in-class ex 4:Individual correlation vs grouped correlation

#愼㸵挼㹥.csv挼㸰ɮɡA愼㸵昼㹤戼㸸g愼㸵H愼㸴U愼㸸B挼㸶JŪ愼㸸昼㹡csv
#step1:change work directory:session-set working directory
#step2:change dta <- read.csv("langMath.csv", h=T)
#愼㸵挼㹥.r挼㸰ɮɡA愼㸵昼㹤愼㸵ΥH愼㸴U戼㹢P愼㹡k挼㸲নrmd挼㸰挼㸹
#knitr::spin("langMath.R", knit=FALSE)

# data management and graphics package
library(tidyverse)

## -- Attaching packages ---------------- tidyverse 1.3.0 --

## √ ggplot2 3.3.2     √ purrr   0.3.4
## √ tibble  3.0.3     √ dplyr   1.0.2
## √ tidyr   1.1.2     √ stringr 1.4.0
## √ readr   1.3.1     √ forcats 0.5.0

## -- Conflicts ------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

# input data
dta <- read.csv("langMath.csv", h=T)

# compute averages by school
dta_a <- dta %>%
        group_by(School) %>%
        summarize(ave_lang = mean(Lang, na.rm=TRUE),
                  ave_arith = mean(Arith, na.rm=TRUE))

## `summarise()` ungrouping output (override with `.groups` argument)

# superimpose two plots
ggplot(data=dta, aes(x=Arith, y=Lang)) +
 geom_point(color="skyblue") +
 stat_smooth(method="lm", formula=y ~ x, se=F, col="skyblue") +
 geom_point(data=dta_a, aes(ave_arith, ave_lang), color="steelblue") +
 stat_smooth(data=dta_a, aes(ave_arith, ave_lang),
             method="lm", formula= y ~ x, se=F, color="steelblue") +
 labs(x="Arithmetic score", 
      y="Language score") +
 theme_bw()

##