Week2_excercise

library packages

pkgs <- c("dplyr", "tidyr", "magrittr", "ggplot2", "car", "mlmRev")
lapply(pkgs, library, character.only = TRUE)

Q2

data("minn38", package = "MASS") #Read data
dat = minn38
str(dat) # Take a look at the data

## 'data.frame':    168 obs. of  5 variables:
##  $ hs : Factor w/ 3 levels "L","M","U": 1 1 1 1 1 1 1 1 1 1 ...
##  $ phs: Factor w/ 4 levels "C","E","N","O": 1 1 1 1 1 1 1 3 3 3 ...
##  $ fol: Factor w/ 7 levels "F1","F2","F3",..: 1 2 3 4 5 6 7 1 2 3 ...
##  $ sex: Factor w/ 2 levels "F","M": 2 2 2 2 2 2 2 2 2 2 ...
##  $ f  : int  87 72 52 88 32 14 20 3 6 17 ...

#2-1
table(dat$sex) #answer

## 
##  F  M 
## 84 84

#2-2
table(dat[dat$phs=="C",]$sex) #answer

## 
##  F  M 
## 21 21

Q3

#Read data
data("nlschools", package = "MASS")
dat = nlschools

#Individual level
IQ.ind = with(dat, cor(IQ,lang)) #answer
IQ.ind

## [1] 0.6098195

#Class level
IQ.class = summarise(group_by(dat, class), cor(IQ,lang)) #answer
IQ.class

## # A tibble: 133 x 2
##     class cor(IQ, lang)
##    <fctr>         <dbl>
## 1     180     0.6533810
## 2     280     0.4268428
## 3    1082     0.9185030
## 4    1280     0.3920230
## 5    1580     0.6622551
## 6    1680     0.5986652
## 7    1880     0.6017628
## 8    2180     0.5808393
## 9    2480     0.6275642
## 10   2680     0.6154951
## # ... with 123 more rows

Q4

 #use read.table(whatever/the/directory/mydata.txt) to read data
str(dat) # Take a look at the data

## 'data.frame':    2287 obs. of  6 variables:
##  $ school  : int  1 1 1 1 1 1 1 1 1 1 ...
##  $ pupil   : int  17001 17002 17003 17004 17005 17006 17007 17008 17009 17010 ...
##  $ viq     : num  15 14.5 9.5 11 8 9.5 9.5 13 9.5 11 ...
##  $ language: int  46 45 33 46 20 30 30 57 36 36 ...
##  $ csize   : int  29 29 29 29 29 29 29 29 29 29 ...
##  $ ses     : int  23 10 15 23 10 10 23 10 13 15 ...

#Plot the data
ggplot(dat, aes(x = viq, y = language, color = ses))+
  scale_color_gradient(low = "blue",high = "green")+
  geom_point(alpha = .5)+
  stat_summary(fun.y = mean, geom = "line", size = 0.7, color = "red")

Q6

#Read data
data("Gcsemv", package = "mlmRev")
dat = Gcsemv
dat = na.omit(dat)
#Calculate correlation based on school
dat_cor = summarise(group_by(dat, school), cor(written, course))[,c(1:2)]
ggplot(dat_cor, aes(x = dat_cor[[2]]))+
  geom_histogram(binwidth = .1, fill = "skyblue")+
  geom_vline(xintercept = mean(dat_cor[[2]], na.rm = TRUE), linetype = "dotted", color = "red")+
  geom_text(aes(x = mean(dat_cor[[2]], na.rm = TRUE),y = 15, label = "Averaged correlations over schools", 
                angle = 90, vjust = -1, hjust = 1.1), color = "red")+
  geom_vline(xintercept = cor(dat$written, dat$course))+
  geom_text(aes(x = cor(dat$written, dat$course),y = 15, label = "Correlations computed over individuals", 
                angle = 90, vjust = 1, hjust = 1.1))+
  labs(x="Correlation coefficient")

Q7

#Read data
library(WWGbook)

data("autism", package ="WWGbook")
#Take a look at data
dat = autism
str(dat)

## 'data.frame':    612 obs. of  4 variables:
##  $ age    : int  2 3 5 9 13 2 3 5 9 13 ...
##  $ vsae   : int  6 7 18 25 27 17 18 12 18 24 ...
##  $ sicdegp: int  3 3 3 3 3 3 3 3 3 3 ...
##  $ childid: int  1 1 1 1 1 3 3 3 3 3 ...

#Plot
ggplot(dat, aes(x = age, y = vsae, group = childid))+
  geom_point(size = 1)+
  geom_line()+
  facet_grid(.~sicdegp)+
  labs(x = "Age (years)", y = "VSAE score")