library(ordinal)

ratings = read.csv('Ratings_Exp3.csv',header=TRUE)

# Remove subject who had very low English proficiency according to Vernon-Warden test
ratings = ratings[ratings$Subject != 17,]

# Get condition means and by-subject SEs
means = data.frame(Aspect = c("Comprehensibility","Comprehensibility","Acceptability","Acceptability"),
                   Language = c("Dutch","English","Dutch","English"),
                   V0 = c(mean(ratings[ratings$Grammaticality=="gram" & ratings$Language=="nl",]$Comprehensibility,na.rm=TRUE),
                          mean(ratings[ratings$Grammaticality=="gram" & ratings$Language=="en",]$Comprehensibility,na.rm=TRUE),
                          mean(ratings[ratings$Grammaticality=="gram" & ratings$Language=="nl",]$Acceptability,na.rm=TRUE),
                          mean(ratings[ratings$Grammaticality=="gram" & ratings$Language=="en",]$Acceptability,na.rm=TRUE)),
                   V0 = c(mean(ratings[ratings$Grammaticality=="ungram" & ratings$Language=="nl",]$Comprehensibility,na.rm=TRUE),
                          mean(ratings[ratings$Grammaticality=="ungram" & ratings$Language=="en",]$Comprehensibility,na.rm=TRUE),
                          mean(ratings[ratings$Grammaticality=="ungram" & ratings$Language=="nl",]$Acceptability,na.rm=TRUE),
                          mean(ratings[ratings$Grammaticality=="ungram" & ratings$Language=="en",]$Acceptability,na.rm=TRUE)))

subj_id   = unique(ratings$Subject)
nr_subj   = length(subj_id)
subj_mean = matrix(nrow=8,ncol=nr_subj)
p = 1
for (s in subj_id) {
  subj_mean[1,p] = mean(ratings[ratings$Subject==s & ratings$Grammaticality=="gram" & ratings$Language=="nl",]$Comprehensibility,na.rm=TRUE)
  subj_mean[2,p] = mean(ratings[ratings$Subject==s & ratings$Grammaticality=="gram" & ratings$Language=="en",]$Comprehensibility,na.rm=TRUE)
  subj_mean[3,p] = mean(ratings[ratings$Subject==s & ratings$Grammaticality=="gram" & ratings$Language=="nl",]$Acceptability,na.rm=TRUE)
  subj_mean[4,p] = mean(ratings[ratings$Subject==s & ratings$Grammaticality=="gram" & ratings$Language=="en",]$Acceptability,na.rm=TRUE)
  subj_mean[5,p] = mean(ratings[ratings$Subject==s & ratings$Grammaticality=="ungram" & ratings$Language=="nl",]$Comprehensibility,na.rm=TRUE)
  subj_mean[6,p] = mean(ratings[ratings$Subject==s & ratings$Grammaticality=="ungram" & ratings$Language=="en",]$Comprehensibility,na.rm=TRUE)
  subj_mean[7,p] = mean(ratings[ratings$Subject==s & ratings$Grammaticality=="ungram" & ratings$Language=="nl",]$Acceptability,na.rm=TRUE)
  subj_mean[8,p] = mean(ratings[ratings$Subject==s & ratings$Grammaticality=="ungram" & ratings$Language=="en",]$Acceptability,na.rm=TRUE)
  p = p+1
}

SEs = data.frame(Aspect = c("Comprehensibility","Comprehensibility","Acceptability","Acceptability"),
                 Language = c("Dutch","English","Dutch","English"),
                 V0 = c(sd(subj_mean[1,])/sqrt(nr_subj),sd(subj_mean[2,])/sqrt(nr_subj),sd(subj_mean[3,])/sqrt(nr_subj),sd(subj_mean[4,])/sqrt(nr_subj)),
                 V2 = c(sd(subj_mean[5,])/sqrt(nr_subj),sd(subj_mean[6,])/sqrt(nr_subj),sd(subj_mean[7,])/sqrt(nr_subj),sd(subj_mean[8,])/sqrt(nr_subj)))

# Turn scores into ordinal variable
ratings$Acceptability     = ordered(ratings$Acceptability)
ratings$Comprehensibility = ordered(ratings$Comprehensibility)

# Turn subject and item numbers into factors
ratings$Subject = as.factor(ratings$Subject)
ratings$Item    = as.factor(ratings$Item)

# Run ordinal mixed-effects analyses with interaction between Grammaticality and Language
model_acceptability     = clmm(Acceptability     ~ Language*Grammaticality + (1+Language+Grammaticality|Subject) + (1+Language+Grammaticality|Item), data=ratings)
model_comprehensibility = clmm(Comprehensibility ~ Language*Grammaticality + (1+Language+Grammaticality|Subject) + (1+Language+Grammaticality|Item), data=ratings)

rm(ratings,subj_id,subj_mean,nr_subj,p,s)
save.image('Exp3.RData')