- package installation and importation
# install.packages("dplyr")
library(dplyr)
## Warning: 패키지 'dplyr'는 R 버전 4.2.2에서 작성되었습니다
##
## 다음의 패키지를 부착합니다: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
# install.packages("ggplot2")
library(ggplot2)
# install.packages("lmerTest")
library(lmerTest)
## Warning: 패키지 'lmerTest'는 R 버전 4.2.2에서 작성되었습니다
## 필요한 패키지를 로딩중입니다: lme4
## Warning: 패키지 'lme4'는 R 버전 4.2.2에서 작성되었습니다
## 필요한 패키지를 로딩중입니다: Matrix
##
## 다음의 패키지를 부착합니다: 'lmerTest'
## The following object is masked from 'package:lme4':
##
## lmer
## The following object is masked from 'package:stats':
##
## step
# install.packages("lme4")
library(lme4)
# install.packages("sciplot")
library(sciplot)
data <- read.table("C:\\Users\\csjja\\Desktop\\data_JCL_22-3-11.txt",sep="\t",header=T)
View(data)
str(data)
## 'data.frame': 1577 obs. of 18 variables:
## $ exp : int 1 1 1 1 1 1 1 1 1 1 ...
## $ register : chr "ids" "ids" "ids" "ids" ...
## $ subject : chr "W01" "W01" "W01" "W01" ...
## $ speaker_gender : chr "f" "f" "f" "f" ...
## $ listener_gender: chr "m" "m" "m" "m" ...
## $ speaker_age : chr "na" "na" "na" "na" ...
## $ listener_age : chr "11;09" "11;09" "11;09" "11;09" ...
## $ item : chr "kkoch" "kkoch" "kkoch" "kkoch" ...
## $ syllableN : int 1 1 1 1 1 1 1 1 1 1 ...
## $ frequency : chr "high" "high" "high" "high" ...
## $ coda : chr "ch" "ch" "ch" "ch" ...
## $ pronounced : chr "ch" "ch" "ch" "ch" ...
## $ ur : int 1 1 1 1 1 1 0 0 0 1 ...
## $ urPal : int 1 1 1 1 1 1 0 1 0 1 ...
## $ suffix : chr "i" "e" "ul" "i" ...
## $ vowel : chr "i" "e" "u" "i" ...
## $ task : chr "scripted" "scripted" "scripted" "scripted" ...
## $ task2 : chr "reading" "reading" "reading" "reading" ...
# ur과 urPal을 factor로 변경
data$ur <- as.factor(data$ur)
data$urPal <- as.factor(data$urPal)
class(data$ur) #class 확인
## [1] "factor"
class(data$urPal) #class 확인
## [1] "factor"
# 열 이름을 변경(task2를 style로)
data <- rename(data, "style" = "task2")
data_1 <- data %>%
filter(exp=="1" & suffix!="e") #접미사 e인 단어는 제외
str(data_1)
## 'data.frame': 828 obs. of 18 variables:
## $ exp : int 1 1 1 1 1 1 1 1 1 1 ...
## $ register : chr "ids" "ids" "ids" "ids" ...
## $ subject : chr "W01" "W01" "W01" "W01" ...
## $ speaker_gender : chr "f" "f" "f" "f" ...
## $ listener_gender: chr "m" "m" "m" "m" ...
## $ speaker_age : chr "na" "na" "na" "na" ...
## $ listener_age : chr "11;09" "11;09" "11;09" "11;09" ...
## $ item : chr "kkoch" "kkoch" "kkoch" "path" ...
## $ syllableN : int 1 1 1 1 1 1 1 1 1 1 ...
## $ frequency : chr "high" "high" "high" "high" ...
## $ coda : chr "ch" "ch" "ch" "th" ...
## $ pronounced : chr "ch" "ch" "ch" "ch" ...
## $ ur : Factor w/ 2 levels "0","1": 2 2 2 1 1 1 2 2 2 2 ...
## $ urPal : Factor w/ 2 levels "0","1": 2 2 2 1 2 1 2 2 2 2 ...
## $ suffix : chr "i" "ul" "i" "ul" ...
## $ vowel : chr "i" "u" "i" "u" ...
## $ task : chr "scripted" "scripted" "scripted" "scripted" ...
## $ style : chr "reading" "reading" "reading" "reading" ...
- depent var: ur(canonical)
- predictor: Register, coda, vowel, style
summary(glmer(ur ~ register + coda + vowel + style + (1|subject), family="binomial", data=data_1))
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: binomial ( logit )
## Formula: ur ~ register + coda + vowel + style + (1 | subject)
## Data: data_1
##
## AIC BIC logLik deviance df.resid
## 818.6 856.3 -401.3 802.6 820
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -7.9882 -0.5467 0.1788 0.5305 4.1888
##
## Random effects:
## Groups Name Variance Std.Dev.
## subject (Intercept) 1.851 1.361
## Number of obs: 828, groups: subject, 22
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.7033 0.5445 3.128 0.00176 **
## registerids 1.6491 0.2004 8.229 < 2e-16 ***
## codaph 0.9052 0.2304 3.929 8.53e-05 ***
## codath -1.7263 0.2329 -7.414 1.23e-13 ***
## voweli -2.1974 0.4333 -5.071 3.96e-07 ***
## vowelu -1.7882 0.4320 -4.139 3.48e-05 ***
## stylespotaneous -0.3521 0.2069 -1.702 0.08883 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) rgstrd codaph codath voweli vowelu
## registerids -0.203
## codaph -0.108 0.061
## codath -0.290 -0.143 0.330
## voweli -0.751 0.007 -0.035 0.247
## vowelu -0.767 0.114 -0.085 0.153 0.892
## stylespotns -0.194 -0.083 -0.099 -0.006 0.071 0.160
# summary(glmer(ur ~ register*coda + register*vowel + register*style + (1 + register + coda + vowel + style|subject), family="binomial",data=data_1))
ggplot(data_1,aes(x=register ,y=ur,color=coda,fill=coda)) +
geom_point(position=position_jitterdodge(dodge.width=0.9)) +
geom_boxplot(outlier.colour = NA, alpha=0.5,
position = position_dodge(width=0.9))+
labs(x = NULL, y="CANONICALITY", title="Canonical output form on Surface in CDS and ADS", tag="", show.legend = T)+
theme(plot.title = element_text(hjust = 0.5))+
scale_x_discrete(labels= c("CDS","ADS"))
