig")
## Loading required package: boot
##
## Attaching package: 'boot'
##
## The following object is masked from 'package:car':
##
## logit
##
## The following object is masked from 'package:psych':
##
## logit
##
## Loading required package: MASS
## Loading required package: sandwich
## ZELIG (Versions 4.2-1, built: 2013-09-12)
##
## +----------------------------------------------------------------+
## | Please refer to http://gking.harvard.edu/zelig for full |
## | documentation or help.zelig() for help with commands and |
## | models support by Zelig. |
## | |
## | Zelig project citations: |
## | Kosuke Imai, Gary King, and Olivia Lau. (2009). |
## | ``Zelig: Everyone's Statistical Software,'' |
## | http://gking.harvard.edu/zelig |
## | and |
## | Kosuke Imai, Gary King, and Olivia Lau. (2008). |
## | ``Toward A Common Framework for Statistical Analysis |
## | and Development,'' Journal of Computational and |
## | Graphical Statistics, Vol. 17, No. 4 (December) |
## | pp. 892-913. |
## | |
## | To cite individual Zelig models, please use the citation |
## | format printed with each model run and in the documentation. |
## +----------------------------------------------------------------+
##
##
##
## Attaching package: 'Zelig'
##
## The following objects are masked from 'package:psych':
##
## alpha, describe, sim
##
## The following object is masked from 'package:utils':
##
## cite
zelig.fit <- zelig(meanAPSI ~ GROUP * WAVE + BASELINE, random = ~1 | ID, data = MI$imputations, model = "ls", cite = FALSE)
summary(zelig.fit)
##
## Model: ls
## Number of multiply imputed data sets: 50
##
## Combined results:
##
## Call:
## lm(formula = formula, weights = weights, model = F, data = data)
##
## Coefficients:
## Value Std. Error t-stat p-value
## (Intercept) 1.49245765 0.26484205 5.6352745 3.090154e-08
## GROUP1 0.45742881 0.21442010 2.1333299 3.312012e-02
## WAVE 0.08705878 0.10441262 0.8337956 4.047977e-01
## BASELINE 0.60302803 0.05607629 10.7537074 1.143795e-22
## GROUP1:WAVE -0.04733942 0.14004871 -0.3380212 7.354471e-01
##
## For combined results from datasets i to j, use summary(x, subset = i:j).
## For separate results, use print(summary(x), subset = i:j).
Check assumptions with Random Computations
data1=MI$imputations[[1]]
library("Zelig")
zelig.fitdata1 <- zelig(meanAPSI ~ GROUP * WAVE + BASELINE, random = ~1 | ID, data = data1, model = "ls", cite = FALSE)
summary(zelig.fitdata1)
##
## Call:
## lm(formula = formula, weights = weights, model = F, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.26130 -0.25303 -0.02228 0.24864 1.09548
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.22522 0.21658 5.657 6.26e-08 ***
## GROUP1 0.41811 0.18946 2.207 0.0286 *
## WAVE 0.10678 0.08608 1.241 0.2165
## BASELINE 0.66387 0.04252 15.613 < 2e-16 ***
## GROUP1:WAVE -0.06021 0.11973 -0.503 0.6157
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3991 on 173 degrees of freedom
## Multiple R-squared: 0.5963, Adjusted R-squared: 0.587
## F-statistic: 63.9 on 4 and 173 DF, p-value: < 2.2e-16
Describe the meanAPSI variable by the GROUP variable
describeBy(data1[,3:4], group = data1$GROUP)
## group: 0
## vars n mean sd median trimmed mad min max range skew
## BASELINE 1 86 3.96 0.63 4.00 4.00 0.56 2.38 5 2.62 -0.48
## meanAPSI 2 86 4.02 0.63 4.12 4.05 0.60 2.25 5 2.75 -0.49
## kurtosis se
## BASELINE -0.17 0.07
## meanAPSI -0.31 0.07
## --------------------------------------------------------
## group: 1
## vars n mean sd median trimmed mad min max range skew
## BASELINE 1 92 3.75 0.77 3.75 3.79 0.74 1.62 5.00 3.38 -0.36
## meanAPSI 2 92 4.21 0.61 4.25 4.24 0.64 2.36 5.22 2.86 -0.58
## kurtosis se
## BASELINE -0.11 0.08
## meanAPSI 0.09 0.06
Create a plot that visualizes meanAPSI variable by the GROUP variable
library(ggplot2)
##
## Attaching package: 'ggplot2'
##
## The following object is masked from 'package:psych':
##
## %+%
library(influence.ME)
##
## Attaching package: 'influence.ME'
##
## The following object is masked from 'package:stats':
##
## influence
Take a look at the residuals
residual <- lm(meanAPSI ~ BASELINE, data=data1)$residual
Plot 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$residual <- NA
sel1 <- which(!is.na(data1$meanAPSI))
sel2 <- which(!is.na(data1$BASELINE))
data1$residual[intersect(sel1,sel2)] <- residual
qplot(GROUP, meanAPSI, data=data1, geom="boxplot")
Plot of the difference between intervention and control groups.
qplot(GROUP, residual, data=data1, geom="boxplot")
Two way repeated measures ======================================================== Graphing the Two-Way Interaction. Both meanAPSI and the Residuals
# Load the nlme package
library(nlme)
with(data1, boxplot(meanAPSI ~ WAVE + GROUP))
with(data1, boxplot(residual ~ WAVE + GROUP))
Comparing Basline to Wave 2 and 3 by Group.
fullModeldata1 <- lme(meanAPSI ~ GROUP * WAVE + BASELINE, random = ~1 | ID, data = data1, method = "ML", na.action = "na.omit")
CookD(fullModeldata1)
plot(fullModeldata1, which="cook")
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(fullModeldata1)
## Linear mixed-effects model fit by maximum likelihood
## Data: data1
## AIC BIC logLik
## 179.0357 201.3081 -82.51783
##
## Random effects:
## Formula: ~1 | ID
## (Intercept) Residual
## StdDev: 0.2134814 0.3305451
##
## Fixed effects: meanAPSI ~ GROUP * WAVE + BASELINE
## Value Std.Error DF t-value p-value
## (Intercept) 1.2406389 0.22524234 87 5.508018 0.0000
## GROUP1 0.4174162 0.16575777 87 2.518230 0.0136
## WAVE 0.1067824 0.07231002 86 1.476731 0.1434
## BASELINE 0.6599836 0.04826536 86 13.674064 0.0000
## GROUP1:WAVE -0.0602796 0.10058481 86 -0.599291 0.5506
## Correlation:
## (Intr) GROUP1 WAVE BASELI
## GROUP1 -0.424
## WAVE -0.482 0.654
## BASELINE -0.849 0.052 0.000
## GROUP1:WAVE 0.338 -0.910 -0.719 0.009
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -2.85505130 -0.58461252 -0.06396883 0.56136518 2.68866193
##
## Number of Observations: 178
## Number of Groups: 89
Another random imputation
data10=MI$imputations[[10]]
library("Zelig")
zelig.fitdata10 <- zelig(meanAPSI ~ GROUP * WAVE + BASELINE, random = ~1 | ID, data = data10, model = "ls", cite = FALSE)
summary(zelig.fitdata10)
##
## Call:
## lm(formula = formula, weights = weights, model = F, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.31354 -0.26400 -0.03461 0.31217 1.08470
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.58732 0.22089 7.186 1.91e-11 ***
## GROUP1 0.55702 0.19430 2.867 0.00466 **
## WAVE 0.14824 0.08822 1.680 0.09470 .
## BASELINE 0.56251 0.04322 13.014 < 2e-16 ***
## GROUP1:WAVE -0.10711 0.12272 -0.873 0.38398
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4091 on 173 degrees of freedom
## Multiple R-squared: 0.5287, Adjusted R-squared: 0.5178
## F-statistic: 48.52 on 4 and 173 DF, p-value: < 2.2e-16
Describe the meanAPSI variable by the GROUP variable
describeBy(data10[,3:4], group = data10$GROUP)
## group: 0
## vars n mean sd median trimmed mad min max range skew
## BASELINE 1 86 3.96 0.63 4.00 4.00 0.56 2.38 5 2.62 -0.48
## meanAPSI 2 86 4.04 0.60 4.07 4.07 0.63 2.25 5 2.75 -0.45
## kurtosis se
## BASELINE -0.17 0.07
## meanAPSI -0.08 0.06
## --------------------------------------------------------
## group: 1
## vars n mean sd median trimmed mad min max range skew
## BASELINE 1 92 3.76 0.78 3.75 3.80 0.93 1.62 5.0 3.38 -0.35
## meanAPSI 2 92 4.32 0.55 4.38 4.36 0.56 2.51 5.5 2.98 -0.59
## kurtosis se
## BASELINE -0.20 0.08
## meanAPSI 0.46 0.06
Create a plot that visualizes meanAPSI variable by the GROUP variable
library(ggplot2)
library(influence.ME)
Take a look at the residuals
residual <- lm(meanAPSI ~ BASELINE, data=data10)$residual
Plot the residuals to see that they are random
plot(density(residual))# A density plot
qqnorm(residual) # A quantile normal plot to checking normality
qqline(residual)
Checking the different between intervention and control groups residuals. This allows us to control for individual unsystematic differences.
data2$residual <- NA
sel1 <- which(!is.na(data10$meanAPSI))
sel2 <- which(!is.na(data10$BASELINE))
data10$residual[intersect(sel1,sel2)] <- residual
qplot(GROUP, meanAPSI, data=data10, geom="boxplot")
Plot of the difference between intervention and control groups.
qplot(GROUP, residual, data=data10, geom="boxplot")
Two way repeated measures ======================================================== Graphing the Two-Way Interaction. Both meanAPSI and the Residuals
# Load the nlme package
library(nlme)
with(data10, boxplot(meanAPSI ~ WAVE + GROUP))
with(data10, boxplot(residual ~ WAVE + GROUP))
Comparing Basline to Wave 2 and 3 by Group.
fullModeldata10 <- lme(meanAPSI ~ GROUP * WAVE + BASELINE, random = ~1 | ID, data = data10, method = "ML", na.action = "na.omit")
CookD(fullModeldata10)
plot(fullModeldata10, which="cook")
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(fullModeldata10)
## Linear mixed-effects model fit by maximum likelihood
## Data: data10
## AIC BIC logLik
## 193.0425 215.315 -89.52126
##
## Random effects:
## Formula: ~1 | ID
## (Intercept) Residual
## StdDev: 0.1694766 0.3659558
##
## Fixed effects: meanAPSI ~ GROUP * WAVE + BASELINE
## Value Std.Error DF t-value p-value
## (Intercept) 1.5926083 0.22607075 87 7.044734 0.0000
## GROUP1 0.5567035 0.18014172 87 3.090364 0.0027
## WAVE 0.1482438 0.08005647 86 1.851740 0.0675
## BASELINE 0.5611779 0.04680907 86 11.988659 0.0000
## GROUP1:WAVE -0.1070792 0.11136145 86 -0.961547 0.3390
## Correlation:
## (Intr) GROUP1 WAVE BASELI
## GROUP1 -0.460
## WAVE -0.531 0.667
## BASELINE -0.820 0.061 0.000
## GROUP1:WAVE 0.390 -0.928 -0.719 -0.010
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -2.82811979 -0.63439172 -0.07315838 0.72087545 2.53840665
##
## Number of Observations: 178
## Number of Groups: 89
Another random imputation
data15=MI$imputations[[15]]
library("Zelig")
zelig.fitdata15 <- zelig(meanAPSI ~ GROUP * WAVE + BASELINE, random = ~1 | ID, data = data15, model = "ls", cite = FALSE)
summary(zelig.fitdata15)
##
## Call:
## lm(formula = formula, weights = weights, model = F, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.24566 -0.28418 -0.03953 0.29258 1.27079
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.54518 0.22226 6.952 7.06e-11 ***
## GROUP1 0.42640 0.19414 2.196 0.0294 *
## WAVE 0.04631 0.08820 0.525 0.6002
## BASELINE 0.60848 0.04368 13.931 < 2e-16 ***
## GROUP1:WAVE -0.01681 0.12269 -0.137 0.8912
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.409 on 173 degrees of freedom
## Multiple R-squared: 0.5526, Adjusted R-squared: 0.5423
## F-statistic: 53.43 on 4 and 173 DF, p-value: < 2.2e-16
Describe the meanAPSI variable by the GROUP variable
describeBy(data15[,3:4], group = data15$GROUP)
## group: 0
## vars n mean sd median trimmed mad min max range skew
## BASELINE 1 86 3.96 0.63 4 4.00 0.56 2.38 5 2.62 -0.48
## meanAPSI 2 86 4.03 0.60 4 4.05 0.57 2.25 5 2.75 -0.40
## kurtosis se
## BASELINE -0.17 0.07
## meanAPSI -0.09 0.06
## --------------------------------------------------------
## group: 1
## vars n mean sd median trimmed mad min max range skew
## BASELINE 1 92 3.75 0.77 3.75 3.78 0.74 1.62 5.00 3.38 -0.34
## meanAPSI 2 92 4.30 0.59 4.37 4.31 0.57 2.83 5.55 2.73 -0.24
## kurtosis se
## BASELINE -0.08 0.08
## meanAPSI -0.33 0.06
Create a plot that visualizes meanAPSI variable by the GROUP variable
library(ggplot2)
library(influence.ME)
Take a look at the residuals
residual <- lm(meanAPSI ~ BASELINE, data=data15)$residual
Plot 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$residual <- NA
sel1 <- which(!is.na(data15$meanAPSI))
sel2 <- which(!is.na(data15$BASELINE))
data15$residual[intersect(sel1,sel2)] <- residual
qplot(GROUP, meanAPSI, data=data15, geom="boxplot")
Plot of the difference between intervention and control groups.
qplot(GROUP, residual, data=data15, geom="boxplot")
Two way repeated measures ======================================================== Graphing the Two-Way Interaction. Both meanAPSI and the Residuals
# Load the nlme package
library(nlme)
with(data15, boxplot(meanAPSI ~ WAVE + GROUP))
with(data15, boxplot(residual ~ WAVE + GROUP))
Comparing Basline to Wave 2 and 3 by Group.
fullModeldata15 <- lme(meanAPSI ~ GROUP * WAVE + BASELINE, random = ~1 | ID, data = data15, method = "ML", na.action = "na.omit")
CookD(fullModeldata15)
plot(fullModeldata15, which="cook")
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(fullModeldata15)
## Linear mixed-effects model fit by maximum likelihood
## Data: data15
## AIC BIC logLik
## 194.1094 216.3819 -90.05472
##
## Random effects:
## Formula: ~1 | ID
## (Intercept) Residual
## StdDev: 0.1484388 0.3748579
##
## Fixed effects: meanAPSI ~ GROUP * WAVE + BASELINE
## Value Std.Error DF t-value p-value
## (Intercept) 1.5489679 0.22653638 87 6.837612 0.0000
## GROUP1 0.4262227 0.18335647 87 2.324558 0.0224
## WAVE 0.0463059 0.08200389 86 0.564679 0.5738
## BASELINE 0.6075265 0.04652364 86 13.058448 0.0000
## GROUP1:WAVE -0.0168332 0.11406906 86 -0.147571 0.8830
## Correlation:
## (Intr) GROUP1 WAVE BASELI
## GROUP1 -0.455
## WAVE -0.543 0.671
## BASELINE -0.814 0.047 0.000
## GROUP1:WAVE 0.383 -0.933 -0.719 0.009
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -2.8540388 -0.5924343 -0.1248252 0.6500930 2.9698728
##
## Number of Observations: 178
## Number of Groups: 89
Another random imputation
data25=MI$imputations[[25]]
library("Zelig")
zelig.fitdata25 <- zelig(meanAPSI ~ GROUP * WAVE + BASELINE, random = ~1 | ID, data = data25, model = "ls", cite = FALSE)
summary(zelig.fitdata25)
##
## Call:
## lm(formula = formula, weights = weights, model = F, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.26903 -0.21839 -0.02437 0.23882 1.05949
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.60897 0.19949 8.065 1.17e-13 ***
## GROUP1 0.56878 0.17510 3.248 0.00139 **
## WAVE 0.07852 0.07952 0.987 0.32483
## BASELINE 0.58143 0.03909 14.874 < 2e-16 ***
## GROUP1:WAVE -0.14414 0.11061 -1.303 0.19425
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3687 on 173 degrees of freedom
## Multiple R-squared: 0.5824, Adjusted R-squared: 0.5728
## F-statistic: 60.32 on 4 and 173 DF, p-value: < 2.2e-16
Describe the meanAPSI variable by the GROUP variable
describeBy(data25[,3:4], group = data25$GROUP)
## group: 0
## vars n mean sd median trimmed mad min max range skew
## BASELINE 1 86 3.96 0.63 4.00 4.00 0.56 2.38 5 2.62 -0.48
## meanAPSI 2 86 4.03 0.59 4.08 4.05 0.63 2.25 5 2.75 -0.41
## kurtosis se
## BASELINE -0.17 0.07
## meanAPSI 0.03 0.06
## --------------------------------------------------------
## group: 1
## vars n mean sd median trimmed mad min max range skew
## BASELINE 1 92 3.77 0.78 3.75 3.80 0.83 1.62 5.0 3.38 -0.37
## meanAPSI 2 92 4.27 0.52 4.26 4.29 0.58 3.00 5.4 2.40 -0.28
## kurtosis se
## BASELINE -0.14 0.08
## meanAPSI -0.53 0.05
Create a plot that visualizes meanAPSI variable by the GROUP variable
library(ggplot2)
library(influence.ME)
Take a look at the residuals
residual <- lm(meanAPSI ~ BASELINE, data=data25)$residual
Plot the residuals to see that they are random
plot(density(residual))# A density plot
qqnorm(residual) # A quantile normal plot to checking normality
qqline(residual)
Checking the different between intervention and control groups residuals. This allows us to control for individual unsystematic differences.
data2$residual <- NA
sel1 <- which(!is.na(data25$meanAPSI))
sel2 <- which(!is.na(data25$BASELINE))
data25$residual[intersect(sel1,sel2)] <- residual
qplot(GROUP, meanAPSI, data=data25, geom="boxplot")
Plot of the difference between intervention and control groups.
qplot(GROUP, residual, data=data25, geom="boxplot")
Two way repeated measures ======================================================== Graphing the Two-Way Interaction. Both meanAPSI and the Residuals
# Load the nlme package
library(nlme)
with(data25, boxplot(meanAPSI ~ WAVE + GROUP))
with(data25, boxplot(residual ~ WAVE + GROUP))
Comparing Basline to Wave 2 and 3 by Group.
fullModeldata25 <- lme(meanAPSI ~ GROUP * WAVE + BASELINE, random = ~1 | ID, data = data25, method = "ML", na.action = "na.omit")
CookD(fullModeldata25)
plot(fullModeldata25, which="cook")
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(fullModeldata25)
## Linear mixed-effects model fit by maximum likelihood
## Data: data25
## AIC BIC logLik
## 155.1489 177.4214 -70.57447
##
## Random effects:
## Formula: ~1 | ID
## (Intercept) Residual
## StdDev: 0.163582 0.3246095
##
## Fixed effects: meanAPSI ~ GROUP * WAVE + BASELINE
## Value Std.Error DF t-value p-value
## (Intercept) 1.6136952 0.20494630 87 7.873746 0.0000
## GROUP1 0.5685211 0.16037256 87 3.545002 0.0006
## WAVE 0.0785161 0.07101154 86 1.105680 0.2719
## BASELINE 0.5802339 0.04279840 86 13.557373 0.0000
## GROUP1:WAVE -0.1441231 0.09877697 86 -1.459076 0.1482
## Correlation:
## (Intr) GROUP1 WAVE BASELI
## GROUP1 -0.452
## WAVE -0.520 0.664
## BASELINE -0.827 0.059 0.000
## GROUP1:WAVE 0.379 -0.924 -0.719 -0.007
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -3.38292777 -0.60530852 -0.06756387 0.63721907 2.73486235
##
## Number of Observations: 178
## Number of Groups: 89
Check assumptions on model without any imputations
Describe the meanAPSI 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
## BASELINE 1 86 3.96 0.63 4.00 4.00 0.56 2.38 5 2.62 -0.48
## meanAPSI 2 59 4.09 0.65 4.12 4.14 0.56 2.25 5 2.75 -0.68
## kurtosis se
## BASELINE -0.17 0.07
## meanAPSI 0.03 0.08
## --------------------------------------------------------
## group: 1
## vars n mean sd median trimmed mad min max range skew
## BASELINE 1 88 3.74 0.78 3.69 3.77 0.83 1.62 5 3.38 -0.32
## meanAPSI 2 54 4.31 0.48 4.38 4.33 0.56 3.00 5 2.00 -0.42
## kurtosis se
## BASELINE -0.18 0.08
## meanAPSI -0.56 0.07
Create a plot that visualizes meanAPSI variable by the GROUP variable
library(ggplot2)
library(influence.ME)
Take a look at the residuals
residual <- lm(meanAPSI ~ BASELINE, data=data2)$residual
Plot the residuals to see that they are random
plot(density(residual))# A density plot
qqnorm(residual) # A quantile normal plot to checking normality
qqline(residual)
Checking the different between intervention and control groups residuals. This allows us to control for individual unsystematic differences.
data2$residual <- NA
sel1 <- which(!is.na(data2$meanAPSI))
sel2 <- which(!is.na(data2$BASELINE))
data2$residual[intersect(sel1,sel2)] <- residual
qplot(GROUP, meanAPSI, 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 meanAPSI and the Residuals
# Load the nlme package
library(nlme)
with(data2, boxplot(meanAPSI ~ WAVE + GROUP))
with(data2, boxplot(residual ~ WAVE + GROUP))
Comparing Basline to Wave 2 and 3 by Group.
fullModel <- lme(meanAPSI ~ GROUP * WAVE + BASELINE, random = ~1 | ID, data = data2, method = "ML", na.action = "na.omit")
CookD(fullModel)
plot(fullModel, which="cook")
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
## 116.0995 134.9389 -51.04973
##
## Random effects:
## Formula: ~1 | ID
## (Intercept) Residual
## StdDev: 0.2831168 0.2911441
##
## Fixed effects: meanAPSI ~ GROUP * WAVE + BASELINE
## Value Std.Error DF t-value p-value
## (Intercept) 1.5245895 0.29719767 66 5.129884 0.0000
## GROUP1 0.4979467 0.19532844 66 2.549279 0.0131
## WAVE 0.0928050 0.08500811 38 1.091719 0.2818
## BASELINE 0.5917203 0.06740176 66 8.779004 0.0000
## GROUP1:WAVE -0.0865771 0.12429379 38 -0.696552 0.4903
## Correlation:
## (Intr) GROUP1 WAVE BASELI
## GROUP1 -0.350
## WAVE -0.338 0.594
## BASELINE -0.895 0.055 -0.062
## GROUP1:WAVE 0.222 -0.877 -0.685 0.052
##
## Standardized Within-Group Residuals:
## Min Q1 Med Q3 Max
## -2.21220762 -0.54771380 -0.03644676 0.59967572 2.44696288
##
## Number of Observations: 109
## Number of Groups: 69
Table with P-value
| | Value| Std.Error| DF| t-value| p-value|
|:------------|-----------:|----------:|---:|-----------:|----------:|
|(Intercept) | 1.5245895| 0.2971977| 66| 5.1298836| 0.0000027|
|GROUP1 | 0.4979467| 0.1953284| 66| 2.5492793| 0.0131262|
|WAVE | 0.0928050| 0.0850081| 38| 1.0917193| 0.2818302|
|BASELINE | 0.5917203| 0.0674018| 66| 8.7790042| 0.0000000|
|GROUP1:WAVE | -0.0865771| 0.1242938| 38| -0.6965522| 0.4903223|
Table with confidence intervals
| est. | lower | upper | |
|---|---|---|---|
| (Intercept) | 1.5245895 | 0.9449844 | 2.1041945 |
| GROUP1 | 0.4979467 | 0.1170106 | 0.8788829 |
| WAVE | 0.0928050 | -0.0752916 | 0.2609016 |
| BASELINE | 0.5917203 | 0.4602711 | 0.7231696 |
| GROUP1:WAVE | -0.0865771 | -0.3323579 | 0.1592037 |