dim(USArrests_Coasts)
## [1] 50 8
names(USArrests_Coasts)
## [1] "X1" "Murder" "Assault" "UrbanPop" "Rape"
## [6] "East Coast" "West Coast" "Any Coast"
attributes(USArrests_Coasts)
## $names
## [1] "X1" "Murder" "Assault" "UrbanPop" "Rape"
## [6] "East Coast" "West Coast" "Any Coast"
##
## $class
## [1] "tbl_df" "tbl" "data.frame"
##
## $row.names
## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
## [24] 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46
## [47] 47 48 49 50
##
## $spec
## cols(
## X1 = col_character(),
## Murder = col_double(),
## Assault = col_integer(),
## UrbanPop = col_integer(),
## Rape = col_double(),
## `East Coast` = col_character(),
## `West Coast` = col_character(),
## `Any Coast` = col_character()
## )
attributes(USArrests_Coasts)$row.names
## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
## [24] 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46
## [47] 47 48 49 50
hist(USArrests_Coasts$Murder)
state.names = row.names(USArrests_Coasts)
barplot(USArrests_Coasts$Murder, names.arg = state.names, las = 2, ylab = "Murder Rate per 100,000",
main = "Murder Rate in the United States in 1973")
USArrests_Coasts$`East Coast`
## [1] "No" "No" "No" "No" "No" "No" "Yes" "Yes" "Yes" "Yes" "No"
## [12] "No" "No" "No" "No" "No" "No" "No" "Yes" "Yes" "Yes" "No"
## [23] "No" "No" "No" "No" "No" "No" "Yes" "Yes" "No" "Yes" "No"
## [34] "No" "No" "No" "No" "Yes" "Yes" "Yes" "No" "No" "No" "No"
## [45] "Yes" "Yes" "No" "No" "No" "No"
USArrests_Coasts$Murder
## [1] 13.2 10.0 8.1 8.8 9.0 7.9 3.3 5.9 15.4 17.4 5.3 2.6 10.4 7.2
## [15] 2.2 6.0 9.7 15.4 2.1 11.3 4.4 12.1 2.7 16.1 9.0 6.0 4.3 12.2
## [29] 2.1 7.4 11.4 11.1 13.0 0.8 7.3 6.6 4.9 6.3 3.4 14.4 3.8 13.2
## [43] 12.7 3.2 2.2 8.5 4.0 5.7 2.6 6.8
plot(y = USArrests$Murder, x = USArrests$Assault, main = "Murder Rate vs. Assault Rate, US, 1973")
summary(USArrests_Coasts)
## X1 Murder Assault UrbanPop
## Length:50 Min. : 0.800 Min. : 45.0 Min. :32.00
## Class :character 1st Qu.: 4.075 1st Qu.:109.0 1st Qu.:54.50
## Mode :character Median : 7.250 Median :159.0 Median :66.00
## Mean : 7.788 Mean :170.8 Mean :65.54
## 3rd Qu.:11.250 3rd Qu.:249.0 3rd Qu.:77.75
## Max. :17.400 Max. :337.0 Max. :91.00
## Rape East Coast West Coast Any Coast
## Min. : 7.30 Length:50 Length:50 Length:50
## 1st Qu.:15.07 Class :character Class :character Class :character
## Median :20.10 Mode :character Mode :character Mode :character
## Mean :21.23
## 3rd Qu.:26.18
## Max. :46.00
mean(USArrests_Coasts$Murder)
## [1] 7.788
mean(USArrests_Coasts$Assault)
## [1] 170.76
mean(USArrests_Coasts$UrbanPop)
## [1] 65.54
mean(USArrests_Coasts$Rape)
## [1] 21.232
sd(USArrests_Coasts$Murder)
## [1] 4.35551
sd(USArrests_Coasts$Assault)
## [1] 83.33766
sd(USArrests_Coasts$UrbanPop)
## [1] 14.47476
sd(USArrests_Coasts$Rape)
## [1] 9.366385
var(USArrests_Coasts$Murder)
## [1] 18.97047
var(USArrests_Coasts$Rape)
## [1] 87.72916
var(USArrests_Coasts$Assault)
## [1] 6945.166
var(USArrests_Coasts$UrbanPop)
## [1] 209.5188
t.test(USArrests_Coasts$Murder~USArrests_Coasts$`East Coast`)
##
## Welch Two Sample t-test
##
## data: USArrests_Coasts$Murder by USArrests_Coasts$`East Coast`
## t = 0.10323, df = 21.811, p-value = 0.9187
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -2.946705 3.255276
## sample estimates:
## mean in group No mean in group Yes
## 7.834286 7.680000
t.test(USArrests_Coasts$Assault~USArrests_Coasts$`East Coast`)
##
## Welch Two Sample t-test
##
## data: USArrests_Coasts$Assault by USArrests_Coasts$`East Coast`
## t = -0.3451, df = 24.496, p-value = 0.733
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -64.82622 46.23574
## sample estimates:
## mean in group No mean in group Yes
## 167.9714 177.2667
t.test(USArrests_Coasts$Rape~USArrests_Coasts$`East Coast`)
##
## Welch Two Sample t-test
##
## data: USArrests_Coasts$Rape by USArrests_Coasts$`East Coast`
## t = 1.846, df = 33.475, p-value = 0.07375
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.4832761 10.0032761
## sample estimates:
## mean in group No mean in group Yes
## 22.66 17.90