Giannakopoulou, Brown, Clayards & Wonnacott
Elizabeth Wonnacott
September, 2016
Load packages and helper functions
packages.
rm(list=ls())
library(ggplot2)
library(plotrix)
suppressPackageStartupMessages(library(dplyr))
suppressPackageStartupMessages(library(plyr))
library(bootstrap)
suppressPackageStartupMessages(library(lme4))
library(knitr)
theme_set(theme_bw())
opts_chunk$set(fig.width=8, fig.height=5,
echo=TRUE, warning=FALSE, message=FALSE, cache=TRUE)helper functions.
SummarySE
This function can be found on the website “Cookbook for R”.
http://www.cookbook-r.com/Graphs/Plotting_means_and_error_bars_(ggplot2)/#Helper
It summarizes data, giving count, mean, standard deviation, standard error of the mean, and confidence interval (default 95%).
data: a data frame.
measurevar: the name of a column that contains the variable to be summarized. groupvars: a vector containing names of columns that contain grouping variables. na.rm: a boolean that indicates whether to ignore NA’s. conf.interval: the percent range of the confidence interval (default is 95%).
summarySE <- function(data=NULL, measurevar, groupvars=NULL, na.rm=FALSE,
conf.interval=.95, .drop=TRUE) {
require(plyr)
# New version of length which can handle NA's: if na.rm==T, don't count them
length2 <- function (x, na.rm=FALSE) {
if (na.rm) sum(!is.na(x))
else length(x)
}
# This does the summary. For each group's data frame, return a vector with
# N, mean, and sd
datac <- ddply(data, groupvars, .drop=.drop,
.fun = function(xx, col) {
c(N = length2(xx[[col]], na.rm=na.rm),
mean = mean (xx[[col]], na.rm=na.rm),
sd = sd (xx[[col]], na.rm=na.rm)
)
},
measurevar
)
# Rename the "mean" column
datac <- rename(datac, c("mean" = measurevar))
datac$se <- datac$sd / sqrt(datac$N) # Calculate standard error of the mean
# Confidence interval multiplier for standard error
# Calculate t-statistic for confidence interval:
# e.g., if conf.interval is .95, use .975 (above/below), and use df=N-1
ciMult <- qt(conf.interval/2 + .5, datac$N-1)
datac$ci <- datac$se * ciMult
return(datac)
}SummarySEwithin
This function can be found on the website “Cookbook for R”.
http://www.cookbook-r.com/Graphs/Plotting_means_and_error_bars_(ggplot2)/#Helper
From that website:
Summarizes data, handling within-subjects variables by removing inter-subject variability. It will still work if there are no within-S variables. Gives count, un-normed mean, normed mean (with same between-group mean), standard deviation, standard error of the mean, and confidence interval. If there are within-subject variables, calculate adjusted values using method from Morey (2008). data: a data frame.
measurevar: the name of a column that contains the variable to be summarized. betweenvars: a vector containing names of columns that are between-subjects variables. withinvars: a vector containing names of columns that are within-subjects variables. idvar: the name of a column that identifies each subject (or matched subjects). na.rm: a boolean that indicates whether to ignore NA’s. conf.interval: the percent range of the confidence interval (default is 95%).
summarySEwithin <- function(data=NULL, measurevar, betweenvars=NULL, withinvars=NULL,
idvar=NULL, na.rm=FALSE, conf.interval=.95, .drop=TRUE) {
# Ensure that the betweenvars and withinvars are factors
factorvars <- vapply(data[, c(betweenvars, withinvars), drop=FALSE],
FUN=is.factor, FUN.VALUE=logical(1))
if (!all(factorvars)) {
nonfactorvars <- names(factorvars)[!factorvars]
message("Automatically converting the following non-factors to factors: ",
paste(nonfactorvars, collapse = ", "))
data[nonfactorvars] <- lapply(data[nonfactorvars], factor)
}
# Get the means from the un-normed data
datac <- summarySE(data, measurevar, groupvars=c(betweenvars, withinvars),
na.rm=na.rm, conf.interval=conf.interval, .drop=.drop)
# Drop all the unused columns (these will be calculated with normed data)
datac$sd <- NULL
datac$se <- NULL
datac$ci <- NULL
# Norm each subject's data
ndata <- normDataWithin(data, idvar, measurevar, betweenvars, na.rm, .drop=.drop)
# This is the name of the new column
measurevar_n <- paste(measurevar, "_norm", sep="")
# Collapse the normed data - now we can treat between and within vars the same
ndatac <- summarySE(ndata, measurevar_n, groupvars=c(betweenvars, withinvars),
na.rm=na.rm, conf.interval=conf.interval, .drop=.drop)
# Apply correction from Morey (2008) to the standard error and confidence interval
# Get the product of the number of conditions of within-S variables
nWithinGroups <- prod(vapply(ndatac[,withinvars, drop=FALSE], FUN=nlevels,
FUN.VALUE=numeric(1)))
correctionFactor <- sqrt( nWithinGroups / (nWithinGroups-1) )
# Apply the correction factor
ndatac$sd <- ndatac$sd * correctionFactor
ndatac$se <- ndatac$se * correctionFactor
ndatac$ci <- ndatac$ci * correctionFactor
# Combine the un-normed means with the normed results
merge(datac, ndatac)
}normDataWithin
This function is used by the SummarySEWithin fucntion above. It can be found on the website “Cookbook for R”.
http://www.cookbook-r.com/Graphs/Plotting_means_and_error_bars_(ggplot2)/#Helper
From that website:
Norms the data within specified groups in a data frame; it normalizes each subject (identified by idvar) so that they have the same mean, within each group specified by betweenvars.
data: a data frame. idvar: the name of a column that identifies each subject (or matched subjects). measurevar: the name of a column that contains the variable to be summariezed. betweenvars: a vector containing names of columns that are between-subjects variables na.rm: a boolean that indicates whether to ignore NA’s
normDataWithin <- function(data=NULL, idvar, measurevar, betweenvars=NULL,
na.rm=FALSE, .drop=TRUE) {
#library(plyr)
# Measure var on left, idvar + between vars on right of formula.
data.subjMean <- ddply(data, c(idvar, betweenvars), .drop=.drop,
.fun = function(xx, col, na.rm) {
c(subjMean = mean(xx[,col], na.rm=na.rm))
},
measurevar,
na.rm
)
# Put the subject means with original data
data <- merge(data, data.subjMean)
# Get the normalized data in a new column
measureNormedVar <- paste(measurevar, "_norm", sep="")
data[,measureNormedVar] <- data[,measurevar] - data[,"subjMean"] +
mean(data[,measurevar], na.rm=na.rm)
# Remove this subject mean column
data$subjMean <- NULL
return(data)
}myCenter
This function ouputsthe centered values of an variable, which can be a numeric variable, a factor, or a data frame. It was taken from Florian Jaegers blog https://hlplab.wordpress.com/2009/04/27/centering-several-variables/.
From his blog:
-If the input is a numeric variable, the output is the centered variable.
-If the input is a factor, the output is a numeric variable with centered factor level values. That is, the factor’s levels are converted into numerical values in their inherent order (if not specified otherwise, R defaults to alphanumerical order). More specifically, this centers any binary factor so that the value below 0 will be the 1st level of the original factor, and the value above 0 will be the 2nd level.
-If the input is a data frame or matrix, the output is a new matrix of the same dimension and with the centered values and column names that correspond to the colnames() of the input preceded by “c” (e.g. “Variable1” will be “cVariable1”).
myCenter= function(x) {
if (is.numeric(x)) { return(x - mean(x, na.rm=T)) }
if (is.factor(x)) {
x= as.numeric(x)
return(x - mean(x, na.rm=T))
}
if (is.data.frame(x) || is.matrix(x)) {
m= matrix(nrow=nrow(x), ncol=ncol(x))
colnames(m)= paste("c", colnames(x), sep="")
for (i in 1:ncol(x)) {
m[,i]= myCenter(x[,i])
}
return(as.data.frame(m))
}
}myCenter
This function ouputs the centered values of an variable, which can be a numeric variable, a factor, or a data frame. It was taken from Florian Jaegers blog https://hlplab.wordpress.com/2009/04/27/centering-several-variables/.
From his blog:
-If the input is a numeric variable, the output is the centered variable.
-If the input is a factor, the output is a numeric variable with centered factor level values. That is, the factor’s levels are converted into numerical values in their inherent order (if not specified otherwise, R defaults to alphanumerical order). More specifically, this centers any binary factor so that the value below 0 will be the 1st level of the original factor, and the value above 0 will be the 2nd level.
-If the input is a data frame or matrix, the output is a new matrix of the same dimension and with the centered values and column names that correspond to the colnames() of the input preceded by “c” (e.g. “Variable1” will be “cVariable1”).
myCenter= function(x) {
if (is.numeric(x)) { return(x - mean(x, na.rm=T)) }
if (is.factor(x)) {
x= as.numeric(x)
return(x - mean(x, na.rm=T))
}
if (is.data.frame(x) || is.matrix(x)) {
m= matrix(nrow=nrow(x), ncol=ncol(x))
colnames(m)= paste("c", colnames(x), sep="")
for (i in 1:ncol(x)) {
m[,i]= myCenter(x[,i])
}
return(as.data.frame(m))
}
}selectCenter
This function provides a wrapper around myCenter allowing you to center a specific list of variables from a dataframe.
x: data frame listfname: a list of the variables to be centered (e.g. list(variable1,variable2))
The output is a copy of the data frame with a column (always a numeric variable) added for each of the centered variables. These columns are labelled with the each column’s previous name, but with “.ct” appended (e.g., “variable1” will become “variable1.ct”).
selectCenter= function(x, listfname)
{
for (i in 1:length(listfname))
{
fname = as.character(listfname[i])
x[paste(fname,".ct", sep="")] = myCenter(x[fname])
}
return(x)
}get_coeffs
This function allows us to inspect just particular coefficients from the output of an lme model by putting them in table.
x: the output returned when running lmer or glmer (i.e. an objet of type lmerMod or glmerMod) list: a list of names of the coefficients to be extracted (e.g. c(“variable1”,“variable1:variable2”))
get_coeffs <- function(x,list){(kable(as.data.frame(summary(x)$coefficients)[list,],digits=3))}filter2
This is a function which filters a column of data removing value which are some number of standard deviations above/below the mean for that participant, possibly in some condition/subcondition
im is the input matrix (a data frame) svn a list of the names of factors grouping by (subject name + one or more conditions) fn name of the column in the data to be filtered lim - how many standardeviations above/below the mean to filter
the function returns an input matrix identical to the input matrix but with an additional columns giving the group means and the “filtered” data
filter2 = function(im, svn, fn, lim)
{
## work out means lisfor each subject for each word
x = list()
y = ""
for(n in svn) x=append(im[n],x)
for(n in svn) y=paste(y,n,sep="_")
means = aggregate(im[fn], by = x, mean, na.rm=T)
head(means)
nocols = dim(means)[2]
colnames(means)[nocols] = "means"
sds = aggregate(im[fn], by = x, sd, na.rm=T)
head(sds)
nocols = dim(sds)[2]
colnames(sds)[nocols] = "sds"
gs = merge(means,sds)
## because if there is just one value it doesn't have a stand deviation and don't want to just disregard all of these
gs$sds[is.na(gs$sds)] = 0
gs$max = gs$means + lim*gs$sds
gs$min = gs$means- lim*gs$sds
im2 = merge(im,gs, sort=F)
im2[paste(fn,"filt",sep="")] = im2[fn]
cn= dim(im2)[2] ## get colnumber (last one added)
im2[,cn][im2[,fn]> im2$max] = ""
im2[,cn][im2[,fn]< im2$min] = ""
im2[,cn]= as.numeric(im2[,cn])
names(im2)[names(im2)=="means"] = paste("mean", y, sep="_")
names(im2)[names(im2)=="sds"] = paste("sd", y, sep="_")
names(im2)[names(im2)=="max"] = paste("max", y, sep="_")
names(im2)[names(im2)=="min"] = paste("min", y, sep="_")
return(im2)
}lmedrop
Given an lmer model (model) and one of the coefficients, this returns p value for that coefficient using model comparison (i.e. comparing identical models with and without those terms). It can be used to get p-values when using lmer rather than gmler and dealing with continuous (rather than binonimal) dv.
lmedrop<-function(model, term) {
model.dropped<-update(model,eval(paste(".~.-",term)));
anova(model.dropped,model) }Load datasets
train = read.csv( "training.csv")
discrim = read.csv( "discrim.csv")
lexd = read.csv( "lexd.csv")
engintro = read.csv( "englishintro.csv")Training
data preparation
check amount of missing data
There should be 320 trials * 10 sessions per participant. Thus for adults there should be 41 adults * 3200 making 1.31210^{5} and for children there should 52 children * 3200 trials making 1.66410^{5} and for
round(1- table(train$agegroup)/c(3200*41, 3200*52),2)##
## adult child
## 0.02 0.06select data for analyses
In order to make a fair comparison across conditions, we only look at trials using the two talkers who were also used in the low variability (one talker) condition.
train2 = subset(train, talker == "female1" | talker == "female2" )
train2$talker = factor(train2$talker)
train2.child = subset(train2, agegroup =="child")
train2.adult = subset(train2, agegroup =="adult")plot means (for figure 3)
adults
train2.adult.participantmeans = aggregate(accuracy~ participant + session + condition, na.rm=T, data = train2.adult, FUN=mean)
train2.adult.groupmeans <- summarySEwithin(train2.adult.participantmeans,
measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session"), idvar="participant", na.rm=FALSE, conf.interval =.95)
## to correct means for imbalance in talkers, get the mean values for participant for each talker (average mean values for each talker); error calculations as done over the whole participant set
train2.adult.participantmeans.t12 = aggregate(accuracy~ participant + session + condition + talker, na.rm=T, data = train2.adult, FUN=mean)
train2.adult.groupmeans.talker1 <- summarySEwithin(subset(train2.adult.participantmeans.t12, talker == "female1"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session"), idvar="participant", na.rm=FALSE, conf.interval=.95)
train2.adult.groupmeans.talker2 <- summarySEwithin(subset(train2.adult.participantmeans.t12, talker == "female2"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session"), idvar="participant", na.rm=FALSE, conf.interval=.95)
train2.adult.groupmeans$accuracy = (train2.adult.groupmeans.talker1$accuracy+train2.adult.groupmeans.talker2$accuracy)/2
## now plot using the standard error for the confidence intervals
epsilon = 0.02
#how big the hat (bar at the top/bottom) is
with(subset(train2.adult.groupmeans, condition == "highvar"),
plot(as.numeric(session), accuracy, type = "p", col="black",pch = 15, xlab = "Session", ylab = "Proportion correct", xlim = c(1,10), ylim = c(0.5, 1)) +
segments(as.numeric(session), (accuracy - ci) ,as.numeric(session), (accuracy + ci), col="black") +
segments(as.numeric(session)-epsilon, (accuracy - ci) ,as.numeric(session)+epsilon, (accuracy - ci), col="black") +
segments(as.numeric(session)-epsilon, (accuracy + ci) ,as.numeric(session)+epsilon, (accuracy + ci), col="black"),
) ## numeric(0)#add low variability to the same plot (using "lines" rather than plot)
with(subset(train2.adult.groupmeans, condition == "lowvar"),
lines(as.numeric(session), accuracy, type = "p", col="grey45",pch = 15, xlab = "Session", ylab = "Proportion correct", xlim = c(1,10), ylim = c(0.5, 1)) +
segments(as.numeric(session), (accuracy - ci) ,as.numeric(session), (accuracy + ci), col="grey45") +
segments(as.numeric(session)-epsilon, (accuracy - ci) ,as.numeric(session)+epsilon, (accuracy - ci), col="grey45") +
segments(as.numeric(session)-epsilon, (accuracy + ci) ,as.numeric(session)+epsilon, (accuracy + ci), col="grey45"),
) ## numeric(0)legend('topleft','groups', c("Low Variability","High Variabiltiy"), col=c("grey45","black"), pch = c(15,17)) 
children
train2.child.participantmeans = aggregate(accuracy~ participant + session + condition, na.rm=T, data = train2.child, FUN=mean)
train2.child.groupmeans <- summarySEwithin(train2.child.participantmeans,
measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session"), idvar="participant", na.rm=FALSE, conf.interval =.95)
## to correct means for imbalance in talkers, get the mean values for participant for each talker (average mean values for each talker); error calculations as done over the whole participant set
train2.child.participantmeans.t12 = aggregate(accuracy~ participant + session + condition + talker, na.rm=T, data = train2.child, FUN=mean)
train2.child.groupmeans.talker1 <- summarySEwithin(subset(train2.child.participantmeans.t12, talker == "female1"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session"), idvar="participant", na.rm=FALSE, conf.interval=.95)
train2.child.groupmeans.talker2 <- summarySEwithin(subset(train2.child.participantmeans.t12, talker == "female2"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session"), idvar="participant", na.rm=FALSE, conf.interval=.95)
train2.child.groupmeans$accuracy = (train2.child.groupmeans.talker1$accuracy+train2.child.groupmeans.talker2$accuracy)/2
## now plot using the standard error for the error bars
epsilon = 0.02
#how big the hat (bar at the top/bottom) is
with(subset(train2.child.groupmeans, condition == "highvar"),
plot(as.numeric(session), accuracy, type = "p", col="black",pch = 15, xlab = "Session", ylab = "Proportion correct", xlim = c(1,10), ylim = c(0.5, 1)) +
segments(as.numeric(session), (accuracy - ci) ,as.numeric(session), (accuracy + ci), col="black") +
segments(as.numeric(session)-epsilon, (accuracy - ci) ,as.numeric(session)+epsilon, (accuracy - ci), col="black") +
segments(as.numeric(session)-epsilon, (accuracy + ci) ,as.numeric(session)+epsilon, (accuracy + ci), col="black"),
) ## numeric(0)#add low variability to the same plot (using "lines" rather than plot)
with(subset(train2.child.groupmeans, condition == "lowvar"),
lines(as.numeric(session), accuracy, type = "p", col="grey45",pch = 15, xlab = "Session", ylab = "Proportion correct", xlim = c(1,10), ylim = c(0.5, 1)) +
segments(as.numeric(session), (accuracy - ci) ,as.numeric(session), (accuracy + ci), col="grey45") +
segments(as.numeric(session)-epsilon, (accuracy - ci) ,as.numeric(session)+epsilon, (accuracy - ci), col="grey45") +
segments(as.numeric(session)-epsilon, (accuracy + ci) ,as.numeric(session)+epsilon, (accuracy + ci), col="grey45"),
) ## numeric(0)legend('topleft','groups', c("Low Variability","High Variabiltiy"), col=c("grey45","black"), pch = c(15,17)) 
statistial analyses
Our approach was to only inspect models for effects and interactions between the experimental variables where there are clear predictions. For the training data, this is the case for both main effects of condition and session and the interaction between them. We therefore begin by inspecting these effects in the model. Wherever we do find reliable effects, we then check to see whether they are qualified by an interaction with talker. Where this is the case, we check to see if the effect holds for each of the talkers separately.
adults
train2.adult = selectCenter(train2.adult, list( "condition","session", "talker" ))
lmer.adult <- glmer(accuracy ~ 1 +
(condition.ct*session.ct*talker.ct)
+ (session.ct|participant),
data = train2.adult, control=glmerControl(optimizer = "bobyqa"),family=binomial)
lmer.adult.coeff = kable(summary(lmer.adult)$coefficients, digits = 3)
get_coeffs(lmer.adult, c("(Intercept)","condition.ct", "session.ct", "condition.ct:session.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 3.072 | 0.154 | 19.992 | 0 |
| condition.ct | 1.638 | 0.254 | 6.442 | 0 |
| session.ct | 0.354 | 0.031 | 11.311 | 0 |
| condition.ct:session.ct | 0.205 | 0.052 | 3.912 | 0 |
There are main effects of training session and condition and a reliable interaction between condition and session. This reflects improvement across sessions and overall better performance in the low variability condition which increases across sessions.
check interactions with talker
check interactions with talker for each of these effects
get_coeffs(lmer.adult, c("talker.ct", "condition.ct:talker.ct", "session.ct:talker.ct","condition.ct:session.ct:talker.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| talker.ct | 2.125 | 0.287 | 7.392 | 0.000 |
| condition.ct:talker.ct | 1.755 | 0.439 | 3.995 | 0.000 |
| session.ct:talker.ct | 0.268 | 0.062 | 4.340 | 0.000 |
| condition.ct:session.ct:talker.ct | 0.262 | 0.103 | 2.552 | 0.011 |
There is a main effect of the control variable talker (reflecting greater accuracy with one talker: female1 0.84 female2 0.94 )
There also interactions with talker for all of the reliable experimental effects. To break down the interactions, we look at each talker separately:
train2.adult.t1 = selectCenter(subset(train2.adult, talker == "female1"), list( "condition","session", "talker" ))
lmer.adult.t1 <- glmer(accuracy ~ 1 +
(condition.ct*session.ct)
+ (session.ct|participant),
data = train2.adult.t1, control=glmerControl(optimizer = "bobyqa"),family=binomial)
kable(summary(lmer.adult.t1)$coefficients, digits = 3)| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 1.941 | 0.171 | 11.374 | 0.000 |
| condition.ct | 0.721 | 0.288 | 2.508 | 0.012 |
| session.ct | 0.212 | 0.020 | 10.401 | 0.000 |
| condition.ct:session.ct | 0.069 | 0.035 | 1.973 | 0.049 |
train2.adult.t2 = selectCenter(subset(train2.adult, talker == "female2"), list( "condition","session", "talker" ))
lmer.adult.t2 <- glmer(accuracy ~ 1 +
(condition.ct*session.ct)
+ (session.ct|participant),
data = train2.adult.t2, control=glmerControl(optimizer = "bobyqa"),family=binomial)
kable(summary(lmer.adult.t2)$coefficients, digits = 3)| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 4.139 | 0.268 | 15.452 | 0.000 |
| condition.ct | 2.473 | 0.443 | 5.578 | 0.000 |
| session.ct | 0.485 | 0.064 | 7.520 | 0.000 |
| condition.ct:session.ct | 0.334 | 0.108 | 3.091 | 0.002 |
These analyses show that the reliable effects of condition and session and the interaction hold for each of the two counterbalanced talkers.
children
Note that a model with full randoms slopes didn’t converge, we therefore removed correlations between slopes (the syntax changed from |participant to ||participant ).
train2.child = selectCenter(train2.child, list( "condition","session", "talker" ))
lmer.child <- glmer(accuracy ~ 1 +
(condition.ct*session.ct*talker.ct)
+ (session.ct||participant),
data = train2.child, control=glmerControl(optimizer = "bobyqa"),family=binomial)
get_coeffs(lmer.child, c("(Intercept)","condition.ct", "session.ct", "condition.ct:session.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 1.070 | 0.140 | 7.646 | 0.000 |
| condition.ct | 0.367 | 0.223 | 1.646 | 0.100 |
| session.ct | 0.224 | 0.031 | 7.215 | 0.000 |
| condition.ct:session.ct | 0.101 | 0.053 | 1.920 | 0.055 |
There was a reliable main effect of session, reflecting improved performance across sessions, but no reliable main effect of condition. There was also a near reliable interaction between session and condition. Inspecting the figure above, this seems to reflect the fact that the difference between conditions emerges only in the second half of training.
Follow up in a model where session is replaced by a binary division into “first half” “second half”
train2.child$testhalf = 2
train2.child$testhalf[train2.child$session < 6] = 1
train2.child = selectCenter(train2.child, list( "condition","testhalf", "talker" ))
lmer.child.2 <- glmer(accuracy ~ 1 +
(condition.ct*testhalf.ct*talker.ct)
+ (testhalf.ct|participant),
data = train2.child, control=glmerControl(optimizer = "bobyqa"),family=binomial)
get_coeffs(lmer.child.2, c("(Intercept)","condition.ct", "testhalf.ct", "condition.ct:testhalf.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 1.001 | 0.120 | 8.348 | 0.000 |
| condition.ct | 0.314 | 0.170 | 1.847 | 0.065 |
| testhalf.ct | 1.062 | 0.134 | 7.948 | 0.000 |
| condition.ct:testhalf.ct | 0.474 | 0.190 | 2.494 | 0.013 |
There is a reliable interaction between condition and testhalf. We explore this by running the model again but with a separate slope for condition for each half of testing.
train2.child$testhalf = factor(train2.child$testhalf)
## run the model again but removing the main effect of condition and the condition by testhalf interaction and replacing with separate effects of condition for each test half
lmer.child.2.v2 <- glmer(accuracy ~ 1 +
+ condition.ct : testhalf
+ (condition.ct*testhalf.ct*talker.ct)
- condition.ct
- condition.ct : testhalf.ct
+ (testhalf.ct|participant),
data = train2.child, control=glmerControl(optimizer = "bobyqa"),family=binomial)
## check that this is the same model as above with the same number of dfs
anova(lmer.child.2, lmer.child.2.v2)## Data: train2.child
## Models:
## lmer.child.2: accuracy ~ 1 + (condition.ct * testhalf.ct * talker.ct) + (testhalf.ct |
## lmer.child.2: participant)
## lmer.child.2.v2: accuracy ~ 1 + +condition.ct:testhalf + (condition.ct * testhalf.ct *
## lmer.child.2.v2: talker.ct) - condition.ct - condition.ct:testhalf.ct + (testhalf.ct |
## lmer.child.2.v2: participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## lmer.child.2 11 106290 106394 -53134 106268
## lmer.child.2.v2 11 106290 106394 -53134 106268 0 0 1get_coeffs(lmer.child.2.v2, c("condition.ct:testhalf1", "condition.ct:testhalf2"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| condition.ct:testhalf1 | 0.079 | 0.092 | 0.857 | 0.391 |
| condition.ct:testhalf2 | 0.553 | 0.264 | 2.096 | 0.036 |
This shows that there is a reliable effect of condition only in the second half of training.
check interactions with talker
Look at the original model (with session as a continuous variable) to see if the reliable effect of session and the (near) realiable session by condition interaction are qualified by an effect of talker
get_coeffs(lmer.child, c("talker.ct", "session.ct:talker.ct", "condition.ct:session.ct:talker.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| talker.ct | 0.231 | 0.244 | 0.946 | 0.344 |
| session.ct:talker.ct | 0.042 | 0.062 | 0.680 | 0.496 |
| condition.ct:session.ct:talker.ct | 0.153 | 0.105 | 1.466 | 0.143 |
No reliable interactions with talker.
Now look at the model with session replaced by test-half.
get_coeffs(lmer.child.2, c("talker.ct", "testhalf.ct:talker.ct", "condition.ct:testhalf.ct:talker.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| talker.ct | 0.185 | 0.178 | 1.042 | 0.297 |
| testhalf.ct:talker.ct | 0.180 | 0.200 | 0.904 | 0.366 |
| condition.ct:testhalf.ct:talker.ct | 0.776 | 0.240 | 3.236 | 0.001 |
No reliable effect of talker and the effect of test half isn’t qualified by an interaction with talker. However the interaction between condition and testhalf is qualified by an interaction with talker. We broke this down by looking to see whether there is a reliable effect of condition in each test half for each talker.
lmer.child.2.v3 <- glmer(accuracy ~ 1 +
+ condition.ct : testhalf : talker
+ (condition.ct*testhalf.ct*talker.ct)
-condition.ct
- condition.ct : testhalf.ct
- condition.ct: talker.ct
- condition.ct : testhalf.ct : talker.ct
+ (testhalf.ct|participant),
data = train2.child, control=glmerControl(optimizer = "bobyqa"),family=binomial)
anova(lmer.child.2, lmer.child.2.v3)## Data: train2.child
## Models:
## lmer.child.2: accuracy ~ 1 + (condition.ct * testhalf.ct * talker.ct) + (testhalf.ct |
## lmer.child.2: participant)
## lmer.child.2.v3: accuracy ~ 1 + +condition.ct:testhalf:talker + (condition.ct *
## lmer.child.2.v3: testhalf.ct * talker.ct) - condition.ct - condition.ct:testhalf.ct -
## lmer.child.2.v3: condition.ct:talker.ct - condition.ct:testhalf.ct:talker.ct +
## lmer.child.2.v3: (testhalf.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## lmer.child.2 11 106290 106394 -53134 106268
## lmer.child.2.v3 11 106290 106394 -53134 106268 0 0 < 2.2e-16
##
## lmer.child.2
## lmer.child.2.v3 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1get_coeffs(lmer.child.2.v3, c("condition.ct:testhalf1:talkerfemale1", "condition.ct:testhalf2:talkerfemale1", "condition.ct:testhalf1:talkerfemale2","condition.ct:testhalf2:talkerfemale2"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| condition.ct:testhalf1:talkerfemale1 | -0.044 | 0.136 | -0.323 | 0.747 |
| condition.ct:testhalf2:talkerfemale1 | 0.066 | 0.411 | 0.160 | 0.873 |
| condition.ct:testhalf1:talkerfemale2 | 0.217 | 0.138 | 1.576 | 0.115 |
| condition.ct:testhalf2:talkerfemale2 | 1.103 | 0.400 | 2.757 | 0.006 |
We only have an effect of condition for the more intelligible talker (female 2) in the second half of training.
adult/child comparison
Since adults are at ceiling in the low-variablity condition, we look at the high variability condition only.
train2.highvar = selectCenter(subset(train2, condition == "highvar"), list("session", "talker","agegroup" ))
lmer.highvar.age <- glmer(accuracy ~ 1 +
+ session.ct*talker.ct*agegroup.ct
+ (session.ct|participant),
data = train2.highvar, control=glmerControl(optimizer = "bobyqa"),family=binomial)
get_coeffs(lmer.highvar.age, c("agegroup.ct", "session.ct:agegroup.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| agegroup.ct | -0.989 | 0.220 | -4.503 | 0.000 |
| session.ct:agegroup.ct | -0.057 | 0.048 | -1.183 | 0.237 |
There is a main effect of age group but no interaction between age group and session.
check interactions with talker
get_coeffs(lmer.highvar.age, c("talker.ct", "talker.ct:agegroup.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| talker.ct | 0.149 | 0.219 | 0.684 | 0.494 |
| talker.ct:agegroup.ct | -1.056 | 0.437 | -2.417 | 0.016 |
The main effect of age group is qualified by an interaction with talker, so we look to see if the benefit for adults over children holds for both talkers:
lmer.highvar.age.v2 <- glmer(accuracy ~ 1 +
+ agegroup.ct : talker
+ session.ct*talker.ct*agegroup.ct
-agegroup.ct
-talker.ct : agegroup.ct
+ (session.ct|participant),
data = train2.highvar, control=glmerControl(optimizer = "bobyqa"),family=binomial)
anova(lmer.highvar.age.v2,lmer.highvar.age)## Data: train2.highvar
## Models:
## lmer.highvar.age.v2: accuracy ~ 1 + +agegroup.ct:talker + session.ct * talker.ct *
## lmer.highvar.age.v2: agegroup.ct - agegroup.ct - talker.ct:agegroup.ct + (session.ct |
## lmer.highvar.age.v2: participant)
## lmer.highvar.age: accuracy ~ 1 + +session.ct * talker.ct * agegroup.ct + (session.ct |
## lmer.highvar.age: participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## lmer.highvar.age.v2 11 39915 40009 -19947 39893
## lmer.highvar.age 11 39915 40009 -19947 39893 0 0 < 2.2e-16
##
## lmer.highvar.age.v2
## lmer.highvar.age ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1get_coeffs(lmer.highvar.age.v2, c("agegroup.ct:talkerfemale1", "agegroup.ct:talkerfemale2"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| agegroup.ct:talkerfemale1 | -0.453 | 0.311 | -1.457 | 0.145 |
| agegroup.ct:talkerfemale2 | -1.510 | 0.314 | -4.809 | 0.000 |
This suggests that the benefit for adults over children is only reliable for the more intelligible talker.
This suggests that the benefit for adults over children is only reliable for the more intelligible talker.
English introduction
data preparation
select data for analyses
engintro.child = subset(engintro, agegroup =="child")
engintro.adult = subset(engintro, agegroup =="adult")get means for table 4
adults
engintro.adult.participantmeans = aggregate(accuracy~ participant + session + condition, na.rm=T, data = engintro.adult, FUN=mean)
engintro.adult.groupmeans <- summarySEwithin(engintro.adult.participantmeans,
measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session"), idvar="participant", na.rm=FALSE, conf.interval =.95)
## to correct means for the imbalance in talkers (rather than the overall mean per participant, get the mean values for each participant for each talker and average those; error calculations remain as done over the whole participant set
engintro.adult.participantmeans.t12 = aggregate(accuracy~ participant + session + condition + talker, na.rm=T, data = engintro.adult, FUN=mean)
engintro.adult.groupmeans.talker1 <- summarySEwithin(subset(engintro.adult.participantmeans.t12, talker == "female1"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session"), idvar="participant", na.rm=FALSE, conf.interval=.95)
engintro.adult.groupmeans.talker2 <- summarySEwithin(subset(engintro.adult.participantmeans.t12, talker == "female2"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session"), idvar="participant", na.rm=FALSE, conf.interval=.95)
engintro.adult.groupmeans$accuracy = (engintro.adult.groupmeans.talker1$accuracy+engintro.adult.groupmeans.talker2$accuracy)/2
kable(engintro.adult.groupmeans, digits = 2)| condition | session | N | accuracy | accuracy_norm | sd | se | ci |
|---|---|---|---|---|---|---|---|
| highvar | post | 22 | 0.98 | 0.99 | 0.10 | 0.02 | 0.04 |
| highvar | pre | 22 | 0.81 | 0.82 | 0.10 | 0.02 | 0.04 |
| lowvar | post | 18 | 1.00 | 0.99 | 0.08 | 0.02 | 0.04 |
| lowvar | pre | 18 | 0.82 | 0.81 | 0.08 | 0.02 | 0.04 |
children
engintro.child.participantmeans = aggregate(accuracy~ participant + session + condition, na.rm=T, data = engintro.child, FUN=mean)
engintro.child.groupmeans <- summarySEwithin(engintro.child.participantmeans,
measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session"), idvar="participant", na.rm=FALSE, conf.interval =.95)
## to correct means for the imbalance in talkers (rather than the overall mean per participant, get the mean values for each participant for each talker and average those; error calculations remain as done over the whole participant set
engintro.child.participantmeans.t12 = aggregate(accuracy~ participant + session + condition + talker, na.rm=T, data = engintro.child, FUN=mean)
engintro.child.groupmeans.talker1 <- summarySEwithin(subset(engintro.child.participantmeans.t12, talker == "female1"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session"), idvar="participant", na.rm=FALSE, conf.interval=.95)
engintro.child.groupmeans.talker2 <- summarySEwithin(subset(engintro.child.participantmeans.t12, talker == "female2"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session"), idvar="participant", na.rm=FALSE, conf.interval=.95)
engintro.child.groupmeans$accuracy = (engintro.child.groupmeans.talker1$accuracy+engintro.child.groupmeans.talker2$accuracy)/2
kable(engintro.child.groupmeans, digits = 2)| condition | session | N | accuracy | accuracy_norm | sd | se | ci |
|---|---|---|---|---|---|---|---|
| highvar | post | 28 | 0.88 | 0.88 | 0.15 | 0.03 | 0.06 |
| highvar | pre | 28 | 0.50 | 0.50 | 0.15 | 0.03 | 0.06 |
| lowvar | post | 24 | 0.92 | 0.92 | 0.09 | 0.02 | 0.04 |
| lowvar | pre | 24 | 0.47 | 0.47 | 0.09 | 0.02 | 0.04 |
statistical analyses
Note we dont do statistical analyses on adult data as they are close to ceiling, even at pre-test.
children
engintro.child = selectCenter(engintro.child, list("session", "condition", "talker"))
lme.engintrochild <- glmer(accuracy ~ 1 + session.ct*condition.ct* talker.ct
+ (session.ct|participant), control=glmerControl(optimizer = "bobyqa"), data = engintro.child,family=binomial)
get_coeffs(lme.engintrochild , c("session.ct","condition.ct","session.ct:condition.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| session.ct | -3.191 | 0.261 | -12.236 | 0.000 |
| condition.ct | 0.331 | 0.285 | 1.163 | 0.245 |
| session.ct:condition.ct | -0.946 | 0.504 | -1.878 | 0.060 |
There was a reliable main effect of session, but not of condition. There was a marginal interaction between session and condition.
check interactions with talker
get_coeffs(lme.engintrochild , c("talker.ct","session.ct:talker.ct","session.ct:condition.ct:talker.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| talker.ct | -0.098 | 0.281 | -0.348 | 0.728 |
| session.ct:talker.ct | 0.138 | 0.496 | 0.279 | 0.780 |
| session.ct:condition.ct:talker.ct | -0.555 | 0.999 | -0.556 | 0.578 |
There was no main effect of talker and neither the main effect of condition nor the interaction between condition and session is qualified by an interaction with talker was realible.
Lexical Decision
data preparation
select data for analyses
remove practice and nonword trials (which aren’t used in any analyses) and then subset into the adult and child data sets for greek and english primes
lexd = subset(lexd, trialnumber != "practice" & trialtype != "NONWORD")
lexd.adult.english = subset(lexd, agegroup =="adult" & primelang == "english")
lexd.adult.greek = subset(lexd, agegroup =="adult" & primelang == "greek")
lexd.child.english = subset(lexd, agegroup =="child" & primelang == "english")
lexd.child.greek = subset(lexd, agegroup =="child" & primelang == "greek")filtering for RT analyses
For each of these data sets, remove the trials that were not answered correctly, and filter the RT data using the filter2 function. This function removes trials where the RT is > or < 2.5 SD from the mean value for that participant in that session. Finally, remove any remaining RTs that are < 200 ms.
flist = c("participant", "session") # list of parameters for calculating means
lim = 2.5 ## number of standard devisations
lexd.adult.greek.RT = subset(lexd.adult.greek, accuracy ==1)
lexd.adult.greek.RT= filter2(lexd.adult.greek.RT, flist, "RT",lim)
lexd.adult.greek.RT$RTfilt[lexd.adult.greek$RTfilt < 200] <- NA
lexd.child.greek.RT = subset(lexd.child.greek, accuracy ==1)
lexd.child.greek.RT= filter2(lexd.child.greek.RT, flist, "RT",lim)
lexd.child.greek.RT$RTfilt[lexd.child.greek$RTfilt < 200] <- NA
lexd.adult.english.RT = subset(lexd.adult.english, accuracy ==1)
lexd.adult.english.RT= filter2(lexd.adult.english.RT, flist, "RT",lim)
lexd.adult.english.RT$RTfilt[lexd.adult.english$RTfilt < 200] <- NA
lexd.child.english.RT = subset(lexd.child.english, accuracy ==1)
lexd.child.english.RT= filter2(lexd.child.english.RT, flist, "RT",lim)
lexd.child.english.RT$RTfilt[lexd.child.english$RTfilt < 200] <- NACalculate % trials removed because targets were incorrectly identified as non words:
#adult, greek-primes percent incorrect:
round(100*(1-dim(lexd.adult.greek.RT)[1]/dim(lexd.adult.greek)[1]))## [1] 5#child, greek-primes percent incorrect:
round(100*(1-dim(lexd.child.greek.RT)[1]/dim(lexd.child.greek)[1]))## [1] 10#adult, english-primes percent incorrect:
round(100*(1-dim(lexd.adult.english.RT)[1]/dim(lexd.adult.english)[1]))## [1] 6#child, english-primes percent incorrect:
round(100*(1-dim(lexd.child.english.RT)[1]/dim(lexd.child.english)[1]))## [1] 16% further trials removed due to filtering:
#adult, greek-primes
round((sum(is.na(lexd.adult.greek.RT$RTfilt))/sum(!is.na(lexd.adult.greek.RT$RT)))*100)## [1] 3#child, greek-primes
round((sum(is.na(lexd.child.greek.RT$RTfilt))/sum(!is.na(lexd.child.greek.RT$RT)))*100)## [1] 3#adult, english-primes
round((sum(is.na(lexd.adult.english.RT$RTfilt))/sum(!is.na(lexd.adult.english.RT$RT)))*100)## [1] 4#child, english-primes
round((sum(is.na(lexd.child.english.RT$RTfilt))/sum(!is.na(lexd.child.english.RT$RT)))*100)## [1] 4get means and plots
greek primes
adults accuracy
lexd.adult.greek.participantmeans = aggregate(accuracy~ participant + session + primetarget_relationship , na.rm=T, data = lexd.adult.greek, FUN=mean)
lexd.adult.greek.groupmeans <- summarySEwithin(lexd.adult.greek.participantmeans,
measurevar="accuracy", betweenvars=NULL, withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval =.95)
kable(lexd.adult.greek.groupmeans, digits =3)| session | primetarget_relationship | N | accuracy | accuracy_norm | sd | se | ci |
|---|---|---|---|---|---|---|---|
| post | related | 41 | 0.973 | 0.973 | 0.032 | 0.005 | 0.010 |
| post | unrelated | 41 | 0.923 | 0.923 | 0.048 | 0.007 | 0.015 |
| pre | related | 41 | 0.974 | 0.974 | 0.046 | 0.007 | 0.014 |
| pre | unrelated | 41 | 0.928 | 0.928 | 0.047 | 0.007 | 0.015 |
adults RT
lexd.adult.greek.RT.participantmeans = aggregate(RTfilt~ participant + session + primetarget_relationship , na.rm=T, data = lexd.adult.greek.RT, FUN=mean)
lexd.adult.greek.RT.groupmeans <- summarySEwithin(lexd.adult.greek.RT.participantmeans,
measurevar="RTfilt", betweenvars=NULL, withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval =.95)
kable(lexd.adult.greek.RT.groupmeans, digits =3)| session | primetarget_relationship | N | RTfilt | RTfilt_norm | sd | se | ci |
|---|---|---|---|---|---|---|---|
| post | related | 41 | 1007.995 | 1007.995 | 184.290 | 28.781 | 58.169 |
| post | unrelated | 41 | 1087.945 | 1087.945 | 144.334 | 22.541 | 45.557 |
| pre | related | 41 | 1031.923 | 1031.923 | 143.959 | 22.483 | 45.439 |
| pre | unrelated | 41 | 1142.395 | 1142.395 | 157.665 | 24.623 | 49.765 |
children accuracy
lexd.child.greek.participantmeans = aggregate(accuracy~ participant + session + primetarget_relationship , na.rm=T, data = lexd.child.greek, FUN=mean)
lexd.child.greek.groupmeans <- summarySEwithin(lexd.child.greek.participantmeans,
measurevar="accuracy", betweenvars=NULL, withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval =.95)
kable(lexd.child.greek.groupmeans, digits =3)| session | primetarget_relationship | N | accuracy | accuracy_norm | sd | se | ci |
|---|---|---|---|---|---|---|---|
| post | related | 52 | 0.907 | 0.907 | 0.095 | 0.013 | 0.026 |
| post | unrelated | 52 | 0.851 | 0.851 | 0.099 | 0.014 | 0.028 |
| pre | related | 52 | 0.946 | 0.946 | 0.094 | 0.013 | 0.026 |
| pre | unrelated | 52 | 0.881 | 0.881 | 0.118 | 0.016 | 0.033 |
children RT
lexd.child.greek.RT.participantmeans = aggregate(RTfilt~ participant + session + primetarget_relationship , na.rm=T, data = lexd.child.greek.RT, FUN=mean)
lexd.child.greek.RT.groupmeans <- summarySEwithin(lexd.child.greek.RT.participantmeans,
measurevar="RTfilt", betweenvars=NULL, withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval =.95)
kable(lexd.child.greek.RT.groupmeans, digits =3)| session | primetarget_relationship | N | RTfilt | RTfilt_norm | sd | se | ci |
|---|---|---|---|---|---|---|---|
| post | related | 52 | 1389.938 | 1389.938 | 356.514 | 49.440 | 99.254 |
| post | unrelated | 52 | 1461.169 | 1461.169 | 330.132 | 45.781 | 91.909 |
| pre | related | 52 | 1552.385 | 1552.385 | 393.381 | 54.552 | 109.518 |
| pre | unrelated | 52 | 1612.984 | 1612.984 | 269.153 | 37.325 | 74.933 |
english primes
adults accuracy
lexd.adult.english.participantmeans = aggregate(accuracy~ participant + session + primetarget_relationship + condition , na.rm=T, data = lexd.adult.english, FUN=mean)
lexd.adult.english.groupmeans <- summarySEwithin(lexd.adult.english.participantmeans,
measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval =.95)
## to correct means for imbalance in talkers, get the mean values for participant for each talker (average mean values for each talker); error calculations as done over the whole participant set
lexd.adult.english.participantmeans.t12 = aggregate(accuracy~ participant + session + condition + talker + primetarget_relationship, na.rm=T, data = lexd.adult.english, FUN=mean)
lexd.adult.english.groupmeans.talker1 <- summarySEwithin(subset(lexd.adult.english.participantmeans.t12, talker == "female1"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval=.95)
lexd.adult.english.groupmeans.talker2 <- summarySEwithin(subset(lexd.adult.english.participantmeans.t12, talker == "female2"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval=.95)
lexd.adult.english.groupmeans$accuracy = (lexd.adult.english.groupmeans.talker1$accuracy + lexd.adult.english.groupmeans.talker2$accuracy)/2
kable(lexd.adult.english.groupmeans, digits =3)| condition | session | primetarget_relationship | N | accuracy | accuracy_norm | sd | se | ci |
|---|---|---|---|---|---|---|---|---|
| highvar | post | related | 22 | 0.982 | 0.976 | 0.036 | 0.008 | 0.016 |
| highvar | post | unrelated | 22 | 0.923 | 0.917 | 0.051 | 0.011 | 0.023 |
| highvar | pre | related | 22 | 0.980 | 0.974 | 0.033 | 0.007 | 0.015 |
| highvar | pre | unrelated | 22 | 0.902 | 0.897 | 0.058 | 0.012 | 0.026 |
| lowvar | post | related | 19 | 0.972 | 0.977 | 0.036 | 0.008 | 0.017 |
| lowvar | post | unrelated | 19 | 0.894 | 0.898 | 0.067 | 0.015 | 0.032 |
| lowvar | pre | related | 19 | 0.958 | 0.967 | 0.037 | 0.009 | 0.018 |
| lowvar | pre | unrelated | 19 | 0.914 | 0.922 | 0.045 | 0.010 | 0.021 |
adults RT
lexd.adult.english.RT.participantmeans = aggregate(RTfilt~ participant + session + primetarget_relationship + condition , na.rm=T, data = lexd.adult.english.RT, FUN=mean)
lexd.adult.english.RT.groupmeans <- summarySEwithin(lexd.adult.english.RT.participantmeans,
measurevar="RTfilt", betweenvars=c("condition"), withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval =.95)
## to correct means for imbalance in talkers, get the mean values for each participant for each talker (average mean values for each talker); error calculations as done over the whole participant set
lexd.adult.english.RT.participantmeans.t12 = aggregate(RTfilt~ participant + session + condition + talker + primetarget_relationship, na.rm=T, data = lexd.adult.english.RT, FUN=mean)
lexd.adult.english.RT.groupmeans.talker1 <- summarySEwithin(subset(lexd.adult.english.RT.participantmeans.t12, talker == "female1"), measurevar="RTfilt", betweenvars=c("condition"), withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval=.95)
lexd.adult.english.RT.groupmeans.talker2 <- summarySEwithin(subset(lexd.adult.english.RT.participantmeans.t12, talker == "female2"), measurevar="RTfilt", betweenvars=c("condition"), withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval=.95)
lexd.adult.english.RT.groupmeans$RTfilt = (lexd.adult.english.RT.groupmeans.talker1$RTfilt + lexd.adult.english.RT.groupmeans.talker2$RTfilt)/2
kable(lexd.adult.english.RT.groupmeans, digits =3)| condition | session | primetarget_relationship | N | RTfilt | RTfilt_norm | sd | se | ci |
|---|---|---|---|---|---|---|---|---|
| highvar | post | related | 22 | 1151.098 | 1138.351 | 199.289 | 42.489 | 88.360 |
| highvar | post | unrelated | 22 | 1234.067 | 1221.320 | 220.874 | 47.091 | 97.930 |
| highvar | pre | related | 22 | 1225.341 | 1212.594 | 289.115 | 61.640 | 128.186 |
| highvar | pre | unrelated | 22 | 1226.076 | 1213.328 | 199.420 | 42.516 | 88.418 |
| lowvar | post | related | 19 | 1097.814 | 1116.801 | 93.480 | 21.446 | 45.056 |
| lowvar | post | unrelated | 19 | 1208.202 | 1231.300 | 239.688 | 54.988 | 115.526 |
| lowvar | pre | related | 19 | 1138.798 | 1151.622 | 129.654 | 29.745 | 62.491 |
| lowvar | pre | unrelated | 19 | 1273.559 | 1285.869 | 166.363 | 38.166 | 80.184 |
plot for figure 4
Note that we have collapsed across condition here.
# first get the means (collapsed across conditions) to plot
lexd.adult.english.RT.participantmeans = aggregate(RTfilt~ participant + session + primetarget_relationship , na.rm=T, data = lexd.adult.english.RT, FUN=mean)
lexd.adult.english.RT.groupmeans <- summarySEwithin(lexd.adult.english.RT.participantmeans,
measurevar="RTfilt", betweenvars=NULL, withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval =.95)
# to correct means for imbalance in talkers, get the mean values for each participant for each talker (average mean values for each talker); error calculations as done over the whole participant set
lexd.adult.english.RT.participantmeans.t12 = aggregate(RTfilt~ participant + session + talker + primetarget_relationship, na.rm=T, data = lexd.adult.english.RT, FUN=mean)
lexd.adult.english.RT.groupmeans.talker1 <- summarySEwithin(subset(lexd.adult.english.RT.participantmeans.t12, talker == "female1"), measurevar="RTfilt", betweenvars=NULL, withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval=.95)
lexd.adult.english.RT.groupmeans.talker2 <- summarySEwithin(subset(lexd.adult.english.RT.participantmeans.t12, talker == "female2"), measurevar="RTfilt", betweenvars=NULL, withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval=.95)
lexd.adult.english.RT.groupmeans$RTfilt = (lexd.adult.english.RT.groupmeans.talker1$RTfilt + lexd.adult.english.RT.groupmeans.talker2$RTfilt)/2
# now plot
lexd.adult.english.RT.groupmeans$session = relevel(lexd.adult.english.RT.groupmeans$session, "pre")
p = ggplot(lexd.adult.english.RT.groupmeans, aes(x = session, y = RTfilt, fill =primetarget_relationship ))
p = p + geom_bar(stat="identity", position="dodge", colour="black", size=.3)
p = p + geom_errorbar(aes(ymin=RTfilt-ci, ymax=RTfilt+ci), width=.4, position=position_dodge(.9))
p = p + xlab("") + ylab("RT(ms)")
p = p + scale_x_discrete(labels=c("pre" = "Pre test", "post" = "Post test"), expand=c(0, 0.6))
p = p + scale_fill_manual(values=c("grey", "white"), name="Prime target relationship", labels=c("related", "unrelated"))
#p = p + scale_y_continuous(limits=c(0,1.1), expand = c(0, 0))
p = p + coord_cartesian(ylim = c(1000, 1900))
p
kids accuracy
lexd.child.english.participantmeans = aggregate(accuracy~ participant + session + primetarget_relationship + condition , na.rm=T, data = lexd.child.english, FUN=mean)
lexd.child.english.groupmeans <- summarySEwithin(lexd.child.english.participantmeans,
measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval =.95)
## to correct means for imbalance in talkers, get the mean values for each participant for each talker (average mean values for each talker); error calculations as done over the whole participant set
lexd.child.english.participantmeans.t12 = aggregate(accuracy~ participant + session + condition + talker + primetarget_relationship, na.rm=T, data = lexd.child.english, FUN=mean)
lexd.child.english.groupmeans.talker1 <- summarySEwithin(subset(lexd.child.english.participantmeans.t12, talker == "female1"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval=.95)
lexd.child.english.groupmeans.talker2 <- summarySEwithin(subset(lexd.child.english.participantmeans.t12, talker == "female2"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval=.95)
lexd.child.english.groupmeans$accuracy = (lexd.child.english.groupmeans.talker1$accuracy + lexd.child.english.groupmeans.talker2$accuracy)/2
kable(lexd.child.english.groupmeans, digits =3)| condition | session | primetarget_relationship | N | accuracy | accuracy_norm | sd | se | ci |
|---|---|---|---|---|---|---|---|---|
| highvar | post | related | 28 | 0.891 | 0.876 | 0.103 | 0.019 | 0.040 |
| highvar | post | unrelated | 28 | 0.834 | 0.819 | 0.114 | 0.021 | 0.044 |
| highvar | pre | related | 28 | 0.884 | 0.869 | 0.086 | 0.016 | 0.033 |
| highvar | pre | unrelated | 28 | 0.820 | 0.805 | 0.129 | 0.024 | 0.050 |
| lowvar | post | related | 24 | 0.867 | 0.889 | 0.113 | 0.023 | 0.048 |
| lowvar | post | unrelated | 24 | 0.815 | 0.836 | 0.094 | 0.019 | 0.040 |
| lowvar | pre | related | 24 | 0.838 | 0.858 | 0.084 | 0.017 | 0.035 |
| lowvar | pre | unrelated | 24 | 0.770 | 0.787 | 0.132 | 0.027 | 0.056 |
kids RT
lexd.child.english.RT.participantmeans = aggregate(RTfilt~ participant + session + primetarget_relationship + condition , na.rm=T, data = lexd.child.english.RT, FUN=mean)
lexd.child.english.RT.groupmeans <- summarySEwithin(lexd.child.english.RT.participantmeans,
measurevar="RTfilt", betweenvars=c("condition"), withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval =.95)
## to correct means for imbalance in talkers, get the mean values for each participant for each talker (average mean values for each talker); error calculations as done over the whole participant set
lexd.child.english.RT.participantmeans.t12 = aggregate(RTfilt~ participant + session + condition + talker + primetarget_relationship, na.rm=T, data = lexd.child.english.RT, FUN=mean)
lexd.child.english.RT.groupmeans.talker1 <- summarySEwithin(subset(lexd.child.english.RT.participantmeans.t12, talker == "female1"), measurevar="RTfilt", betweenvars=c("condition"), withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval=.95)
lexd.child.english.RT.groupmeans.talker2 <- summarySEwithin(subset(lexd.child.english.RT.participantmeans.t12, talker == "female2"), measurevar="RTfilt", betweenvars=c("condition"), withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval=.95)
lexd.child.english.RT.groupmeans$RTfilt = (lexd.child.english.RT.groupmeans.talker1$RTfilt + lexd.child.english.RT.groupmeans.talker2$RTfilt)/2
kable(lexd.child.english.RT.groupmeans, digits =3)| condition | session | primetarget_relationship | N | RTfilt | RTfilt_norm | sd | se | ci |
|---|---|---|---|---|---|---|---|---|
| highvar | post | related | 28 | 1486.777 | 1536.915 | 378.880 | 71.602 | 146.914 |
| highvar | post | unrelated | 28 | 1574.379 | 1624.517 | 274.708 | 51.915 | 106.521 |
| highvar | pre | related | 28 | 1669.582 | 1719.720 | 351.204 | 66.371 | 136.183 |
| highvar | pre | unrelated | 28 | 1665.049 | 1715.187 | 290.669 | 54.931 | 112.710 |
| lowvar | post | related | 24 | 1494.584 | 1439.786 | 331.837 | 67.736 | 140.122 |
| lowvar | post | unrelated | 24 | 1622.993 | 1562.857 | 468.758 | 95.685 | 197.939 |
| lowvar | pre | related | 24 | 1811.015 | 1765.427 | 444.960 | 90.827 | 187.890 |
| lowvar | pre | unrelated | 24 | 1869.315 | 1828.268 | 409.474 | 83.584 | 172.906 |
plot for figure 4
Note that we have collapsed across condition here.
# first get the means (collapsed across conditions) to plot
lexd.child.english.RT.participantmeans = aggregate(RTfilt~ participant + session + primetarget_relationship , na.rm=T, data = lexd.child.english.RT, FUN=mean)
lexd.child.english.RT.groupmeans <- summarySEwithin(lexd.child.english.RT.participantmeans,
measurevar="RTfilt", betweenvars=NULL, withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval =.95)
## to correct means for imbalance in talkers, get the mean values for each participant for each talker (average mean values for each talker); error calculations as done over the whole participant set
lexd.child.english.RT.participantmeans.t12 = aggregate(RTfilt~ participant + session + talker + primetarget_relationship, na.rm=T, data = lexd.child.english.RT, FUN=mean)
lexd.child.english.RT.groupmeans.talker1 <- summarySEwithin(subset(lexd.child.english.RT.participantmeans.t12, talker == "female1"), measurevar="RTfilt", betweenvars=NULL, withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval=.95)
lexd.child.english.RT.groupmeans.talker2 <- summarySEwithin(subset(lexd.child.english.RT.participantmeans.t12, talker == "female2"), measurevar="RTfilt", betweenvars=NULL, withinvars= c("session","primetarget_relationship"), idvar="participant", na.rm=FALSE, conf.interval=.95)
lexd.child.english.RT.groupmeans$RTfilt = (lexd.child.english.RT.groupmeans.talker1$RTfilt + lexd.child.english.RT.groupmeans.talker2$RTfilt)/2
# now plot
lexd.child.english.RT.groupmeans$session = relevel(lexd.child.english.RT.groupmeans$session, "pre")
p = ggplot(lexd.child.english.RT.groupmeans, aes(x = session, y = RTfilt, fill =primetarget_relationship ))
p = p + geom_bar(stat="identity", position="dodge", colour="black", size=.3)
p = p + geom_errorbar(aes(ymin=RTfilt-ci, ymax=RTfilt+ci), width=.4, position=position_dodge(.9))
p = p + xlab("") + ylab("RT(ms)")
p = p + scale_x_discrete(labels=c("pre" = "Pre test", "post" = "Post test"), expand=c(0, 0.6))
p = p + scale_fill_manual(values=c("grey", "white"), name="Prime target relationship", labels=c("related", "unrelated"))
#p = p + scale_y_continuous(limits=c(0,1.1), expand = c(0, 0))
p = p + coord_cartesian(ylim = c(1000, 1900))
p
statistical analyses
adults greek, RT
lexd.adult.greek.RT$primetarget_relationship = factor(lexd.adult.greek.RT$primetarget_relationship)
lexd.adult.greek.RT = selectCenter(lexd.adult.greek.RT, list("session", "primetarget_relationship"))
lme.greek.adult<- lmer(RTfilt ~ session.ct* primetarget_relationship.ct+
(session.ct* primetarget_relationship.ct|participant), data = lexd.adult.greek.RT, control=lmerControl(optimizer = "bobyqa") )
kable(summary(lme.greek.adult)$coefficients, digits=3)| Estimate | Std. Error | t value | |
|---|---|---|---|
| (Intercept) | 1066.967 | 24.233 | 44.030 |
| session.ct | 37.884 | 39.941 | 0.948 |
| primetarget_relationship.ct | 101.272 | 13.679 | 7.403 |
| session.ct:primetarget_relationship.ct | 17.752 | 26.491 | 0.670 |
use model comparison to get p values
lmedrop(lme.greek.adult,"session.ct")## Data: lexd.adult.greek.RT
## Models:
## model.dropped: RTfilt ~ primetarget_relationship.ct + (session.ct * primetarget_relationship.ct |
## model.dropped: participant) + session.ct:primetarget_relationship.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct + (session.ct *
## model: primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 14 44067 44151 -22020 44039
## model 15 44068 44158 -22019 44038 0.9123 1 0.3395lmedrop(lme.greek.adult,"primetarget_relationship.ct")## Data: lexd.adult.greek.RT
## Models:
## model.dropped: RTfilt ~ session.ct + (session.ct * primetarget_relationship.ct |
## model.dropped: participant) + session.ct:primetarget_relationship.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct + (session.ct *
## model: primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 14 44100 44184 -22036 44072
## model 15 44068 44158 -22019 44038 34.009 1 5.486e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1lmedrop(lme.greek.adult,"session.ct:primetarget_relationship.ct")## Data: lexd.adult.greek.RT
## Models:
## model.dropped: RTfilt ~ session.ct + primetarget_relationship.ct + (session.ct *
## model.dropped: primetarget_relationship.ct | participant)
## model: RTfilt ~ session.ct * primetarget_relationship.ct + (session.ct *
## model: primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 14 44067 44151 -22019 44039
## model 15 44068 44158 -22019 44038 0.4494 1 0.5026An effect of prime-target relationship (related = 1014 unrelated = 1114 but no effect of test session and no interaction.
adult english, RT
begin by looking at experimental effects with predictions:
lexd.adult.english.RT$primetarget_relationship=factor(lexd.adult.english.RT$primetarget_relationship)
lexd.adult.english.RT$talker=factor(lexd.adult.english.RT$talker)
lexd.adult.english.RT = selectCenter(lexd.adult.english.RT, list("session", "primetarget_relationship","talker","condition"))
lme.english.adult<- lmer(RTfilt ~ session.ct* primetarget_relationship.ct*condition.ct*talker.ct+
(session.ct* primetarget_relationship.ct|participant), data = lexd.adult.english.RT, control=lmerControl(optimizer = "bobyqa") )
get_coeffs(lme.english.adult, c("(Intercept)", "session.ct", "primetarget_relationship.ct","session.ct:primetarget_relationship.ct","session.ct:primetarget_relationship.ct:condition.ct"))| Estimate | Std. Error | t value | |
|---|---|---|---|
| (Intercept) | 1195.189 | 30.623 | 39.029 |
| session.ct | 42.124 | 51.205 | 0.823 |
| primetarget_relationship.ct | 83.597 | 20.706 | 4.037 |
| session.ct:primetarget_relationship.ct | -37.417 | 43.590 | -0.858 |
| session.ct:primetarget_relationship.ct:condition.ct | 95.931 | 87.482 | 1.097 |
use model comparison to get p values
lmedrop(lme.english.adult,"session.ct")## Data: lexd.adult.english.RT
## Models:
## model.dropped: RTfilt ~ primetarget_relationship.ct + condition.ct + talker.ct +
## model.dropped: (session.ct * primetarget_relationship.ct | participant) +
## model.dropped: session.ct:primetarget_relationship.ct + session.ct:condition.ct +
## model.dropped: primetarget_relationship.ct:condition.ct + session.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:talker.ct + condition.ct:talker.ct +
## model.dropped: session.ct:primetarget_relationship.ct:condition.ct + session.ct:primetarget_relationship.ct:talker.ct +
## model.dropped: session.ct:condition.ct:talker.ct + primetarget_relationship.ct:condition.ct:talker.ct +
## model.dropped: session.ct:primetarget_relationship.ct:condition.ct:talker.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct * condition.ct *
## model: talker.ct + (session.ct * primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 26 45205 45361 -22577 45153
## model 27 45206 45368 -22576 45152 0.7447 1 0.3882lmedrop(lme.english.adult,"primetarget_relationship.ct")## Data: lexd.adult.english.RT
## Models:
## model.dropped: RTfilt ~ session.ct + condition.ct + talker.ct + (session.ct *
## model.dropped: primetarget_relationship.ct | participant) + session.ct:primetarget_relationship.ct +
## model.dropped: session.ct:condition.ct + primetarget_relationship.ct:condition.ct +
## model.dropped: session.ct:talker.ct + primetarget_relationship.ct:talker.ct +
## model.dropped: condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct +
## model.dropped: session.ct:primetarget_relationship.ct:talker.ct + session.ct:condition.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct:talker.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct * condition.ct *
## model: talker.ct + (session.ct * primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 26 45219 45375 -22584 45167
## model 27 45206 45368 -22576 45152 14.979 1 0.0001087 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1lmedrop(lme.english.adult,"session.ct:primetarget_relationship.ct")## Data: lexd.adult.english.RT
## Models:
## model.dropped: RTfilt ~ session.ct + primetarget_relationship.ct + condition.ct +
## model.dropped: talker.ct + (session.ct * primetarget_relationship.ct | participant) +
## model.dropped: session.ct:condition.ct + primetarget_relationship.ct:condition.ct +
## model.dropped: session.ct:talker.ct + primetarget_relationship.ct:talker.ct +
## model.dropped: condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct +
## model.dropped: session.ct:primetarget_relationship.ct:talker.ct + session.ct:condition.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct:talker.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct * condition.ct *
## model: talker.ct + (session.ct * primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 26 45205 45361 -22577 45153
## model 27 45206 45368 -22576 45152 0.7897 1 0.3742lmedrop(lme.english.adult, "condition.ct:session.ct:primetarget_relationship.ct")## Data: lexd.adult.english.RT
## Models:
## model.dropped: RTfilt ~ session.ct + primetarget_relationship.ct + condition.ct +
## model.dropped: talker.ct + (session.ct * primetarget_relationship.ct | participant) +
## model.dropped: session.ct:primetarget_relationship.ct + session.ct:condition.ct +
## model.dropped: primetarget_relationship.ct:condition.ct + session.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:talker.ct + condition.ct:talker.ct +
## model.dropped: session.ct:primetarget_relationship.ct:talker.ct + session.ct:condition.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct:talker.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct * condition.ct *
## model: talker.ct + (session.ct * primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 26 45206 45362 -22577 45154
## model 27 45206 45368 -22576 45152 1.2932 1 0.2555An effect of prime-target relationship (related = 1153 unrelated = 1238) but no effect of test session, no interaction between prime target relationship and test session, and no three way interaction between condition, prime-target relationship and test sesssion.
This indicates semantic priming across the langauges, but no indication that it is influenced by training.
check interactions with talker
Check whether effect of primetarget relationship is qualified by interaction with talker
get_coeffs(lme.english.adult, c("talker", "primetarget_relationship.ct:talker"))| Estimate | Std. Error | t value | |
|---|---|---|---|
| talker.ct | -47.731 | 60.929 | -0.783 |
| primetarget_relationship.ct:talker.ct | -71.708 | 41.463 | -1.729 |
lmedrop(lme.english.adult,"talker.ct")## Data: lexd.adult.english.RT
## Models:
## model.dropped: RTfilt ~ session.ct + primetarget_relationship.ct + condition.ct +
## model.dropped: (session.ct * primetarget_relationship.ct | participant) +
## model.dropped: session.ct:primetarget_relationship.ct + session.ct:condition.ct +
## model.dropped: primetarget_relationship.ct:condition.ct + session.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:talker.ct + condition.ct:talker.ct +
## model.dropped: session.ct:primetarget_relationship.ct:condition.ct + session.ct:primetarget_relationship.ct:talker.ct +
## model.dropped: session.ct:condition.ct:talker.ct + primetarget_relationship.ct:condition.ct:talker.ct +
## model.dropped: session.ct:primetarget_relationship.ct:condition.ct:talker.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct * condition.ct *
## model: talker.ct + (session.ct * primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 26 45205 45361 -22577 45153
## model 27 45206 45368 -22576 45152 0.67 1 0.413lmedrop(lme.english.adult,"primetarget_relationship.ct:talker.ct")## Data: lexd.adult.english.RT
## Models:
## model.dropped: RTfilt ~ session.ct + primetarget_relationship.ct + condition.ct +
## model.dropped: talker.ct + (session.ct * primetarget_relationship.ct | participant) +
## model.dropped: session.ct:primetarget_relationship.ct + session.ct:condition.ct +
## model.dropped: primetarget_relationship.ct:condition.ct + session.ct:talker.ct +
## model.dropped: condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct +
## model.dropped: session.ct:primetarget_relationship.ct:talker.ct + session.ct:condition.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct:talker.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct * condition.ct *
## model: talker.ct + (session.ct * primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 26 45208 45364 -22578 45156
## model 27 45206 45368 -22576 45152 3.0837 1 0.07908 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1No effect overall effect of talker, but it did interact marginally with prime=target relationship. Looking at the means this reflects more priming with the less intelligble talker (female 1)
kable(with(lexd.adult.english.RT, tapply(RTfilt, list(primetarget_relationship, talker), mean, na.rm=T)), digits=0)| female1 | female2 | |
|---|---|---|
| related | 1163 | 1143 |
| unrelated | 1284 | 1193 |
child greek, RT
lexd.child.greek.RT$primetarget_relationship = factor(lexd.child.greek.RT$primetarget_relationship)
lexd.child.greek.RT = selectCenter(lexd.child.greek.RT, list("session", "primetarget_relationship"))
lme.greek.child<- lmer(RTfilt ~ session.ct* primetarget_relationship.ct+
(primetarget_relationship.ct *session.ct|participant), data = lexd.child.greek.RT, control=lmerControl(optimizer = "bobyqa") )
kable(summary(lme.greek.child)$coefficients, digits=3)| Estimate | Std. Error | t value | |
|---|---|---|---|
| (Intercept) | 1509.928 | 43.678 | 34.569 |
| session.ct | 136.386 | 69.924 | 1.950 |
| primetarget_relationship.ct | 72.344 | 29.293 | 2.470 |
| session.ct:primetarget_relationship.ct | -25.172 | 68.611 | -0.367 |
use model comparison to get p values
lmedrop(lme.greek.child,"session.ct")## Data: lexd.child.greek.RT
## Models:
## model.dropped: RTfilt ~ primetarget_relationship.ct + (primetarget_relationship.ct *
## model.dropped: session.ct | participant) + session.ct:primetarget_relationship.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct + (primetarget_relationship.ct *
## model: session.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 14 59007 59093 -29489 58979
## model 15 59005 59098 -29487 58975 3.7534 1 0.0527 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1lmedrop(lme.greek.child,"primetarget_relationship.ct")## Data: lexd.child.greek.RT
## Models:
## model.dropped: RTfilt ~ session.ct + (primetarget_relationship.ct * session.ct |
## model.dropped: participant) + session.ct:primetarget_relationship.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct + (primetarget_relationship.ct *
## model: session.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 14 59009 59095 -29490 58981
## model 15 59005 59098 -29487 58975 5.8744 1 0.01536 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1lmedrop(lme.greek.child,"session.ct:primetarget_relationship.ct")## Data: lexd.child.greek.RT
## Models:
## model.dropped: RTfilt ~ session.ct + primetarget_relationship.ct + (primetarget_relationship.ct *
## model.dropped: session.ct | participant)
## model: RTfilt ~ session.ct * primetarget_relationship.ct + (primetarget_relationship.ct *
## model: session.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 14 59003 59090 -29488 58975
## model 15 59005 59098 -29487 58975 0.1374 1 0.7109An effect of prime-target relationship (related = 1487 unrelated = 1549). A marginal effect of test session (pre = 1563 post = 1469). All interactions are non-significant.
child english, RT
lexd.child.english.RT$primetarget_relationship=factor(lexd.child.english.RT$primetarget_relationship)
lexd.child.english.RT$talker=factor(lexd.child.english.RT$talker)
lexd.child.english.RT = selectCenter(lexd.child.english.RT, list("session", "primetarget_relationship","talker","condition"))
lme.english.child<- lmer(RTfilt ~ session.ct* primetarget_relationship.ct*condition.ct*talker.ct+
(session.ct* primetarget_relationship.ct|participant), data = lexd.child.english.RT, control=lmerControl(optimizer = "bobyqa") )
get_coeffs(lme.english.child, c("(Intercept)", "session.ct", "primetarget_relationship.ct","session.ct:primetarget_relationship.ct","session.ct:primetarget_relationship.ct:condition.ct"))| Estimate | Std. Error | t value | |
|---|---|---|---|
| (Intercept) | 1641.077 | 50.620 | 32.420 |
| session.ct | 183.421 | 77.734 | 2.360 |
| primetarget_relationship.ct | 65.482 | 33.444 | 1.958 |
| session.ct:primetarget_relationship.ct | -52.332 | 66.688 | -0.785 |
| session.ct:primetarget_relationship.ct:condition.ct | -7.361 | 133.987 | -0.055 |
use model comparison to get p values:
lmedrop(lme.english.child,"session.ct")## Data: lexd.child.english.RT
## Models:
## model.dropped: RTfilt ~ primetarget_relationship.ct + condition.ct + talker.ct +
## model.dropped: (session.ct * primetarget_relationship.ct | participant) +
## model.dropped: session.ct:primetarget_relationship.ct + session.ct:condition.ct +
## model.dropped: primetarget_relationship.ct:condition.ct + session.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:talker.ct + condition.ct:talker.ct +
## model.dropped: session.ct:primetarget_relationship.ct:condition.ct + session.ct:primetarget_relationship.ct:talker.ct +
## model.dropped: session.ct:condition.ct:talker.ct + primetarget_relationship.ct:condition.ct:talker.ct +
## model.dropped: session.ct:primetarget_relationship.ct:condition.ct:talker.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct * condition.ct *
## model: talker.ct + (session.ct * primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 26 56143 56302 -28045 56091
## model 27 56139 56304 -28043 56085 5.7117 1 0.01685 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1lmedrop(lme.english.child,"primetarget_relationship.ct")## Data: lexd.child.english.RT
## Models:
## model.dropped: RTfilt ~ session.ct + condition.ct + talker.ct + (session.ct *
## model.dropped: primetarget_relationship.ct | participant) + session.ct:primetarget_relationship.ct +
## model.dropped: session.ct:condition.ct + primetarget_relationship.ct:condition.ct +
## model.dropped: session.ct:talker.ct + primetarget_relationship.ct:talker.ct +
## model.dropped: condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct +
## model.dropped: session.ct:primetarget_relationship.ct:talker.ct + session.ct:condition.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct:talker.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct * condition.ct *
## model: talker.ct + (session.ct * primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 26 56141 56300 -28044 56089
## model 27 56139 56304 -28043 56085 3.7458 1 0.05294 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1lmedrop(lme.english.child,"session.ct:primetarget_relationship.ct")## Data: lexd.child.english.RT
## Models:
## model.dropped: RTfilt ~ session.ct + primetarget_relationship.ct + condition.ct +
## model.dropped: talker.ct + (session.ct * primetarget_relationship.ct | participant) +
## model.dropped: session.ct:condition.ct + primetarget_relationship.ct:condition.ct +
## model.dropped: session.ct:talker.ct + primetarget_relationship.ct:talker.ct +
## model.dropped: condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct +
## model.dropped: session.ct:primetarget_relationship.ct:talker.ct + session.ct:condition.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct:talker.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct * condition.ct *
## model: talker.ct + (session.ct * primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 26 56138 56297 -28043 56086
## model 27 56139 56304 -28043 56085 0.619 1 0.4314lmedrop(lme.english.child, "condition.ct:session.ct:primetarget_relationship.ct")## Data: lexd.child.english.RT
## Models:
## model.dropped: RTfilt ~ session.ct + primetarget_relationship.ct + condition.ct +
## model.dropped: talker.ct + (session.ct * primetarget_relationship.ct | participant) +
## model.dropped: session.ct:primetarget_relationship.ct + session.ct:condition.ct +
## model.dropped: primetarget_relationship.ct:condition.ct + session.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:talker.ct + condition.ct:talker.ct +
## model.dropped: session.ct:primetarget_relationship.ct:talker.ct + session.ct:condition.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct:talker.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct * condition.ct *
## model: talker.ct + (session.ct * primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 26 56137 56296 -28043 56085
## model 27 56139 56304 -28043 56085 0.0032 1 0.9551An marginal effect of prime-target relationship (related = 1620 unrelated = 1664 d == , lexd.child.english.RT$primetarget_relationship, mean, na.rm=T). A main effect of test session (pre = 1704post = 1580
check interactions with talker
get_coeffs(lme.english.child, c("(Intercept)", "talker.ct", "session.ct:talker.ct","primetarget_relationship.ct:talker.ct"))| Estimate | Std. Error | t value | |
|---|---|---|---|
| (Intercept) | 1641.077 | 50.620 | 32.420 |
| talker.ct | -71.695 | 101.318 | -0.708 |
| session.ct:talker.ct | -245.063 | 155.613 | -1.575 |
| primetarget_relationship.ct:talker.ct | -8.197 | 66.991 | -0.122 |
lmedrop(lme.english.child,"talker.ct")## Data: lexd.child.english.RT
## Models:
## model.dropped: RTfilt ~ session.ct + primetarget_relationship.ct + condition.ct +
## model.dropped: (session.ct * primetarget_relationship.ct | participant) +
## model.dropped: session.ct:primetarget_relationship.ct + session.ct:condition.ct +
## model.dropped: primetarget_relationship.ct:condition.ct + session.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:talker.ct + condition.ct:talker.ct +
## model.dropped: session.ct:primetarget_relationship.ct:condition.ct + session.ct:primetarget_relationship.ct:talker.ct +
## model.dropped: session.ct:condition.ct:talker.ct + primetarget_relationship.ct:condition.ct:talker.ct +
## model.dropped: session.ct:primetarget_relationship.ct:condition.ct:talker.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct * condition.ct *
## model: talker.ct + (session.ct * primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 26 56138 56297 -28043 56086
## model 27 56139 56304 -28043 56085 0.5261 1 0.4683lmedrop(lme.english.child,"session.ct:talker.ct")## Data: lexd.child.english.RT
## Models:
## model.dropped: RTfilt ~ session.ct + primetarget_relationship.ct + condition.ct +
## model.dropped: talker.ct + (session.ct * primetarget_relationship.ct | participant) +
## model.dropped: session.ct:primetarget_relationship.ct + session.ct:condition.ct +
## model.dropped: primetarget_relationship.ct:condition.ct + primetarget_relationship.ct:talker.ct +
## model.dropped: condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct +
## model.dropped: session.ct:primetarget_relationship.ct:talker.ct + session.ct:condition.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct:talker.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct * condition.ct *
## model: talker.ct + (session.ct * primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 26 56140 56299 -28044 56088
## model 27 56139 56304 -28043 56085 2.6365 1 0.1044lmedrop(lme.english.child,"primetarget_relationship.ct:talker.ct")## Data: lexd.child.english.RT
## Models:
## model.dropped: RTfilt ~ session.ct + primetarget_relationship.ct + condition.ct +
## model.dropped: talker.ct + (session.ct * primetarget_relationship.ct | participant) +
## model.dropped: session.ct:primetarget_relationship.ct + session.ct:condition.ct +
## model.dropped: primetarget_relationship.ct:condition.ct + session.ct:talker.ct +
## model.dropped: condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct +
## model.dropped: session.ct:primetarget_relationship.ct:talker.ct + session.ct:condition.ct:talker.ct +
## model.dropped: primetarget_relationship.ct:condition.ct:talker.ct + session.ct:primetarget_relationship.ct:condition.ct:talker.ct
## model: RTfilt ~ session.ct * primetarget_relationship.ct * condition.ct *
## model: talker.ct + (session.ct * primetarget_relationship.ct | participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## model.dropped 26 56137 56296 -28043 56085
## model 27 56139 56304 -28043 56085 0.0149 1 0.9027no effect of talker, marginal interaction, looking at the means this reflects more priming with less intelligble talker
kable(with(lexd.child.english.RT, tapply(RTfilt, list(primetarget_relationship, talker), mean, na.rm=T)), digits=0)| female1 | female2 | |
|---|---|---|
| related | 1629 | 1609 |
| unrelated | 1678 | 1649 |
child english, accuracy
lexd.child.english$primetarget_relationship=factor(lexd.child.english$primetarget_relationship)
lexd.child.english$talker=factor(lexd.child.english$talker)
lexd.child.english = selectCenter(lexd.child.english, list("session", "primetarget_relationship","talker","condition"))
lme.english.child.acc<- glmer(accuracy ~ session.ct* primetarget_relationship.ct*condition.ct*talker.ct+
(session.ct* primetarget_relationship.ct|participant), data = lexd.child.english, control=glmerControl(optimizer = "bobyqa" ),family=binomial)
get_coeffs(lme.english.child.acc, c("(Intercept)", "session.ct", "primetarget_relationship.ct","session.ct:primetarget_relationship.ct", "session.ct:primetarget_relationship.ct:condition.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 2.029 | 0.132 | 15.354 | 0.000 |
| session.ct | -0.320 | 0.168 | -1.906 | 0.057 |
| primetarget_relationship.ct | -0.708 | 0.127 | -5.595 | 0.000 |
| session.ct:primetarget_relationship.ct | 0.261 | 0.232 | 1.123 | 0.261 |
| session.ct:primetarget_relationship.ct:condition.ct | 0.012 | 0.399 | 0.030 | 0.976 |
A reliable main effect of prime-target relationship (related = 0.87 unrelated = 0.81and no other effects. A main effect of test session (pre = 0.83 post = 0.85)
check interactions with talker
get_coeffs(lme.english.child.acc, c("(Intercept)", "talker.ct", "primetarget_relationship.ct:talker.ct","session.ct:talker.ct", "session.ct:talker.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 2.029 | 0.132 | 15.354 | 0.000 |
| talker.ct | -0.195 | 0.260 | -0.750 | 0.453 |
| primetarget_relationship.ct:talker.ct | 0.130 | 0.227 | 0.575 | 0.566 |
| session.ct:talker.ct | 0.625 | 0.322 | 1.944 | 0.052 |
| session.ct:talker.ct.1 | 0.625 | 0.322 | 1.944 | 0.052 |
no effect talker and effect of primetarget relationship isn’t qualified by an interaction with talker. Affect of session is qualified by an interaction with talker. This relfects the fact that children only showed improvements withfrom pre to post test with one of the two speakers (female 1 - the less intelligible one)
female 1 : pre = 0.82 post = 0.89 female 2 :pre = 0.84 post = 0.81
Discrimination
data preparation
Select data for analyses.
discrim.child = subset(discrim, agegroup =="child")
discrim.adult = subset(discrim, agegroup =="adult")get means and plots
adults
table of means
discrim.adult.participantmeans = aggregate(accuracy~ participant + session + condition + word_oldnew + voice_oldnew, na.rm=T, data = discrim.adult, FUN=mean)
discrim.adult.groupmeans <- summarySEwithin(discrim.adult.participantmeans,
measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session","voice_oldnew","word_oldnew"), idvar="participant", na.rm=FALSE, conf.interval =.95)
## to correct means for imbalance in talkers, get the mean values for each participant for each talker (average mean values for each talker); error calculations as done over the whole participant set
discrim.adult.participantmeans.t12 = aggregate(accuracy~ participant + session + condition + talker + word_oldnew + voice_oldnew, na.rm=T, data = discrim.adult, FUN=mean)
discrim.adult.groupmeans.talker1 <- summarySEwithin(subset(discrim.adult.participantmeans.t12, talker == "female1"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session","voice_oldnew","word_oldnew"), idvar="participant", na.rm=FALSE, conf.interval=.95)
discrim.adult.groupmeans.talker2 <- summarySEwithin(subset(discrim.adult.participantmeans.t12, talker == "female2"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session","voice_oldnew","word_oldnew"), idvar="participant", na.rm=FALSE, conf.interval=.95)
discrim.adult.groupmeans$accuracy = (discrim.adult.groupmeans.talker1$accuracy + discrim.adult.groupmeans.talker2$accuracy)/2
kable(discrim.adult.groupmeans, digits=3)| condition | session | voice_oldnew | word_oldnew | N | accuracy | accuracy_norm | sd | se | ci |
|---|---|---|---|---|---|---|---|---|---|
| highvar | post | newvoice | newword | 22 | 0.836 | 0.835 | 0.193 | 0.041 | 0.086 |
| highvar | post | newvoice | oldword | 22 | 0.823 | 0.821 | 0.134 | 0.029 | 0.059 |
| highvar | post | oldvoice | newword | 22 | 0.800 | 0.798 | 0.184 | 0.039 | 0.082 |
| highvar | post | oldvoice | oldword | 22 | 0.841 | 0.839 | 0.175 | 0.037 | 0.078 |
| highvar | pre | newvoice | newword | 22 | 0.709 | 0.708 | 0.191 | 0.041 | 0.085 |
| highvar | pre | newvoice | oldword | 22 | 0.755 | 0.753 | 0.185 | 0.039 | 0.082 |
| highvar | pre | oldvoice | newword | 22 | 0.800 | 0.798 | 0.186 | 0.040 | 0.082 |
| highvar | pre | oldvoice | oldword | 22 | 0.764 | 0.762 | 0.186 | 0.040 | 0.083 |
| lowvar | post | newvoice | newword | 19 | 0.836 | 0.833 | 0.205 | 0.047 | 0.099 |
| lowvar | post | newvoice | oldword | 19 | 0.810 | 0.807 | 0.186 | 0.043 | 0.090 |
| lowvar | post | oldvoice | newword | 19 | 0.791 | 0.802 | 0.186 | 0.043 | 0.089 |
| lowvar | post | oldvoice | oldword | 19 | 0.776 | 0.786 | 0.161 | 0.037 | 0.078 |
| lowvar | pre | newvoice | newword | 19 | 0.812 | 0.812 | 0.126 | 0.029 | 0.061 |
| lowvar | pre | newvoice | oldword | 19 | 0.767 | 0.765 | 0.179 | 0.041 | 0.086 |
| lowvar | pre | oldvoice | newword | 19 | 0.741 | 0.749 | 0.186 | 0.043 | 0.090 |
| lowvar | pre | oldvoice | oldword | 19 | 0.752 | 0.760 | 0.150 | 0.034 | 0.072 |
plot for figure 5
plot of the difference scores (showing improvement from pre- to post- test)
discrim.adult.participantmeans.2 = reshape(discrim.adult.participantmeans, timevar = "session", idvar=c("participant", "condition", "word_oldnew","voice_oldnew"), direction = "wide")
discrim.adult.participantmeans.2$accuracy.diff = discrim.adult.participantmeans.2$accuracy.post - discrim.adult.participantmeans.2$accuracy.pre
discrim.adult.groupmeans.diff <- summarySEwithin(discrim.adult.participantmeans.2,
measurevar="accuracy.diff", betweenvars=c("condition"), withinvars= c("voice_oldnew","word_oldnew"), idvar="participant", na.rm=FALSE, conf.interval =.95)
## to correct means for imbalance in talkers, get the mean values for each participant for each talker (average mean values for each talker); error calculations as done over the whole participant set
discrim.adult.participantmeans.t12.2 = reshape(discrim.adult.participantmeans.t12, timevar = "session", idvar=c("participant", "condition", "word_oldnew","voice_oldnew","talker"), direction = "wide")
discrim.adult.participantmeans.t12.2$accuracy.diff = discrim.adult.participantmeans.t12.2$accuracy.post - discrim.adult.participantmeans.t12.2$accuracy.pre
discrim.adult.groupmeans.diff.t1 <- summarySEwithin(subset(discrim.adult.participantmeans.t12.2, talker =="female1"),
measurevar="accuracy.diff", betweenvars=c("condition"), withinvars= c("voice_oldnew","word_oldnew"), idvar="participant", na.rm=FALSE, conf.interval =.95)
discrim.adult.groupmeans.diff.t2 <- summarySEwithin(subset(discrim.adult.participantmeans.t12.2, talker =="female2"),
measurevar="accuracy.diff", betweenvars=c("condition"), withinvars= c("voice_oldnew","word_oldnew"), idvar="participant", na.rm=FALSE, conf.interval =.95)
discrim.adult.groupmeans.diff$accuracy.diff = (discrim.adult.groupmeans.diff.t1$accuracy.diff+discrim.adult.groupmeans.diff.t2$accuracy.diff)/2
## now plot
discrim.adult.groupmeans.diff$word_oldnew = relevel(discrim.adult.groupmeans.diff$word_oldnew, "oldword")
discrim.adult.groupmeans.diff$novelty = paste(as.character(discrim.adult.groupmeans.diff$word_oldnew), as.character(discrim.adult.groupmeans.diff$voice_oldnew))
discrim.adult.groupmeans.diff$novelty=factor(discrim.adult.groupmeans.diff$novelty)
discrim.adult.groupmeans.diff$novelty = factor(discrim.adult.groupmeans.diff$novelty,
levels = c("oldword oldvoice","oldword newvoice","newword oldvoice","newword newvoice"))
p = ggplot(discrim.adult.groupmeans.diff, aes(x = novelty, y = accuracy.diff, fill = condition))
p = p + geom_bar(stat="identity", position="dodge", colour="black", size=.3)
p = p + geom_errorbar(aes(ymin=accuracy.diff-ci, ymax=accuracy.diff+ci), width=.4, position=position_dodge(.9))
p = p + xlab("") + ylab("% increase in correct responses")
p = p + scale_x_discrete(labels=c("oldword oldvoice" = " trained words \n trained voice",
"oldword newvoice" = " trained words \n untrained voice",
"newword oldvoice" = " untrained words \n trained voice",
"newword newvoice" = " untrained words \n untrained voice"
), expand=c(0, 0.6))
p = p + scale_fill_manual(values=c("grey", "white"), name="Condition", labels=c("high-variablity", "low-variablity"))
p = p + coord_cartesian(ylim = c(0, .4))
p
children
table of means:
discrim.child.participantmeans = aggregate(accuracy~ participant + session + condition + word_oldnew + voice_oldnew, na.rm=T, data = discrim.child, FUN=mean)
discrim.child.groupmeans <- summarySEwithin(discrim.child.participantmeans,
measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session","voice_oldnew","word_oldnew"), idvar="participant", na.rm=FALSE, conf.interval =.95)
## to correct means for imbalance in talkers, get the mean values for each participant for each talker (average mean values for each talker); error calculations as done over the whole participant set
discrim.child.participantmeans.t12 = aggregate(accuracy~ participant + session + condition + talker + word_oldnew + voice_oldnew, na.rm=T, data = discrim.child, FUN=mean)
discrim.child.groupmeans.talker1 <- summarySEwithin(subset(discrim.child.participantmeans.t12, talker == "female1"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session","voice_oldnew","word_oldnew"), idvar="participant", na.rm=FALSE, conf.interval=.95)
discrim.child.groupmeans.talker2 <- summarySEwithin(subset(discrim.child.participantmeans.t12, talker == "female2"), measurevar="accuracy", betweenvars=c("condition"), withinvars= c("session","voice_oldnew","word_oldnew"), idvar="participant", na.rm=FALSE, conf.interval=.95)
discrim.child.groupmeans$accuracy = (discrim.child.groupmeans.talker1$accuracy + discrim.child.groupmeans.talker2$accuracy)/2
kable(discrim.child.groupmeans, digits=3)| condition | session | voice_oldnew | word_oldnew | N | accuracy | accuracy_norm | sd | se | ci |
|---|---|---|---|---|---|---|---|---|---|
| highvar | post | newvoice | newword | 28 | 0.746 | 0.724 | 0.163 | 0.031 | 0.063 |
| highvar | post | newvoice | oldword | 28 | 0.754 | 0.731 | 0.148 | 0.028 | 0.057 |
| highvar | post | oldvoice | newword | 28 | 0.714 | 0.692 | 0.148 | 0.028 | 0.057 |
| highvar | post | oldvoice | oldword | 28 | 0.754 | 0.731 | 0.148 | 0.028 | 0.057 |
| highvar | pre | newvoice | newword | 28 | 0.664 | 0.642 | 0.192 | 0.036 | 0.075 |
| highvar | pre | newvoice | oldword | 28 | 0.629 | 0.606 | 0.196 | 0.037 | 0.076 |
| highvar | pre | oldvoice | newword | 28 | 0.686 | 0.663 | 0.154 | 0.029 | 0.060 |
| highvar | pre | oldvoice | oldword | 28 | 0.668 | 0.646 | 0.131 | 0.025 | 0.051 |
| lowvar | post | newvoice | newword | 24 | 0.770 | 0.801 | 0.167 | 0.034 | 0.070 |
| lowvar | post | newvoice | oldword | 24 | 0.748 | 0.780 | 0.218 | 0.045 | 0.092 |
| lowvar | post | oldvoice | newword | 24 | 0.720 | 0.738 | 0.166 | 0.034 | 0.070 |
| lowvar | post | oldvoice | oldword | 24 | 0.744 | 0.759 | 0.180 | 0.037 | 0.076 |
| lowvar | pre | newvoice | newword | 24 | 0.584 | 0.613 | 0.206 | 0.042 | 0.087 |
| lowvar | pre | newvoice | oldword | 24 | 0.526 | 0.555 | 0.153 | 0.031 | 0.064 |
| lowvar | pre | oldvoice | newword | 24 | 0.588 | 0.609 | 0.176 | 0.036 | 0.074 |
| lowvar | pre | oldvoice | oldword | 24 | 0.567 | 0.580 | 0.178 | 0.036 | 0.075 |
plot for figure 5
plot of the difference scores (showing improvement from pre- to post- test)
discrim.child.participantmeans.2 = reshape(discrim.child.participantmeans, timevar = "session", idvar=c("participant", "condition", "word_oldnew","voice_oldnew"), direction = "wide")
discrim.child.participantmeans.2$accuracy.diff = discrim.child.participantmeans.2$accuracy.post - discrim.child.participantmeans.2$accuracy.pre
discrim.child.groupmeans.diff <- summarySEwithin(discrim.child.participantmeans.2,
measurevar="accuracy.diff", betweenvars=c("condition"), withinvars= c("voice_oldnew","word_oldnew"), idvar="participant", na.rm=FALSE, conf.interval =.95)
## to correct means for imbalance in talkers, get the mean values for each participant for each talker (average mean values for each talker); error calculations as done over the whole participant set
discrim.child.participantmeans.t12.2 = reshape(discrim.child.participantmeans.t12, timevar = "session", idvar=c("participant", "condition", "word_oldnew","voice_oldnew","talker"), direction = "wide")
discrim.child.participantmeans.t12.2$accuracy.diff = discrim.child.participantmeans.t12.2$accuracy.post - discrim.child.participantmeans.t12.2$accuracy.pre
discrim.child.groupmeans.diff.t1 <- summarySEwithin(subset(discrim.child.participantmeans.t12.2, talker =="female1"),
measurevar="accuracy.diff", betweenvars=c("condition"), withinvars= c("voice_oldnew","word_oldnew"), idvar="participant", na.rm=FALSE, conf.interval =.95)
discrim.child.groupmeans.diff.t2 <- summarySEwithin(subset(discrim.child.participantmeans.t12.2, talker =="female2"),
measurevar="accuracy.diff", betweenvars=c("condition"), withinvars= c("voice_oldnew","word_oldnew"), idvar="participant", na.rm=FALSE, conf.interval =.95)
discrim.child.groupmeans.diff$accuracy.diff = (discrim.child.groupmeans.diff.t1$accuracy.diff+discrim.child.groupmeans.diff.t2$accuracy.diff)/2
## now plot
discrim.child.groupmeans.diff$word_oldnew = relevel(discrim.child.groupmeans.diff$word_oldnew, "oldword")
discrim.child.groupmeans.diff$novelty = paste(as.character(discrim.child.groupmeans.diff$word_oldnew), as.character(discrim.child.groupmeans.diff$voice_oldnew))
discrim.child.groupmeans.diff$novelty=factor(discrim.child.groupmeans.diff$novelty)
discrim.child.groupmeans.diff$novelty = factor(discrim.child.groupmeans.diff$novelty,
levels = c("oldword oldvoice","oldword newvoice","newword oldvoice","newword newvoice"))
p = ggplot(discrim.child.groupmeans.diff, aes(x = novelty, y = accuracy.diff, fill = condition))
p = p + geom_bar(stat="identity", position="dodge", colour="black", size=.3)
p = p + geom_errorbar(aes(ymin=accuracy.diff-ci, ymax=accuracy.diff+ci), width=.4, position=position_dodge(.9))
p = p + xlab("") + ylab("% increase in correct responses")
p = p + scale_x_discrete(labels=c("oldword oldvoice" = " trained words \n trained voice",
"oldword newvoice" = " trained words \n untrained voice",
"newword oldvoice" = " untrained words \n trained voice",
"newword newvoice" = " untrained words \n untrained voice"
), expand=c(0, 0.6))
p = p + scale_fill_manual(values=c("grey", "white"), name="Condition", labels=c("high-variablity", "low-variablity"))
p = p + coord_cartesian(ylim = c(0, .4))
p
statistical analyses
adults
Note: A version with correlations between slopes didn’t converge, these are removed in the model below (i.e. using the “(x||participant)”" syntax)
discrim.adult= selectCenter(discrim.adult, list("session","word_oldnew","voice_oldnew", "talker", "condition", "agegroup", "mean_replay_in_training"))
adult.lmer <- glmer(accuracy ~ 1 +
+ (condition.ct *session.ct*word_oldnew.ct*voice_oldnew.ct *talker.ct)
+ mean_replay_in_training.ct
+ (word_oldnew.ct*voice_oldnew.ct*session.ct||participant)
,data = discrim.adult,
control=glmerControl(optimizer = "bobyqa", optCtrl=list(maxfun=1e5)) ,
family=binomial)
get_coeffs(adult.lmer, c("(Intercept", "condition.ct", "session.ct", "word_oldnew.ct", "condition.ct:session.ct", "session.ct:word_oldnew.ct",
"session.ct:voice_oldnew.ct", "condition.ct:session.ct:word_oldnew.ct", "condition.ct:session.ct:voice_oldnew.ct",
"condition.ct:word_oldnew.ct:voice_oldnew.ct", "session.ct:word_oldnew.ct:voice_oldnew.ct",
"condition.ct:session.ct:word_oldnew.ct:voice_oldnew.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 1.638 | 0.095 | 17.203 | 0.000 |
| condition.ct | -0.055 | 0.186 | -0.295 | 0.768 |
| session.ct | -0.504 | 0.141 | -3.579 | 0.000 |
| word_oldnew.ct | -0.154 | 0.109 | -1.417 | 0.157 |
| condition.ct:session.ct | 0.043 | 0.282 | 0.153 | 0.879 |
| session.ct:word_oldnew.ct | 0.066 | 0.217 | 0.302 | 0.762 |
| session.ct:voice_oldnew.ct | 0.179 | 0.219 | 0.819 | 0.413 |
| condition.ct:session.ct:word_oldnew.ct | 0.251 | 0.435 | 0.577 | 0.564 |
| condition.ct:session.ct:voice_oldnew.ct | -0.894 | 0.439 | -2.039 | 0.041 |
| condition.ct:word_oldnew.ct:voice_oldnew.ct | 0.008 | 0.435 | 0.019 | 0.985 |
| session.ct:word_oldnew.ct:voice_oldnew.ct | -0.646 | 0.435 | -1.486 | 0.137 |
| condition.ct:session.ct:word_oldnew.ct:voice_oldnew.ct | 1.959 | 0.869 | 2.254 | 0.024 |
There is a reliable effect of test-session but no predicted test-session by condition interaction. There is a test-session by condition by voice-novelty interaction, but this is qualified by a four way test-session by condition by voice-novelty by word-novelty interaction.
We break down the four way interaction by re-running the model so that we have a slope for the three way test-session by condition by voice-novelty interaction for each of trained and untrained words
adult.lmer.v2 <- glmer(accuracy ~ 1 +
+ (condition.ct: session.ct:voice_oldnew.ct:word_oldnew)
+ (condition.ct *session.ct*word_oldnew.ct*voice_oldnew.ct *talker.ct)
- (condition.ct: session.ct:word_oldnew.ct:voice_oldnew.ct)
- (condition.ct: session.ct:voice_oldnew.ct)
+ mean_replay_in_training.ct
+ (word_oldnew.ct*voice_oldnew.ct*session.ct||participant)
,data = discrim.adult,
control=glmerControl(optimizer = "bobyqa", optCtrl=list(maxfun=1e5)) ,
family=binomial)
## checking it's the same model (i.e. identical dfs)
anova(adult.lmer.v2, adult.lmer)## Data: discrim.adult
## Models:
## adult.lmer.v2: accuracy ~ 1 + +(condition.ct:session.ct:voice_oldnew.ct:word_oldnew) +
## adult.lmer.v2: (condition.ct * session.ct * word_oldnew.ct * voice_oldnew.ct *
## adult.lmer.v2: talker.ct) - (condition.ct:session.ct:word_oldnew.ct:voice_oldnew.ct) -
## adult.lmer.v2: (condition.ct:session.ct:voice_oldnew.ct) + mean_replay_in_training.ct +
## adult.lmer.v2: (word_oldnew.ct * voice_oldnew.ct * session.ct || participant)
## adult.lmer: accuracy ~ 1 + +(condition.ct * session.ct * word_oldnew.ct *
## adult.lmer: voice_oldnew.ct * talker.ct) + mean_replay_in_training.ct +
## adult.lmer: (word_oldnew.ct * voice_oldnew.ct * session.ct || participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## adult.lmer.v2 41 3082.3 3332.2 -1500.1 3000.3
## adult.lmer 41 3082.3 3332.2 -1500.1 3000.3 0 0 < 2.2e-16
##
## adult.lmer.v2
## adult.lmer ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1get_coeffs(adult.lmer.v2, c("condition.ct:session.ct:voice_oldnew.ct:word_oldnewnewword","condition.ct:session.ct:voice_oldnew.ct:word_oldnewoldword"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| condition.ct:session.ct:voice_oldnew.ct:word_oldnewnewword | -1.874 | 0.659 | -2.844 | 0.004 |
| condition.ct:session.ct:voice_oldnew.ct:word_oldnewoldword | 0.085 | 0.571 | 0.149 | 0.881 |
The condition by session by voice-novelty interaction is reliable only for untrained words.
We further break down the condition by session by voice-novelty interaction for untrained words.
adult.lmer.v3 <- glmer(accuracy ~ 1 +
+ (condition.ct: session.ct:word_oldnew:voice_oldnew)
+ (condition.ct *session.ct*word_oldnew.ct*voice_oldnew.ct *talker.ct)
- (condition.ct: session.ct:word_oldnew.ct:voice_oldnew.ct)
- (condition.ct: session.ct:voice_oldnew.ct)
- (condition.ct: session.ct:word_oldnew.ct)
- (condition.ct: session.ct)
+ mean_replay_in_training.ct
+ (word_oldnew.ct*voice_oldnew.ct*session.ct||participant)
,data = discrim.adult,
control=glmerControl(optimizer = "bobyqa", optCtrl=list(maxfun=1e5)) ,
family=binomial)
anova(adult.lmer.v3, adult.lmer)## Data: discrim.adult
## Models:
## adult.lmer.v3: accuracy ~ 1 + +(condition.ct:session.ct:word_oldnew:voice_oldnew) +
## adult.lmer.v3: (condition.ct * session.ct * word_oldnew.ct * voice_oldnew.ct *
## adult.lmer.v3: talker.ct) - (condition.ct:session.ct:word_oldnew.ct:voice_oldnew.ct) -
## adult.lmer.v3: (condition.ct:session.ct:voice_oldnew.ct) - (condition.ct:session.ct:word_oldnew.ct) -
## adult.lmer.v3: (condition.ct:session.ct) + mean_replay_in_training.ct +
## adult.lmer.v3: (word_oldnew.ct * voice_oldnew.ct * session.ct || participant)
## adult.lmer: accuracy ~ 1 + +(condition.ct * session.ct * word_oldnew.ct *
## adult.lmer: voice_oldnew.ct * talker.ct) + mean_replay_in_training.ct +
## adult.lmer: (word_oldnew.ct * voice_oldnew.ct * session.ct || participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## adult.lmer.v3 41 3082.3 3332.2 -1500.1 3000.3
## adult.lmer 41 3082.3 3332.2 -1500.1 3000.3 0 0 < 2.2e-16
##
## adult.lmer.v3
## adult.lmer ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1get_coeffs(adult.lmer.v3, c("condition.ct:session.ct:word_oldnewnewword:voice_oldnewnewvoice","condition.ct:session.ct:word_oldnewnewword:voice_oldnewoldvoice"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| condition.ct:session.ct:word_oldnewnewword:voice_oldnewnewvoice | 0.854 | 0.475 | 1.798 | 0.072 |
| condition.ct:session.ct:word_oldnewnewword:voice_oldnewoldvoice | -1.019 | 0.522 | -1.954 | 0.051 |
There is a marginal condition by session interaction for the untrained voice which went in the predicted direction, but also a marginal interaction in the opposite direction for the trained voice. In other words, the interaction rests both on a trend towards a greater benefit of high-variability input compared with low-variability input for untrained words-untrained voice items (which is predicted since novelty should aid generalization) and a trend towards a greater benefit of low-variability for untrained words-trained voice items (which is not predicted).
check interactions with talker:
get_coeffs(adult.lmer, c("talker.ct", "session.ct:talker.ct", "condition.ct:session.ct:word_oldnew.ct:talker.ct", "condition.ct:session.ct:word_oldnew.ct:voice_oldnew.ct:talker.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| talker.ct | 1.657 | 0.130 | 12.716 | 0.000 |
| session.ct:talker.ct | -0.596 | 0.219 | -2.718 | 0.007 |
| condition.ct:session.ct:word_oldnew.ct:talker.ct | 0.430 | 0.869 | 0.494 | 0.621 |
| condition.ct:session.ct:word_oldnew.ct:voice_oldnew.ct:talker.ct | 1.946 | 1.738 | 1.120 | 0.263 |
There is a reliable main effect of talker, reflecting female being overall more intelligible (female1 0.68, female2 0.9).
The main effect of test-session is qualified by an interaction with talker. We look to see if the effect of test-session holds for each talker;
adult.lmer.v4 <- glmer(accuracy ~ 1 +
+ session.ct : talker
+ (condition.ct *session.ct*word_oldnew.ct*voice_oldnew.ct *talker.ct)
-session.ct : talker.ct
- session.ct
+ mean_replay_in_training.ct
+ (word_oldnew.ct*voice_oldnew.ct*session.ct||participant)
,data = discrim.adult,
control=glmerControl(optimizer = "bobyqa", optCtrl=list(maxfun=1e5)) ,
family=binomial)
anova(adult.lmer.v4, adult.lmer)## Data: discrim.adult
## Models:
## adult.lmer.v4: accuracy ~ 1 + +session.ct:talker + (condition.ct * session.ct *
## adult.lmer.v4: word_oldnew.ct * voice_oldnew.ct * talker.ct) - session.ct:talker.ct -
## adult.lmer.v4: session.ct + mean_replay_in_training.ct + (word_oldnew.ct *
## adult.lmer.v4: voice_oldnew.ct * session.ct || participant)
## adult.lmer: accuracy ~ 1 + +(condition.ct * session.ct * word_oldnew.ct *
## adult.lmer: voice_oldnew.ct * talker.ct) + mean_replay_in_training.ct +
## adult.lmer: (word_oldnew.ct * voice_oldnew.ct * session.ct || participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## adult.lmer.v4 41 3082.3 3332.2 -1500.1 3000.3
## adult.lmer 41 3082.3 3332.2 -1500.1 3000.3 0 0 < 2.2e-16
##
## adult.lmer.v4
## adult.lmer ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1get_coeffs(adult.lmer.v4, c("session.ct:talkerfemale1", "session.ct:talkerfemale2"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| session.ct:talkerfemale1 | -0.206 | 0.141 | -1.465 | 0.143 |
| session.ct:talkerfemale2 | -0.802 | 0.209 | -3.831 | 0.000 |
The effect of session is only reliable for the more intelligible voice (female 2) although means are in the same direction in each case.
female 1 : pre = 0.66 post = 0.7 female 2 :pre = 0.87 post = 0.93
children
note that a model containing correlations between slopes didn’t converge, these are removed in the model below (ie using the “(x||participant) syntax)
discrim.child= selectCenter(discrim.child, list("session","word_oldnew","voice_oldnew", "talker", "condition", "agegroup", "mean_replay_in_training"))
child.lmer <- glmer(accuracy ~ 1 +
+ (condition.ct *session.ct*word_oldnew.ct*voice_oldnew.ct *talker.ct)
+ mean_replay_in_training.ct
+ (word_oldnew.ct*voice_oldnew.ct*session.ct||participant)
,data = discrim.child,
control=glmerControl(optimizer = "bobyqa", optCtrl=list(maxfun=1e5)) ,
family=binomial)
get_coeffs(child.lmer, c("(Intercept", "condition.ct", "session.ct", "word_oldnew.ct", "condition.ct:session.ct", "session.ct:word_oldnew.ct",
"session.ct:voice_oldnew.ct", "condition.ct:session.ct:word_oldnew.ct", "condition.ct:session.ct:voice_oldnew.ct",
"condition.ct:word_oldnew.ct:voice_oldnew.ct", "session.ct:word_oldnew.ct:voice_oldnew.ct",
"condition.ct:session.ct:word_oldnew.ct:voice_oldnew.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 0.870 | 0.080 | 10.941 | 0.000 |
| condition.ct | -0.249 | 0.160 | -1.552 | 0.121 |
| session.ct | -0.671 | 0.099 | -6.774 | 0.000 |
| word_oldnew.ct | -0.027 | 0.072 | -0.378 | 0.705 |
| condition.ct:session.ct | -0.490 | 0.198 | -2.477 | 0.013 |
| session.ct:word_oldnew.ct | -0.250 | 0.145 | -1.729 | 0.084 |
| session.ct:voice_oldnew.ct | 0.216 | 0.154 | 1.405 | 0.160 |
| condition.ct:session.ct:word_oldnew.ct | 0.073 | 0.290 | 0.251 | 0.802 |
| condition.ct:session.ct:voice_oldnew.ct | -0.020 | 0.308 | -0.064 | 0.949 |
| condition.ct:word_oldnew.ct:voice_oldnew.ct | 0.085 | 0.290 | 0.294 | 0.769 |
| session.ct:word_oldnew.ct:voice_oldnew.ct | -0.134 | 0.301 | -0.445 | 0.656 |
| condition.ct:session.ct:word_oldnew.ct:voice_oldnew.ct | -0.042 | 0.602 | -0.070 | 0.944 |
There was no reliable main effect of word-novelty. There was a reliable effect of test-session, indicating an effect of training (pre-test 0.62, post test 0.74). There was a marginal interaction between word-novelty and test session (untrained words 0.63 –> 0.74, untrained words 0.6 –> 0.75 However there is reliable interaction between test-session and condition. This is the reverse to the predicted direction - greater improvement in the low variability condition (0.18) than in the highvariablity condition (0.08)
Breaking this down:
discrim.child= selectCenter(discrim.child, list("session","word_oldnew","voice_oldnew", "talker", "condition", "agegroup", "mean_replay_in_training"))
child.lmer.v2 <- glmer(accuracy ~ 1 +
+ condition.ct : session
+ (condition.ct *session.ct*word_oldnew.ct*voice_oldnew.ct *talker.ct)
- condition.ct : session.ct
- condition.ct
+ mean_replay_in_training.ct
+ (word_oldnew.ct*voice_oldnew.ct*session.ct||participant)
,data = discrim.child,
control=glmerControl(optimizer = "bobyqa", optCtrl=list(maxfun=1e5)) ,
family=binomial)
anova(child.lmer, child.lmer.v2 )## Data: discrim.child
## Models:
## child.lmer: accuracy ~ 1 + +(condition.ct * session.ct * word_oldnew.ct *
## child.lmer: voice_oldnew.ct * talker.ct) + mean_replay_in_training.ct +
## child.lmer: (word_oldnew.ct * voice_oldnew.ct * session.ct || participant)
## child.lmer.v2: accuracy ~ 1 + +condition.ct:session + (condition.ct * session.ct *
## child.lmer.v2: word_oldnew.ct * voice_oldnew.ct * talker.ct) - condition.ct:session.ct -
## child.lmer.v2: condition.ct + mean_replay_in_training.ct + (word_oldnew.ct *
## child.lmer.v2: voice_oldnew.ct * session.ct || participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## child.lmer 41 4920.5 5180.1 -2419.2 4838.5
## child.lmer.v2 41 4920.5 5180.1 -2419.2 4838.5 0 0 1get_coeffs(child.lmer.v2, c("condition.ct:sessionpost","condition.ct:sessionpre"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| condition.ct:sessionpost | -0.003 | 0.192 | -0.018 | 0.986 |
| condition.ct:sessionpre | -0.494 | 0.184 | -2.683 | 0.007 |
There is a reliable difference between the conditions at pre-test (low variability: 0.56, high-variability: 0.66) but although children in the low-variability have caught up by post-test, they have not overtaken the high-variability condition (low variability: 0.74, high-variability: 0.74).
check interactions with talker
get_coeffs(child.lmer.v2, c("talker.ct","condition.ct:session.ct:talker.ct","session.ct:word_oldnew.ct:talker.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| talker.ct | 0.801 | 0.074 | 10.819 | 0.000 |
| condition.ct:session.ct:talker.ct | -0.358 | 0.309 | -1.160 | 0.246 |
| session.ct:word_oldnew.ct:talker.ct | -0.167 | 0.300 | -0.556 | 0.578 |
There is a reliable main effect of talker, reflecting female 2 being overall more intelligible (female 1 0.6, female 2 0.76. )
The interactions between word-type and session, and condition and session do not interact with talker. However, since the benefit of low-variability is unexpected, particularly for untrained voices, consider whether the pattern is ordinal across counterbalances. Looking at the difference scores by talker:
discrim.child.talker = aggregate(accuracy~ session + condition + talker + voice_oldnew, na.rm=T, data = discrim.child, FUN=mean)
discrim.child.talker.2 = reshape(discrim.child.talker, timevar = "session", idvar=c("condition", "talker","voice_oldnew"), direction = "wide")
discrim.child.talker.2$accuracy.diff = discrim.child.talker.2$accuracy.post - discrim.child.talker.2$accuracy.pre
kable(discrim.child.talker.2,digits=3)| condition | talker | voice_oldnew | accuracy.post | accuracy.pre | accuracy.diff | |
|---|---|---|---|---|---|---|
| 1 | highvar | female1 | newvoice | 0.686 | 0.568 | 0.118 |
| 3 | lowvar | female1 | newvoice | 0.691 | 0.509 | 0.182 |
| 5 | highvar | female2 | newvoice | 0.814 | 0.725 | 0.089 |
| 7 | lowvar | female2 | newvoice | 0.827 | 0.600 | 0.227 |
| 9 | highvar | female1 | oldvoice | 0.664 | 0.604 | 0.061 |
| 11 | lowvar | female1 | oldvoice | 0.623 | 0.473 | 0.150 |
| 13 | highvar | female2 | oldvoice | 0.804 | 0.750 | 0.054 |
| 15 | lowvar | female2 | oldvoice | 0.841 | 0.682 | 0.159 |
This suggests that for both counterbalances, for both trained and untrained voices, there is more improvement in the low variability condition.
age group comparison
discrim= selectCenter(discrim, list("session","word_oldnew","voice_oldnew", "talker", "condition", "agegroup", "mean_replay_in_training","agegroup"))
age.lmer <- glmer(accuracy ~ 1 +
+ (condition.ct *session.ct*word_oldnew.ct*voice_oldnew.ct*agegroup.ct*talker.ct)
+ mean_replay_in_training.ct
+ (word_oldnew.ct*voice_oldnew.ct*session.ct||participant)
,data = discrim,
control=glmerControl(optimizer = "bobyqa", optCtrl=list(maxfun=1e5)) ,
family=binomial)
get_coeffs(age.lmer, c("(Intercept)","agegroup.ct","session.ct:agegroup.ct","condition.ct:session.ct:agegroup.ct", "session.ct:word_oldnew.ct:agegroup.ct","session.ct:voice_oldnew.ct:agegroup.ct", "condition.ct:session.ct:word_oldnew.ct:agegroup.ct", "condition.ct:session.ct:voice_oldnew.ct:agegroup.ct","session.ct:word_oldnew.ct:voice_oldnew.ct:agegroup.ct","condition.ct:session.ct:word_oldnew.ct:voice_oldnew.ct:agegroup.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 1.203 | 0.060 | 19.890 | 0.000 |
| agegroup.ct | -0.807 | 0.126 | -6.427 | 0.000 |
| session.ct:agegroup.ct | -0.172 | 0.170 | -1.015 | 0.310 |
| condition.ct:session.ct:agegroup.ct | -0.537 | 0.340 | -1.579 | 0.114 |
| session.ct:word_oldnew.ct:agegroup.ct | -0.316 | 0.261 | -1.211 | 0.226 |
| session.ct:voice_oldnew.ct:agegroup.ct | 0.034 | 0.267 | 0.128 | 0.898 |
| condition.ct:session.ct:word_oldnew.ct:agegroup.ct | -0.174 | 0.521 | -0.334 | 0.739 |
| condition.ct:session.ct:voice_oldnew.ct:agegroup.ct | 0.876 | 0.534 | 1.642 | 0.101 |
| session.ct:word_oldnew.ct:voice_oldnew.ct:agegroup.ct | 0.506 | 0.521 | 0.970 | 0.332 |
| condition.ct:session.ct:word_oldnew.ct:voice_oldnew.ct:agegroup.ct | -1.995 | 1.037 | -1.923 | 0.054 |
Main effect of age-group (children 0.68, adults 0.79)
No reliable interaction between age-group and test-session and no higher interaction with any combination of condition, word-novetly or voice-novelty. There was however, a near reliable five way interaction (reflecting different factors in the models above)
check interactions with talker
get_coeffs(age.lmer, c("talker.ct", "agegroup.ct:talker.ct", "condition.ct:session.ct:word_oldnew.ct:voice_oldnew.ct:talker.ct"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| talker.ct | 1.171 | 0.068 | 17.283 | 0.000 |
| agegroup.ct:talker.ct | -0.825 | 0.138 | -5.975 | 0.000 |
| condition.ct:session.ct:word_oldnew.ct:voice_oldnew.ct:talker.ct | 1.103 | 0.998 | 1.105 | 0.269 |
There was a effect of talker. Moreover the main effect of age group was qualified by an interaction with talker (the five way interaction was not). Breaking down talker by age group interaction:
age.lmer.v2 <- glmer(accuracy ~ 1 +
+ agegroup.ct:talker
+ (condition.ct *session.ct*word_oldnew.ct*voice_oldnew.ct*agegroup.ct*talker.ct)
- agegroup.ct:talker.ct
- agegroup.ct
+ mean_replay_in_training.ct
+ (word_oldnew.ct*voice_oldnew.ct*session.ct||participant)
,data = discrim,
control=glmerControl(optimizer = "bobyqa", optCtrl=list(maxfun=1e5)) ,
family=binomial)
anova(age.lmer, age.lmer.v2)## Data: discrim
## Models:
## age.lmer: accuracy ~ 1 + +(condition.ct * session.ct * word_oldnew.ct *
## age.lmer: voice_oldnew.ct * agegroup.ct * talker.ct) + mean_replay_in_training.ct +
## age.lmer: (word_oldnew.ct * voice_oldnew.ct * session.ct || participant)
## age.lmer.v2: accuracy ~ 1 + +agegroup.ct:talker + (condition.ct * session.ct *
## age.lmer.v2: word_oldnew.ct * voice_oldnew.ct * agegroup.ct * talker.ct) -
## age.lmer.v2: agegroup.ct:talker.ct - agegroup.ct + mean_replay_in_training.ct +
## age.lmer.v2: (word_oldnew.ct * voice_oldnew.ct * session.ct || participant)
## Df AIC BIC logLik deviance Chisq Chi Df Pr(>Chisq)
## age.lmer 73 7987.2 8492 -3920.6 7841.2
## age.lmer.v2 73 7987.2 8492 -3920.6 7841.2 0 0 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1get_coeffs(age.lmer.v2,c("(Intercept)","agegroup.ct:talkerfemale1","agegroup.ct:talkerfemale2"))| Estimate | Std. Error | z value | Pr(>|z|) | |
|---|---|---|---|---|
| (Intercept) | 1.203 | 0.060 | 19.890 | 0.000 |
| agegroup.ct:talkerfemale1 | -0.395 | 0.131 | -3.018 | 0.003 |
| agegroup.ct:talkerfemale2 | -1.219 | 0.155 | -7.878 | 0.000 |
The difference between age groups holds for each talker.