Data management
# install.package("mlmRev")
library(mlmRev)
# load the data from the package
data(Gcsemv, package="mlmRev")
# view first 6 lines
head(Gcsemv)
school student gender written course
1 20920 16 M 23 NA
2 20920 25 F NA 71.2
3 20920 27 F 39 76.8
4 20920 31 F 36 87.9
5 20920 42 M 16 44.4
6 20920 62 F 36 NA
Summary statistics
with(Gcsemv, cor(written, course, use="pairwise"))
[1] 0.47417
# compute the means by school
course_schavg <- with(Gcsemv, tapply(course, school, mean, na.rm=T))
written_schavg <- with(Gcsemv, tapply(written, school, mean, na.rm=T))
cor(course_schavg, written_schavg)
[1] 0.39568
Visualization
library(tidyverse)
dta <- Gcsemv %>%
group_by(school) %>%
mutate(r_sch = cor(course, written, use="pairwise"))
dtar <- dta[!duplicated(dta$school),"r_sch"]
##使用GGplot 畫圖疊層
ggplot(data=Gcsemv, aes(x=course, y=written)) +
geom_point(color="skyblue") +
geom_smooth(method="lm", formula=y ~ x, se=F, col="skyblue") +
geom_point(data=dtar, aes(x=course_schavg, y=written_schavg), color="steelblue") + geom_smooth(data=dtar, aes(course_schavg, written_schavg),
method="lm", formula= y ~ x, se=F, color="steelblue") +labs(x="course score",y="written score") +
theme_bw()
The end