Set-up
Required packages are loaded, workspace is defined, data is loaded
and transformed into a final format. For more information on the loaded
data check separate Qual/VPT/JND Rcodes.
### some basic settings
# Check packages installed:
required_packages <- c("rstudioapi","plyr", "dplyr", "stringr",
"readr", "gridExtra", "moments", "readxl",
"tidyr", "ggplot2","ggpubr","extrafont",
"kableExtra", "broom", "knitr","broom.mixed",
"haven", "lubridate", "magrittr", "rstatix",
"ggbeeswarm", "ggstatsplot", "stats", "effsize",
"lmboot", "BayesFactor")
need_install <- required_packages[!(required_packages) %in% installed.packages()]
# Install packages that were not:
if(length(need_install)> 0) {
install.packages(need_install)
}
# Load packages
invisible(lapply(required_packages, require, character.only=TRUE))
# Set working directory and font
dir_qual <- dirname(rstudioapi::getSourceEditorContext()$path)
setwd(dir_qual)
windowsFonts(sans=windowsFont("Helvetica"))
### Load data
VPT_df <- read.csv2("Data/VPT_aggregated_wide.csv")
JND_df <- read.csv2("Data/JND_aggregated_wide.csv")
Qual_df <- read.csv2("Data/Qualtrics_merged_coderesponses.csv")
colnames(VPT_df)[10:length(VPT_df)] <- paste0("VPT_", colnames(VPT_df[10:length(VPT_df)]))
colnames(JND_df)[2:length(JND_df)] <- paste0("JND_", colnames(JND_df[2:length(JND_df)]))
### Merge data
Total_df <- merge(Qual_df, VPT_df, by="ppn", all.x=TRUE)
Total_df <- merge(Total_df, JND_df, by="ppn", all.x=TRUE)
Total_df <- Total_df %>% mutate_all(na_if,"") ## replace empty cells by NA
### Select relevant data
Total_df <- Total_df %>% select(ppn, Exclusion, Gender_bio, Gender_id, Age_test, Age_cat, Education, Autism,
Autism_year_1_1, ADHD, Psych, Psych_past, Neuro, Alcohol, Drugs, Meds, Sleep_qual_1,
Sleep_quant, AQ_10_sum, MMQCon_sum, MMQAb_sum, MMQStrat_sum, Strategy_VPT, Coded_specific,
Coded_aggregated,Coded_summary, Strategy_JND,Concentration_VPT, Effort_VPT, Performance_VPT, Concentration_JND,
Effort_JND, Performance_JND, VPT_span_traditional_high, VPT_span_traditional_low,
VPT_span_traditional_mean_high, VPT_span_traditional_mean_low,
VPT_mrt_wo_high, VPT_mrt_wo_low,VPT_mrt_cor_wo_high,VPT_mrt_cor_wo_low, VPT_acc_wo_high,
VPT_acc_wo_low, VPT_n_outlier_high, VPT_n_outlier_low, VPT_n_FaR_high, VPT_n_FaR_low,
JND_mrt_wo_full, JND_acc_wo_full, JND_mrt_cor_wo_full,JND_score_wo_full,
JND_mrt_wo_final, JND_acc_wo_final,JND_mrt_cor_wo_final, JND_score_wo_final,
JND_n_outlier_full, JND_n_FaR_full, JND_n_min_full, JND_n_max_full)
# Add concatenated group variable
Total_df$Groups <- paste0(Total_df$Autism, "_", Total_df$Age_cat)
Total_df$Groups <- factor(Total_df$Groups, levels=c("autism_younger", "autism_older", "no-autism_younger", "no-autism_older"))
levels(Total_df$Groups) <- list(aut_yng = "autism_younger" , aut_old = "autism_older",
naut_yng = "no-autism_younger", naut_old = "no-autism_older")
Total_df$Age_cat <- factor(Total_df$Age_cat, levels=c("younger", "older"))
levels(Total_df$Age_cat) <- list(yng = "younger" , old = "older")
Total_df$Autism <- factor(Total_df$Autism, levels=c("autism", "no-autism"))
levels(Total_df$Autism) <- list(aut = "autism", naut= "no-autism")
Total_df$Gender_bio <- factor(Total_df$Gender_bio, levels = c("man", "woman", "other"))
Total_df$Edu_cat <- ifelse(Total_df$Education < 5, "low",
ifelse(Total_df$Education < 7, "middle", "high"))
Total_df$Edu_cat <- factor(Total_df$Edu_cat, levels = c("low", "middle", "high"))
Exclude participants
#general exclude
Total_df <- Total_df %>% filter(Exclusion == 0) #N exclusion = 4 (all based on autism family)
#VPT exclude
VPT_long_df <- Total_df %>% pivot_longer(c(VPT_span_traditional_high:VPT_n_FaR_low),
names_to = c(".value","type"),
names_pattern = "(.*)_(.*)")
VPT_exclusion_df <- VPT_long_df %>% select(ppn, Exclusion, Age_cat, Autism, type, VPT_mrt_wo)
VPT_avg <- VPT_exclusion_df %>%
group_by(type, Age_cat, Autism) %>%
summarise(mean_mrt = mean(VPT_mrt_wo, na.rm=TRUE),
sd_mrt = sd(VPT_mrt_wo, na.rm=TRUE)) %>%
ungroup()
VPT_exclusion_df <- merge(VPT_exclusion_df, VPT_avg, by=c("type", "Age_cat", "Autism"))
VPT_exclusion_df$Exclusion_VPT <- ifelse(VPT_exclusion_df$VPT_mrt_wo > (VPT_exclusion_df$mean_mrt+(3*VPT_exclusion_df$sd_mrt)), 1,
ifelse(VPT_exclusion_df$VPT_mrt_wo < (VPT_exclusion_df$mean_mrt-(3*VPT_exclusion_df$sd_mrt)),1,0))
VPT_exclusion_df <- pivot_wider(VPT_exclusion_df, names_from = type, names_sep= "_", values_from = c(VPT_mrt_wo:Exclusion_VPT))
VPT_exclusion_df$Exclusion_VPT <- ifelse(VPT_exclusion_df$Exclusion_VPT_high == 1 | VPT_exclusion_df$Exclusion_VPT_low == 1, 1, 0)
VPT_exclusion_df <- select(VPT_exclusion_df, c(ppn, Exclusion_VPT))
Total_df <- merge(Total_df, VPT_exclusion_df, by = "ppn") #add to total_df
Total_df$Exclusion_VPT <- ifelse(is.na(Total_df$Exclusion_VPT), -9, Total_df$Exclusion_VPT) #set NA to -9, because then no VPT data was present
VPT_long_df <- merge(VPT_long_df, VPT_exclusion_df, by = "ppn")
VPT_long_df$Exclusion_VPT <- ifelse(is.na(VPT_long_df$Exclusion_VPT), -9, VPT_long_df$Exclusion_VPT) # here too.
#JND exclude
JND_long_df <- Total_df %>% pivot_longer(c(JND_mrt_wo_full:JND_score_wo_final),
names_to = c(".value", "dataset"),
names_pattern = "(.*)_(.*)")
JND_exclusion_df <- JND_long_df %>% select(ppn, Exclusion, Age_cat, Autism, dataset, JND_mrt_wo)
JND_avg <- JND_exclusion_df %>%
group_by(dataset, Age_cat, Autism) %>%
summarise(mean_mrt = mean(JND_mrt_wo, na.rm=TRUE),
sd_mrt = sd(JND_mrt_wo, na.rm=TRUE)) %>%
ungroup()
JND_exclusion_df <- merge(JND_exclusion_df, JND_avg, by=c("dataset", "Age_cat", "Autism"))
JND_exclusion_df$Exclusion_JND <- ifelse(JND_exclusion_df$JND_mrt_wo > (JND_exclusion_df$mean_mrt+(3*JND_exclusion_df$sd_mrt)), 1,
ifelse(JND_exclusion_df$JND_mrt_wo < (JND_exclusion_df$mean_mrt-(3*JND_exclusion_df$sd_mrt)),1,0))
JND_exclusion_df <- pivot_wider(JND_exclusion_df, names_from = dataset, names_sep= "_", values_from = c(JND_mrt_wo:Exclusion_JND))
## even the outlier responder (N=1) is really fast (<2 sec) with no indication of taking brakes, so are not removed.
JND_exclusion_df$Exclusion_JND <- ifelse(JND_exclusion_df$Exclusion_JND_full, 0, 0) ## no one is excluded.
JND_exclusion_df <- select(JND_exclusion_df, c(ppn, Exclusion_JND))
Total_df <- merge(Total_df, JND_exclusion_df, by = "ppn") #add to total_df
Total_df$Exclusion_JND <- ifelse(is.na(Total_df$Exclusion_JND), -9, Total_df$Exclusion_JND)
JND_long_df <- merge(JND_long_df, JND_exclusion_df, by = "ppn")
JND_long_df$Exclusion_JND <- ifelse(is.na(JND_long_df$Exclusion_JND), -9, JND_long_df$Exclusion_JND)
write_csv2(Total_df, "Datasets_merged.csv") # save total dataset with excluded ppns indicated.
Descriptives (Aut/nAut)
We create basic information tables for N and means/sds for all
relevant variables.
get_N = function(data, var, title){
Ns <- list()
for (i in 1:length(var)){
var1 = sym(var[i])
groups = c("Autism", "Age_cat", var[i])
N_df <- data %>% #getting some info on categorical data
group_by(.dots = groups) %>%
summarise(N = n()) %>%
pivot_wider(names_from = c("Age_cat", "Autism"), values_from = N)
colnames(N_df)[1] <- "category"
Chidf <- data %>%
group_by(Age_cat) %>%
summarise(Chi = chisq.test(Autism, !!var1)$statistic,
p = chisq.test(Autism, !!var1)$p.value) %>%
mutate_if(is.numeric, round, 3) %>%
pivot_wider(names_from = "Age_cat", values_from = c(Chi, p))
Var <- var[i]
N_df <- cbind(N_df, Chidf)
N_df <- cbind(Var, N_df)
Ns[[i]] <- N_df
}
finalNs <- do.call(rbind,Ns)
return(kbl(finalNs, caption=paste0(title), digits = 3,booktabs = TRUE) %>%
kable_classic(full_width = F, font_size = 11) %>%
kable_styling(latex_options = "HOLD_position"))
}
nvars <- c("Gender_bio","Edu_cat", "ADHD", "Psych", "Psych_past", "Neuro", "Drugs", "Alcohol")
get_N(Total_df, nvars, title="N demographs")
N demographs
Var
|
category
|
yng_aut
|
old_aut
|
yng_naut
|
old_naut
|
Chi_yng
|
Chi_old
|
p_yng
|
p_old
|
Gender_bio
|
man
|
9
|
31
|
11
|
21
|
0.127
|
1.790
|
0.721
|
0.409
|
Gender_bio
|
woman
|
23
|
15
|
20
|
16
|
0.127
|
1.790
|
0.721
|
0.409
|
Gender_bio
|
other
|
|
1
|
|
|
0.127
|
1.790
|
0.721
|
0.409
|
Edu_cat
|
middle
|
22
|
30
|
15
|
19
|
3.309
|
1.635
|
0.191
|
0.441
|
Edu_cat
|
high
|
10
|
14
|
15
|
16
|
3.309
|
1.635
|
0.191
|
0.441
|
Edu_cat
|
low
|
|
3
|
1
|
2
|
3.309
|
1.635
|
0.191
|
0.441
|
ADHD
|
ADHD
|
4
|
12
|
4
|
|
0.000
|
9.035
|
1.000
|
0.003
|
ADHD
|
no-ADHD
|
28
|
35
|
27
|
37
|
0.000
|
9.035
|
1.000
|
0.003
|
Psych
|
no
|
26
|
39
|
27
|
37
|
0.084
|
5.126
|
0.772
|
0.024
|
Psych
|
yes
|
6
|
8
|
4
|
|
0.084
|
5.126
|
0.772
|
0.024
|
Psych_past
|
no
|
17
|
34
|
28
|
34
|
8.931
|
3.943
|
0.003
|
0.047
|
Psych_past
|
yes
|
15
|
13
|
3
|
3
|
8.931
|
3.943
|
0.003
|
0.047
|
Neuro
|
no
|
28
|
42
|
31
|
34
|
2.303
|
0.000
|
0.129
|
0.986
|
Neuro
|
yes
|
4
|
5
|
|
3
|
2.303
|
0.000
|
0.129
|
0.986
|
Drugs
|
no
|
31
|
47
|
31
|
36
|
0.000
|
0.015
|
1.000
|
0.904
|
Drugs
|
yes
|
1
|
|
|
1
|
0.000
|
0.015
|
1.000
|
0.904
|
Alcohol
|
no
|
31
|
34
|
24
|
25
|
3.765
|
0.055
|
0.052
|
0.814
|
Alcohol
|
yes
|
1
|
13
|
7
|
12
|
3.765
|
0.055
|
0.052
|
0.814
|
nvarsVPT <- c("Gender_bio","Edu_cat", "ADHD", "Psych", "Psych_past", "Neuro", "Alcohol")
get_N(subset(Total_df, Exclusion_VPT == 0), nvarsVPT, title= "N demographics VPT sample")
N demographics VPT sample
Var
|
category
|
yng_aut
|
old_aut
|
yng_naut
|
old_naut
|
Chi_yng
|
Chi_old
|
p_yng
|
p_old
|
Gender_bio
|
man
|
6
|
26
|
10
|
20
|
0.517
|
1.602
|
0.472
|
0.449
|
Gender_bio
|
woman
|
21
|
12
|
19
|
14
|
0.517
|
1.602
|
0.472
|
0.449
|
Gender_bio
|
other
|
|
1
|
|
|
0.517
|
1.602
|
0.472
|
0.449
|
Edu_cat
|
middle
|
18
|
25
|
13
|
16
|
3.239
|
2.772
|
0.198
|
0.250
|
Edu_cat
|
high
|
9
|
11
|
15
|
16
|
3.239
|
2.772
|
0.198
|
0.250
|
Edu_cat
|
low
|
|
3
|
1
|
2
|
3.239
|
2.772
|
0.198
|
0.250
|
ADHD
|
ADHD
|
3
|
12
|
4
|
|
0.000
|
10.380
|
1.000
|
0.001
|
ADHD
|
no-ADHD
|
24
|
27
|
25
|
34
|
0.000
|
10.380
|
1.000
|
0.001
|
Psych
|
no
|
22
|
34
|
25
|
34
|
0.014
|
2.886
|
0.907
|
0.089
|
Psych
|
yes
|
5
|
5
|
4
|
|
0.014
|
2.886
|
0.907
|
0.089
|
Psych_past
|
no
|
14
|
29
|
26
|
31
|
8.026
|
2.455
|
0.005
|
0.117
|
Psych_past
|
yes
|
13
|
10
|
3
|
3
|
8.026
|
2.455
|
0.005
|
0.117
|
Neuro
|
no
|
23
|
35
|
29
|
31
|
2.663
|
0.000
|
0.103
|
1.000
|
Neuro
|
yes
|
4
|
4
|
|
3
|
2.663
|
0.000
|
0.103
|
1.000
|
Alcohol
|
no
|
26
|
27
|
22
|
23
|
3.245
|
0.000
|
0.072
|
1.000
|
Alcohol
|
yes
|
1
|
12
|
7
|
11
|
3.245
|
0.000
|
0.072
|
1.000
|
get_N(subset(Total_df, Exclusion_JND == 0), c("Gender_bio"), title= "N (sex) JND sample")
N (sex) JND sample
Var
|
category
|
yng_aut
|
old_aut
|
yng_naut
|
old_naut
|
Chi_yng
|
Chi_old
|
p_yng
|
p_old
|
Gender_bio
|
man
|
5
|
25
|
10
|
20
|
0.935
|
2.167
|
0.334
|
0.338
|
Gender_bio
|
woman
|
22
|
10
|
20
|
14
|
0.935
|
2.167
|
0.334
|
0.338
|
Gender_bio
|
other
|
|
1
|
|
|
0.935
|
2.167
|
0.334
|
0.338
|
get_chi_agg <- function(data, var, title){
Chi <- list()
for (i in 1:length(var)){
var1 = sym(var[i])
Chidf <- data %>%
summarise(Chi_autism = chisq.test(Autism,!!var1)$statistic,
p_autism = chisq.test(Autism,!!var1)$p.value,
Chi_age = chisq.test(Age_cat,!!var1)$statistic,
p_age = chisq.test(Age_cat,!!var1)$p.value) %>%
mutate_if(is.numeric, round, 3) %>%
pivot_longer(everything(),names_to = c("statistic", "predictor"), names_pattern = "(.*)_(.*)")
Chidf$outcome <- var[i]
Chi[[i]] <- Chidf
}
finalchi <- do.call(rbind, Chi)
return(kbl(finalchi, caption=paste0(title), digits = 3,booktabs = TRUE) %>%
kable_classic(full_width = F, font_size = 11) %>%
kable_styling(latex_options = "HOLD_position"))
}
get_chi_agg(Total_df, nvars, title="main effects demographics")
main effects demographics
statistic
|
predictor
|
value
|
outcome
|
Chi
|
autism
|
1.126
|
Gender_bio
|
p
|
autism
|
0.569
|
Gender_bio
|
Chi
|
age
|
14.463
|
Gender_bio
|
p
|
age
|
0.001
|
Gender_bio
|
Chi
|
autism
|
3.857
|
Edu_cat
|
p
|
autism
|
0.145
|
Edu_cat
|
Chi
|
age
|
1.833
|
Edu_cat
|
p
|
age
|
0.400
|
Edu_cat
|
Chi
|
autism
|
5.256
|
ADHD
|
p
|
autism
|
0.022
|
ADHD
|
Chi
|
age
|
0.001
|
ADHD
|
p
|
age
|
0.972
|
ADHD
|
Chi
|
autism
|
3.729
|
Psych
|
p
|
autism
|
0.053
|
Psych
|
Chi
|
age
|
0.824
|
Psych
|
p
|
age
|
0.364
|
Psych
|
Chi
|
autism
|
13.106
|
Psych_past
|
p
|
autism
|
0.000
|
Psych_past
|
Chi
|
age
|
1.340
|
Psych_past
|
p
|
age
|
0.247
|
Psych_past
|
Chi
|
autism
|
1.535
|
Neuro
|
p
|
autism
|
0.215
|
Neuro
|
Chi
|
age
|
0.153
|
Neuro
|
p
|
age
|
0.696
|
Neuro
|
Chi
|
autism
|
0.000
|
Drugs
|
p
|
autism
|
1.000
|
Drugs
|
Chi
|
age
|
0.000
|
Drugs
|
p
|
age
|
1.000
|
Drugs
|
Chi
|
autism
|
1.645
|
Alcohol
|
p
|
autism
|
0.200
|
Alcohol
|
Chi
|
age
|
5.081
|
Alcohol
|
p
|
age
|
0.024
|
Alcohol
|
get_chi_agg(subset(Total_df, Exclusion_VPT == 0), nvarsVPT, title= "main effects demographics VPT sample")
main effects demographics VPT sample
statistic
|
predictor
|
value
|
outcome
|
Chi
|
autism
|
0.995
|
Gender_bio
|
p
|
autism
|
0.608
|
Gender_bio
|
Chi
|
age
|
16.533
|
Gender_bio
|
p
|
age
|
0.000
|
Gender_bio
|
Chi
|
autism
|
5.028
|
Edu_cat
|
p
|
autism
|
0.081
|
Edu_cat
|
Chi
|
age
|
2.027
|
Edu_cat
|
p
|
age
|
0.363
|
Edu_cat
|
Chi
|
autism
|
5.642
|
ADHD
|
p
|
autism
|
0.018
|
ADHD
|
Chi
|
age
|
0.141
|
ADHD
|
p
|
age
|
0.708
|
ADHD
|
Chi
|
autism
|
1.752
|
Psych
|
p
|
autism
|
0.186
|
Psych
|
Chi
|
age
|
1.914
|
Psych
|
p
|
age
|
0.167
|
Psych
|
Chi
|
autism
|
10.453
|
Psych_past
|
p
|
autism
|
0.001
|
Psych_past
|
Chi
|
age
|
1.534
|
Psych_past
|
p
|
age
|
0.215
|
Psych_past
|
Chi
|
autism
|
1.394
|
Neuro
|
p
|
autism
|
0.238
|
Neuro
|
Chi
|
age
|
0.031
|
Neuro
|
p
|
age
|
0.861
|
Neuro
|
Chi
|
autism
|
0.947
|
Alcohol
|
p
|
autism
|
0.331
|
Alcohol
|
Chi
|
age
|
4.248
|
Alcohol
|
p
|
age
|
0.039
|
Alcohol
|
Descriptives <- c("Age_test", "AQ_10_sum", "Sleep_qual_1", "Sleep_quant")
Describe_long <- Total_df %>%
pivot_longer(cols = all_of(Descriptives), names_to ="var", values_to = "value")
get_ss_df = function (data,title) {
ss_df <- data %>%
group_by(var, Age_cat, Autism)%>%
summarise(mean = round(mean(value, na.rm=TRUE),2),
sd = round(sd(value, na.rm=TRUE),2),
min = round(min(value, na.rm=TRUE),2),
max = round(max(value, na.rm=TRUE),2),
final = paste0(mean, ",", sd, "(", min, "-", max, ")")) %>%
pivot_wider(names_from = c(Autism, Age_cat), values_from = c(mean, sd, min,max, final))
ss_df <- ss_df[,c(1,(length(ss_df)-3):length(ss_df))]
tval <- data %>%
group_by(var, Age_cat) %>%
summarise(tval = t.test(value[Autism=="aut"], value[Autism=="naut"])$statistic,
pval = t.test(value[Autism=="aut"], value[Autism=="naut"])$p.value,
n1 = sum(Autism=="aut"),
n2 = sum(Autism=="naut"),
dval = cohen.d(value[Autism=="aut"], value[Autism=="naut"], na.rm=TRUE)$estimate,
BF = exp(ttest.tstat(t = tval, n1 = n1, n2=n2, rscale = 0.707)$bf)) %>%
select(!c(n1,n2)) %>%
mutate_if(is.numeric, round, 3) %>%
pivot_wider(names_from = Age_cat,values_from = c(tval, pval, dval, BF))
ss_df <- merge(ss_df, tval, by = "var")
ss_df <- ss_df %>% relocate(c(tval_yng, pval_yng, dval_yng, BF_yng), .after=`final_naut_yng`)
names(ss_df) <- sub('final_', '', names(ss_df))
return(kbl(ss_df, caption = paste0(title), digits = 3, booktabs = TRUE, row.names=FALSE)
%>% kable_classic(full_width = F, font_size = 13) %>%
kable_styling(latex_options = "HOLD_position"))
}
get_ss_df(Describe_long, "Descriptives per group")
Descriptives per group
var
|
aut_yng
|
naut_yng
|
tval_yng
|
pval_yng
|
dval_yng
|
BF_yng
|
aut_old
|
naut_old
|
tval_old
|
pval_old
|
dval_old
|
BF_old
|
Age_test
|
36.63,3.69(24.25-40.82)
|
32.45,4.57(25.06-40.6)
|
3.987
|
0.000
|
1.008
|
1.325810e+02
|
71.83,4.67(65.19-82.23)
|
73.69,5.07(65.13-87.75)
|
-1.736
|
0.087
|
-0.385
|
8.430000e-01
|
AQ_10_sum
|
6.84,1.95(1-9)
|
2.52,1.79(0-6)
|
9.182
|
0.000
|
2.311
|
1.231554e+10
|
7,1.98(2-10)
|
2.32,1.62(0-6)
|
11.850
|
0.000
|
2.560
|
1.694087e+16
|
Sleep_qual_1
|
5.22,2.6(0-10)
|
6.32,1.89(3-10)
|
-1.933
|
0.058
|
-0.485
|
1.221000e+00
|
6.61,2.14(0-10)
|
7.03,1.62(3-10)
|
-1.011
|
0.315
|
-0.217
|
3.570000e-01
|
Sleep_quant
|
7.03,2.19(1-10)
|
6.84,1.04(5-9)
|
0.448
|
0.656
|
0.112
|
2.800000e-01
|
7.07,1.68(2-10)
|
7.11,1.02(5-10)
|
-0.137
|
0.891
|
-0.029
|
2.310000e-01
|
get_ss_df(subset(Describe_long, Exclusion_VPT==0), "Descriptives per group VPT sample")
Descriptives per group VPT sample
var
|
aut_yng
|
naut_yng
|
tval_yng
|
pval_yng
|
dval_yng
|
BF_yng
|
aut_old
|
naut_old
|
tval_old
|
pval_old
|
dval_old
|
BF_old
|
Age_test
|
36.99,3.06(28.87-40.82)
|
32.66,4.59(25.06-40.6)
|
4.175
|
0.000
|
1.101
|
2.048990e+02
|
71.72,4.77(65.19-82.23)
|
73.96,5.12(65.13-87.75)
|
-1.924
|
0.059
|
-0.454
|
1.1660e+00
|
AQ_10_sum
|
6.74,1.99(1-9)
|
2.48,1.82(0-6)
|
8.322
|
0.000
|
2.233
|
2.087548e+08
|
7.26,1.95(2-10)
|
2.24,1.63(0-6)
|
11.881
|
0.000
|
2.777
|
2.1491e+15
|
Sleep_qual_1
|
5.07,2.56(0-8)
|
6.34,1.88(3-10)
|
-2.108
|
0.040
|
-0.570
|
1.659000e+00
|
6.39,2.3(0-10)
|
7.24,1.5(3-10)
|
-1.857
|
0.068
|
-0.429
|
1.0500e+00
|
Sleep_quant
|
7.15,2.13(1-10)
|
6.86,0.99(5-9)
|
0.638
|
0.527
|
0.175
|
3.200000e-01
|
6.89,1.74(2-10)
|
7.18,1(5-10)
|
-0.854
|
0.396
|
-0.196
|
3.3100e-01
|
### anova function
get_anova_df <- function(Data, Variables, Title){
AOV_sum_list <- list()
for (i in 1:length(Variables)){
Describe_temp <- Data[Data['var']==Variables[i],]
AOV_descr <- aov(value ~ Age_cat*Autism, data=Describe_temp)
AOV_sum <- data.frame(matrix(ncol = 0, nrow = 3))
rownames(AOV_sum) <- c("Age_cat", "Autism", "Age_cat*Autism")
AOV_sum$Fval <- summary(AOV_descr)[[1]][["F value"]][1:3]
AOV_sum$Pval <- summary(AOV_descr)[[1]][["Pr(>F)"]][1:3]
AOV_sum$Eta <- (summary(AOV_descr)[[1]][["Sum Sq"]]/sum(summary(AOV_descr)[[1]][["Sum Sq"]]))[1:3]
AOV_sum <- round(AOV_sum,3)
Predictors <- rownames(AOV_sum)
AOV_sum <- cbind(Predictors, AOV_sum)
Outcome <- Variables[i] #AOV_sum <- AOV_sum %>% pivot_wider(names_from ="Predictors", values_from = c(Fval, Pval, Eta))
AOV_sum <- cbind(Outcome, AOV_sum)
AOV_sum_list[[i]] <- AOV_sum
}
Anovas <- do.call(rbind, AOV_sum_list)
return(kbl(Anovas, caption = paste0(Title), digits = 3, booktabs = TRUE, row.names=FALSE) %>% kable_classic(full_width = F, font_size = 13) %>%
kable_styling(latex_options = "HOLD_position"))
}
get_anova_df(Describe_long, Descriptives, "Anova Descriptives")
Anova Descriptives
Outcome
|
Predictors
|
Fval
|
Pval
|
Eta
|
Age_test
|
Age_cat
|
2507.117
|
0.000
|
0.940
|
Age_test
|
Autism
|
0.973
|
0.326
|
0.000
|
Age_test
|
Age_cat*Autism
|
15.721
|
0.000
|
0.006
|
AQ_10_sum
|
Age_cat
|
0.426
|
0.515
|
0.001
|
AQ_10_sum
|
Autism
|
217.698
|
0.000
|
0.604
|
AQ_10_sum
|
Age_cat*Autism
|
0.317
|
0.575
|
0.001
|
Sleep_qual_1
|
Age_cat
|
8.784
|
0.004
|
0.056
|
Sleep_qual_1
|
Autism
|
4.270
|
0.041
|
0.027
|
Sleep_qual_1
|
Age_cat*Autism
|
0.961
|
0.328
|
0.006
|
Sleep_quant
|
Age_cat
|
0.324
|
0.570
|
0.002
|
Sleep_quant
|
Autism
|
0.055
|
0.816
|
0.000
|
Sleep_quant
|
Age_cat*Autism
|
0.199
|
0.656
|
0.001
|
get_anova_df(subset(Describe_long, Exclusion_VPT ==0), Descriptives, "Anova Descriptives VPT sample")
Anova Descriptives VPT sample
Outcome
|
Predictors
|
Fval
|
Pval
|
Eta
|
Age_test
|
Age_cat
|
2236.429
|
0.000
|
0.940
|
Age_test
|
Autism
|
0.594
|
0.442
|
0.000
|
Age_test
|
Age_cat*Autism
|
16.601
|
0.000
|
0.007
|
AQ_10_sum
|
Age_cat
|
1.144
|
0.287
|
0.003
|
AQ_10_sum
|
Autism
|
204.517
|
0.000
|
0.618
|
AQ_10_sum
|
Age_cat*Autism
|
1.356
|
0.246
|
0.004
|
Sleep_qual_1
|
Age_cat
|
8.156
|
0.005
|
0.058
|
Sleep_qual_1
|
Autism
|
7.797
|
0.006
|
0.056
|
Sleep_qual_1
|
Age_cat*Autism
|
0.335
|
0.564
|
0.002
|
Sleep_quant
|
Age_cat
|
0.010
|
0.919
|
0.000
|
Sleep_quant
|
Autism
|
0.015
|
0.903
|
0.000
|
Sleep_quant
|
Age_cat*Autism
|
1.086
|
0.299
|
0.009
|
MMQ
Descriptives and analyses for MMQ are provided below. Including
figures.
### some figures and prelim analyses MMQ
MMQVars <- c("MMQCon_sum", "MMQAb_sum", "MMQStrat_sum")
MMQ_long <- Total_df %>%
pivot_longer(cols = all_of(MMQVars), names_to ="var", values_to = "value")
get_ss_df(MMQ_long, "MMQ per group")
MMQ per group
var
|
aut_yng
|
naut_yng
|
tval_yng
|
pval_yng
|
dval_yng
|
BF_yng
|
aut_old
|
naut_old
|
tval_old
|
pval_old
|
dval_old
|
BF_old
|
MMQAb_sum
|
55.22,12.67(30-78)
|
64.1,8.14(37-74)
|
-3.320
|
0.002
|
-0.831
|
21.685
|
56.3,13(12-73)
|
63.49,7.57(43-76)
|
-3.142
|
0.002
|
-0.657
|
14.720
|
MMQCon_sum
|
48.19,13.16(23-69)
|
55.65,9.31(34-71)
|
-2.603
|
0.012
|
-0.653
|
4.162
|
44.04,15.02(9-72)
|
52.73,9.54(32-72)
|
-3.202
|
0.002
|
-0.675
|
17.190
|
MMQStrat_sum
|
27.47,12.37(6-66)
|
24.58,9.66(7-45)
|
1.034
|
0.305
|
0.260
|
0.404
|
24.04,10.39(6-47)
|
19.41,7.14(7-34)
|
2.404
|
0.019
|
0.510
|
2.721
|
get_anova_df(MMQ_long, MMQVars, "Anova MMQ")
Anova MMQ
Outcome
|
Predictors
|
Fval
|
Pval
|
Eta
|
MMQCon_sum
|
Age_cat
|
3.694
|
0.057
|
0.023
|
MMQCon_sum
|
Autism
|
15.996
|
0.000
|
0.099
|
MMQCon_sum
|
Age_cat*Autism
|
0.089
|
0.766
|
0.001
|
MMQAb_sum
|
Age_cat
|
0.002
|
0.964
|
0.000
|
MMQAb_sum
|
Autism
|
19.402
|
0.000
|
0.120
|
MMQAb_sum
|
Age_cat*Autism
|
0.219
|
0.641
|
0.001
|
MMQStrat_sum
|
Age_cat
|
5.923
|
0.016
|
0.039
|
MMQStrat_sum
|
Autism
|
5.439
|
0.021
|
0.035
|
MMQStrat_sum
|
Age_cat*Autism
|
0.272
|
0.603
|
0.002
|
# and for only those with VPT data:
get_ss_df(subset(MMQ_long, Exclusion_VPT==0), "MMQ VPT sample per group")
MMQ VPT sample per group
var
|
aut_yng
|
naut_yng
|
tval_yng
|
pval_yng
|
dval_yng
|
BF_yng
|
aut_old
|
naut_old
|
tval_old
|
pval_old
|
dval_old
|
BF_old
|
MMQAb_sum
|
57.19,11.33(35-78)
|
65.1,6.6(51-74)
|
-3.166
|
0.003
|
-0.862
|
14.332
|
55.89,13.38(12-73)
|
63.68,7.53(43-76)
|
-3.081
|
0.003
|
-0.706
|
12.401
|
MMQCon_sum
|
50.48,12.35(23-69)
|
56.34,9.2(34-71)
|
-2.004
|
0.051
|
-0.541
|
1.397
|
43,14.82(9-72)
|
52.62,9.54(32-72)
|
-3.308
|
0.002
|
-0.763
|
21.993
|
MMQStrat_sum
|
25,9.98(6-47)
|
24.48,9.93(7-45)
|
0.194
|
0.847
|
0.052
|
0.274
|
25.05,10.72(6-47)
|
19.24,6.92(7-34)
|
2.762
|
0.007
|
0.637
|
5.873
|
get_anova_df(subset(MMQ_long, Exclusion_VPT==0), MMQVars, "Anova MMQ VPT sample")
Anova MMQ VPT sample
Outcome
|
Predictors
|
Fval
|
Pval
|
Eta
|
MMQCon_sum
|
Age_cat
|
7.992
|
0.005
|
0.054
|
MMQCon_sum
|
Autism
|
14.419
|
0.000
|
0.098
|
MMQCon_sum
|
Age_cat*Autism
|
0.787
|
0.377
|
0.005
|
MMQAb_sum
|
Age_cat
|
0.882
|
0.350
|
0.006
|
MMQAb_sum
|
Autism
|
18.651
|
0.000
|
0.130
|
MMQAb_sum
|
Age_cat*Autism
|
0.001
|
0.970
|
0.000
|
MMQStrat_sum
|
Age_cat
|
2.056
|
0.154
|
0.015
|
MMQStrat_sum
|
Autism
|
4.325
|
0.040
|
0.033
|
MMQStrat_sum
|
Age_cat*Autism
|
2.446
|
0.120
|
0.018
|
plotting <- function(data, y,lims,ylab,title){
plotting <- ggplot(data, aes(x=Groups, y=y))+
stat_boxplot(geom = "errorbar", width = 0.05) +
geom_boxplot(size=.75, width=.3, outlier.alpha = 0)+
geom_beeswarm(cex = 1.2, size=1,alpha=.6, aes(color=Groups))+
stat_summary(fun=mean, aes(group=1), size=2, geom="point", color="darkgrey", alpha=.7) +
scale_color_manual(name="Groups",values = c("#059D05", "#07D607",
"#9933FF", "#BF80FF"))+
theme_classic(base_size = 7)+
coord_cartesian(ylim = lims)+
scale_x_discrete(labels = c("aut_old" = "AutOld",
"aut_yng" = "AutYoung",
"naut_old" = "nAutOld",
"naut_yng" = "nAutYoung"))+
ylab(paste0(ylab))+
xlab("")+
theme(text=element_text(family="sans", size=12))+
ggtitle(" ")+
theme(legend.position = "bottom",legend.justification = "bottom", legend.title = element_blank())
ggsave(filename=paste0(title), plot = plotting, device = NULL, path = NULL,
scale = 1, units = c("in"), width=5, height =6, dpi = 600, limitsize = TRUE)
plotting
}
plotting(Total_df, y=Total_df$MMQCon_sum,lims = c(0,72),ylab="MMQ Contentment", title="MMQ_contentment.png")

plotting(Total_df, y=Total_df$MMQAb_sum,lims = c(0,80),ylab="MMQ Ability", title="MMQ_ability.png")

plotting(Total_df, y=Total_df$MMQStrat_sum,lims = c(0,76),ylab="MMQ Strategies", title="MMQ_strategy.png")

# only vpt
plotting(subset(Total_df, Exclusion_VPT ==0), y=subset(Total_df, Exclusion_VPT ==0)$MMQStrat_sum,lims = c(0,76),ylab="MMQ Strategies", title="MMQ_strategy_VPTSample.png")
## VPT
Descriptives and analyses for VPT are provided below. Including
figures. New functions are needed due to the extra “within” level for
these data. Motivation stats/checks can be done using generic
functions.
VPT_long_df <- subset(VPT_long_df, Exclusion_VPT==0)
VPT_vars <- c("VPT_span_traditional", "VPT_span_traditional_mean", "VPT_acc_wo", "VPT_mrt_cor_wo")
VPT_analyses_df <- VPT_long_df %>%
pivot_longer(cols = all_of(VPT_vars), names_to ="vars", values_to = "value")
get_vpt_descriptives <- function(data, title) {
VPT_df <- data %>%
group_by(vars,type, Age_cat, Autism)%>%
summarise(mean = round(mean(value, na.rm=TRUE),2),
sd = round(sd(value, na.rm=TRUE),2),
min = round(min(value, na.rm=TRUE),2),
max = round(max(value, na.rm=TRUE),2),
final = paste0(mean, ",", sd, "(", min, "-", max, ")")) %>%
pivot_wider(names_from = type, values_from = c(mean, sd, min,max, final))
VPT_df <- VPT_df[,c(1:3,(length(VPT_df)-1):length(VPT_df))]
Pairs_tot <- VPT_analyses_df %>%
group_by(vars, Autism, Age_cat) %>%
summarise(tval = t.test(value[type=="high"], value[type=="low"], paired=TRUE)$statistic,
pval = t.test(value[type=="high"], value[type=="low"], paired=TRUE)$p.value,
dval = cohen.d(value[type=="high"], value[type=="low"], na.rm=TRUE, paired=TRUE)$estimate,
n1 = n()/2,
BF = exp(ttest.tstat(t = tval, n1 = n1, rscale = 0.707)$bf)) %>%
select(!n1) %>%
mutate_if(is.numeric, round, 3)
VPT_df <- merge(VPT_df, Pairs_tot, by = c("vars","Age_cat", "Autism"))
names(VPT_df) <- sub('final_', '', names(VPT_df))
return(kbl(VPT_df, caption = paste0(title), digits = 3, booktabs = TRUE, row.names=FALSE)%>% kable_classic(full_width = F, font_size = 13) %>%
kable_styling(latex_options = "HOLD_position"))
}
get_anova_VPT <- function (data){
AOV_VPT_three = get_anova_table(anova_test(data = data, dv = value, wid = ppn, between = c(Autism, Age_cat), within = type),
correction="auto")
AOV_VPT_three = AOV_VPT_three[AOV_VPT_three$Effect == "Autism:Age_cat:type",]
AOV_VPT_btw = get_anova_table(anova_test(data = data, dv = value, between = c(Autism, Age_cat)))
AOV_VPT_btw = AOV_VPT_btw[AOV_VPT_btw$Effect == "Autism:Age_cat",]
AOV_VPT_wth1 = get_anova_table(anova_test(data = data, dv = value, wid = ppn, between = c(Age_cat), within = type),
correction="auto")
AOV_VPT_wth1 = AOV_VPT_wth1[AOV_VPT_wth1$Effect == "Age_cat:type",]
AOV_VPT_wth2 = get_anova_table(anova_test(data = data, dv = value, wid = ppn, between = c(Autism), within = type),
correction="auto")
AOV_VPT_wth2 = AOV_VPT_wth2[AOV_VPT_wth2$Effect == "Autism:type",]
AOV_tot = rbind(AOV_VPT_three, AOV_VPT_btw, AOV_VPT_wth1, AOV_VPT_wth2)
AOV_VPT_Aut = get_anova_table(anova_test(data = data, dv = value, between = Autism))
AOV_VPT_Aut = AOV_VPT_Aut[AOV_VPT_Aut$Effect == "Autism",]
AOV_VPT_Age = get_anova_table(anova_test(data = data, dv = value, between = Age_cat))
AOV_VPT_Age = AOV_VPT_Age[AOV_VPT_Age$Effect == "Age_cat",]
AOV_VPT_type = get_anova_table(anova_test(data = data, dv = value, within = type, wid=ppn))
AOV_VPT_type = AOV_VPT_type[AOV_VPT_type$Effect == "type",]
AOV_tot = rbind(AOV_tot, AOV_VPT_Aut, AOV_VPT_Age, AOV_VPT_type)
}
get_vpt_descriptives(VPT_analyses_df, "VPT differences high/low per group")
VPT differences high/low per group
vars
|
Age_cat
|
Autism
|
high
|
low
|
tval
|
pval
|
dval
|
BF
|
VPT_acc_wo
|
old
|
aut
|
0.74,0.12(0.52-0.95)
|
0.69,0.11(0.41-0.86)
|
2.669
|
0.011
|
0.471
|
3.754
|
VPT_acc_wo
|
old
|
naut
|
0.73,0.1(0.5-0.91)
|
0.68,0.09(0.5-0.86)
|
2.593
|
0.014
|
0.493
|
3.233
|
VPT_acc_wo
|
yng
|
aut
|
0.78,0.1(0.57-0.95)
|
0.72,0.13(0.38-0.91)
|
2.527
|
0.018
|
0.498
|
2.863
|
VPT_acc_wo
|
yng
|
naut
|
0.77,0.09(0.59-0.95)
|
0.76,0.12(0.5-1)
|
0.463
|
0.647
|
0.116
|
0.218
|
VPT_mrt_cor_wo
|
old
|
aut
|
3326.61,869.02(1776.74-5708.74)
|
3640.6,934.69(2086.05-6257.5)
|
-3.906
|
0.000
|
-0.345
|
74.444
|
VPT_mrt_cor_wo
|
old
|
naut
|
3050.84,780.79(1994.45-5763.42)
|
3481.81,1195.85(2004.57-8219.81)
|
-3.083
|
0.004
|
-0.384
|
9.247
|
VPT_mrt_cor_wo
|
yng
|
aut
|
2938.73,821.3(1875.02-4687.39)
|
3285.52,1046.41(1805.78-5525.51)
|
-2.714
|
0.012
|
-0.352
|
4.099
|
VPT_mrt_cor_wo
|
yng
|
naut
|
2887.9,692.5(1760.21-4712.96)
|
3243.48,879.94(2181.65-5484.79)
|
-2.870
|
0.008
|
-0.437
|
5.670
|
VPT_span_traditional
|
old
|
aut
|
12.44,3.09(6-15)
|
11.16,3.03(6-15)
|
2.266
|
0.029
|
0.448
|
1.671
|
VPT_span_traditional
|
old
|
naut
|
12.55,2.72(7-15)
|
10.32,2.74(6-15)
|
3.384
|
0.002
|
0.795
|
18.553
|
VPT_span_traditional
|
yng
|
aut
|
12.96,2.62(7-15)
|
11.85,2.97(7-15)
|
1.938
|
0.064
|
0.395
|
1.032
|
VPT_span_traditional
|
yng
|
naut
|
13.21,2.38(7-15)
|
12.45,3.12(7-15)
|
0.933
|
0.359
|
0.274
|
0.294
|
VPT_span_traditional_mean
|
old
|
aut
|
11.41,3.28(5.33-14.67)
|
9.99,3.1(5.33-14.67)
|
2.365
|
0.024
|
0.512
|
2.021
|
VPT_span_traditional_mean
|
old
|
naut
|
11.3,2.96(5.33-14.67)
|
9,2.87(5.33-14.67)
|
3.235
|
0.003
|
0.760
|
13.090
|
VPT_span_traditional_mean
|
yng
|
aut
|
11.83,3(5.33-14.67)
|
10.56,3.19(5.33-14.67)
|
2.013
|
0.055
|
0.410
|
1.163
|
VPT_span_traditional_mean
|
yng
|
naut
|
12.01,2.63(5.67-14.67)
|
11.39,3.42(5.67-14.67)
|
0.707
|
0.486
|
0.204
|
0.248
|
ANOVA_vpt <- VPT_analyses_df %>% group_by(vars) %>% do(data.frame(val=get_anova_VPT(.)))
kbl(ANOVA_vpt, caption = "VPT ANOVAs", digits = 3, booktabs = TRUE, row.names=FALSE )%>%
kable_classic(full_width = F, font_size = 13) %>% kable_styling(latex_options = "HOLD_position")
VPT ANOVAs
vars
|
val.Effect
|
val.DFn
|
val.DFd
|
val.F
|
val.p
|
val.p..05
|
val.ges
|
VPT_acc_wo
|
Autism:Age_cat:type
|
1
|
125
|
0.833
|
0.363
|
|
0.002
|
VPT_acc_wo
|
Autism:Age_cat
|
1
|
254
|
0.859
|
0.355
|
|
0.003
|
VPT_acc_wo
|
Age_cat:type
|
1
|
127
|
0.500
|
0.481
|
|
0.001
|
VPT_acc_wo
|
Autism:type
|
1
|
127
|
1.279
|
0.260
|
|
0.003
|
VPT_acc_wo
|
Autism
|
1
|
256
|
0.056
|
0.813
|
|
0.000
|
VPT_acc_wo
|
Age_cat
|
1
|
256
|
11.827
|
0.001
|
|
0.044
|
VPT_acc_wo
|
type
|
1
|
128
|
16.043
|
0.000
|
|
0.038
|
VPT_mrt_cor_wo
|
Autism:Age_cat:type
|
1
|
125
|
0.209
|
0.649
|
|
0.000
|
VPT_mrt_cor_wo
|
Autism:Age_cat
|
1
|
254
|
0.535
|
0.465
|
|
0.002
|
VPT_mrt_cor_wo
|
Age_cat:type
|
1
|
127
|
0.021
|
0.884
|
|
0.000
|
VPT_mrt_cor_wo
|
Autism:type
|
1
|
127
|
0.350
|
0.555
|
|
0.000
|
VPT_mrt_cor_wo
|
Autism
|
1
|
256
|
1.827
|
0.178
|
|
0.007
|
VPT_mrt_cor_wo
|
Age_cat
|
1
|
256
|
6.371
|
0.012
|
|
0.024
|
VPT_mrt_cor_wo
|
type
|
1
|
128
|
38.652
|
0.000
|
|
0.037
|
VPT_span_traditional
|
Autism:Age_cat:type
|
1
|
123
|
0.759
|
0.385
|
|
0.003
|
VPT_span_traditional
|
Autism:Age_cat
|
1
|
252
|
1.192
|
0.276
|
|
0.005
|
VPT_span_traditional
|
Age_cat:type
|
1
|
125
|
1.511
|
0.221
|
|
0.005
|
VPT_span_traditional
|
Autism:type
|
1
|
125
|
0.147
|
0.702
|
|
0.000
|
VPT_span_traditional
|
Autism
|
1
|
254
|
0.003
|
0.960
|
|
0.000
|
VPT_span_traditional
|
Age_cat
|
1
|
254
|
7.354
|
0.007
|
|
0.028
|
VPT_span_traditional
|
type
|
1
|
126
|
17.520
|
0.000
|
|
0.055
|
VPT_span_traditional_mean
|
Autism:Age_cat:type
|
1
|
120
|
0.776
|
0.380
|
|
0.003
|
VPT_span_traditional_mean
|
Autism:Age_cat
|
1
|
249
|
1.799
|
0.181
|
|
0.007
|
VPT_span_traditional_mean
|
Age_cat:type
|
1
|
122
|
1.804
|
0.182
|
|
0.006
|
VPT_span_traditional_mean
|
Autism:type
|
1
|
122
|
0.000
|
0.989
|
|
0.000
|
VPT_span_traditional_mean
|
Autism
|
1
|
251
|
0.008
|
0.929
|
|
0.000
|
VPT_span_traditional_mean
|
Age_cat
|
1
|
251
|
6.390
|
0.012
|
|
0.025
|
VPT_span_traditional_mean
|
type
|
1
|
123
|
16.383
|
0.000
|
|
0.054
|
VPT_analyses_df$var <- paste0(VPT_analyses_df$vars, "_", VPT_analyses_df$type)
get_ss_df(VPT_analyses_df, "VPT group differences AUT/NAUT")
VPT group differences AUT/NAUT
var
|
aut_yng
|
naut_yng
|
tval_yng
|
pval_yng
|
dval_yng
|
BF_yng
|
aut_old
|
naut_old
|
tval_old
|
pval_old
|
dval_old
|
BF_old
|
VPT_acc_wo_high
|
0.78,0.1(0.57-0.95)
|
0.77,0.09(0.59-0.95)
|
0.305
|
0.762
|
0.082
|
0.281
|
0.74,0.12(0.52-0.95)
|
0.73,0.1(0.5-0.91)
|
0.525
|
0.601
|
0.122
|
0.273
|
VPT_acc_wo_low
|
0.72,0.13(0.38-0.91)
|
0.76,0.12(0.5-1)
|
-1.158
|
0.252
|
-0.311
|
0.471
|
0.69,0.11(0.41-0.86)
|
0.68,0.09(0.5-0.86)
|
0.306
|
0.761
|
0.071
|
0.252
|
VPT_mrt_cor_wo_high
|
2938.73,821.3(1875.02-4687.39)
|
2887.9,692.5(1760.21-4712.96)
|
0.249
|
0.804
|
0.067
|
0.277
|
3326.61,869.02(1776.74-5708.74)
|
3050.84,780.79(1994.45-5763.42)
|
1.428
|
0.158
|
0.333
|
0.579
|
VPT_mrt_cor_wo_low
|
3285.52,1046.41(1805.78-5525.51)
|
3243.48,879.94(2181.65-5484.79)
|
0.162
|
0.872
|
0.044
|
0.273
|
3640.6,934.69(2086.05-6257.5)
|
3481.81,1195.85(2004.57-8219.81)
|
0.625
|
0.534
|
0.149
|
0.287
|
VPT_span_traditional_high
|
12.96,2.62(7-15)
|
13.21,2.38(7-15)
|
-0.363
|
0.718
|
-0.098
|
0.285
|
12.44,3.09(6-15)
|
12.55,2.72(7-15)
|
-0.160
|
0.873
|
-0.037
|
0.245
|
VPT_span_traditional_low
|
11.85,2.97(7-15)
|
12.45,3.12(7-15)
|
-0.732
|
0.467
|
-0.196
|
0.338
|
11.16,3.03(6-15)
|
10.32,2.74(6-15)
|
1.228
|
0.224
|
0.288
|
0.462
|
VPT_span_traditional_mean_high
|
11.83,3(5.33-14.67)
|
12.01,2.63(5.67-14.67)
|
-0.244
|
0.808
|
-0.065
|
0.277
|
11.41,3.28(5.33-14.67)
|
11.3,2.96(5.33-14.67)
|
0.147
|
0.883
|
0.035
|
0.244
|
VPT_span_traditional_mean_low
|
10.56,3.19(5.33-14.67)
|
11.39,3.42(5.67-14.67)
|
-0.945
|
0.349
|
-0.252
|
0.392
|
9.99,3.1(5.33-14.67)
|
9,2.87(5.33-14.67)
|
1.387
|
0.170
|
0.331
|
0.552
|
# in figures:
GroupNames <- c(
`aut_old` = "AutOld",
`aut_yng` = "AutYoung",
`naut_old` = "nAutOld",
`naut_yng` = "nAutYoung")
plot_agg <- function(y,lims,ylab,title){
plot_agg_wo <- ggplot(VPT_long_df, aes(x=type, y=y))+
stat_boxplot(geom = "errorbar", width = 0.05) +
geom_boxplot(size=.75, width=.3, outlier.alpha = 0)+
geom_beeswarm(cex = 1.2, size=1,alpha=.6, aes(color=type))+
geom_line(aes(group=ppn),alpha=.7, size=.1, color="grey")+
stat_summary(fun=mean, aes(group=1), size=1, geom="line", color="darkgrey", alpha=.7) +
stat_summary(fun=mean, aes(group=1), size=2, geom="point", color="darkgrey", alpha=.7) +
scale_color_manual(name="type",values = c("#059D05", "#9933FF"), labels=c("high","low"))+
theme_classic(base_size = 7)+
facet_wrap(~Groups, labeller=as_labeller(GroupNames))+
coord_cartesian(ylim = lims)+
ylab(paste0(ylab))+
theme(text=element_text(family="sans", size=12))+
ggtitle(" ")+
theme(legend.position = "bottom",legend.justification = "bottom", legend.title = element_blank())
ggsave(filename=paste0(title), plot = plot_agg_wo, device = NULL, path = NULL,
scale = 1, units = c("in"), width=5, height =6, dpi = 600, limitsize = TRUE)
plot_agg_wo
}
plot_agg(y=VPT_long_df$VPT_acc_wo,lims = c(0,1),ylab="accuracy", title="VPT_accuracy_pergroup.png")

plot_agg(y=VPT_long_df$VPT_span_traditional,lims = c(4,15),ylab="VPT span traditional", title="VPT_span_traditional_pergroup.png")

plot_agg(y=VPT_long_df$VPT_span_traditional_mean,lims = c(4,15),ylab="VPT mean span traditional", title="VPT_span_traditional_mean_pergroup.png")
