MPG - Automatic vs Manual Transmissions

Executive Summary

Objectives of this project is to answer the following main questions
- “Is an automatic or manual transmission better for MPG?”
- “How different is the MPG between automatic manual transmission?”
Conclusions
- Manual transmissions are more fuel efficient than Automatics.
- The difference is that Manual transmissions are 80% (1.8) better than Automatics in fuel economy (MPG).

Data Processing

Load data and identify variables to factor using str().

data(mtcars)
str(mtcars)

Factor variables cyl,vs,gear,carb and including am to mtcarsdata.

mtcarsdata <- mtcars
mtcarsdata$cyl <- factor(mtcarsdata$cyl)
mtcarsdata$am <- factor(ifelse(mtcarsdata$am == 0, "Automatic", "Manual"))
mtcarsdata$vs <- factor(mtcarsdata$vs)
mtcarsdata$gear <- factor(mtcarsdata$gear)
mtcarsdata$carb <- factor(mtcarsdata$carb)

Exploratory Data Analysis

Plotted a boxplot of mpg per transmission type.
Manual transmission are more efficient than Automatic transmission.
Check Appendix - Figure1 (Barplot Transimission Type Comparison) - Page3

boxplot(mpg ~ am, data = mtcarsdata, notch=FALSE, xlab = "Transmission Type", ylab = "MPG",
        main = "Transmission Comparison", varwidth = TRUE, col = c("orange","blue"))
legend("topleft", inset=.05, title="Transmissions",c("Automatic","Manual"), 
       fill=c("orange","blue"), horiz=TRUE)

Scatterplot to show mpg paired with all variables. Check Appendix - Figure2 (Scatterplot) - Page4

pairs(mpg ~ ., data = mtcarsdata,col="green")

Regression Modeling

Used step wise with multiple model methods ‘forward’ and ‘backward’ for modeling. Coefficients cyl (Cylinders),hp (Horsepower),wt (Weight) and am (Transmission Type)

fitmodel <- step(lm(data=mtcarsdata, mpg~.), direction="both")

summary(fitmodel)$coef

##             Estimate Std. Error t value  Pr(>|t|)
## (Intercept) 33.70832    2.60489 12.9404 7.733e-13
## cyl6        -3.03134    1.40728 -2.1540 4.068e-02
## cyl8        -2.16368    2.28425 -0.9472 3.523e-01
## hp          -0.03211    0.01369 -2.3450 2.693e-02
## wt          -2.49683    0.88559 -2.8194 9.081e-03
## amManual     1.80921    1.39630  1.2957 2.065e-01

t.test(mpg ~ am, data = mtcars)

## 
##  Welch Two Sample t-test
## 
## data:  mpg by am
## t = -3.767, df = 18.33, p-value = 0.001374
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -11.28  -3.21
## sample estimates:
## mean in group 0 mean in group 1 
##           17.15           24.39

Residuals and Diagnostics

The Residuals vs. Fitted plot scattered opoints in the plot (independence).
The Normal Q-Q plot have points lie consistent within the line.
The Scale-Location plot consists of points laid out on scattered pattern.
There are some distinct points of interest (outliers) on the right.
Check Appendix - Figure3 (Residuals) - Page5

par(mfrow=c(2, 2))
plot(fitmodel)

Results (Findings)

The modeling shows that the best model includes the cyl6, cyl8 cyl, hp hp, wt wt, and amManual am variables (overall p-value<0.001).
The adjusted R-squared indicates that about 84% of the variance is explained by the final model. mpg increases having a Manual Transmission (by 1.8).

Inference (Conclusions)

Manual transmission are more efficient than Automatic transmission.
The rate of change of the conditional mean mpg with respect to am is about 1.8.

Appendix: Plots

Figure1 (Barplot Transimission Type Comparison)

Figure2 (Scatterplot)

Figure3 (Residuals)