# data evaluation

# set working directory

# packages

library(desk)
library(car)
library(stargazer)
library(sandwich)
library(lmtest)
library(psych)

# data import

Daten2=read.csv(file="Daten12.02.2024.csv", sep=";",dec=".", header=T)

# only valid cases

Daten1<-subset(Daten2, LASTPAGE==39)

# at least 7 minutes

Daten=subset(Daten1, Daten1$A106_01==2)

# check for marketing, remove participants if necessary

table(Daten2$A101_17)
table(Daten1$A101_17)
table(Daten$A101_17)
which(Daten$A101_17 == 2)
Daten <- Daten[-65,]

# check for meat and dairy industry

table(Daten2$A101_07)
table(Daten1$A101_07)
table(Daten$A101_07)

table(Daten2$A102_01)
table(Daten2$A102_02)
table(Daten1$A102_01)
table(Daten1$A102_02)
table(Daten$A102_01)
table(Daten$A102_02)

# average time to complete questionnaire

mean(Daten$TIME_SUM)

#############################################

# occupational field

table(Daten$A101_01)
table(Daten$A101_02)
table(Daten$A101_03)
table(Daten$A101_04)
table(Daten$A101_05)
table(Daten$A101_06)
table(Daten$A101_07)
table(Daten$A101_08)
table(Daten$A101_09)
table(Daten$A101_10)
table(Daten$A101_11)
table(Daten$A101_12)
table(Daten$A101_13)
table(Daten$A101_14)
table(Daten$A101_15)
table(Daten$A101_16)
table(Daten$A101_17)
table(Daten$A101_18)
table(Daten$A101_18a)

# agriculture

table(Daten$A102_01)
table(Daten$A102_02)
table(Daten$A102_03)
table(Daten$A102_04)

# organic consumption

Daten$bio[Daten$A203>0 & Daten$A203 <=2]<-"rarely"
Daten$bio[Daten$A203>2 & Daten$A203 <=4]<-"regular"
Daten$bio[Daten$A203>4 & Daten$A203 <=6]<-"frequent"

table(Daten$bio)
table(Daten$A203)
barplot(table(Daten$bio))

# association goods

Daten$verband[Daten$A204_01<=2 & Daten$A204_01>=1] <- "low"
Daten$verband[Daten$A204_01==3] <- "medium"
Daten$verband[Daten$A204_01<=5 & Daten$A204_01>=4] <- "high"

mean(Daten$A204_01, na.rm=T)
sd(Daten$A204_01, na.rm=T)
table(Daten$verband)
barplot(table(Daten$verband))

# associations

Daten$verband1[Daten$A205_01==2] <- "Biokreis"
Daten$verband1[Daten$A205_02==2] <- "Bioland"
Daten$verband1[Daten$A205_03==2] <- "Biopark"
Daten$verband1[Daten$A205_04==2] <- "Biozyklisch-veganer Anbau"
Daten$verband1[Daten$A205_05==2] <- "Demeter"
Daten$verband1[Daten$A205_06==2] <- "Ecoland"
Daten$verband1[Daten$A205_07==2] <- "Naturland"
Daten$verband1[Daten$A205_08==2] <- "Verbund Ökohöfe"
Daten$verband1[Daten$A205_09==2] <- "other"
Daten$verband1[Daten$A205_10==2] <- "none"

table(Daten$A205)
table(Daten$verband1)
table(Daten$A205_09a)
barplot(table(Daten$verband1))

# age

Daten$age[Daten$A202_01<=44 & Daten$A202_01>=18] <- "18-44 years old"
Daten$age[Daten$A202_01<=70 & Daten$A202_01>=45] <- "45-70 years old"
table(Daten$age)
table(Daten$A202_01)
hist(Daten$A202_01)
mean(Daten$A202_01)
sd(Daten$A202_01)

# gender

Daten$geschlecht[Daten$A201==1] <- "female"
Daten$geschlecht[Daten$A201==2] <- "male"
Daten$geschlecht[Daten$A201==3] <- "diverse"

table(Daten$geschlecht)
barplot(table(Daten$geschlecht))

# employment

Daten$erwerb[Daten$A801==1] <- "working"
Daten$erwerb[Daten$A801==2] <- "not working"

table(Daten$erwerb)
barplot(table(Daten$erwerb))

# income

Daten$einkommen[Daten$A802==1] <- "less than 900 Euro"
Daten$einkommen[Daten$A802==2] <- "900 to <1.300 Euro"
Daten$einkommen[Daten$A802==3] <- "1.300 to <1.500 Euro"
Daten$einkommen[Daten$A802==4] <- "1.500 to <2.000 Euro"
Daten$einkommen[Daten$A802==5] <- "2.000 to <2.600 Euro"
Daten$einkommen[Daten$A802==6] <- "2.600 to <3.600 Euro"
Daten$einkommen[Daten$A802==7] <- "3.600 to <5.000 Euro"
Daten$einkommen[Daten$A802==8] <- "5.000 Euro and more"

table(Daten$einkommen)

# persons in the household (persons who have indicated "1" for A803_02/ A803_03 "1" are excluded)

which(Daten$A803_02==1)
Daten3<-Daten[-c(89,92),]
which(Daten3$A803_03==1)
Daten3<-Daten3[-c(4,29,95),]

table(Daten3$A803)
mean(Daten3$A803_02, na.rm=T)
sd(Daten3$A803_02, na.rm=T)
min(Daten3$A803_02, na.rm=T)
max(Daten3$A803_02, na.rm=T)
mean(Daten3$A803_03, na.rm=T)
sd(Daten3$A803_03, na.rm=T)
min(Daten3$A803_03, na.rm=T)
max(Daten3$A803_03, na.rm=T)
table(Daten$A804)
Daten3$ohnekinder <-with (Daten3, A803_03-A804)

# education

Daten$schule[Daten$A805==1] <- "no degree"
Daten$schule[Daten$A805==2] <- "still in training"
Daten$schule[Daten$A805==3] <- "apprenticeship"
Daten$schule[Daten$A805==4] <- "technical college qualification"
Daten$schule[Daten$A805==5] <- "university degree"
Daten$schule[Daten$A805==6] <- "doctorate"
Daten$schule[Daten$A805==7] <- "other degree"

table(Daten$schule)
table(Daten$A805_07)
barplot(table(Daten$schule))

# place of residence

Daten$wohnort[Daten$A806==1] <- "rural"
Daten$wohnort[Daten$A806==2] <- "rather rural"
Daten$wohnort[Daten$A806==3] <- "rather urban"
Daten$wohnort[Daten$A806==4] <- "urban"

table(Daten$wohnort)
barplot(table(Daten$wohnort))

# diet

Daten$ernaehrung[Daten$A807==1] <- "vegan"
Daten$ernaehrung[Daten$A807==2] <- "vegetarian"
Daten$ernaehrung[Daten$A807==3] <- "omnivorous"
Daten$ernaehrung[Daten$A807==4] <- "flexitarian"
Daten$ernaehrung[Daten$A807==5] <- "other"

table(Daten$ernaehrung)
barplot(table(Daten$ernaehrung))
table(Daten$A807_05)
table(Daten$A807_05[Daten$A807==3])
table(Daten$A807_05[Daten$A807==5])

# dairy consumption

Daten$milch[Daten$A808==1] <- "never"
Daten$milch[Daten$A808==2] <- "less than once a month"
Daten$milch[Daten$A808==3] <- "once a month"
Daten$milch[Daten$A808==4] <- "twice to three times a month"
Daten$milch[Daten$A808==5] <- "once a week"
Daten$milch[Daten$A808==6] <- "more than once a week"
Daten$milch[Daten$A808==7] <- "daily"

table(Daten$milch)
barplot(table(Daten$milch))

# plant-based milk substitute consumption

Daten$milch1[Daten$A809==1] <- "never"
Daten$milch1[Daten$A809==2] <- "less than once a month"
Daten$milch1[Daten$A809==3] <- "once a month"
Daten$milch1[Daten$A809==4] <- "twice to three times a month"
Daten$milch1[Daten$A809==5] <- "once a week"
Daten$milch1[Daten$A809==6] <- "more than once a week"
Daten$milch1[Daten$A809==7] <- "daily"

table(Daten$milch1)
barplot(table(Daten$milch1))

# objective knowledge

table(Daten$A301_01)
table(Daten$A301_02)
table(Daten$A301_03)
table(Daten$A301_04)
table(Daten$A301_05)
table(Daten$A301_06)
table(Daten$A301_07)
table(Daten$A301_08)
table(Daten$A301_09)

# Recoding

Daten$A301_05_rec <- recode(Daten$A301_05, 
                            "1=0;2=1;3=0;-9=0")
Daten$A301_06_rec <- recode(Daten$A301_06, 
                            "1=0;2=1;3=0;-9=0")
Daten$A301_07_rec <- recode(Daten$A301_07, 
                            "1=0;2=1;3=0;-9=0")
Daten$A301_09_rec <- recode(Daten$A301_09, 
                            "1=0;2=1;3=0;-9=0")
Daten$A301_01_rec <- recode(Daten$A301_01, 
                            "1=1;2=0;3=0;-9=0")
Daten$A301_02_rec <- recode(Daten$A301_02, 
                            "1=1;2=0;3=0;-9=0")
Daten$A301_03_rec <- recode(Daten$A301_03, 
                            "1=1;2=0;3=0;-9=0")
Daten$A301_04_rec <- recode(Daten$A301_04, 
                            "1=1;2=0;3=0;-9=0")
Daten$A301_08_rec <- recode(Daten$A301_08, 
                            "1=1;2=0;3=0;-9=0")


# new variable "wissenlevel"

Daten$wissengesamt <- NA
Daten$wissengesamt <- rowSums(Daten[,c("A301_01_rec","A301_02_rec","A301_03_rec",
                                       "A301_04_rec","A301_05_rec","A301_06_rec",
                                       "A301_07_rec","A301_08_rec","A301_09_rec")])
mean(Daten$wissengesamt) # on average 4 questions answered correctly ( = 5 wrong)
Daten$wissenlevel <- NA
Daten$wissenlevel[Daten$wissengesamt<4] <- 1 # 0-3 correct
Daten$wissenlevel[Daten$wissengesamt==4|Daten$wissengesamt==5] <- 2 # 4-5 correct
Daten$wissenlevel[Daten$wissengesamt>5] <- 3 # 6-9 correct
table(Daten$wissenlevel)

wissenhoch <- subset(Daten, Daten$wissenlevel ==3)
wissenmittel <- subset(Daten, Daten$wissenlevel ==2)
wissengering <- subset(Daten, Daten$wissenlevel ==1)

table(Daten$wissenlevel)
barplot(table(Daten$wissenlevel))

table(Daten$wissengesamt)
barplot(table(Daten$wissengesamt),
        xlab= "number of correct answers",
        ylab= "frequency",
        ylim=c(0,250),
        las=1)

# 3 organic buyer groups

Daten$bio <- factor(Daten$bio)

rarely <- subset(Daten, Daten$bio=="rarely")
regular <- subset(Daten, Daten$bio=="regular")
frequent <- subset(Daten, Daten$bio=="frequent")

# expectations

table(Daten$A401_01)
table(Daten$A401_02)
table(Daten$A401_03)
table(Daten$A401_04)

table(Daten$A402_01)
table(Daten$A402_02)
table(Daten$A402_03)
table(Daten$A402_04)
table(Daten$A402_05)

table(Daten$A403_01)
table(Daten$A403_02)
table(Daten$A403_03)
table(Daten$A403_04)

table(Daten$A404_01)
table(Daten$A404_02)
table(Daten$A404_03)

table(Daten$A405_01)
table(Daten$A405_02)

table(Daten$A406_01)
table(Daten$A406_02)
table(Daten$A406_03)

table(Daten$A407_01)
table(Daten$A407_02)
table(Daten$A407_03)

table(Daten$A408_01)
table(Daten$A408_02)
table(Daten$A408_03)
table(Daten$A408_04)
table(Daten$A408_05)

table(Daten$A409_01)
table(Daten$A409_02)
table(Daten$A409_03)

table(Daten$A410_01)
table(Daten$A410_02)

Daten$A401_01[Daten$A401_01==-1] <- NA
Daten$A401_02[Daten$A401_02==-1] <- NA
Daten$A401_03[Daten$A401_03==-1] <- NA
Daten$A401_04[Daten$A401_04==-1] <- NA

Daten$A402_01[Daten$A402_01==-1] <- NA
Daten$A402_02[Daten$A402_02==-1] <- NA
Daten$A402_03[Daten$A402_03==-1] <- NA
Daten$A402_04[Daten$A402_04==-1] <- NA
Daten$A402_05[Daten$A402_05==-1] <- NA

Daten$A403_01[Daten$A403_01==-1] <- NA
Daten$A403_02[Daten$A403_02==-1] <- NA
Daten$A403_03[Daten$A403_03==-1] <- NA
Daten$A403_04[Daten$A403_04==-1] <- NA

Daten$A404_01[Daten$A404_01==-1] <- NA
Daten$A404_02[Daten$A404_02==-1] <- NA
Daten$A404_03[Daten$A404_03==-1] <- NA

Daten$A405_01[Daten$A405_01==-1] <- NA
Daten$A405_02[Daten$A405_02==-1] <- NA

Daten$A406_01[Daten$A406_01==-1] <- NA
Daten$A406_02[Daten$A406_02==-1] <- NA
Daten$A406_03[Daten$A406_03==-1] <- NA

Daten$A407_01[Daten$A407_01==-1] <- NA
Daten$A407_02[Daten$A407_02==-1] <- NA
Daten$A407_03[Daten$A407_03==-1] <- NA

Daten$A408_01[Daten$A408_01==-1] <- NA
Daten$A408_02[Daten$A408_02==-1] <- NA
Daten$A408_03[Daten$A408_03==-1] <- NA
Daten$A408_04[Daten$A408_04==-1] <- NA
Daten$A408_05[Daten$A408_05==-1] <- NA

Daten$A409_01[Daten$A409_01==-1] <- NA
Daten$A409_02[Daten$A409_02==-1] <- NA
Daten$A409_03[Daten$A409_03==-1] <- NA

Daten$A410_01[Daten$A410_01==-1] <- NA
Daten$A410_02[Daten$A410_02==-1] <- NA

# NEP: recoding

Daten$A501_02_rec <- recode(Daten$A501_02, 
                            "1=5;2=4;3=3;4=2;5=1")
Daten$A501_04_rec <- recode(Daten$A501_04, 
                            "1=5;2=4;3=3;4=2;5=1")
Daten$A501_06_rec <- recode(Daten$A501_06, 
                            "1=5;2=4;3=3;4=2;5=1")
Daten$A502_01_rec <- recode(Daten$A502_01, 
                            "1=5;2=4;3=3;4=2;5=1")
Daten$A502_03_rec <- recode(Daten$A502_03, 
                            "1=5;2=4;3=3;4=2;5=1")
Daten$A502_05_rec <- recode(Daten$A502_05, 
                            "1=5;2=4;3=3;4=2;5=1")
Daten$A502_07_rec <- recode(Daten$A502_07, 
                            "1=5;2=4;3=3;4=2;5=1")

# NEP

Daten$NEP <- rowMeans(subset(Daten, select = c(A501_01, A501_02_rec, A501_03, A501_04_rec, A501_05, A501_06_rec,
                                               A501_07, A502_01_rec, A502_02, A502_03_rec, A502_04, A502_05_rec,
                                               A502_06, A502_07_rec, A502_08)), na.rm = TRUE)

# Naturalness

Daten$Natuerlichkeit <- rowMeans(subset(Daten, select = c(A601_01,A601_02,A601_03,A601_04,A601_05,A601_06,
                                                          A601_07,A601_08,A601_09)), na.rm = TRUE)

# animal ethical intuition

# original anthropocentrism

Daten$anthro <- rowMeans(subset(Daten, select = c(A701_01,A701_02,A701_03)), na.rm = TRUE)

# anthropocentrism with indirect duties

Daten$anthroindirekt <- rowMeans(subset(Daten, select = c(A702_01,A702_02,A702_03)), na.rm = TRUE)

# utilitarianism

Daten$utilitarismus <- rowMeans(subset(Daten, select = c(A703_01,A703_02,A703_03)), na.rm = TRUE)

# New Deal

Daten$newdeal <- rowMeans(subset(Daten, select = c(A704_01,A704_02,A704_03)), na.rm = TRUE)

# relationalism

Daten$relationismus <- rowMeans(subset(Daten, select = c(A705_01,A705_02,A705_03)), na.rm = TRUE)

# strict animal rights position

Daten$tierrechtestreng <- rowMeans(subset(Daten, select = c(A706_01,A706_02,A706_03)), na.rm = TRUE)

# weak animal rights position

Daten$tierrechteschwach <- rowMeans(subset(Daten, select = c(A706_04,A706_05)), na.rm = TRUE)

# abolitionism

Daten$abolitionismus <- rowMeans(subset(Daten, select = c(A707_01,A707_02,A707_03)), na.rm = TRUE)

# AEI

Daten$AEI <- rowMeans(subset(Daten, select = c(A401_01, A402_01, A402_05, A406_01, A406_03, A408_02, A409_01)), na.rm = TRUE)

# SAI

Daten$SAI <- rowMeans(subset(Daten, select = c(A401_03, A401_04, A402_02, A402_03, A404_02, A404_03, A405_01, A405_02,
                                               A406_02, A407_03, A408_01, A408_03)), na.rm = TRUE)
# 3 organic buyer groups after NA assignment

rarely <- subset(Daten, Daten$bio=="rarely")
regular <- subset(Daten, Daten$bio=="regular")
frequent <- subset(Daten, Daten$bio=="frequent")

# 3 knowledge groups after NA assignment

wissenhoch <- subset(Daten, Daten$wissenlevel ==3)
wissenmittel <- subset(Daten, Daten$wissenlevel ==2)
wissengering <- subset(Daten, Daten$wissenlevel ==1)

# mean AEI

mean(Daten$AEI, na.rm=T)

# mean SAI

mean(Daten$SAI, na.rm=T)

# mean expectations

Daten$expectationsgesamt <- rowMeans(subset(Daten, select = c(A401_01,A401_02,A401_03,A401_04,
                                       A402_01, A402_02, A402_03, A402_04, A402_05,
                                       A403_01, A403_02, A403_03, A403_04,
                                       A404_01, A404_02, A404_03,
                                       A405_01, A405_02,
                                       A406_01, A406_02, A406_03,
                                       A407_01, A407_02, A407_03,
                                       A408_01, A408_02, A408_03, A408_04, A408_05,
                                       A409_01, A409_02, A409_03,
                                       A410_01, A410_02)), na.rm = TRUE)
mean(Daten$expectationsgesamt, na.rm = T) # average agreement: 3.26

options(digits=3)
mean(Daten$A401_01, na.rm=T)
mean(Daten$A401_02, na.rm=T)
mean(Daten$A401_03, na.rm=T)
mean(Daten$A401_04, na.rm=T)
mean(Daten$A402_05, na.rm=T)
mean(Daten$A402_01, na.rm=T)
mean(Daten$A402_04, na.rm=T)
mean(Daten$A402_02, na.rm=T)
mean(Daten$A402_03, na.rm=T)
mean(Daten$A403_04, na.rm=T)
mean(Daten$A403_01, na.rm=T)
mean(Daten$A403_02, na.rm=T)
mean(Daten$A403_03, na.rm=T)
mean(Daten$A404_01, na.rm=T)
mean(Daten$A404_02, na.rm=T)
mean(Daten$A404_03, na.rm=T)
mean(Daten$A405_02, na.rm=T)
mean(Daten$A405_01, na.rm=T)
mean(Daten$A406_01, na.rm=T)
mean(Daten$A406_03, na.rm=T)
mean(Daten$A406_02, na.rm=T)
mean(Daten$A407_02, na.rm=T)
mean(Daten$A407_01, na.rm=T)
mean(Daten$A407_03, na.rm=T)
mean(Daten$A408_02, na.rm=T)
mean(Daten$A408_05, na.rm=T)
mean(Daten$A408_03, na.rm=T)
mean(Daten$A408_04, na.rm=T)
mean(Daten$A408_01, na.rm=T)
mean(Daten$A409_01, na.rm=T)
mean(Daten$A409_02, na.rm=T)
mean(Daten$A409_03, na.rm=T)
mean(Daten$A410_01, na.rm=T)
mean(Daten$A410_02, na.rm=T)

# mean NEP

mean(Daten$NEP, na.rm=T)

# mean naturalness

mean(Daten$Natuerlichkeit, na.rm=T)

# mean original anthropocentrism

mean(Daten$anthro, na.rm=T)

# mean anthropocentrism with indirect duties

mean(Daten$anthroindirekt, na.rm=T)

# mean utilitarianism

mean(Daten$utilitarismus, na.rm=T)

# mean New Deal

mean(Daten$newdeal, na.rm=T)

# mean relationism

mean(Daten$relationismus, na.rm=T)

# mean strict animals rights position

mean(Daten$tierrechtestreng, na.rm=T)

# mean weak animal rights position

mean(Daten$tierrechteschwach, na.rm=T)

# mean abolitionism

mean(Daten$abolitionismus, na.rm=T)

# sd AEI

sd(Daten$AEI, na.rm=T)

# sd SAI

sd(Daten$SAI, na.rm=T)

# sd expectations

sd(Daten$A401_01, na.rm=T)
sd(Daten$A401_02, na.rm=T)
sd(Daten$A401_03, na.rm=T)
sd(Daten$A401_04, na.rm=T)
sd(Daten$A402_05, na.rm=T)
sd(Daten$A402_01, na.rm=T)
sd(Daten$A402_04, na.rm=T)
sd(Daten$A402_02, na.rm=T)
sd(Daten$A402_03, na.rm=T)
sd(Daten$A403_04, na.rm=T)
sd(Daten$A403_01, na.rm=T)
sd(Daten$A403_02, na.rm=T)
sd(Daten$A403_03, na.rm=T)
sd(Daten$A404_01, na.rm=T)
sd(Daten$A404_02, na.rm=T)
sd(Daten$A404_03, na.rm=T)
sd(Daten$A405_02, na.rm=T)
sd(Daten$A405_01, na.rm=T)
sd(Daten$A406_01, na.rm=T)
sd(Daten$A406_03, na.rm=T)
sd(Daten$A406_02, na.rm=T)
sd(Daten$A407_02, na.rm=T)
sd(Daten$A407_01, na.rm=T)
sd(Daten$A407_03, na.rm=T)
sd(Daten$A408_02, na.rm=T)
sd(Daten$A408_05, na.rm=T)
sd(Daten$A408_03, na.rm=T)
sd(Daten$A408_04, na.rm=T)
sd(Daten$A408_01, na.rm=T)
sd(Daten$A409_01, na.rm=T)
sd(Daten$A409_02, na.rm=T)
sd(Daten$A409_03, na.rm=T)
sd(Daten$A410_01, na.rm=T)
sd(Daten$A410_02, na.rm=T)

# sd NEP

sd(Daten$NEP, na.rm=T)

# sd naturalness

sd(Daten$Natuerlichkeit, na.rm=T)

# sd original anthropocentrism

sd(Daten$anthro, na.rm=T)

# sd anthropocentrism with indirect duties

sd(Daten$anthroindirekt, na.rm=T)

# sd utilitarianism

sd(Daten$utilitarismus, na.rm=T)

# sd New Deal

sd(Daten$newdeal, na.rm=T)

# sd relationism

sd(Daten$relationismus, na.rm=T)

# sd strict animal rights position

sd(Daten$tierrechtestreng, na.rm=T)

# sd weak animal rights position

sd(Daten$tierrechteschwach, na.rm=T)

# sd abolitionism

sd(Daten$abolitionismus, na.rm=T)

# Cronbach's alpha

# Cronbach's alpha NEP

alpha(subset(Daten, select = c(A501_01, A501_02_rec, A501_03, A501_04_rec, A501_05, A501_06_rec,
                               A501_07, A502_01_rec, A502_02, A502_03_rec, A502_04, A502_05_rec,
                               A502_06, A502_07_rec, A502_08)), check.keys =TRUE)

# Cronbach's alpha Naturalness


alpha(subset(Daten, select = c(A601_01,A601_02,A601_03,A601_04,A601_05,A601_06,
                               A601_07,A601_08,A601_09)), check.keys =TRUE)

# Cronbach's alpha animal ethical intuition

alpha(subset(Daten, select = c(A701_01,A701_02,A701_03,A702_01,A702_02,A702_03,
                               A703_01,A703_02,A703_03,A704_01,A704_02,A704_03,
                               A705_01,A705_02,A705_03,A706_01,A706_02,A706_03,
                               A706_04,A706_05,A707_01,A707_02,A707_03)), check.keys =TRUE)

#######################################################################

# descriptive statistics knowledge groups

mean(wissengering$A202_01, na.rm=T) # age
mean(wissenmittel$A202_01, na.rm=T) # age
mean(wissenhoch$A202_01, na.rm=T) # age
sd(wissengering$A202_01, na.rm=T) # age
sd(wissenmittel$A202_01, na.rm=T) # age
sd(wissenhoch$A202_01, na.rm=T) # age

table(wissengering$A201) # gender
table(wissenmittel$A201) # gender
table(wissenhoch$A201) # gender

table(wissengering$ernaehrung) # diet
table(wissenmittel$ernaehrung) # diet
table(wissenhoch$ernaehrung) # diet

table(wissengering$schule) # education
table(wissenmittel$schule) # education
table(wissenhoch$schule) # education

table(wissengering$einkommen) # income
table(wissenmittel$einkommen) # income
table(wissenhoch$einkommen) # income

table(wissengering$wohnort) # residence
table(wissenmittel$wohnort) # residence
table(wissenhoch$wohnort) # residence

table(wissengering$bio) # organic purchase frequency
table(wissenmittel$bio) # organic purchase frequency
table(wissenhoch$bio) # organic purchase frequency

table(wissengering$milch) # dairy consumption
table(wissenmittel$milch) # dairy consumption
table(wissenhoch$milch) # dairy consumption

table(wissengering$milch1) # plant-based milk consumption
table(wissenmittel$milch1) # plant-based milk consumption
table(wissenhoch$milch1) # plant-based milk consumption

mean(wissengering$AEI, na.rm=T); sd(wissengering$AEI, na.rm=T)
mean(wissenmittel$AEI, na.rm=T); sd(wissenmittel$AEI, na.rm=T)
mean(wissenhoch$AEI, na.rm=T); sd(wissenhoch$AEI, na.rm=T)

mean(wissengering$SAI, na.rm=T); sd(wissengering$SAI, na.rm=T)
mean(wissenmittel$SAI, na.rm=T); sd(wissenmittel$SAI, na.rm=T)
mean(wissenhoch$SAI, na.rm=T); sd(wissenhoch$SAI, na.rm=T)

mean(wissengering$NEP); sd(wissengering$NEP)
mean(wissenmittel$NEP); sd(wissenmittel$NEP)
mean(wissenhoch$NEP); sd(wissenhoch$NEP)

mean(wissengering$Natuerlichkeit); sd(wissengering$Natuerlichkeit)
mean(wissenmittel$Natuerlichkeit); sd(wissenmittel$Natuerlichkeit)
mean(wissenhoch$Natuerlichkeit); sd(wissenhoch$Natuerlichkeit)

mean(wissengering$anthro); sd(wissengering$anthro)
mean(wissengering$anthroindirekt); sd(wissengering$anthroindirekt)
mean(wissengering$utilitarismus); sd(wissengering$utilitarismus)
mean(wissengering$newdeal); sd(wissengering$newdeal)
mean(wissengering$relationismus); sd(wissengering$relationismus)
mean(wissengering$tierrechtestreng); sd(wissengering$tierrechtestreng)
mean(wissengering$tierrechteschwach); sd(wissengering$tierrechteschwach)
mean(wissengering$abolitionismus); sd(wissengering$abolitionismus)

mean(wissenmittel$anthro); sd(wissenmittel$anthro)
mean(wissenmittel$anthroindirekt); sd(wissenmittel$anthroindirekt)
mean(wissenmittel$utilitarismus); sd(wissenmittel$utilitarismus)
mean(wissenmittel$newdeal); sd(wissenmittel$newdeal)
mean(wissenmittel$relationismus); sd(wissenmittel$relationismus)
mean(wissenmittel$tierrechtestreng); sd(wissenmittel$tierrechtestreng)
mean(wissenmittel$tierrechteschwach); sd(wissenmittel$tierrechteschwach)
mean(wissenmittel$abolitionismus); sd(wissenmittel$abolitionismus)

mean(wissenhoch$anthro); sd(wissenhoch$anthro)
mean(wissenhoch$anthroindirekt); sd(wissenhoch$anthroindirekt)
mean(wissenhoch$utilitarismus); sd(wissenhoch$utilitarismus)
mean(wissenhoch$newdeal); sd(wissenhoch$newdeal)
mean(wissenhoch$relationismus); sd(wissenhoch$relationismus)
mean(wissenhoch$tierrechtestreng); sd(wissenhoch$tierrechtestreng)
mean(wissenhoch$tierrechteschwach); sd(wissenhoch$tierrechteschwach)
mean(wissenhoch$abolitionismus); sd(wissenhoch$abolitionismus)

mean(wissengering$A401_01, na.rm=T)
mean(wissengering$A401_02, na.rm=T)
mean(wissengering$A401_03, na.rm=T)
mean(wissengering$A401_04, na.rm=T)
mean(wissengering$A402_05, na.rm=T)
mean(wissengering$A402_01, na.rm=T)
mean(wissengering$A402_04, na.rm=T)
mean(wissengering$A402_02, na.rm=T)
mean(wissengering$A402_03, na.rm=T)
mean(wissengering$A403_04, na.rm=T)
mean(wissengering$A403_01, na.rm=T)
mean(wissengering$A403_02, na.rm=T)
mean(wissengering$A403_03, na.rm=T)
mean(wissengering$A404_01, na.rm=T)
mean(wissengering$A404_02, na.rm=T)
mean(wissengering$A404_03, na.rm=T)
mean(wissengering$A405_02, na.rm=T)
mean(wissengering$A405_01, na.rm=T)
mean(wissengering$A406_01, na.rm=T)
mean(wissengering$A406_03, na.rm=T)
mean(wissengering$A406_02, na.rm=T)
mean(wissengering$A407_02, na.rm=T)
mean(wissengering$A407_01, na.rm=T)
mean(wissengering$A407_03, na.rm=T)
mean(wissengering$A408_02, na.rm=T)
mean(wissengering$A408_05, na.rm=T)
mean(wissengering$A408_03, na.rm=T)
mean(wissengering$A408_04, na.rm=T)
mean(wissengering$A408_01, na.rm=T)
mean(wissengering$A409_01, na.rm=T)
mean(wissengering$A409_02, na.rm=T)
mean(wissengering$A409_03, na.rm=T)
mean(wissengering$A410_01, na.rm=T)
mean(wissengering$A410_02, na.rm=T)

mean(wissenmittel$A401_01, na.rm=T)
mean(wissenmittel$A401_02, na.rm=T)
mean(wissenmittel$A401_03, na.rm=T)
mean(wissenmittel$A401_04, na.rm=T)
mean(wissenmittel$A402_05, na.rm=T)
mean(wissenmittel$A402_01, na.rm=T)
mean(wissenmittel$A402_04, na.rm=T)
mean(wissenmittel$A402_02, na.rm=T)
mean(wissenmittel$A402_03, na.rm=T)
mean(wissenmittel$A403_04, na.rm=T)
mean(wissenmittel$A403_01, na.rm=T)
mean(wissenmittel$A403_02, na.rm=T)
mean(wissenmittel$A403_03, na.rm=T)
mean(wissenmittel$A404_01, na.rm=T)
mean(wissenmittel$A404_02, na.rm=T)
mean(wissenmittel$A404_03, na.rm=T)
mean(wissenmittel$A405_02, na.rm=T)
mean(wissenmittel$A405_01, na.rm=T)
mean(wissenmittel$A406_01, na.rm=T)
mean(wissenmittel$A406_03, na.rm=T)
mean(wissenmittel$A406_02, na.rm=T)
mean(wissenmittel$A407_02, na.rm=T)
mean(wissenmittel$A407_01, na.rm=T)
mean(wissenmittel$A407_03, na.rm=T)
mean(wissenmittel$A408_02, na.rm=T)
mean(wissenmittel$A408_05, na.rm=T)
mean(wissenmittel$A408_03, na.rm=T)
mean(wissenmittel$A408_04, na.rm=T)
mean(wissenmittel$A408_01, na.rm=T)
mean(wissenmittel$A409_01, na.rm=T)
mean(wissenmittel$A409_02, na.rm=T)
mean(wissenmittel$A409_03, na.rm=T)
mean(wissenmittel$A410_01, na.rm=T)
mean(wissenmittel$A410_02, na.rm=T)

mean(wissenhoch$A401_01, na.rm=T)
mean(wissenhoch$A401_02, na.rm=T)
mean(wissenhoch$A401_03, na.rm=T)
mean(wissenhoch$A401_04, na.rm=T)
mean(wissenhoch$A402_05, na.rm=T)
mean(wissenhoch$A402_01, na.rm=T)
mean(wissenhoch$A402_04, na.rm=T)
mean(wissenhoch$A402_02, na.rm=T)
mean(wissenhoch$A402_03, na.rm=T)
mean(wissenhoch$A403_04, na.rm=T)
mean(wissenhoch$A403_01, na.rm=T)
mean(wissenhoch$A403_02, na.rm=T)
mean(wissenhoch$A403_03, na.rm=T)
mean(wissenhoch$A404_01, na.rm=T)
mean(wissenhoch$A404_02, na.rm=T)
mean(wissenhoch$A404_03, na.rm=T)
mean(wissenhoch$A405_02, na.rm=T)
mean(wissenhoch$A405_01, na.rm=T)
mean(wissenhoch$A406_01, na.rm=T)
mean(wissenhoch$A406_03, na.rm=T)
mean(wissenhoch$A406_02, na.rm=T)
mean(wissenhoch$A407_02, na.rm=T)
mean(wissenhoch$A407_01, na.rm=T)
mean(wissenhoch$A407_03, na.rm=T)
mean(wissenhoch$A408_02, na.rm=T)
mean(wissenhoch$A408_05, na.rm=T)
mean(wissenhoch$A408_03, na.rm=T)
mean(wissenhoch$A408_04, na.rm=T)
mean(wissenhoch$A408_01, na.rm=T)
mean(wissenhoch$A409_01, na.rm=T)
mean(wissenhoch$A409_02, na.rm=T)
mean(wissenhoch$A409_03, na.rm=T)
mean(wissenhoch$A410_01, na.rm=T)
mean(wissenhoch$A410_02, na.rm=T)

sd(wissengering$A401_01, na.rm=T)
sd(wissengering$A401_02, na.rm=T)
sd(wissengering$A401_03, na.rm=T)
sd(wissengering$A401_04, na.rm=T)
sd(wissengering$A402_05, na.rm=T)
sd(wissengering$A402_01, na.rm=T)
sd(wissengering$A402_04, na.rm=T)
sd(wissengering$A402_02, na.rm=T)
sd(wissengering$A402_03, na.rm=T)
sd(wissengering$A403_04, na.rm=T)
sd(wissengering$A403_01, na.rm=T)
sd(wissengering$A403_02, na.rm=T)
sd(wissengering$A403_03, na.rm=T)
sd(wissengering$A404_01, na.rm=T)
sd(wissengering$A404_02, na.rm=T)
sd(wissengering$A404_03, na.rm=T)
sd(wissengering$A405_02, na.rm=T)
sd(wissengering$A405_01, na.rm=T)
sd(wissengering$A406_01, na.rm=T)
sd(wissengering$A406_03, na.rm=T)
sd(wissengering$A406_02, na.rm=T)
sd(wissengering$A407_02, na.rm=T)
sd(wissengering$A407_01, na.rm=T)
sd(wissengering$A407_03, na.rm=T)
sd(wissengering$A408_02, na.rm=T)
sd(wissengering$A408_05, na.rm=T)
sd(wissengering$A408_03, na.rm=T)
sd(wissengering$A408_04, na.rm=T)
sd(wissengering$A408_01, na.rm=T)
sd(wissengering$A409_01, na.rm=T)
sd(wissengering$A409_02, na.rm=T)
sd(wissengering$A409_03, na.rm=T)
sd(wissengering$A410_01, na.rm=T)
sd(wissengering$A410_02, na.rm=T)

sd(wissenmittel$A401_01, na.rm=T)
sd(wissenmittel$A401_02, na.rm=T)
sd(wissenmittel$A401_03, na.rm=T)
sd(wissenmittel$A401_04, na.rm=T)
sd(wissenmittel$A402_05, na.rm=T)
sd(wissenmittel$A402_01, na.rm=T)
sd(wissenmittel$A402_04, na.rm=T)
sd(wissenmittel$A402_02, na.rm=T)
sd(wissenmittel$A402_03, na.rm=T)
sd(wissenmittel$A403_04, na.rm=T)
sd(wissenmittel$A403_01, na.rm=T)
sd(wissenmittel$A403_02, na.rm=T)
sd(wissenmittel$A403_03, na.rm=T)
sd(wissenmittel$A404_01, na.rm=T)
sd(wissenmittel$A404_02, na.rm=T)
sd(wissenmittel$A404_03, na.rm=T)
sd(wissenmittel$A405_02, na.rm=T)
sd(wissenmittel$A405_01, na.rm=T)
sd(wissenmittel$A406_01, na.rm=T)
sd(wissenmittel$A406_03, na.rm=T)
sd(wissenmittel$A406_02, na.rm=T)
sd(wissenmittel$A407_02, na.rm=T)
sd(wissenmittel$A407_01, na.rm=T)
sd(wissenmittel$A407_03, na.rm=T)
sd(wissenmittel$A408_02, na.rm=T)
sd(wissenmittel$A408_05, na.rm=T)
sd(wissenmittel$A408_03, na.rm=T)
sd(wissenmittel$A408_04, na.rm=T)
sd(wissenmittel$A408_01, na.rm=T)
sd(wissenmittel$A409_01, na.rm=T)
sd(wissenmittel$A409_02, na.rm=T)
sd(wissenmittel$A409_03, na.rm=T)
sd(wissenmittel$A410_01, na.rm=T)
sd(wissenmittel$A410_02, na.rm=T)

sd(wissenhoch$A401_01, na.rm=T)
sd(wissenhoch$A401_02, na.rm=T)
sd(wissenhoch$A401_03, na.rm=T)
sd(wissenhoch$A401_04, na.rm=T)
sd(wissenhoch$A402_05, na.rm=T)
sd(wissenhoch$A402_01, na.rm=T)
sd(wissenhoch$A402_04, na.rm=T)
sd(wissenhoch$A402_02, na.rm=T)
sd(wissenhoch$A402_03, na.rm=T)
sd(wissenhoch$A403_04, na.rm=T)
sd(wissenhoch$A403_01, na.rm=T)
sd(wissenhoch$A403_02, na.rm=T)
sd(wissenhoch$A403_03, na.rm=T)
sd(wissenhoch$A404_01, na.rm=T)
sd(wissenhoch$A404_02, na.rm=T)
sd(wissenhoch$A404_03, na.rm=T)
sd(wissenhoch$A405_02, na.rm=T)
sd(wissenhoch$A405_01, na.rm=T)
sd(wissenhoch$A406_01, na.rm=T)
sd(wissenhoch$A406_03, na.rm=T)
sd(wissenhoch$A406_02, na.rm=T)
sd(wissenhoch$A407_02, na.rm=T)
sd(wissenhoch$A407_01, na.rm=T)
sd(wissenhoch$A407_03, na.rm=T)
sd(wissenhoch$A408_02, na.rm=T)
sd(wissenhoch$A408_05, na.rm=T)
sd(wissenhoch$A408_03, na.rm=T)
sd(wissenhoch$A408_04, na.rm=T)
sd(wissenhoch$A408_01, na.rm=T)
sd(wissenhoch$A409_01, na.rm=T)
sd(wissenhoch$A409_02, na.rm=T)
sd(wissenhoch$A409_03, na.rm=T)
sd(wissenhoch$A410_01, na.rm=T)
sd(wissenhoch$A410_02, na.rm=T)

# mean comparisons knowledge

Daten$wissenlevel<-as.factor(Daten$wissenlevel)

#AEI
# Shapiro-Wilk-Test

model <- lm(AEI~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$AEI, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$AEI~Daten$wissenlevel)

#SAI
# Shapiro-Wilk-Test

model <- lm(SAI~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$SAI, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$SAI~Daten$wissenlevel)

#anthro
# Shapiro-Wilk-Test

model <- lm(anthro~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$anthro, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$anthro~Daten$wissenlevel)

boxplot(Daten$anthro~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval",
        main = "anthropocentrism")

pairwise.wilcox.test(Daten$anthro, Daten$wissenlevel, p.adjust = "bonferroni")

#anthroindirect
# Shapiro-Wilk-Test

model <- lm(anthroindirekt~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$anthroindirekt, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$anthroindirekt~Daten$wissenlevel)

#utilitarianism
# Shapiro-Wilk-Test

model <- lm(utilitarismus~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$utilitarismus, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$utilitarismus~Daten$wissenlevel)

boxplot(Daten$utilitarismus~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval",
        main = "utilitarism")

pairwise.wilcox.test(Daten$utilitarismus, Daten$wissenlevel, p.adjust = "bonferroni")

#newdeal
# Shapiro-Wilk-Test

model <- lm(newdeal~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$newdeal, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$newdeal~Daten$wissenlevel)

boxplot(Daten$newdeal~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval",
        main = "newdeal")

pairwise.wilcox.test(Daten$newdeal, Daten$wissenlevel, p.adjust = "bonferroni")

#relationism
# Shapiro-Wilk-Test

model <- lm(relationismus~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$relationismus, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$relationismus~Daten$wissenlevel)

#strictanimalrights
# Shapiro-Wilk-Test

model <- lm(tierrechtestreng~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$tierrechtestreng, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$tierrechtestreng~Daten$wissenlevel)

#weakanimalrights
# Shapiro-Wilk-Test

model <- lm(tierrechteschwach~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$tierrechteschwach, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$tierrechteschwach~Daten$wissenlevel)

#abolitionism
# Shapiro-Wilk-Test

model <- lm(abolitionismus~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$abolitionismus, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$abolitionismus~Daten$wissenlevel)

boxplot(Daten$anthro~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval",
        main = "abolitionism")

pairwise.wilcox.test(Daten$abolitionismus, Daten$wissenlevel, p.adjust = "bonferroni")

#NEP
# Shapiro-Wilk-Test

model <- lm(NEP~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$NEP, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$NEP~Daten$wissenlevel)

#Naturalness
# Shapiro-Wilk-Test

model <- lm(Natuerlichkeit~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$Natuerlichkeit, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$Natuerlichkeit~Daten$wissenlevel)

boxplot(Daten$Natuerlichkeit~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval",
        main = "Naturalness")

pairwise.wilcox.test(Daten$Natuerlichkeit, Daten$wissenlevel, p.adjust = "bonferroni")

options(digits=8)

#A401_01
# Shapiro-Wilk-Test

model <- lm(A401_01~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A401_01, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A401_01~Daten$wissenlevel)

boxplot(Daten$A401_01~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A401_01, Daten$wissenlevel, p.adjust = "bonferroni")

#A401_02
# Shapiro-Wilk-Test

model <- lm(A401_02~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A401_02, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A401_02~Daten$wissenlevel)

#A401_03
# Shapiro-Wilk-Test

model <- lm(A401_03~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A401_03, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A401_03~Daten$wissenlevel)

#A401_04
# Shapiro-Wilk-Test

model <- lm(A401_04~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A401_04, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A401_04~Daten$wissenlevel)

#A402_01
# Shapiro-Wilk-Test

model <- lm(A402_01~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A402_01, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A402_01~Daten$wissenlevel)

boxplot(Daten$A402_01~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A402_01, Daten$wissenlevel, p.adjust = "bonferroni")

#A402_02
# Shapiro-Wilk-Test

model <- lm(A402_02~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A402_02, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A402_02~Daten$wissenlevel)

#A402_03
# Shapiro-Wilk-Test

model <- lm(A402_03~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A402_03, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A402_03~Daten$wissenlevel)

#A402_04
# Shapiro-Wilk-Test

model <- lm(A402_04~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A402_04, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A402_04~Daten$wissenlevel)

boxplot(Daten$A402_04~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A402_04, Daten$wissenlevel, p.adjust = "bonferroni")

#A402_05
# Shapiro-Wilk-Test

model <- lm(A402_05~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A402_05, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A402_05~Daten$wissenlevel)

#A403_01
# Shapiro-Wilk-Test

model <- lm(A403_01~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A403_01, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A403_01~Daten$wissenlevel)

boxplot(Daten$A403_01~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A403_01, Daten$wissenlevel, p.adjust = "bonferroni")

#A403_02
# Shapiro-Wilk-Test

model <- lm(A403_02~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A403_02, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A403_02~Daten$wissenlevel)

#A403_03
# Shapiro-Wilk-Test

model <- lm(A403_03~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A403_03, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A403_03~Daten$wissenlevel)

#A403_04
# Shapiro-Wilk-Test

model <- lm(A403_04~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A403_04, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A403_04~Daten$wissenlevel)

#A404_01
# Shapiro-Wilk-Test

model <- lm(A404_01~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A404_01, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A404_01~Daten$wissenlevel)

#A404_02
# Shapiro-Wilk-Test

model <- lm(A404_02~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A404_02, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A404_02~Daten$wissenlevel)

#A404_03
# Shapiro-Wilk-Test

model <- lm(A404_03~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A404_03, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A404_03~Daten$wissenlevel)

#A405_01
# Shapiro-Wilk-Test

model <- lm(A405_01~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A405_01, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A405_01~Daten$wissenlevel)

boxplot(Daten$A405_01~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A405_01, Daten$wissenlevel, p.adjust = "bonferroni")

#A405_02
# Shapiro-Wilk-Test

model <- lm(A405_02~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A405_02, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A405_02~Daten$wissenlevel)

#A406_01
# Shapiro-Wilk-Test

model <- lm(A406_01~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A406_01, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A406_01~Daten$wissenlevel)

boxplot(Daten$A406_01~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A406_01, Daten$wissenlevel, p.adjust = "bonferroni")

#A406_02
# Shapiro-Wilk-Test

model <- lm(A406_02~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A406_02, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A406_02~Daten$wissenlevel)

#A406_03
# Shapiro-Wilk-Test

model <- lm(A406_03~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A406_03, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A406_03~Daten$wissenlevel)

#A407_01
# Shapiro-Wilk-Test

model <- lm(A407_01~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A407_01, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A407_01~Daten$wissenlevel)

#A407_02
# Shapiro-Wilk-Test

model <- lm(A407_02~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A407_02, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A407_02~Daten$wissenlevel)

boxplot(Daten$A407_02~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A407_02, Daten$wissenlevel, p.adjust = "bonferroni")

#A407_03
# Shapiro-Wilk-Test

model <- lm(A407_03~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A407_03, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A407_03~Daten$wissenlevel)

#A408_01
# Shapiro-Wilk-Test

model <- lm(A408_01~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A408_01, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A408_01~Daten$wissenlevel)

#A408_02
# Shapiro-Wilk-Test

model <- lm(A408_02~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A408_02, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A408_02~Daten$wissenlevel)

#A408_03
# Shapiro-Wilk-Test

model <- lm(A408_03~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A408_03, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A408_03~Daten$wissenlevel)

#A408_04
# Shapiro-Wilk-Test

model <- lm(A408_04~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A408_04, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A408_04~Daten$wissenlevel)

boxplot(Daten$A408_04~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A408_04, Daten$wissenlevel, p.adjust = "bonferroni")

#A408_05
# Shapiro-Wilk-Test

model <- lm(A408_05~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A408_05, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A408_05~Daten$wissenlevel)

#A409_01
# Shapiro-Wilk-Test

model <- lm(A409_01~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A409_01, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A409_01~Daten$wissenlevel)

#A409_02
# Shapiro-Wilk-Test

model <- lm(A409_02~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A409_02, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A409_02~Daten$wissenlevel)

#A409_03
# Shapiro-Wilk-Test

model <- lm(A409_03~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A409_03, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A409_03~Daten$wissenlevel)

#A410_01
# Shapiro-Wilk-Test

model <- lm(A410_01~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A410_01, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A410_01~Daten$wissenlevel)

#A410_02
# Shapiro-Wilk-Test

model <- lm(A410_02~wissenlevel, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A410_02, Daten$wissenlevel)

# Kruskal-Wallis-Test

kruskal.test(Daten$A410_02~Daten$wissenlevel)

boxplot(Daten$A410_02~Daten$wissenlevel,
        xlab = "knowledgegroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A410_02, Daten$wissenlevel, p.adjust = "bonferroni")

################################################################################

# descriptive statistics of the buyer groups

mean(rarely$A202_01, na.rm=T) # age
mean(regular$A202_01, na.rm=T) # age
mean(frequent$A202_01, na.rm=T) # age
sd(rarely$A202_01, na.rm=T) # age
sd(regular$A202_01, na.rm=T) # age
sd(frequent$A202_01, na.rm=T) # age

table(rarely$A201) # gender
table(regular$A201) # gender
table(frequent$A201) # gender

table(rarely$ernaehrung) # diet
table(regular$ernaehrung) # diet
table(frequent$ernaehrung) # diet

table(rarely$schule) # education
table(regular$schule) # education
table(frequent$schule) # education

table(rarely$einkommen) # income
table(regular$einkommen) # income
table(frequent$einkommen) # income

table(rarely$wohnort) # residence
table(regular$wohnort) # residence
table(frequent$wohnort) # residence

table(rarely$wissenlevel) # knowledge
table(regular$wissenlevel) # knowledge
table(frequent$wissenlevel) # knowledge

table(rarely$milch) # dairy consumption
table(regular$milch) # dairy consumption
table(frequent$milch) # dairy consumption

table(rarely$milch1) # plant-based milk consumption
table(regular$milch1) # plant-based milk consumption
table(frequent$milch1) # plant-based milk consumption

mean(rarely$AEI, na.rm=T); sd(rarely$AEI, na.rm=T)
mean(regular$AEI, na.rm=T); sd(regular$AEI, na.rm=T)
mean(frequent$AEI, na.rm=T); sd(frequent$AEI, na.rm=T)

mean(rarely$SAI, na.rm=T); sd(rarely$SAI, na.rm=T)
mean(regular$SAI, na.rm=T); sd(regular$SAI, na.rm=T)
mean(frequent$SAI, na.rm=T); sd(frequent$SAI, na.rm=T)

mean(rarely$NEP); sd(rarely$NEP)
mean(regular$NEP); sd(regular$NEP)
mean(frequent$NEP); sd(frequent$NEP)

mean(rarely$Natuerlichkeit); sd(rarely$Natuerlichkeit)
mean(regular$Natuerlichkeit); sd(regular$Natuerlichkeit)
mean(frequent$Natuerlichkeit); sd(frequent$Natuerlichkeit)

mean(rarely$anthro); sd(rarely$anthro)
mean(rarely$anthroindirekt); sd(rarely$anthroindirekt)
mean(rarely$utilitarismus); sd(rarely$utilitarismus)
mean(rarely$newdeal); sd(rarely$newdeal)
mean(rarely$relationismus); sd(rarely$relationismus)
mean(rarely$tierrechtestreng); sd(rarely$tierrechtestreng)
mean(rarely$tierrechteschwach); sd(rarely$tierrechteschwach)
mean(rarely$abolitionismus); sd(rarely$abolitionismus)

mean(regular$anthro); sd(regular$anthro)
mean(regular$anthroindirekt); sd(regular$anthroindirekt)
mean(regular$utilitarismus); sd(regular$utilitarismus)
mean(regular$newdeal); sd(regular$newdeal)
mean(regular$relationismus); sd(regular$relationismus)
mean(regular$tierrechtestreng); sd(regular$tierrechtestreng)
mean(regular$tierrechteschwach); sd(regular$tierrechteschwach)
mean(regular$abolitionismus); sd(regular$abolitionismus)

mean(frequent$anthro); sd(frequent$anthro)
mean(frequent$anthroindirekt); sd(frequent$anthroindirekt)
mean(frequent$utilitarismus); sd(frequent$utilitarismus)
mean(frequent$newdeal); sd(frequent$newdeal)
mean(frequent$relationismus); sd(frequent$relationismus)
mean(frequent$tierrechtestreng); sd(frequent$tierrechtestreng)
mean(frequent$tierrechteschwach); sd(frequent$tierrechteschwach)
mean(frequent$abolitionismus); sd(frequent$abolitionismus)

mean(rarely$A401_01, na.rm=T)
mean(rarely$A401_02, na.rm=T)
mean(rarely$A401_03, na.rm=T)
mean(rarely$A401_04, na.rm=T)
mean(rarely$A402_05, na.rm=T)
mean(rarely$A402_01, na.rm=T)
mean(rarely$A402_04, na.rm=T)
mean(rarely$A402_02, na.rm=T)
mean(rarely$A402_03, na.rm=T)
mean(rarely$A403_04, na.rm=T)
mean(rarely$A403_01, na.rm=T)
mean(rarely$A403_02, na.rm=T)
mean(rarely$A403_03, na.rm=T)
mean(rarely$A404_01, na.rm=T)
mean(rarely$A404_02, na.rm=T)
mean(rarely$A404_03, na.rm=T)
mean(rarely$A405_02, na.rm=T)
mean(rarely$A405_01, na.rm=T)
mean(rarely$A406_01, na.rm=T)
mean(rarely$A406_03, na.rm=T)
mean(rarely$A406_02, na.rm=T)
mean(rarely$A407_02, na.rm=T)
mean(rarely$A407_01, na.rm=T)
mean(rarely$A407_03, na.rm=T)
mean(rarely$A408_02, na.rm=T)
mean(rarely$A408_05, na.rm=T)
mean(rarely$A408_03, na.rm=T)
mean(rarely$A408_04, na.rm=T)
mean(rarely$A408_01, na.rm=T)
mean(rarely$A409_01, na.rm=T)
mean(rarely$A409_02, na.rm=T)
mean(rarely$A409_03, na.rm=T)
mean(rarely$A410_01, na.rm=T)
mean(rarely$A410_02, na.rm=T)

mean(regular$A401_01, na.rm=T)
mean(regular$A401_02, na.rm=T)
mean(regular$A401_03, na.rm=T)
mean(regular$A401_04, na.rm=T)
mean(regular$A402_05, na.rm=T)
mean(regular$A402_01, na.rm=T)
mean(regular$A402_04, na.rm=T)
mean(regular$A402_02, na.rm=T)
mean(regular$A402_03, na.rm=T)
mean(regular$A403_04, na.rm=T)
mean(regular$A403_01, na.rm=T)
mean(regular$A403_02, na.rm=T)
mean(regular$A403_03, na.rm=T)
mean(regular$A404_01, na.rm=T)
mean(regular$A404_02, na.rm=T)
mean(regular$A404_03, na.rm=T)
mean(regular$A405_02, na.rm=T)
mean(regular$A405_01, na.rm=T)
mean(regular$A406_01, na.rm=T)
mean(regular$A406_03, na.rm=T)
mean(regular$A406_02, na.rm=T)
mean(regular$A407_02, na.rm=T)
mean(regular$A407_01, na.rm=T)
mean(regular$A407_03, na.rm=T)
mean(regular$A408_02, na.rm=T)
mean(regular$A408_05, na.rm=T)
mean(regular$A408_03, na.rm=T)
mean(regular$A408_04, na.rm=T)
mean(regular$A408_01, na.rm=T)
mean(regular$A409_01, na.rm=T)
mean(regular$A409_02, na.rm=T)
mean(regular$A409_03, na.rm=T)
mean(regular$A410_01, na.rm=T)
mean(regular$A410_02, na.rm=T)

mean(frequent$A401_01, na.rm=T)
mean(frequent$A401_02, na.rm=T)
mean(frequent$A401_03, na.rm=T)
mean(frequent$A401_04, na.rm=T)
mean(frequent$A402_05, na.rm=T)
mean(frequent$A402_01, na.rm=T)
mean(frequent$A402_04, na.rm=T)
mean(frequent$A402_02, na.rm=T)
mean(frequent$A402_03, na.rm=T)
mean(frequent$A403_04, na.rm=T)
mean(frequent$A403_01, na.rm=T)
mean(frequent$A403_02, na.rm=T)
mean(frequent$A403_03, na.rm=T)
mean(frequent$A404_01, na.rm=T)
mean(frequent$A404_02, na.rm=T)
mean(frequent$A404_03, na.rm=T)
mean(frequent$A405_02, na.rm=T)
mean(frequent$A405_01, na.rm=T)
mean(frequent$A406_01, na.rm=T)
mean(frequent$A406_03, na.rm=T)
mean(frequent$A406_02, na.rm=T)
mean(frequent$A407_02, na.rm=T)
mean(frequent$A407_01, na.rm=T)
mean(frequent$A407_03, na.rm=T)
mean(frequent$A408_02, na.rm=T)
mean(frequent$A408_05, na.rm=T)
mean(frequent$A408_03, na.rm=T)
mean(frequent$A408_04, na.rm=T)
mean(frequent$A408_01, na.rm=T)
mean(frequent$A409_01, na.rm=T)
mean(frequent$A409_02, na.rm=T)
mean(frequent$A409_03, na.rm=T)
mean(frequent$A410_01, na.rm=T)
mean(frequent$A410_02, na.rm=T)

sd(rarely$A401_01, na.rm=T)
sd(rarely$A401_02, na.rm=T)
sd(rarely$A401_03, na.rm=T)
sd(rarely$A401_04, na.rm=T)
sd(rarely$A402_05, na.rm=T)
sd(rarely$A402_01, na.rm=T)
sd(rarely$A402_04, na.rm=T)
sd(rarely$A402_02, na.rm=T)
sd(rarely$A402_03, na.rm=T)
sd(rarely$A403_04, na.rm=T)
sd(rarely$A403_01, na.rm=T)
sd(rarely$A403_02, na.rm=T)
sd(rarely$A403_03, na.rm=T)
sd(rarely$A404_01, na.rm=T)
sd(rarely$A404_02, na.rm=T)
sd(rarely$A404_03, na.rm=T)
sd(rarely$A405_02, na.rm=T)
sd(rarely$A405_01, na.rm=T)
sd(rarely$A406_01, na.rm=T)
sd(rarely$A406_03, na.rm=T)
sd(rarely$A406_02, na.rm=T)
sd(rarely$A407_02, na.rm=T)
sd(rarely$A407_01, na.rm=T)
sd(rarely$A407_03, na.rm=T)
sd(rarely$A408_02, na.rm=T)
sd(rarely$A408_05, na.rm=T)
sd(rarely$A408_03, na.rm=T)
sd(rarely$A408_04, na.rm=T)
sd(rarely$A408_01, na.rm=T)
sd(rarely$A409_01, na.rm=T)
sd(rarely$A409_02, na.rm=T)
sd(rarely$A409_03, na.rm=T)
sd(rarely$A410_01, na.rm=T)
sd(rarely$A410_02, na.rm=T)

sd(regular$A401_01, na.rm=T)
sd(regular$A401_02, na.rm=T)
sd(regular$A401_03, na.rm=T)
sd(regular$A401_04, na.rm=T)
sd(regular$A402_05, na.rm=T)
sd(regular$A402_01, na.rm=T)
sd(regular$A402_04, na.rm=T)
sd(regular$A402_02, na.rm=T)
sd(regular$A402_03, na.rm=T)
sd(regular$A403_04, na.rm=T)
sd(regular$A403_01, na.rm=T)
sd(regular$A403_02, na.rm=T)
sd(regular$A403_03, na.rm=T)
sd(regular$A404_01, na.rm=T)
sd(regular$A404_02, na.rm=T)
sd(regular$A404_03, na.rm=T)
sd(regular$A405_02, na.rm=T)
sd(regular$A405_01, na.rm=T)
sd(regular$A406_01, na.rm=T)
sd(regular$A406_03, na.rm=T)
sd(regular$A406_02, na.rm=T)
sd(regular$A407_02, na.rm=T)
sd(regular$A407_01, na.rm=T)
sd(regular$A407_03, na.rm=T)
sd(regular$A408_02, na.rm=T)
sd(regular$A408_05, na.rm=T)
sd(regular$A408_03, na.rm=T)
sd(regular$A408_04, na.rm=T)
sd(regular$A408_01, na.rm=T)
sd(regular$A409_01, na.rm=T)
sd(regular$A409_02, na.rm=T)
sd(regular$A409_03, na.rm=T)
sd(regular$A410_01, na.rm=T)
sd(regular$A410_02, na.rm=T)

sd(frequent$A401_01, na.rm=T)
sd(frequent$A401_02, na.rm=T)
sd(frequent$A401_03, na.rm=T)
sd(frequent$A401_04, na.rm=T)
sd(frequent$A402_05, na.rm=T)
sd(frequent$A402_01, na.rm=T)
sd(frequent$A402_04, na.rm=T)
sd(frequent$A402_02, na.rm=T)
sd(frequent$A402_03, na.rm=T)
sd(frequent$A403_04, na.rm=T)
sd(frequent$A403_01, na.rm=T)
sd(frequent$A403_02, na.rm=T)
sd(frequent$A403_03, na.rm=T)
sd(frequent$A404_01, na.rm=T)
sd(frequent$A404_02, na.rm=T)
sd(frequent$A404_03, na.rm=T)
sd(frequent$A405_02, na.rm=T)
sd(frequent$A405_01, na.rm=T)
sd(frequent$A406_01, na.rm=T)
sd(frequent$A406_03, na.rm=T)
sd(frequent$A406_02, na.rm=T)
sd(frequent$A407_02, na.rm=T)
sd(frequent$A407_01, na.rm=T)
sd(frequent$A407_03, na.rm=T)
sd(frequent$A408_02, na.rm=T)
sd(frequent$A408_05, na.rm=T)
sd(frequent$A408_03, na.rm=T)
sd(frequent$A408_04, na.rm=T)
sd(frequent$A408_01, na.rm=T)
sd(frequent$A409_01, na.rm=T)
sd(frequent$A409_02, na.rm=T)
sd(frequent$A409_03, na.rm=T)
sd(frequent$A410_01, na.rm=T)
sd(frequent$A410_02, na.rm=T)

# mean comparisons

options(digits=8)

#AEI
# Shapiro-Wilk-Test

model <- lm(AEI~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$AEI, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$AEI~Daten$bio)

Daten$bio <- factor(Daten$bio, levels = c("rarely", "regular", "frequent"))
levels(Daten$bio)
levels(Daten$bio) <- c("rare", "regular", "frequent")

boxplot(Daten$AEI~Daten$bio,
        xlab = "Organic buyer groups",
        ylab = "")

pairwise.wilcox.test(Daten$AEI, Daten$bio, p.adjust = "bonferroni")

Daten$bio <- factor(Daten$bio, levels = c("frequent", "rare", "regular"))
levels(Daten$bio) <- c("frequent", "rarely", "regular")

#SAI
# Shapiro-Wilk-Test

model <- lm(SAI~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$SAI, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$SAI~Daten$bio)

#anthro
# Shapiro-Wilk-Test

model <- lm(anthro~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$anthro, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$anthro~Daten$bio)

#anthroindirect
# Shapiro-Wilk-Test

model <- lm(anthroindirekt~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$anthroindirekt, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$anthroindirekt~Daten$bio)

boxplot(Daten$anthroindirekt~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$anthroindirekt, Daten$bio, p.adjust = "bonferroni")

#utilitarianism
# Shapiro-Wilk-Test

model <- lm(utilitarismus~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$utilitarismus, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$utilitarismus~Daten$bio)

#newdeal
# Shapiro-Wilk-Test

model <- lm(newdeal~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$newdeal, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$newdeal~Daten$bio)

#relationism
# Shapiro-Wilk-Test

model <- lm(relationismus~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$relationismus, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$relationismus~Daten$bio)

boxplot(Daten$relationismus~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$relationismus, Daten$bio, p.adjust = "bonferroni")

#strictanimalrights
# Shapiro-Wilk-Test

model <- lm(tierrechtestreng~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$tierrechtestreng, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$tierrechtestreng~Daten$bio)

boxplot(Daten$tierrechtestreng~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$tierrechtestreng, Daten$bio, p.adjust = "bonferroni")

#weakanimalrights
# Shapiro-Wilk-Test

model <- lm(tierrechteschwach~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$tierrechteschwach, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$tierrechteschwach~Daten$bio)

boxplot(Daten$tierrechteschwach~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$tierrechteschwach, Daten$bio, p.adjust = "bonferroni")

#abolitionism
# Shapiro-Wilk-Test

model <- lm(abolitionismus~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$abolitionismus, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$abolitionismus~Daten$bio)

boxplot(Daten$abolitionismus~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$abolitionismus, Daten$bio, p.adjust = "bonferroni")

#NEP
# Shapiro-Wilk-Test

model <- lm(NEP~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$NEP, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$NEP~Daten$bio)

boxplot(Daten$NEP~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$NEP, Daten$bio, p.adjust = "bonferroni")

#Naturalness
# Shapiro-Wilk-Test

model <- lm(Natuerlichkeit~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$Natuerlichkeit, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$Natuerlichkeit~Daten$bio)

boxplot(Daten$Natuerlichkeit~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$Natuerlichkeit, Daten$bio, p.adjust = "bonferroni")

#A401_01
# Shapiro-Wilk-Test

model <- lm(A401_01~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A401_01, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A401_01~Daten$bio)

boxplot(Daten$A401_01~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A401_01, Daten$bio, p.adjust = "bonferroni")

#A401_02
# Shapiro-Wilk-Test

model <- lm(A401_02~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A401_02, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A401_02~Daten$bio)

#A401_03
# Shapiro-Wilk-Test

model <- lm(A401_03~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A401_03, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A401_03~Daten$bio)

#A401_04
# Shapiro-Wilk-Test

model <- lm(A401_04~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A401_04, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A401_04~Daten$bio)

#A402_01
# Shapiro-Wilk-Test

model <- lm(A402_01~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A402_01, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A402_01~Daten$bio)

boxplot(Daten$A402_01~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A402_01, Daten$bio, p.adjust = "bonferroni")

#A402_02
# Shapiro-Wilk-Test

model <- lm(A402_02~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A402_02, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A402_02~Daten$bio)

boxplot(Daten$A402_02~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A402_02, Daten$bio, p.adjust = "bonferroni")

#A402_03
# Shapiro-Wilk-Test

model <- lm(A402_03~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A402_03, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A402_03~Daten$bio)

#A402_04
# Shapiro-Wilk-Test

model <- lm(A402_04~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A402_04, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A402_04~Daten$bio)

#A402_05
# Shapiro-Wilk-Test

model <- lm(A402_05~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A402_05, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A402_05~Daten$bio)

#A403_01
# Shapiro-Wilk-Test

model <- lm(A403_01~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A403_01, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A403_01~Daten$bio)

boxplot(Daten$A403_01~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A403_01, Daten$bio, p.adjust = "bonferroni")

#A403_02
# Shapiro-Wilk-Test

model <- lm(A403_02~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A403_02, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A403_02~Daten$bio)

#A403_03
# Shapiro-Wilk-Test

model <- lm(A403_03~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A403_03, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A403_03~Daten$bio)

#A403_04
# Shapiro-Wilk-Test

model <- lm(A403_04~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A403_04, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A403_04~Daten$bio)

#A404_01
# Shapiro-Wilk-Test

model <- lm(A404_01~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A404_01, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A404_01~Daten$bio)

#A404_02
# Shapiro-Wilk-Test

model <- lm(A404_02~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A404_02, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A404_02~Daten$bio)

#A404_03
# Shapiro-Wilk-Test

model <- lm(A404_03~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A404_03, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A404_03~Daten$bio)

#A405_01
# Shapiro-Wilk-Test

model <- lm(A405_01~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A405_01, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A405_01~Daten$bio)

#A405_02
# Shapiro-Wilk-Test

model <- lm(A405_02~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A405_02, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A405_02~Daten$bio)

#A406_01
# Shapiro-Wilk-Test

model <- lm(A406_01~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A406_01, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A406_01~Daten$bio)

boxplot(Daten$A406_01~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A406_01, Daten$bio, p.adjust = "bonferroni")

#A406_02
# Shapiro-Wilk-Test

model <- lm(A406_02~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A406_02, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A406_02~Daten$bio)

#A406_03
# Shapiro-Wilk-Test

model <- lm(A406_03~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A406_03, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A406_03~Daten$bio)

boxplot(Daten$A406_03~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A406_03, Daten$bio, p.adjust = "bonferroni")

#A407_01
# Shapiro-Wilk-Test

model <- lm(A407_01~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A407_01, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A407_01~Daten$bio)

#A407_02
# Shapiro-Wilk-Test

model <- lm(A407_02~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A407_02, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A407_02~Daten$bio)

boxplot(Daten$A407_02~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A407_02, Daten$bio, p.adjust = "bonferroni")

#A407_03
# Shapiro-Wilk-Test

model <- lm(A407_03~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A407_03, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A407_03~Daten$bio)

boxplot(Daten$A407_03~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A407_03, Daten$bio, p.adjust = "bonferroni")

#A408_01
# Shapiro-Wilk-Test

model <- lm(A408_01~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A408_01, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A408_01~Daten$bio)

#A408_02
# Shapiro-Wilk-Test

model <- lm(A408_02~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A408_02, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A408_02~Daten$bio)

#A408_03
# Shapiro-Wilk-Test

model <- lm(A408_03~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A408_03, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A408_03~Daten$bio)

#A408_04
# Shapiro-Wilk-Test

model <- lm(A408_04~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A408_04, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A408_04~Daten$bio)

boxplot(Daten$A408_04~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A408_04, Daten$bio, p.adjust = "bonferroni")

#A408_05
# Shapiro-Wilk-Test

model <- lm(A408_05~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A408_05, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A408_05~Daten$bio)

#A409_01
# Shapiro-Wilk-Test

model <- lm(A409_01~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A409_01, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A409_01~Daten$bio)

boxplot(Daten$A409_01~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A409_01, Daten$bio, p.adjust = "bonferroni")

#A409_02
# Shapiro-Wilk-Test

model <- lm(A409_02~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A409_02, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A409_02~Daten$bio)

#A409_03
# Shapiro-Wilk-Test

model <- lm(A409_03~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A409_03, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A409_03~Daten$bio)

#A410_01
# Shapiro-Wilk-Test

model <- lm(A410_01~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A410_01, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A410_01~Daten$bio)

boxplot(Daten$A410_01~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A410_01, Daten$bio, p.adjust = "bonferroni")

#A410_02
# Shapiro-Wilk-Test

model <- lm(A410_02~bio, data = Daten)
shapiro.test(residuals(model))

# Levene-Test

leveneTest(Daten$A410_02, Daten$bio)

# Kruskal-Wallis-Test

kruskal.test(Daten$A410_02~Daten$bio)

boxplot(Daten$A410_02~Daten$bio,
        xlab = "consumergroup",
        ylab = "degree of approval")

pairwise.wilcox.test(Daten$A410_02, Daten$bio, p.adjust = "bonferroni")

################################################################################


rm(list=ls())