library(foreign)
library(psych)
library(ggplot2)
library(plyr)
library(car)
library(rms)


## Get Education
vpr1 <- read.spss("questionnaire part 1a.sav", to.data.frame=TRUE, use.value.labels = F)
izo <- vpr1[,"V02"]
izo2 <- as.numeric(levels(izo))[izo]
izo2[izo2<3|izo2>5] <- NA
izo2[izo2==5]<-0  # Tehniki
izo2[izo2==3|izo2==4]<-1 # Diplomirane MS

izo2 <- factor(izo2,labels=c("Low","High"))
newTab <- data.frame(Education = izo2)


## CARATIVE FACTORS
vpr2 <- read.spss("questionnaire part 2a.sav", to.data.frame=TRUE, use.value.labels = F)
vpr2 <- vpr2[,4:73]

sets2 <- list(c(1:6), c(7:13), c(14:19), c(20:26), c(27:32), c(33:38), c(39:47), c(48:54), c(55:64), c(65:70))

for(s in sets2) 
  newTab <- cbind(newTab,(apply(vpr2[,s], 1, mean)))

nameStrs <- c("Humanism", "Hope", "Sensibility", "HelpingRelationship", "ExpresionOfEmotions",
              "ProblemSolving", "Teaching", "Environment", "Needs", "Spirituality")

names(newTab)[2:11] <- nameStrs


newTab <- na.omit(newTab)

logitEdu <- glm(Education ~ ., data = newTab, family = "binomial")
summary(logitEdu)
vif(logitEdu)


# Multiple t-tests
pVals <- c()
for(i in 2:11) {
  res <- t.test(newTab[newTab$Education=="Low",i],newTab[newTab$Education=="High",i])
  pVals <- c(pVals, res$p.value)
  conf.int1 <- t.test(newTab[newTab$Education=="Low",i])$conf.int
}

p.adjust(pVals, method = "BH")







pdf("plotsPaper3_.pdf", width = 6, height = 3)


dev.off()