An investigation of the association between transmission
and MPG
An investigation of the association between transmission and MPG
Research Question 1: Is an automatic or manual transmission better for MPG
Research Question 2: Quantify the MPG difference between automatic and manual transmissions
Summary
The manual transmission car in 1974 is better on mpg than the automatic The mpg difference is
if other coefficients held constant, for every unit increase of mpg, the manual car is higher than
the automatic car in 1974, given the best fitted model.
In this report, we explored the association of transmission to mpg in 1974 trend
magazine dataset, which includes 32 cars. To answer the first question, we
ploted a boxplot (see appendix) to compare the means of mpg between auto and
manual. It illustrated that manual cars have a higher mpg of 7.2449393 than the
auto.
To tackle the second question, we tended to fit a parsimonious model first by using backward elimination
method, where we constructed first a full model, then removed the predictor that had the highest p-value
before we fitted the model again;we repeated this method until all the predictors had lowest p-value less than
the critical value 0.05.
Appendix
1. load data and libraries
data(mtcars)
library(ggplot2)
library(dplyr)
2.Exploratory analysis
str(mtcars)
## 'data.frame': 32 obs. of 11 variables:
## $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
## $ cyl : num 6 6 4 6 8 6 8 4 4 6 ...
## $ disp: num 160 160 108 258 360 ...
## $ hp : num 110 110 93 110 175 105 245 62 95 123 ...
## $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
## $ wt : num 2.62 2.88 2.32 3.21 3.44 ...
## $ qsec: num 16.5 17 18.6 19.4 17 ...
## $ vs : num 0 0 1 1 0 1 0 1 1 1 ...
## $ am : num 1 1 1 0 0 0 0 0 0 0 ...
1
## $ gear: num 4 4 4 3 3 3 3 4 4 4 ...
## $ carb: num 4 4 1 1 2 1 4 2 2 4 ...
summary(mtcars$mpg)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10.40 15.42 19.20 20.09 22.80 33.90
mtcars$am <- as.factor(mtcars$am)
mtcars$cyl <- as.factor(mtcars$cyl)
mtcars$vs <- as.factor(mtcars$vs)
mtcars$gear <- as.factor(mtcars$gear)
mtcars$carb <- as.factor(mtcars$carb)
# look for correlation
pairs(mtcars, panel = panel.smooth)
1.0 2.5 50 300 2 4 1.0 1.8 1.0 2.5
mpg
10
cyl
1.0
disp
100
hp
50
drat
3.0
wt
2
qsec
16
vs
1.0
am
gear 1.0
1.0
1 6
carb
10 30 100 3.0 5.0 16 22 1.0 1.8 1 4
# mpg difference between manual and auto transmission
diff(tapply(mtcars$mpg, mtcars$am, mean))
## 1
## 7.244939
boxplot(mpg ~ am, data = mtcars, main = "auto vs manual on mpg", xlab = "transmission( 0 : auto, 1: manu
2
auto vs manual on mpg
30
25
mpg
20
15
10
0 1
transmission( 0 : auto, 1: manual)
The paired plot showed that there are correlations of am versus vs, gear, carb. The boxplot revealed that
manual cars have higher mpg than automatic cars.
Conclusion for Question 1: In 1973 to 1974 models of 32 cars, manual transmission is generally
better for mpg compared with automatic transmission.
3. select models
# Backward Elimination
mdl_whole <- lm(mpg ~., data = mtcars)
summary(mdl_whole)$coef
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 23.87913244 20.06582026 1.19004018 0.25252548
## cyl6 -2.64869528 3.04089041 -0.87102622 0.39746642
## cyl8 -0.33616298 7.15953951 -0.04695316 0.96317000
## disp 0.03554632 0.03189920 1.11433290 0.28267339
## hp -0.07050683 0.03942556 -1.78835344 0.09393155
## drat 1.18283018 2.48348458 0.47627845 0.64073922
## wt -4.52977584 2.53874584 -1.78425732 0.09461859
## qsec 0.36784482 0.93539569 0.39325050 0.69966720
## vs1 1.93085054 2.87125777 0.67247551 0.51150791
## am1 1.21211570 3.21354514 0.37718957 0.71131573
## gear4 1.11435494 3.79951726 0.29328856 0.77332027
## gear5 2.52839599 3.73635801 0.67670068 0.50889747
## carb2 -0.97935432 2.31797446 -0.42250436 0.67865093
## carb3 2.99963875 4.29354611 0.69863900 0.49546781
3
## carb4 1.09142288 4.44961992 0.24528452 0.80956031
## carb6 4.47756921 6.38406242 0.70136677 0.49381268
## carb8 7.25041126 8.36056638 0.86721532 0.39948495
mdl <- lm(mpg ~. - cyl - carb - gear - vs -drat - disp - hp, data = mtcars)
summary(mdl)$coef
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 9.617781 6.9595930 1.381946 1.779152e-01
## wt -3.916504 0.7112016 -5.506882 6.952711e-06
## qsec 1.225886 0.2886696 4.246676 2.161737e-04
## am1 2.935837 1.4109045 2.080819 4.671551e-02
model = mpg ~ wt + qsec + am1 is the most parsimonious model after backward elimination of
greater p values.
4. residual plot
res <- resid(mdl)
qqnorm(res)
qqline(res)
Normal Q−Q Plot
4
Sample Quantiles
2
0
−2
−2 −1 0 1 2
Theoretical Quantiles
hist(res, breaks = 5)
4
Histogram of res
10
8
Frequency
6
4
2
0
−4 −2 0 2 4 6
res
The residuals of the fitted model seem like skewed to the right. Under this model, the mpg
difference is if other coefficients held constant, for every unit increase of mpg, the manual car is
2.9358372 mpg higher than the automatic car in 1974.
