Data Management HW W5 EX02,4,5

pacman::p_load(Ecdat, HSAUR3, tidyr, datasets, dplyr, foreign, mosaic, memisc, gmodels, GGally)

EX02

dta_02 <- Caschool %>%
  group_by(county) %>%
  sample_n(1)

with(dta_02, plot(mathscr ~ readscr, 
                xlab = "average math score", 
                ylab = "average reading score"))

EX04

head(dta_04 <- backpain)

##   ID  status driver suburban
## 1  1    case    yes      yes
## 2  1 control    yes       no
## 3  2    case    yes      yes
## 4  2 control    yes      yes
## 5  3    case    yes       no
## 6  3 control    yes      yes

dta_04 <- backpain %>% 
  group_by(status, driver, suburban) %>% 
  summarise(n = n()) %>% 
  ungroup() %>% 
  spread(status, n) %>% 
  mutate(total = case + control); dta_04

## # A tibble: 4 x 5
##   driver suburban  case control total
##   <fct>  <fct>    <int>   <int> <int>
## 1 no     no          26      47    73
## 2 no     yes          6       7    13
## 3 yes    no          64      63   127
## 4 yes    yes        121     100   221

EX05

library(datasets)
dta_05 <- merge(state.x77, USArrests, "row.names")
cor(dta_05[, -1])

##             Population      Income  Illiteracy    Life Exp    Murder.x
## Population  1.00000000  0.20822756  0.10762237 -0.06805195  0.34364275
## Income      0.20822756  1.00000000 -0.43707519  0.34025534 -0.23007761
## Illiteracy  0.10762237 -0.43707519  1.00000000 -0.58847793  0.70297520
## Life Exp   -0.06805195  0.34025534 -0.58847793  1.00000000 -0.78084575
## Murder.x    0.34364275 -0.23007761  0.70297520 -0.78084575  1.00000000
## HS Grad    -0.09848975  0.61993232 -0.65718861  0.58221620 -0.48797102
## Frost      -0.33215245  0.22628218 -0.67194697  0.26206801 -0.53888344
## Area        0.02254384  0.36331544  0.07726113 -0.10733194  0.22839021
## Murder.y    0.32024487 -0.21520501  0.70677564 -0.77849850  0.93369089
## Assault     0.31702281  0.04093255  0.51101299 -0.62665800  0.73976479
## UrbanPop    0.51260491  0.48053302 -0.06219936  0.27146824  0.01638255
## Rape        0.30523361  0.35738678  0.15459686 -0.26956828  0.57996132
##                HS Grad      Frost        Area    Murder.y     Assault
## Population -0.09848975 -0.3321525  0.02254384  0.32024487  0.31702281
## Income      0.61993232  0.2262822  0.36331544 -0.21520501  0.04093255
## Illiteracy -0.65718861 -0.6719470  0.07726113  0.70677564  0.51101299
## Life Exp    0.58221620  0.2620680 -0.10733194 -0.77849850 -0.62665800
## Murder.x   -0.48797102 -0.5388834  0.22839021  0.93369089  0.73976479
## HS Grad     1.00000000  0.3667797  0.33354187 -0.52159126 -0.23030510
## Frost       0.36677970  1.0000000  0.05922910 -0.54139702 -0.46823989
## Area        0.33354187  0.0592291  1.00000000  0.14808597  0.23120879
## Murder.y   -0.52159126 -0.5413970  0.14808597  1.00000000  0.80187331
## Assault    -0.23030510 -0.4682399  0.23120879  0.80187331  1.00000000
## UrbanPop    0.35868123 -0.2461862 -0.06154747  0.06957262  0.25887170
## Rape        0.27072504 -0.2792054  0.52495510  0.56357883  0.66524123
##               UrbanPop       Rape
## Population  0.51260491  0.3052336
## Income      0.48053302  0.3573868
## Illiteracy -0.06219936  0.1545969
## Life Exp    0.27146824 -0.2695683
## Murder.x    0.01638255  0.5799613
## HS Grad     0.35868123  0.2707250
## Frost      -0.24618618 -0.2792054
## Area       -0.06154747  0.5249551
## Murder.y    0.06957262  0.5635788
## Assault     0.25887170  0.6652412
## UrbanPop    1.00000000  0.4113412
## Rape        0.41134124  1.0000000

ggpairs(dta_05[, -1])