#Data Wrangling for Negators Selection
raw60 <- read.csv('CriticalAnalysis(n60).csv', header = T, sep = "," )
filtered_raw60 <- raw60[-which(raw60$Procedure.Block. == "InterimBreak"), ]
filtered_raw60 <- filtered_raw60 %>% mutate_at(c("Subject", "ConCode", "SetID", "IntentionType",
"BoundednessType", "Verb", "Trial", "BlockID"), as.factor)
unique(is.na(filtered_raw60$TargetS.RESP))## [1] FALSEcritical_raw60 <- filtered_raw60 %>% filter(IntentionType != "Filler") %>%
mutate(TarRes = case_when(TargetS.RESP=="f"~"bu", TargetS.RESP=="j"~"mei")) %>%
mutate(PreAns = case_when(PredictedAnswer=="不"~"bu",
PredictedAnswer=="沒"~"mei",
PredictedAnswer=="不或沒"~"both"))
critical_raw60 <- critical_raw60 %>% mutate_at(c("TarRes", "PreAns"), as.factor)
critical_raw60_revisedV <- critical_raw60
critical_raw60_revisedV$IntentionWord <- ifelse(critical_raw60_revisedV$SetID == "s25" &
critical_raw60_revisedV$ConCode == "D" &
critical_raw60_revisedV$IntentionWord == "可望", "非得",
ifelse(critical_raw60_revisedV$SetID == "s25" &
critical_raw60_revisedV$ConCode == "C" &
critical_raw60_revisedV$IntentionWord == "期盼", "可望",
ifelse(critical_raw60_revisedV$SetID == "s03" &
critical_raw60_revisedV$ConCode == "B" &
critical_raw60_revisedV$IntentionWord == "甘願", "應當",
ifelse(critical_raw60_revisedV$SetID == "s04" &
critical_raw60_revisedV$ConCode == "B" &
critical_raw60_revisedV$IntentionWord == "甘願", "非得",
critical_raw60_revisedV$IntentionWord))))
n60_res_critical <- critical_raw60_revisedV %>% mutate(Bu = ifelse(critical_raw60_revisedV$TargetS.RESP == "f", 1, 0)) %>% mutate(Mei = ifelse(critical_raw60_revisedV$TargetS.RESP == "j", 1, 0))
unique(is.na(n60_res_critical$IntentionType))## [1] FALSEunique(is.na(n60_res_critical$BoundednessType))## [1] FALSEstr(n60_res_critical)## 'data.frame': 7200 obs. of 29 variables:
## $ ExperimentName : chr "ProjectXRC_Questionnaire_v0_Subject01" "ProjectXRC_Questionnaire_v0_Subject01" "ProjectXRC_Questionnaire_v0_Subject01" "ProjectXRC_Questionnaire_v0_Subject01" ...
## $ Subject : Factor w/ 60 levels "1","2","3","4",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ Block : int 1 1 1 1 1 1 1 1 1 1 ...
## $ BlockList : int 1 1 1 1 1 1 1 1 1 1 ...
## $ Procedure.Block. : chr "SessionProc1" "SessionProc1" "SessionProc1" "SessionProc1" ...
## $ Trial : Factor w/ 60 levels "1","2","3","4",..: 1 3 4 7 9 10 14 16 17 18 ...
## $ BlockID : Factor w/ 30 levels "b01","b02","b03",..: 8 8 8 8 22 22 22 22 5 5 ...
## $ ListID : chr "List2A" "List2A" "List2A" "List2A" ...
## $ SetID : Factor w/ 90 levels "f01","f02","f03",..: 48 52 50 46 76 78 74 80 44 46 ...
## $ ConCode : Factor w/ 8 levels "A","B","C","D",..: 2 4 3 1 2 3 1 4 3 4 ...
## $ IntentionType : Factor w/ 3 levels "Filler","Intention",..: 3 3 2 2 3 2 2 3 2 3 ...
## $ BoundednessType : Factor w/ 4 levels "Boundedness",..: 1 4 1 4 1 1 4 4 1 4 ...
## $ Verb : Factor w/ 30 levels "打","生","丟",..: 18 11 18 12 26 2 14 25 12 12 ...
## $ ContextS : chr "表弟那次去酒吧應當就只點汽水，" "哥哥向來理應超時工作當志工，" "表妹上次決心要避免引起過敏，" "小傑每次旅行都期盼有新發現，" ...
## $ ContextS.RT : int 3225 4447 3413 3853 2433 5108 3246 2437 2090 3041 ...
## $ TargetS : chr "所以他_____喝調酒。" "所以他_____拿加班費。" "所以她_____喝牛奶。" "所以他_____做計畫。" ...
## $ TargetS.RT : int 2262 4117 2557 3557 5064 3520 4516 4081 2442 3009 ...
## $ TargetS.RESP : chr "j" "f" "f" "j" ...
## $ PredictedAnswer : chr "沒" "不或沒" "不或沒" "不" ...
## $ IntentionWord : chr "應當" "理應" "決心" "期盼" ...
## $ BoundednessWord : chr "那次" "向來" "上次" "每次" ...
## $ OptionA : chr "(A)不" "(A)不" "(A)不" "(A)不" ...
## $ OptionB : chr "(B)沒" "(B)沒" "(B)沒" "(B)沒" ...
## $ TargetS.OnsetTime : int 16837 33807 42416 62149 74539 85548 108278 121451 128328 134558 ...
## $ TargetS.OffsetTime: int 19099 37924 44974 65706 79603 89068 112794 125532 130770 137568 ...
## $ TarRes : Factor w/ 2 levels "bu","mei": 2 1 1 2 2 1 2 1 2 1 ...
## $ PreAns : Factor w/ 3 levels "both","bu","mei": 3 1 1 2 3 1 2 1 1 1 ...
## $ Bu : num 0 1 1 0 0 1 0 1 0 1 ...
## $ Mei : num 1 0 0 1 1 0 1 0 1 0 ...#Data Wrangling for Reaction Time
n60_rt_num <- n60_res_critical %>% mutate_at("TargetS.RT", as.numeric)
str(n60_rt_num)## 'data.frame': 7200 obs. of 29 variables:
## $ ExperimentName : chr "ProjectXRC_Questionnaire_v0_Subject01" "ProjectXRC_Questionnaire_v0_Subject01" "ProjectXRC_Questionnaire_v0_Subject01" "ProjectXRC_Questionnaire_v0_Subject01" ...
## $ Subject : Factor w/ 60 levels "1","2","3","4",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ Block : int 1 1 1 1 1 1 1 1 1 1 ...
## $ BlockList : int 1 1 1 1 1 1 1 1 1 1 ...
## $ Procedure.Block. : chr "SessionProc1" "SessionProc1" "SessionProc1" "SessionProc1" ...
## $ Trial : Factor w/ 60 levels "1","2","3","4",..: 1 3 4 7 9 10 14 16 17 18 ...
## $ BlockID : Factor w/ 30 levels "b01","b02","b03",..: 8 8 8 8 22 22 22 22 5 5 ...
## $ ListID : chr "List2A" "List2A" "List2A" "List2A" ...
## $ SetID : Factor w/ 90 levels "f01","f02","f03",..: 48 52 50 46 76 78 74 80 44 46 ...
## $ ConCode : Factor w/ 8 levels "A","B","C","D",..: 2 4 3 1 2 3 1 4 3 4 ...
## $ IntentionType : Factor w/ 3 levels "Filler","Intention",..: 3 3 2 2 3 2 2 3 2 3 ...
## $ BoundednessType : Factor w/ 4 levels "Boundedness",..: 1 4 1 4 1 1 4 4 1 4 ...
## $ Verb : Factor w/ 30 levels "打","生","丟",..: 18 11 18 12 26 2 14 25 12 12 ...
## $ ContextS : chr "表弟那次去酒吧應當就只點汽水，" "哥哥向來理應超時工作當志工，" "表妹上次決心要避免引起過敏，" "小傑每次旅行都期盼有新發現，" ...
## $ ContextS.RT : int 3225 4447 3413 3853 2433 5108 3246 2437 2090 3041 ...
## $ TargetS : chr "所以他_____喝調酒。" "所以他_____拿加班費。" "所以她_____喝牛奶。" "所以他_____做計畫。" ...
## $ TargetS.RT : num 2262 4117 2557 3557 5064 ...
## $ TargetS.RESP : chr "j" "f" "f" "j" ...
## $ PredictedAnswer : chr "沒" "不或沒" "不或沒" "不" ...
## $ IntentionWord : chr "應當" "理應" "決心" "期盼" ...
## $ BoundednessWord : chr "那次" "向來" "上次" "每次" ...
## $ OptionA : chr "(A)不" "(A)不" "(A)不" "(A)不" ...
## $ OptionB : chr "(B)沒" "(B)沒" "(B)沒" "(B)沒" ...
## $ TargetS.OnsetTime : int 16837 33807 42416 62149 74539 85548 108278 121451 128328 134558 ...
## $ TargetS.OffsetTime: int 19099 37924 44974 65706 79603 89068 112794 125532 130770 137568 ...
## $ TarRes : Factor w/ 2 levels "bu","mei": 2 1 1 2 2 1 2 1 2 1 ...
## $ PreAns : Factor w/ 3 levels "both","bu","mei": 3 1 1 2 3 1 2 1 1 1 ...
## $ Bu : num 0 1 1 0 0 1 0 1 0 1 ...
## $ Mei : num 1 0 0 1 1 0 1 0 1 0 ...n60_res_num.d2 <- n60_rt_num %>% mutate(zRT = as.numeric(scale(TargetS.RT))) %>% filter(abs(zRT) <= 3)%>% mutate(logRT=log(TargetS.RT))
str(n60_res_num.d2) ### 7062 obs. ## 'data.frame': 7062 obs. of 31 variables:
## $ ExperimentName : chr "ProjectXRC_Questionnaire_v0_Subject01" "ProjectXRC_Questionnaire_v0_Subject01" "ProjectXRC_Questionnaire_v0_Subject01" "ProjectXRC_Questionnaire_v0_Subject01" ...
## $ Subject : Factor w/ 60 levels "1","2","3","4",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ Block : int 1 1 1 1 1 1 1 1 1 1 ...
## $ BlockList : int 1 1 1 1 1 1 1 1 1 1 ...
## $ Procedure.Block. : chr "SessionProc1" "SessionProc1" "SessionProc1" "SessionProc1" ...
## $ Trial : Factor w/ 60 levels "1","2","3","4",..: 1 3 4 7 9 10 14 16 17 18 ...
## $ BlockID : Factor w/ 30 levels "b01","b02","b03",..: 8 8 8 8 22 22 22 22 5 5 ...
## $ ListID : chr "List2A" "List2A" "List2A" "List2A" ...
## $ SetID : Factor w/ 90 levels "f01","f02","f03",..: 48 52 50 46 76 78 74 80 44 46 ...
## $ ConCode : Factor w/ 8 levels "A","B","C","D",..: 2 4 3 1 2 3 1 4 3 4 ...
## $ IntentionType : Factor w/ 3 levels "Filler","Intention",..: 3 3 2 2 3 2 2 3 2 3 ...
## $ BoundednessType : Factor w/ 4 levels "Boundedness",..: 1 4 1 4 1 1 4 4 1 4 ...
## $ Verb : Factor w/ 30 levels "打","生","丟",..: 18 11 18 12 26 2 14 25 12 12 ...
## $ ContextS : chr "表弟那次去酒吧應當就只點汽水，" "哥哥向來理應超時工作當志工，" "表妹上次決心要避免引起過敏，" "小傑每次旅行都期盼有新發現，" ...
## $ ContextS.RT : int 3225 4447 3413 3853 2433 5108 3246 2437 2090 3041 ...
## $ TargetS : chr "所以他_____喝調酒。" "所以他_____拿加班費。" "所以她_____喝牛奶。" "所以他_____做計畫。" ...
## $ TargetS.RT : num 2262 4117 2557 3557 5064 ...
## $ TargetS.RESP : chr "j" "f" "f" "j" ...
## $ PredictedAnswer : chr "沒" "不或沒" "不或沒" "不" ...
## $ IntentionWord : chr "應當" "理應" "決心" "期盼" ...
## $ BoundednessWord : chr "那次" "向來" "上次" "每次" ...
## $ OptionA : chr "(A)不" "(A)不" "(A)不" "(A)不" ...
## $ OptionB : chr "(B)沒" "(B)沒" "(B)沒" "(B)沒" ...
## $ TargetS.OnsetTime : int 16837 33807 42416 62149 74539 85548 108278 121451 128328 134558 ...
## $ TargetS.OffsetTime: int 19099 37924 44974 65706 79603 89068 112794 125532 130770 137568 ...
## $ TarRes : Factor w/ 2 levels "bu","mei": 2 1 1 2 2 1 2 1 2 1 ...
## $ PreAns : Factor w/ 3 levels "both","bu","mei": 3 1 1 2 3 1 2 1 1 1 ...
## $ Bu : num 0 1 1 0 0 1 0 1 0 1 ...
## $ Mei : num 1 0 0 1 1 0 1 0 1 0 ...
## $ zRT : num -0.234 0.538 -0.111 0.305 0.932 ...
## $ logRT : num 7.72 8.32 7.85 8.18 8.53 ...nrow(n60_rt_num) - nrow(n60_res_num.d2) ### 138## [1] 138(nrow(n60_rt_num) - nrow(n60_res_num.d2))/nrow(n60_rt_num)*100 ## 1.916667% data loss## [1] 1.916667#Data Wrangling for AQ
wideAQ <- read.csv('AQ(n60).csv', header = T, sep = "," )
longAQ <- wideAQ %>% gather("QuestionID","Response",Q01:Q50) %>% mutate_at(c("SubjectID", "Gender", "Age", "QuestionID", "Response"), as.factor)
longAQ_score <- longAQ %>% mutate(QuestionType = ifelse(QuestionID %in% c("Q01", "Q03","Q08", "Q10", "Q11", "Q14", "Q15", "Q17", "Q24", "Q25", "Q27", "Q28", "Q29", "Q30", "Q31", "Q32", "Q34", "Q36", "Q37", "Q38", "Q40", "Q44", "Q47", "Q48", "Q49", "Q50"), "lowQ", "highQ")) %>%
mutate(Score = case_when(QuestionType=="lowQ" & Response %in% c("稍微不同意", "完全不同意")~1,
QuestionType=="lowQ" & Response %in% c("稍微同意", "完全同意")~0,
QuestionType=="highQ" & Response %in% c("稍微不同意", "完全不同意")~0,
QuestionType=="highQ" & Response %in% c("稍微同意", "完全同意")~1)) %>%
mutate_at(c("SubjectID", "Gender", "Age", "QuestionID", "Response", "QuestionType"), as.factor)
AQscore_sub <- longAQ_score %>% na.omit() %>% group_by(SubjectID) %>% summarize(total_score = sum(Score)) %>% ungroup()
mean_AQ <- mean(AQscore_sub$total_score, na.rm = TRUE)
AQscore_sub$AQgroup <- ifelse(AQscore_sub$total_score < mean_AQ, 1, 2)
AQscore_sub$AQgroup <- as.factor(AQscore_sub$AQgroup)
names(AQscore_sub) <- c("Subject", "AQscore", "AQgroup")
AQscore_sub$Subject <- c(1:60)
AQscore_sub <- AQscore_sub %>% mutate_at(c("Subject", "AQgroup"), as.factor)
str(AQscore_sub)## tibble [60 × 3] (S3: tbl_df/tbl/data.frame)
## $ Subject: Factor w/ 60 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
## $ AQscore: num [1:60] 24 21 16 23 25 34 22 19 17 23 ...
## $ AQgroup: Factor w/ 2 levels "1","2": 2 1 1 2 2 2 1 1 1 2 ...n60_res_critical.AQ <- merge(n60_res_critical, AQscore_sub, by="Subject", all=T)
lrt.inter.bu <- mixed(Bu ~ BoundednessType*IntentionType + (BoundednessType+IntentionType|Subject) + (BoundednessType+IntentionType|SetID), family = binomial, data = n60_res_critical.AQ, method="LRT")## Contrasts set to contr.sum for the following variables: BoundednessType, IntentionType, Subject, SetIDanova(lrt.inter.bu)## Mixed Model Anova Table (Type 3 tests, LRT-method)
##
## Model: Bu ~ BoundednessType * IntentionType + (BoundednessType + IntentionType |
## Model: Subject) + (BoundednessType + IntentionType | SetID)
## Data: n60_res_critical.AQ
## Df full model: 16
## Df Chisq Chi Df Pr(>Chisq)
## BoundednessType 15 75.0308 1 < 2.2e-16 ***
## IntentionType 15 0.5608 1 0.4539568
## BoundednessType:IntentionType 15 13.7826 1 0.0002052 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1print(lrt.inter.bu)## Mixed Model Anova Table (Type 3 tests, LRT-method)
##
## Model: Bu ~ BoundednessType * IntentionType + (BoundednessType + IntentionType |
## Model: Subject) + (BoundednessType + IntentionType | SetID)
## Data: n60_res_critical.AQ
## Df full model: 16
## Effect df Chisq p.value
## 1 BoundednessType 1 75.03 *** <.001
## 2 IntentionType 1 0.56 .454
## 3 BoundednessType:IntentionType 1 13.78 *** <.001
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '+' 0.1 ' ' 1#afex()for 3-way interaction (Negators Selection and AQ)
lrt.inter.bu.AQ <- mixed(Bu ~ BoundednessType*IntentionType*AQgroup + (BoundednessType|Subject) + (1|SetID), family = binomial, data = n60_res_critical.AQ, method="LRT")## Contrasts set to contr.sum for the following variables: BoundednessType, IntentionType, AQgroup, Subject, SetIDanova(lrt.inter.bu.AQ)## Mixed Model Anova Table (Type 3 tests, LRT-method)
##
## Model: Bu ~ BoundednessType * IntentionType * AQgroup + (BoundednessType |
## Model: Subject) + (1 | SetID)
## Data: n60_res_critical.AQ
## Df full model: 12
## Df Chisq Chi Df Pr(>Chisq)
## BoundednessType 11 78.5348 1 < 2.2e-16 ***
## IntentionType 11 2.1895 1 0.1389538
## AQgroup 11 0.2514 1 0.6160692
## BoundednessType:IntentionType 11 12.3700 1 0.0004363 ***
## BoundednessType:AQgroup 11 1.3989 1 0.2369059
## IntentionType:AQgroup 11 9.3900 1 0.0021817 **
## BoundednessType:IntentionType:AQgroup 11 0.0502 1 0.8227747
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1print(lrt.inter.bu.AQ)## Mixed Model Anova Table (Type 3 tests, LRT-method)
##
## Model: Bu ~ BoundednessType * IntentionType * AQgroup + (BoundednessType |
## Model: Subject) + (1 | SetID)
## Data: n60_res_critical.AQ
## Df full model: 12
## Effect df Chisq p.value
## 1 BoundednessType 1 78.53 *** <.001
## 2 IntentionType 1 2.19 .139
## 3 AQgroup 1 0.25 .616
## 4 BoundednessType:IntentionType 1 12.37 *** <.001
## 5 BoundednessType:AQgroup 1 1.40 .237
## 6 IntentionType:AQgroup 1 9.39 ** .002
## 7 BoundednessType:IntentionType:AQgroup 1 0.05 .823
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '+' 0.1 ' ' 1#afex()for 3-way interaction (Reaction Time and AQ)
critical.rt.filter.AQ <- merge(n60_res_num.d2, AQscore_sub, by="Subject", all=T)
lrt.inter.rt.AQ <- mixed(logRT ~ IntentionType*BoundednessType*AQgroup + (1|Subject) + (IntentionType|SetID), data = critical.rt.filter.AQ, method="LRT")## Contrasts set to contr.sum for the following variables: IntentionType, BoundednessType, AQgroup, Subject, SetID## REML argument to lmer() set to FALSE for method = 'PB' or 'LRT'anova(lrt.inter.rt.AQ)## Mixed Model Anova Table (Type 3 tests, LRT-method)
##
## Model: logRT ~ IntentionType * BoundednessType * AQgroup + (1 | Subject) +
## Model: (IntentionType | SetID)
## Data: critical.rt.filter.AQ
## Df full model: 13
## Df Chisq Chi Df Pr(>Chisq)
## IntentionType 12 8.5852 1 0.003389 **
## BoundednessType 12 2.7937 1 0.094634 .
## AQgroup 12 0.5037 1 0.477880
## IntentionType:BoundednessType 12 0.5032 1 0.478093
## IntentionType:AQgroup 12 0.1296 1 0.718812
## BoundednessType:AQgroup 12 0.0468 1 0.828706
## IntentionType:BoundednessType:AQgroup 12 3.7161 1 0.053890 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1print(lrt.inter.rt.AQ)## Mixed Model Anova Table (Type 3 tests, LRT-method)
##
## Model: logRT ~ IntentionType * BoundednessType * AQgroup + (1 | Subject) +
## Model: (IntentionType | SetID)
## Data: critical.rt.filter.AQ
## Df full model: 13
## Effect df Chisq p.value
## 1 IntentionType 1 8.59 ** .003
## 2 BoundednessType 1 2.79 + .095
## 3 AQgroup 1 0.50 .478
## 4 IntentionType:BoundednessType 1 0.50 .478
## 5 IntentionType:AQgroup 1 0.13 .719
## 6 BoundednessType:AQgroup 1 0.05 .829
## 7 IntentionType:BoundednessType:AQgroup 1 3.72 + .054
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '+' 0.1 ' ' 1#afex()跟emmeans()結合以對應pairwise comparison的結果是否符合
#2-Way的組間比較，用2-way的模型
emm <- emmeans(lrt.inter.bu, ~ BoundednessType * IntentionType)
pairwise_results <- pairs(emm, adjust = "tukey")
print(pairwise_results)## contrast estimate SE df
## Boundedness Intention - UnBoundedness Intention -2.079 0.175 Inf
## Boundedness Intention - Boundedness NonIntention -0.140 0.116 Inf
## Boundedness Intention - UnBoundedness NonIntention -1.787 0.208 Inf
## UnBoundedness Intention - Boundedness NonIntention 1.940 0.176 Inf
## UnBoundedness Intention - UnBoundedness NonIntention 0.293 0.118 Inf
## Boundedness NonIntention - UnBoundedness NonIntention -1.647 0.172 Inf
## z.ratio p.value
## -11.902 <.0001
## -1.204 0.6242
## -8.600 <.0001
## 10.998 <.0001
## 2.479 0.0632
## -9.559 <.0001
##
## Results are given on the log odds ratio (not the response) scale.
## P value adjustment: tukey method for comparing a family of 4 estimatesemm_AQ <- emmeans(lrt.inter.bu.AQ, ~ BoundednessType * IntentionType | AQgroup)
pairwise_AQresults <- pairs(emm_AQ, adjust = "tukey")
print(pairwise_AQresults)## AQgroup = 1:
## contrast estimate SE df
## Boundedness Intention - UnBoundedness Intention -1.8067 0.209 Inf
## Boundedness Intention - Boundedness NonIntention 0.0687 0.107 Inf
## Boundedness Intention - UnBoundedness NonIntention -1.3765 0.207 Inf
## UnBoundedness Intention - Boundedness NonIntention 1.8754 0.209 Inf
## UnBoundedness Intention - UnBoundedness NonIntention 0.4302 0.107 Inf
## Boundedness NonIntention - UnBoundedness NonIntention -1.4452 0.207 Inf
## z.ratio p.value
## -8.661 <.0001
## 0.645 0.9174
## -6.662 <.0001
## 8.979 <.0001
## 4.012 0.0004
## -6.986 <.0001
##
## AQgroup = 2:
## contrast estimate SE df
## Boundedness Intention - UnBoundedness Intention -2.1624 0.217 Inf
## Boundedness Intention - Boundedness NonIntention -0.2923 0.112 Inf
## Boundedness Intention - UnBoundedness NonIntention -2.0440 0.216 Inf
## UnBoundedness Intention - Boundedness NonIntention 1.8702 0.215 Inf
## UnBoundedness Intention - UnBoundedness NonIntention 0.1184 0.111 Inf
## Boundedness NonIntention - UnBoundedness NonIntention -1.7518 0.214 Inf
## z.ratio p.value
## -9.987 <.0001
## -2.599 0.0461
## -9.468 <.0001
## 8.700 <.0001
## 1.065 0.7111
## -8.173 <.0001
##
## Results are given on the log odds ratio (not the response) scale.
## P value adjustment: tukey method for comparing a family of 4 estimates#"1"="低AQ組", "2"="高AQ組"