Revised_Week4_combine
Weijia Bao
8/7/2019
#load data
wave2<-read.csv("~/Downloads/GG identification across groups Wave 2.csv") %>%
dplyr::select(CONDITION:Trust_levelup_4) %>%
mutate(CONDITION=dplyr::recode(CONDITION, '1'="1", '2'="2",'3'="3",'4'="4")) %>%
dplyr::filter(Trust_levelup_4 > 1) %>%
dplyr::select(CONDITION:workerId)Heatmap
htmap4.p<-read.csv("~/Desktop/w4_anova_p.csv"); htmap4.f<-read.csv("~/Desktop/w4_anova_f.csv")
##wide to long, using Base R
htmap4.mp<-melt(htmap4.p) #wide to long base R, equivalently as the following
htmap4.mf<-melt(htmap4.f)
#equivalently, using dplyr
#htmap.mp<-htmap.p %>% gather("comparison", "p_value", Ingroup.dual.p:control.outgroup.p)
#htmap.mt<-htmap.t %>% gather("comparison", "t_value", Ingroup.dual.t:control.outgroup.t)
htmap4.mp$f_val<-htmap4.mf$value; names(htmap4.mp)<-c("var", "comparison", "p_val", "f_val")
combine4.pf<-htmap4.mp
#combine4.pf
#htmap.m<-ddply(htmap.m, .(variable), transform, rescale = rescale(value)) make the discrete p-val to continuous scale
combine4.pf$sig_level <- ifelse(combine4.pf$p_val <= 0.05, "sig",
ifelse(combine4.pf$p_val > 0.1, "non_sig", "marginally_sig")) #nested if_else statements to classify p-val into 3 groups: 0-0.05 very sig, 0.05-0.1 sig, >0.1 non_sig
combine4.pf$dir <- ifelse(combine4.pf$f_val > 0, "positive", "negative")
combine4.pf$sig_level<-factor(combine4.pf$sig_level, levels = c("sig", "marginally_sig", "non-sig")) #define the order of legend bar
ggplot(combine4.pf, aes(comparison, var, fill = sig_level, colour = dir)) + #x-axis comparison
geom_tile() +
scale_fill_manual(values = c(sig = "black",marginally_sig = "gray",non_sig = "white")) +
scale_colour_manual(values = c(positive = "green", negative = "red", size=50))+
xlab("") +
theme(axis.text.x = element_text( angle = 90, hjust = 1))
merge data and prepare for multilevel analysis
#merge data
wave_1<-read.csv("~/Downloads/GG identification across groups Wave 1.csv") %>%
dplyr::select(CONDITION:Gender, LocationLatitude, LocationLongitude, workerId) %>%
mutate(CONDITION=dplyr::recode(CONDITION, '0'="Experiment", '1'="Control"))
wave_merge<-merge(wave_1, wave2, by="workerId") %>% dplyr::select(-workerId)
wave_total <- wave_merge %>% dplyr::select(contains(".")) %>%
dplyr::select(Essentialism_SCL.x, Essentialism_SCL.y, Identification_SCL.x, Identification_SCL.y) %>%
tibble::rowid_to_column() %>%
gather(key, value, Essentialism_SCL.x:Identification_SCL.y)
#########################
wave_select <- wave_merge %>% dplyr::select(CONDITION.y,Essentialism_SCL.x, Essentialism_SCL.y, Identification_SCL.x, Identification_SCL.y, Mexican_3, Mexican_4, GG_level_Mexican, GG_level_3, GG_level_4, GG_Level) %>% dplyr::rename(CONDITION = CONDITION.y)
wave_total$gp <- ifelse(grepl("^.+\\.(x)$", wave_total$key) == TRUE, "wave1", "wave2") #use regular expression to extract the last digit of group (eg:Muslims_4 -> 4)
wave_total$key <-
ifelse(wave_total$key == 'Essentialism_SCL.x' |wave_total$key == 'Essentialism_SCL.y',
"Essentialism_SCL",
ifelse(wave_total$key=='Identification_SCL.x'|wave_total$key=='Identification_SCL.y', "Identification_SCL",
ifelse(wave_total$key=='Age.x'|wave_total$key=='Age.y', "Age", "Gender")))
wave <- wave_total %>% select(key,gp, value) %>% mutate()###Compare the difference in "GG_Level"
wave.compare<-wave_merge
wave.compare$diff <-
ifelse(wave.compare$GG_Level > wave.compare$GG_level_Mexican ,"increase",
ifelse(wave.compare$GG_Level < wave.compare$GG_level_Mexican,"decrease","same"))
wave.compare<- wave.compare %>%
dplyr::select(diff, Simon_Dual_identity_SCL:Gender.y)%>%
dplyr::rename(Identification_SCL = Identification_SCL.y, Essentialism_SCL = Essentialism_SCL.y, Age= Age.y, Gender= Gender.y)%>%
drop_na(diff)
###Compare the difference in "Mexican_3"
wave.compare3<-wave_merge
wave.compare3$diff <-
ifelse(wave.compare3$GG_level_3 > wave.compare3$Mexican_3 ,"increase",
ifelse(wave.compare3$GG_level_3 < wave.compare3$Mexican_3,"decrease","same"))
wave.compare3<- wave.compare3 %>%
dplyr::select(diff, Simon_Dual_identity_SCL:Gender.y)%>%
dplyr::rename(Identification_SCL = Identification_SCL.y, Essentialism_SCL = Essentialism_SCL.y, Age= Age.y, Gender= Gender.y)%>%
drop_na(diff)
###Compare the difference in "Mexican_4"
wave.compare4<-wave_merge
wave.compare4$diff <-
ifelse(wave.compare4$GG_level_4 > wave.compare4$Mexican_4 ,"increase",
ifelse(wave.compare4$GG_level_4 < wave.compare4$Mexican_4,"decrease","same"))
wave.compare4<- wave.compare4 %>%
dplyr::select(diff, Simon_Dual_identity_SCL:Gender.y)%>%
dplyr::rename(Identification_SCL = Identification_SCL.y, Essentialism_SCL = Essentialism_SCL.y, Age= Age.y, Gender= Gender.y)%>%
drop_na(diff)anova comparisons for each 33 dependent variables
library(multcomp)
#The function TukeyHD() takes the fitted ANOVA as an argument
#anova-p-results
p_rst<-function(X, data){
resul<-TukeyHSD(aov(X ~ diff, data = data))
return(resul$diff[,4])
}
anova_p<-function(X, data){
res.aov<-aov(X~diff, data=data)
res.anova<-anova(res.aov)
return(res.anova$`Pr(>F)`[1])
}
#anova-f-results
f_rst<-function(X, data){
result<-summary(glht(lm(X ~ diff, data = data), linfct = mcp(diff = "Tukey")))
return(result$test$tstat)
}
anova_f<-function(X, data){
res.aov<-aov(X~diff, data=data)
res.anova<-anova(res.aov)
return(res.anova$`F value`[1])
}
###GG_Level
wave.compare$diff<-as.factor(wave.compare$diff)
wave.compare3$diff<-as.factor(wave.compare3$diff)
wave.compare4$diff<-as.factor(wave.compare4$diff)
###test functions above, all worked !!!
#p_rst(wave.compare3$GG_Angst, wave.compare3)
#anova_p(wave.compare$GG_Angst, wave.compare3)
#f_rst(wave.compare$GG_Angst, wave.compare3)
#anova_f(wave.compare$GG_Angst, wave.compare3)result preparation
GG_Level
###p-value preparation
p_GG_Level<- data.frame(matrix(ncol = 4))
for (i in 2:34){
p_GG_Level[(i-1),] <- c(p_rst(wave.compare[,i], wave.compare), anova_p(wave.compare[,i], wave.compare))
}
colnames(p_GG_Level) <- c("increase-decrease", "same-decrease", "same-increase", "ANOVA")
p_GG_Level$var<-colnames(wave.compare[,-1])
###f-value preparation
f_GG_Level<-data.frame(matrix(ncol = 4))
for (i in 2:34){
f_GG_Level[(i-1),] <- c(f_rst(wave.compare[,i], wave.compare), anova_f(wave.compare[,i], wave.compare))
}
colnames(f_GG_Level) <- c("increase-decrease", "same-decrease", "same-increase", "ANOVA")
f_GG_Level$var <-colnames(wave.compare[,-1])
p_GG_Level;f_GG_Level## increase-decrease same-decrease same-increase ANOVA
## 1 0.29984565 8.747923e-02 5.592627e-01 8.340027e-02
## 2 0.99733913 8.476278e-03 6.357651e-03 5.136427e-03
## 3 0.55227870 7.199666e-03 3.921190e-04 6.294379e-04
## 4 0.79126653 2.385674e-04 2.376385e-05 2.756228e-05
## 5 0.49121398 3.097606e-05 3.831217e-07 6.141102e-07
## 6 0.68332545 7.585790e-05 3.434732e-06 4.442838e-06
## 7 0.99910326 2.231525e-05 1.961500e-05 8.289604e-06
## 8 0.99832985 3.298897e-02 2.701060e-02 2.349450e-02
## 9 0.73563601 2.892140e-01 9.364428e-02 1.144493e-01
## 10 0.78755905 3.662794e-03 5.280300e-04 6.807195e-04
## 11 0.59778696 5.492170e-03 3.466864e-04 5.402859e-04
## 12 0.97400471 3.225853e-03 1.566902e-03 1.380080e-03
## 13 0.76645719 6.123785e-03 8.670617e-04 1.157315e-03
## 14 0.60731101 2.118117e-01 4.160060e-02 5.379728e-02
## 15 0.91546442 1.379197e-02 4.800450e-03 5.309156e-03
## 16 0.66493809 2.075563e-03 1.475121e-04 2.157432e-04
## 17 0.81387688 5.687123e-02 1.641946e-02 2.107987e-02
## 18 0.90550981 5.665290e-02 2.264084e-02 2.621219e-02
## 19 0.61372891 9.380703e-03 7.219606e-04 1.105387e-03
## 20 0.59575940 6.822451e-03 4.487338e-04 6.989819e-04
## 21 0.06889727 7.191020e-01 6.480707e-01 8.578662e-02
## 22 0.57334678 2.102608e-01 3.706550e-02 4.812318e-02
## 23 0.68890230 1.422431e-02 1.675136e-03 2.410769e-03
## 24 0.64159946 6.099618e-03 4.829156e-04 7.261736e-04
## 25 0.99416459 3.968352e-03 2.647838e-03 2.101176e-03
## 26 0.18215681 5.020139e-01 3.748337e-02 3.161163e-02
## 27 0.31633081 1.565994e-03 1.517995e-05 2.929835e-05
## 28 0.42728910 9.392130e-01 8.223998e-01 4.554729e-01
## 29 0.50502833 2.009688e-03 6.344576e-05 1.069571e-04
## 30 0.89689863 3.817979e-02 1.375559e-02 1.604826e-02
## 31 0.49318774 1.721208e-02 9.073028e-04 1.466702e-03
## 32 0.91081864 9.983936e-01 9.293169e-01 8.942851e-01
## 33 0.92614569 7.020339e-01 8.559464e-01 7.236039e-01
## var
## 1 Simon_Dual_identity_SCL
## 2 GG_Angst
## 3 Stereotype_SCL
## 4 Symb_Threat_SCL
## 5 Real_Threat_SCL
## 6 ITT
## 7 Humanization
## 8 Peception_of_GC_mediator
## 9 Peception_of_GC_bridge
## 10 Peception_of_GC_fifth_column
## 11 Peception_of_GC_traitors
## 12 Peception_of_GC_unique
## 13 Peception_of_GC_weak
## 14 Peception_of_GC_lmlm
## 15 Positive_perception_of_GC_SCL
## 16 Negative_perception_of_GC_SCL
## 17 Surprise
## 18 Common_fate_SCL
## 19 CIIM_SCL
## 20 SDO_SCL
## 21 Identification_SCL
## 22 Essentialism_SCL
## 23 Hatered
## 24 Fear
## 25 Anger
## 26 Hope
## 27 Empathy
## 28 Despair
## 29 Policy_SCL
## 30 Resource_allocation_SCL
## 31 Social_Distance_SCL
## 32 Age
## 33 Gender## increase-decrease same-decrease same-increase ANOVA
## 1 1.48374338 2.11824448 1.0285892 2.5002009
## 2 0.06951833 -2.98439196 -3.0755293 5.3442366
## 3 1.03969245 -3.03642038 -3.8587300 7.5136107
## 4 0.65214070 -3.98413408 -4.5269543 10.7906517
## 5 1.13809580 -4.46743250 -5.3824366 14.8478728
## 6 0.83207984 -4.26114145 -4.9430483 12.7272826
## 7 0.04033907 4.54098230 4.5696358 12.0634130
## 8 -0.05506250 2.51390610 2.5880432 3.7877726
## 9 -0.74697550 1.50598476 2.0879984 2.1798733
## 10 0.65865921 -3.24380836 -3.7819135 7.4322471
## 11 0.96763705 -3.12097819 -3.8901326 7.6723637
## 12 -0.21859103 3.28147759 3.4887215 6.6995596
## 13 0.69516455 -3.08722665 -3.6507832 6.8818085
## 14 0.95260972 -1.68609544 -2.4252833 2.9448301
## 15 -0.40036586 2.82410154 3.1622681 5.3102460
## 16 0.86144234 -3.40936246 -4.1023058 8.6292419
## 17 0.61164469 -2.30373262 -2.7696614 3.9118052
## 18 0.42443816 -2.30237641 -2.6518865 3.6761924
## 19 -0.94248474 2.95166158 3.6996766 6.9293625
## 20 0.97083709 -3.05339768 -3.8240831 7.4047523
## 21 -2.22122284 -0.77419172 0.8882222 2.4716251
## 22 1.00625819 -1.69012117 -2.4697562 3.0580267
## 23 0.82312976 -2.81365929 -3.4700117 6.1231777
## 24 0.89846738 -3.08845848 -3.8051086 7.3651239
## 25 0.10303233 -3.21984628 -3.3392787 6.2650487
## 26 -1.76694930 1.12047423 2.4654696 3.4854077
## 27 -1.45016094 3.48888342 4.6261382 10.7261549
## 28 -1.24525533 -0.33733482 0.5958996 0.7880277
## 29 1.11557546 -3.41854951 -4.3029627 9.3636944
## 30 -0.44441233 2.45841545 2.8249935 4.1768237
## 31 -1.13486681 2.74835602 3.6385831 6.6365762
## 32 -0.41174226 0.05400026 0.3647250 0.1117631
## 33 0.37313574 0.80195650 0.5314271 0.3237832
## var
## 1 Simon_Dual_identity_SCL
## 2 GG_Angst
## 3 Stereotype_SCL
## 4 Symb_Threat_SCL
## 5 Real_Threat_SCL
## 6 ITT
## 7 Humanization
## 8 Peception_of_GC_mediator
## 9 Peception_of_GC_bridge
## 10 Peception_of_GC_fifth_column
## 11 Peception_of_GC_traitors
## 12 Peception_of_GC_unique
## 13 Peception_of_GC_weak
## 14 Peception_of_GC_lmlm
## 15 Positive_perception_of_GC_SCL
## 16 Negative_perception_of_GC_SCL
## 17 Surprise
## 18 Common_fate_SCL
## 19 CIIM_SCL
## 20 SDO_SCL
## 21 Identification_SCL
## 22 Essentialism_SCL
## 23 Hatered
## 24 Fear
## 25 Anger
## 26 Hope
## 27 Empathy
## 28 Despair
## 29 Policy_SCL
## 30 Resource_allocation_SCL
## 31 Social_Distance_SCL
## 32 Age
## 33 GenderDraw heatmap
ggplot(combine.pf, aes(comparison, var, fill = sig_level, colour = dir)) + #x-axis comparison
geom_tile() +
scale_fill_manual(values = c(sig = "black",marginally_sig = "gray",non_sig = "white")) +
scale_colour_manual(values = c(positive = "green", negative = "red", size=50))+
xlab("") + ylab("")+
ggtitle("Heatmap focus on difference in \"GG level\"")+
theme(axis.text.x = element_text( angle = 90, hjust = 1))
Mexican_3
###p-value preparation
p_Mexican_3<- data.frame(matrix(ncol = 4))
for (i in 2:34){
p_Mexican_3[(i-1),] <- c(p_rst(wave.compare3[,i], wave.compare3), anova_p(wave.compare3[,i], wave.compare3))
}
colnames(p_Mexican_3) <- c("increase-decrease", "same-decrease", "same-increase", "ANOVA")
p_Mexican_3$var<-colnames(wave.compare3[,-1])
###f-value preparation
f_Mexican_3<-data.frame(matrix(ncol = 4))
for (i in 2:34){
f_Mexican_3[(i-1),] <- c(f_rst(wave.compare3[,i], wave.compare3), anova_f(wave.compare3[,i], wave.compare3))
}
colnames(f_Mexican_3) <- c("increase-decrease", "same-decrease", "same-increase", "ANOVA")
f_Mexican_3$var <-colnames(wave.compare3[,-1])
p_Mexican_3; f_Mexican_3## increase-decrease same-decrease same-increase ANOVA
## 1 0.9074727 1.108938e-01 3.862873e-02 3.511621e-02
## 2 0.9732761 4.225900e-05 8.224435e-05 6.786824e-06
## 3 0.8450830 3.366135e-07 3.468514e-06 4.382387e-08
## 4 0.4395175 0.000000e+00 9.889668e-09 1.382964e-12
## 5 0.9516825 0.000000e+00 0.000000e+00 7.369765e-16
## 6 0.9213060 1.107260e-10 6.793365e-10 1.646308e-12
## 7 0.9147573 2.932662e-07 2.269922e-08 1.745227e-09
## 8 0.9265700 2.099302e-04 7.011039e-04 6.721236e-05
## 9 0.9984866 1.454041e-03 1.458044e-03 3.603132e-04
## 10 0.1880325 3.717420e-09 1.768939e-05 3.076580e-09
## 11 0.4918158 4.215730e-08 8.169107e-06 1.511738e-08
## 12 0.9562909 5.107854e-06 9.170317e-07 1.076606e-07
## 13 0.9944997 1.390918e-05 1.603820e-05 1.244142e-06
## 14 0.9109896 1.125039e-01 2.350483e-01 1.076194e-01
## 15 0.9987569 6.117537e-06 5.484143e-06 3.831025e-07
## 16 0.2605471 8.585161e-10 2.340829e-06 4.311442e-10
## 17 0.8030955 5.044800e-07 1.156031e-08 2.086988e-09
## 18 0.8382205 8.024942e-05 5.929942e-04 3.167065e-05
## 19 0.9913629 1.080759e-04 1.404562e-04 1.704353e-05
## 20 0.6231028 1.322183e-06 6.633026e-09 1.591544e-09
## 21 0.9320125 1.877347e-01 3.294327e-01 1.817760e-01
## 22 0.4329889 8.810629e-04 3.893666e-06 3.802310e-06
## 23 0.9622286 2.441911e-05 5.437676e-06 8.678099e-07
## 24 0.8013678 1.815743e-06 4.819503e-08 7.924776e-09
## 25 0.9927810 1.243272e-06 1.503776e-06 6.345726e-08
## 26 0.9999720 1.066131e-03 8.565217e-04 2.142302e-04
## 27 0.1273559 1.138574e-03 1.623942e-07 2.776350e-07
## 28 0.8518135 8.742331e-01 5.565077e-01 5.861759e-01
## 29 0.9807892 5.186917e-09 1.030526e-09 2.179723e-11
## 30 0.6592391 9.347604e-05 2.035139e-03 6.479487e-05
## 31 0.9834609 8.443530e-07 1.362654e-06 4.676703e-08
## 32 0.9295302 9.730442e-01 8.283668e-01 8.390033e-01
## 33 0.7875216 9.899952e-01 8.654541e-01 7.850196e-01
## var
## 1 Simon_Dual_identity_SCL
## 2 GG_Angst
## 3 Stereotype_SCL
## 4 Symb_Threat_SCL
## 5 Real_Threat_SCL
## 6 ITT
## 7 Humanization
## 8 Peception_of_GC_mediator
## 9 Peception_of_GC_bridge
## 10 Peception_of_GC_fifth_column
## 11 Peception_of_GC_traitors
## 12 Peception_of_GC_unique
## 13 Peception_of_GC_weak
## 14 Peception_of_GC_lmlm
## 15 Positive_perception_of_GC_SCL
## 16 Negative_perception_of_GC_SCL
## 17 Surprise
## 18 Common_fate_SCL
## 19 CIIM_SCL
## 20 SDO_SCL
## 21 Identification_SCL
## 22 Essentialism_SCL
## 23 Hatered
## 24 Fear
## 25 Anger
## 26 Hope
## 27 Empathy
## 28 Despair
## 29 Policy_SCL
## 30 Resource_allocation_SCL
## 31 Social_Distance_SCL
## 32 Age
## 33 Gender## increase-decrease same-decrease same-increase ANOVA
## 1 -0.419779878 2.0110527 2.4539262 3.3783957
## 2 -0.221675159 -4.3968198 -4.2421067 12.2760771
## 3 -0.552838607 -5.4074505 -4.9410163 17.7110846
## 4 -1.224310068 -7.1596487 -6.0568582 29.3384951
## 5 -0.299758158 -7.7131758 -7.5295985 38.1966905
## 6 -0.385672361 -6.7941347 -6.5125582 29.1377149
## 7 -0.402114323 5.4339927 5.9090915 21.2605740
## 8 0.372019670 4.0158589 3.7074505 9.8514509
## 9 0.052413461 3.5095566 3.5087924 8.0940790
## 10 -1.750229477 -6.2271132 -4.5924834 20.6319514
## 11 -1.137110883 -5.7970156 -4.7604044 18.8765622
## 12 -0.284759047 4.8600981 5.2112161 16.7318719
## 13 -0.100021657 -4.6452787 -4.6140634 14.0887818
## 14 -0.411328267 -2.0043631 -1.6280460 2.2421113
## 15 0.047498060 4.8220048 4.8451164 15.3567643
## 16 -1.568573651 -6.4741388 -5.0221209 22.8188468
## 17 0.631167616 -5.3630574 -6.0783836 21.4464797
## 18 -0.566085163 -4.2478967 -3.7515929 10.6439741
## 19 0.125438522 4.1772421 4.1141904 11.2989079
## 20 0.927692906 -5.1380611 -6.1268494 21.3629596
## 21 -0.357443376 -1.7510678 -1.4241836 1.7125527
## 22 1.235462186 -3.6464794 -4.9169586 12.8933276
## 23 0.264299956 -4.5208762 -4.8469119 14.4757368
## 24 0.634201669 -5.0739451 -5.7725551 19.5869362
## 25 -0.114638468 -5.1504239 -5.1121281 17.3072258
## 26 -0.007132052 3.5949081 3.6540662 8.6365951
## 27 -1.945915427 3.5769755 5.5466298 15.7047378
## 28 0.539640306 -0.4939644 -1.0329665 0.5348771
## 29 0.187584463 -6.1696066 -6.4439437 26.1833218
## 30 0.870504426 4.2118129 3.4149673 9.8899599
## 31 0.173933114 5.2276094 5.1319953 17.6401165
## 32 0.364153255 -0.2226483 -0.5847660 0.1756207
## 33 0.658724797 0.1350528 -0.5121911 0.2421989
## var
## 1 Simon_Dual_identity_SCL
## 2 GG_Angst
## 3 Stereotype_SCL
## 4 Symb_Threat_SCL
## 5 Real_Threat_SCL
## 6 ITT
## 7 Humanization
## 8 Peception_of_GC_mediator
## 9 Peception_of_GC_bridge
## 10 Peception_of_GC_fifth_column
## 11 Peception_of_GC_traitors
## 12 Peception_of_GC_unique
## 13 Peception_of_GC_weak
## 14 Peception_of_GC_lmlm
## 15 Positive_perception_of_GC_SCL
## 16 Negative_perception_of_GC_SCL
## 17 Surprise
## 18 Common_fate_SCL
## 19 CIIM_SCL
## 20 SDO_SCL
## 21 Identification_SCL
## 22 Essentialism_SCL
## 23 Hatered
## 24 Fear
## 25 Anger
## 26 Hope
## 27 Empathy
## 28 Despair
## 29 Policy_SCL
## 30 Resource_allocation_SCL
## 31 Social_Distance_SCL
## 32 Age
## 33 GenderDraw heatmap
ggplot(combine.pf, aes(comparison, var, fill = sig_level, colour = dir)) + #x-axis comparison
geom_tile() +
scale_fill_manual(values = c(sig = "black",marginally_sig = "gray",non_sig = "white")) +
scale_colour_manual(values = c(positive = "green", negative = "red", size=50))+
xlab("") + ylab("")+
ggtitle("Heatmap focus on difference in \"Mexican_3\"")+
theme(axis.text.x = element_text( angle = 90, hjust = 1))
Mexican_4
###p-value preparation
p_Mexican_4<- data.frame(matrix(ncol = 4))
for (i in 2:34){
p_Mexican_4[(i-1),] <- c(p_rst(wave.compare4[,i], wave.compare4), anova_p(wave.compare4[,i], wave.compare4))
}
colnames(p_Mexican_4) <- c("increase-decrease", "same-decrease", "same-increase", "ANOVA")
p_Mexican_4$var<-colnames(wave.compare4[,-1])
###f-value preparation
f_Mexican_4<-data.frame(matrix(ncol = 4))
for (i in 2:34){
f_Mexican_4[(i-1),] <- c(f_rst(wave.compare4[,i], wave.compare4), anova_f(wave.compare4[,i], wave.compare4))
}
colnames(f_Mexican_4) <- c("increase-decrease", "same-decrease", "same-increase", "ANOVA")
f_Mexican_4$var <-colnames(wave.compare4[,-1])
p_Mexican_4;f_Mexican_4## increase-decrease same-decrease same-increase ANOVA
## 1 0.154065147 0.0907075781 0.8546304224 5.630736e-02
## 2 0.814060371 0.0094759400 0.0525936731 1.212146e-02
## 3 0.999398088 0.0085913394 0.0138152849 6.750637e-03
## 4 0.819130256 0.0002180490 0.0025360192 2.601431e-04
## 5 0.988263105 0.0001462121 0.0004765781 9.897056e-05
## 6 0.911094479 0.0001874061 0.0013044745 1.821618e-04
## 7 0.525074514 0.0001006629 0.0050322635 1.663013e-04
## 8 0.116037038 0.0137494279 0.5047004024 1.132806e-02
## 9 0.022917859 0.0381782222 0.9683791539 8.689948e-03
## 10 0.972927281 0.0213894811 0.0179796636 1.316472e-02
## 11 0.998781882 0.0031785325 0.0057868287 2.366955e-03
## 12 0.114069597 0.0019400658 0.2115386390 2.213905e-03
## 13 0.801403249 0.0534901708 0.0181786292 2.002604e-02
## 14 0.291731276 0.4731806933 0.0552574478 6.179414e-02
## 15 0.028238971 0.0023197458 0.4653697481 1.304987e-03
## 16 0.994266896 0.0047256980 0.0056896989 2.980615e-03
## 17 0.230907928 0.0015221306 0.0872009090 2.282992e-03
## 18 0.936226278 0.0728536184 0.1624580296 8.104885e-02
## 19 0.674172085 0.0016588543 0.0229933625 2.407893e-03
## 20 0.194752158 0.0034845816 0.1929374679 4.468273e-03
## 21 0.041596144 0.2642502273 0.8986354058 4.138036e-02
## 22 0.337406023 0.1904451159 0.8491619741 1.555863e-01
## 23 0.973846900 0.0153328036 0.0131161303 9.179056e-03
## 24 0.765806969 0.0009944959 0.0109488819 1.325623e-03
## 25 0.800409478 0.0023605510 0.0187569232 3.051463e-03
## 26 0.603648420 0.1072457657 0.4692546630 1.259374e-01
## 27 0.600077029 0.0001163688 0.0041050962 1.804907e-04
## 28 0.386193330 0.9827912385 0.6531203904 3.997956e-01
## 29 0.598545352 0.0003918812 0.0103302951 6.082460e-04
## 30 0.463453161 0.0944363940 0.5459513509 1.037119e-01
## 31 0.942192812 0.0056332559 0.0189307484 5.865683e-03
## 32 0.008990561 0.2331657882 0.7022508433 1.082707e-02
## 33 0.971022633 0.9877118777 0.9990817475 9.712111e-01
## var
## 1 Simon_Dual_identity_SCL
## 2 GG_Angst
## 3 Stereotype_SCL
## 4 Symb_Threat_SCL
## 5 Real_Threat_SCL
## 6 ITT
## 7 Humanization
## 8 Peception_of_GC_mediator
## 9 Peception_of_GC_bridge
## 10 Peception_of_GC_fifth_column
## 11 Peception_of_GC_traitors
## 12 Peception_of_GC_unique
## 13 Peception_of_GC_weak
## 14 Peception_of_GC_lmlm
## 15 Positive_perception_of_GC_SCL
## 16 Negative_perception_of_GC_SCL
## 17 Surprise
## 18 Common_fate_SCL
## 19 CIIM_SCL
## 20 SDO_SCL
## 21 Identification_SCL
## 22 Essentialism_SCL
## 23 Hatered
## 24 Fear
## 25 Anger
## 26 Hope
## 27 Empathy
## 28 Despair
## 29 Policy_SCL
## 30 Resource_allocation_SCL
## 31 Social_Distance_SCL
## 32 Age
## 33 Gender## increase-decrease same-decrease same-increase ANOVA
## 1 1.85276502 2.1022007 0.53405159 2.89853546
## 2 -0.61125319 -2.9483825 -2.33251720 4.46374452
## 3 -0.03304664 -2.9800578 -2.82353097 5.06356978
## 4 -0.60194682 -4.0064678 -3.35179153 8.43380455
## 5 -0.14634179 -4.1044544 -3.80852907 9.44509072
## 6 -0.41107397 -4.0438370 -3.53961802 8.80609738
## 7 1.08319248 4.1941986 3.14785798 8.90138130
## 8 1.98994047 2.8251447 1.11610799 4.53302103
## 9 2.64753255 2.4584312 0.24143802 4.80456704
## 10 0.22313725 -2.6721564 -2.73321193 4.37928501
## 11 -0.04701899 -3.2858348 -3.10481558 6.14210319
## 12 1.99792880 3.4285675 1.68680280 6.21109474
## 13 0.63413824 -2.3256971 -2.72937978 3.95071619
## 14 1.50067483 -1.1677907 -2.31252819 2.80417495
## 15 2.57172366 3.3775111 1.18077002 6.75746386
## 16 0.10212253 -3.1670507 -3.11005883 5.90436501
## 17 -1.63916573 -3.5068217 -2.12194537 6.21300813
## 18 -0.34579861 -2.1975503 -1.82600550 2.52917392
## 19 0.84672261 3.4727532 2.64635381 6.12440922
## 20 -1.73155621 -3.2586456 -1.73655361 5.48751294
## 21 -2.42532493 -1.5602538 0.44044133 3.21144257
## 22 -1.40865753 -1.7434715 -0.54486532 1.86957501
## 23 0.21926247 -2.7881230 -2.84102464 4.74845096
## 24 -0.69627465 -3.6137964 -2.90111380 6.74122428
## 25 -0.63591533 -3.3724934 -2.71844817 5.88015458
## 26 0.95838806 2.0264959 1.17430513 2.08316140
## 27 0.96402316 4.1595373 3.20966664 8.81573552
## 28 -1.31764324 -0.1774499 0.88021751 0.91898850
## 29 -0.96644019 -3.8588853 -2.92022376 7.54919853
## 30 1.18396646 2.0842287 1.04977193 2.27952970
## 31 0.32870164 3.1131433 2.71522045 5.20783671
## 32 -2.96541535 -1.6326013 0.80160546 4.57932500
## 33 -0.23096708 -0.1497600 0.04082035 0.02921363
## var
## 1 Simon_Dual_identity_SCL
## 2 GG_Angst
## 3 Stereotype_SCL
## 4 Symb_Threat_SCL
## 5 Real_Threat_SCL
## 6 ITT
## 7 Humanization
## 8 Peception_of_GC_mediator
## 9 Peception_of_GC_bridge
## 10 Peception_of_GC_fifth_column
## 11 Peception_of_GC_traitors
## 12 Peception_of_GC_unique
## 13 Peception_of_GC_weak
## 14 Peception_of_GC_lmlm
## 15 Positive_perception_of_GC_SCL
## 16 Negative_perception_of_GC_SCL
## 17 Surprise
## 18 Common_fate_SCL
## 19 CIIM_SCL
## 20 SDO_SCL
## 21 Identification_SCL
## 22 Essentialism_SCL
## 23 Hatered
## 24 Fear
## 25 Anger
## 26 Hope
## 27 Empathy
## 28 Despair
## 29 Policy_SCL
## 30 Resource_allocation_SCL
## 31 Social_Distance_SCL
## 32 Age
## 33 GenderDraw heatmap
ggplot(combine.pf, aes(comparison, var, fill = sig_level, colour = dir)) + #x-axis comparison
geom_tile() +
scale_fill_manual(values = c(sig = "black",marginally_sig = "gray",non_sig = "white")) +
scale_colour_manual(values = c(positive = "green", negative = "red", size=50))+
xlab("") + ylab("")+
ggtitle("Heatmap focus on difference in \"Mexican_4\"")+
theme(axis.text.x = element_text( angle = 90, hjust = 1))
within subject analysis comparing wave 1 and wave 2
#Multiple grouping variables
#Two independent sample comparisons after grouping the data by another variable:
#ggboxplot(wave, x = "key", y = "value",
# color = "gp", palette = "jco", add = "jitter")+
#stat_compare_means(aes(group = gp), method = "anova", label.y = 6.5)+
#xlab("")
ggboxplot(wave, x = "gp", y = "value",
color = "gp", palette = "jco",
add = "jitter",
facet.by = "key")+
stat_compare_means(label = "p.format", method = "anova", label.x = 1.5)
wave$gp<-as.factor(wave$gp)
wave$key<-as.factor(wave$key)
#Paired sample comparisons after grouping the data by another variable
#ggpaired(wave, x = "key", y = "value",
# color = "key", palette = "jco",
# line.color = "gray", line.size = 0.4,
# facet.by = "gp")+
# stat_compare_means(label = "p.format", paired = TRUE)
##wave 1 vs wave 2 Overall Comparison
###Essentialism
wave.ess<-wave_select %>% dplyr::select(Essentialism_SCL.x, Essentialism_SCL.y) %>%
dplyr::rename(wave1=Essentialism_SCL.x, wave2=Essentialism_SCL.y)
p1<-ggpaired(wave.ess, cond1 = "wave1", cond2 = "wave2",
color = "condition", palette = "jco",
line.color="gray", line.size = 0.4)+
xlab("Essentialism")+
stat_compare_means(label = "p.format", paired = TRUE)
###Identification
wave.id<-wave_select %>% dplyr::select(Identification_SCL.x, Identification_SCL.y) %>%
dplyr::rename(wave1=Identification_SCL.x, wave2=Identification_SCL.y)
p2<-ggpaired(wave.id, cond1 = "wave1", cond2 = "wave2",
color = "condition", palette = "jco",
line.color="gray", line.size = 0.4)+
xlab("Identification")+
stat_compare_means(label = "p.format", paired = TRUE)
###Mexican_3
wave.mx3<-wave_select %>% dplyr::select(Mexican_3, GG_level_3) %>%
dplyr::rename(wave1=Mexican_3, wave2=GG_level_3)
p3<-ggpaired(wave.mx3, cond1 = "wave1", cond2 = "wave2",
color = "condition", palette = "jco",
line.color="gray", line.size = 0.4)+
xlab("Mexican_3")+
stat_compare_means(label = "p.format", paired = TRUE)
###Mexican_4
wave.mx4<-wave_select %>% dplyr::select(Mexican_4, GG_level_4) %>%
dplyr::rename(wave1=Mexican_4, wave2=GG_level_4)
p4<-ggpaired(wave.mx4, cond1 = "wave1", cond2 = "wave2",
color = "condition", palette = "jco",
line.color="gray", line.size = 0.4)+
xlab("Mexican_4")+
stat_compare_means(label = "p.format", paired = TRUE)
###GG_level_Mexican
wave.mx<-wave_select %>% dplyr::select(GG_level_Mexican, GG_Level) %>%
dplyr::rename(wave1=GG_level_Mexican, wave2=GG_Level)
p5 <- ggpaired(wave.mx, cond1 = "wave1", cond2 = "wave2",
color = "condition", palette = "jco",
line.color="gray", line.size = 0.4)+
xlab("GG_level_Mexican")+
stat_compare_means(label = "p.format", paired = TRUE)
grid.arrange(p1,p2,p3,p4,p5, nrow = 2, top = "Overall Comparison")
######### 4 Conditions
x<-c("1", "2","3", "4")
y<-c("Essentialism", "Identification", "Mexican_3", "Mexican_4", "GG_level_Mexican")
pairplot <- function(i,j){
cond1 <- wave_select %>% dplyr::filter(CONDITION == x[i])
plotdata <- cond1[,(2*j):(2*j+1)]
colnames(plotdata)<-c("wave1","wave2")
p<-ggpaired(plotdata, cond1 = "wave1", cond2 = "wave2",
color = "condition", palette = "jco",
line.color="gray", line.size = 0.4)+
ggtitle(paste('Condition', i, y[j]))+
xlab("")+
stat_compare_means(label = "p.format", paired = TRUE)
print(p)
}
#pairplot(2,1)
for (i in 1:4) {
for (j in 1:5) {
pairplot(i,j)
}
}## Warning: Removed 2 rows containing non-finite values (stat_boxplot).## Warning: Removed 2 rows containing non-finite values (stat_compare_means).## Warning: Computation failed in `stat_compare_means()`:
## 'x' and 'y' must have the same length## Warning: Removed 2 rows containing missing values (geom_path).## Warning: Removed 2 rows containing missing values (geom_point).
## Warning: Removed 2 rows containing non-finite values (stat_boxplot).## Warning: Removed 2 rows containing non-finite values (stat_compare_means).## Warning: Computation failed in `stat_compare_means()`:
## 'x' and 'y' must have the same length## Warning: Removed 2 rows containing missing values (geom_path).## Warning: Removed 2 rows containing missing values (geom_point).
## Warning: Removed 4 rows containing non-finite values (stat_boxplot).## Warning: Removed 4 rows containing non-finite values (stat_compare_means).## Warning: Removed 4 rows containing missing values (geom_path).## Warning: Removed 4 rows containing missing values (geom_point).
## Warning: Removed 2 rows containing non-finite values (stat_boxplot).## Warning: Removed 2 rows containing non-finite values (stat_compare_means).## Warning: Computation failed in `stat_compare_means()`:
## 'x' and 'y' must have the same length## Warning: Removed 2 rows containing missing values (geom_path).## Warning: Removed 2 rows containing missing values (geom_point).
## Warning: Removed 2 rows containing non-finite values (stat_boxplot).## Warning: Removed 2 rows containing non-finite values (stat_compare_means).## Warning: Computation failed in `stat_compare_means()`:
## 'x' and 'y' must have the same length## Warning: Removed 2 rows containing missing values (geom_path).## Warning: Removed 2 rows containing missing values (geom_point).
## Warning: Removed 2 rows containing non-finite values (stat_boxplot).## Warning: Removed 2 rows containing non-finite values (stat_compare_means).## Warning: Computation failed in `stat_compare_means()`:
## 'x' and 'y' must have the same length## Warning: Removed 2 rows containing missing values (geom_path).## Warning: Removed 2 rows containing missing values (geom_point).
## Warning: Removed 6 rows containing non-finite values (stat_boxplot).## Warning: Removed 6 rows containing non-finite values (stat_compare_means).## Warning: Removed 6 rows containing missing values (geom_path).## Warning: Removed 6 rows containing missing values (geom_point).
## Warning: Removed 3 rows containing non-finite values (stat_boxplot).## Warning: Removed 3 rows containing non-finite values (stat_compare_means).## Warning: Computation failed in `stat_compare_means()`:
## 'x' and 'y' must have the same length## Warning: Removed 3 rows containing missing values (geom_path).## Warning: Removed 3 rows containing missing values (geom_point).
## Warning: Removed 2 rows containing non-finite values (stat_boxplot).## Warning: Removed 2 rows containing non-finite values (stat_compare_means).## Warning: Removed 2 rows containing missing values (geom_path).## Warning: Removed 2 rows containing missing values (geom_point).
## Warning: Removed 1 rows containing non-finite values (stat_boxplot).## Warning: Removed 1 rows containing non-finite values (stat_compare_means).## Warning: Computation failed in `stat_compare_means()`:
## 'x' and 'y' must have the same length## Warning: Removed 1 rows containing missing values (geom_path).## Warning: Removed 1 rows containing missing values (geom_point).
## Warning: Removed 4 rows containing non-finite values (stat_boxplot).## Warning: Removed 4 rows containing non-finite values (stat_compare_means).## Warning: Computation failed in `stat_compare_means()`:
## 'x' and 'y' must have the same length## Warning: Removed 4 rows containing missing values (geom_path).## Warning: Removed 4 rows containing missing values (geom_point).
## Warning: Removed 4 rows containing non-finite values (stat_boxplot).## Warning: Removed 4 rows containing non-finite values (stat_compare_means).## Warning: Computation failed in `stat_compare_means()`:
## 'x' and 'y' must have the same length## Warning: Removed 4 rows containing missing values (geom_path).## Warning: Removed 4 rows containing missing values (geom_point).
## Warning: Removed 10 rows containing non-finite values (stat_boxplot).## Warning: Removed 10 rows containing non-finite values (stat_compare_means).## Warning: Removed 10 rows containing missing values (geom_path).## Warning: Removed 10 rows containing missing values (geom_point).
## Warning: Removed 5 rows containing non-finite values (stat_boxplot).## Warning: Removed 5 rows containing non-finite values (stat_compare_means).## Warning: Computation failed in `stat_compare_means()`:
## 'x' and 'y' must have the same length## Warning: Removed 5 rows containing missing values (geom_path).## Warning: Removed 5 rows containing missing values (geom_point).
