library(ISLR2)
Auto <- na.omit(Auto)

9a)

Quantitative Qualitative
Qualitative origin
Qualitative name
Qualitative cylinders
mpg
displacement
horsepower
weight
acceleration
year

9b)

data.frame(
    "Quantitative"=c("MPG", "Cylinders", "Displacement", "Horse Power", "Weight", "Acceleration", "Year"),
    "Lower Range"=c(range(Auto$mpg)[1], range(Auto$cylinders)[1], range(Auto$displacement)[1], range(Auto$horsepower)[1], range(Auto$weight)[1], range(Auto$acceleration)[1], range(Auto$year)[1]),
    "Upper Range"=c(range(Auto$mpg)[2], range(Auto$cylinders)[2], range(Auto$displacement)[2], range(Auto$horsepower)[2], range(Auto$weight)[2], range(Auto$acceleration)[2], range(Auto$year)[2])
  )
##   Quantitative Lower.Range Upper.Range
## 1          MPG           9        46.6
## 2    Cylinders           3         8.0
## 3 Displacement          68       455.0
## 4  Horse Power          46       230.0
## 5       Weight        1613      5140.0
## 6 Acceleration           8        24.8
## 7         Year          70        82.0

9c)

data.frame(
    "Quantitative"=c("MPG", "Cylinders", "Displacement", "Horse Power", "Weight", "Acceleration", "Year"),
    "Mean"=c(mean(Auto$mpg), mean(Auto$cylinders), mean(Auto$displacement), mean(Auto$horsepower), mean(Auto$weight), mean(Auto$acceleration), mean(Auto$year)),
    "Standard Deviation"=c(sd(Auto$mpg),sd(Auto$cylinders),sd(Auto$displacement),sd(Auto$horsepower),sd(Auto$weight),sd(Auto$acceleration),sd(Auto$year))
)
##   Quantitative        Mean Standard.Deviation
## 1          MPG   23.445918           7.805007
## 2    Cylinders    5.471939           1.705783
## 3 Displacement  194.411990         104.644004
## 4  Horse Power  104.469388          38.491160
## 5       Weight 2977.584184         849.402560
## 6 Acceleration   15.541327           2.758864
## 7         Year   75.979592           3.683737
Auto_filtered <- Auto[-c(10:85), ]
dim(Auto_filtered)
## [1] 316   9
dim(Auto)
## [1] 392   9

9d)

data.frame(
    "Quantitative"=c("MPG", "Cylinders", "Displacement", "Horse Power", "Weight", "Acceleration", "Year"),
    "Range"=c(range(Auto_filtered$mpg),range(Auto_filtered$cylinders),range(Auto_filtered$displacement),range(Auto_filtered$horsepower),range(Auto_filtered$weight),range(Auto_filtered$acceleration),range(Auto_filtered$year)),
    "Mean"=c(mean(Auto_filtered$mpg),mean(Auto_filtered$cylinders),mean(Auto_filtered$displacement),mean(Auto_filtered$horsepower),mean(Auto_filtered$weight),mean(Auto_filtered$acceleration),mean(Auto_filtered$year)),
    "Standard Deviation" = c(sd(Auto_filtered$mpg),sd(Auto_filtered$cylinders),sd(Auto_filtered$displacement),sd(Auto_filtered$horsepower),sd(Auto_filtered$weight),sd(Auto_filtered$acceleration),sd(Auto_filtered$year))
)
##    Quantitative  Range        Mean Standard.Deviation
## 1           MPG   11.0   24.404430           7.867283
## 2     Cylinders   46.6    5.373418           1.654179
## 3  Displacement    3.0  187.240506          99.678367
## 4   Horse Power    8.0  100.721519          35.708853
## 5        Weight   68.0 2935.971519         811.300208
## 6  Acceleration  455.0   15.726899           2.693721
## 7          Year   46.0   77.145570           3.106217
## 8           MPG  230.0   24.404430           7.867283
## 9     Cylinders 1649.0    5.373418           1.654179
## 10 Displacement 4997.0  187.240506          99.678367
## 11  Horse Power    8.5  100.721519          35.708853
## 12       Weight   24.8 2935.971519         811.300208
## 13 Acceleration   70.0   15.726899           2.693721
## 14         Year   82.0   77.145570           3.106217

9e)

pairs(Auto)

This shows that horsepower, mpg, displacement, and weight all have strong correlations with each other

plot(Auto$cylinders, Auto$mpg)

plot(Auto$acceleration, Auto$mpg)

plot(Auto$horsepower, Auto$mpg)

plot(Auto$displacement, Auto$mpg)

I believe horsepower and displacement would be useful to determine mpg. There may be some use in including acceleration, but because of the spread, it may not be easy to get a precise answer.

library(ISLR2)

10a) 506 rows, 13 columns The rows are each a separate suburb of Boston. The columns are 13 different variables related to housing values

10b)

pairs(Boston)

There are many correlations between the different columns. Some do not correlate. For example, the Charles River (dummy variable) has no bearing on anything.

10c)

plot(Boston$crim,Boston$medv)

plot(Boston$zn, Boston$crim)

plot(Boston$indus, Boston$crim)

plot(Boston$nox, Boston$crim)

plot(Boston$rm, Boston$crim)

plot(Boston$age, Boston$crim)

plot(Boston$dis, Boston$crim)

plot(Boston$rad, Boston$crim)

plot(Boston$tax, Boston$crim)

plot(Boston$ptratio, Boston$crim)

plot(Boston$lstat, Boston$crim)

The proportion of owner-occupied units built before 1940, the lower status of the population, and the lower status of the population are positively related to the crime rate. The median value of owner-occupied homes is negatively correlated.

10d)

plot(Boston$tax)

plot(Boston$ptratio)

plot(Boston$crim)

range(Boston$ptratio)
## [1] 12.6 22.0
range(Boston$crim)
## [1]  0.00632 88.97620
range(Boston$tax)
## [1] 187 711

There are some census tracts with extremely high crime rates, tax rates, and pupil-to-teacher ratios. The range of pupil-to-teacher ratio is not relatively large (12.6 to 22.0). However, there is a wide range of crime and tax rates. Crime rates range: 0.00632 to 88.97620 and tax rates range: 187 to 711.

10e)

sum(Boston$chas)
## [1] 35

35

10f)

summary(Boston$ptratio)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   12.60   17.40   19.05   18.46   20.20   22.00

19.05

10g)

Boston[which.min(Boston$medv), ]
##        crim zn indus chas   nox    rm age    dis rad tax ptratio lstat medv
## 399 38.3518  0  18.1    0 0.693 5.453 100 1.4896  24 666    20.2 30.59    5
range(Boston$crim)
## [1]  0.00632 88.97620
range(Boston$zn)
## [1]   0 100
range(Boston$nox)
## [1] 0.385 0.871
range(Boston$rm)
## [1] 3.561 8.780
range(Boston$age)
## [1]   2.9 100.0
range(Boston$dis)
## [1]  1.1296 12.1265
range(Boston$rad)
## [1]  1 24
range(Boston$tax)
## [1] 187 711
range(Boston$ptratio)
## [1] 12.6 22.0
range(Boston$lstat)
## [1]  1.73 37.97
range(Boston$medv)
## [1]  5 50
range(Boston$indus)
## [1]  0.46 27.74

In crime, they’re in the middle of the range. In proportion of non-retail business acres per town, it is on the higher end. In nitrogen oxide concentration, they are on the higher end. In average number of rooms, they are in the middle of the range. In age, they are at the highest end. In distance from Boston employment centers, they are on the lower end. In accessibility to radial highways, they are on the highest end. In tax rate, they are on the higher end. In pupil-to-teacher ratio, they are on the higher end. In the lower status of the population, they are on the higher end. I think it is quite interesting to see that a majority of predictors are on the higher end for a census tract with the lowest median value.

10h)

data.frame(
  "Avg Room gt 7" = c(sum(Boston$rm>7)),
  "Avg Room gt 8" = c(sum(Boston$rm>8))
)
##   Avg.Room.gt.7 Avg.Room.gt.8
## 1            64            13
Boston[Boston$rm>8,]
##        crim zn indus chas    nox    rm  age    dis rad tax ptratio lstat medv
## 98  0.12083  0  2.89    0 0.4450 8.069 76.0 3.4952   2 276    18.0  4.21 38.7
## 164 1.51902  0 19.58    1 0.6050 8.375 93.9 2.1620   5 403    14.7  3.32 50.0
## 205 0.02009 95  2.68    0 0.4161 8.034 31.9 5.1180   4 224    14.7  2.88 50.0
## 225 0.31533  0  6.20    0 0.5040 8.266 78.3 2.8944   8 307    17.4  4.14 44.8
## 226 0.52693  0  6.20    0 0.5040 8.725 83.0 2.8944   8 307    17.4  4.63 50.0
## 227 0.38214  0  6.20    0 0.5040 8.040 86.5 3.2157   8 307    17.4  3.13 37.6
## 233 0.57529  0  6.20    0 0.5070 8.337 73.3 3.8384   8 307    17.4  2.47 41.7
## 234 0.33147  0  6.20    0 0.5070 8.247 70.4 3.6519   8 307    17.4  3.95 48.3
## 254 0.36894 22  5.86    0 0.4310 8.259  8.4 8.9067   7 330    19.1  3.54 42.8
## 258 0.61154 20  3.97    0 0.6470 8.704 86.9 1.8010   5 264    13.0  5.12 50.0
## 263 0.52014 20  3.97    0 0.6470 8.398 91.5 2.2885   5 264    13.0  5.91 48.8
## 268 0.57834 20  3.97    0 0.5750 8.297 67.0 2.4216   5 264    13.0  7.44 50.0
## 365 3.47428  0 18.10    1 0.7180 8.780 82.9 1.9047  24 666    20.2  5.29 21.9

All census tracts that have more than 8 average rooms seem to have ;ow lower status of population, low crime rate, and high median value.