Random Motors Project

Submission
Name – Surendranath Kolachalam
Q-1a) Formulate the null hypotheses to check whether the new models are
performing as per the desired design specifications.

For Rocinante36: For Marengo32:

Mileage HO : mean = 22 km/ltr Mileage HO : mean = 15 km/ltr

Top speed HO : mean = 140km/hr Top speed HO : mean = 210 km/hr

Q-1b) Formulate the alternate hypotheses to check whether the new models are
performing as per the desired design specifications.

For Rocinante36: For Marengo32:

Mileage H1 : mean ≠ 22 km/ltr Mileage H1 : mean ≠ 15 km/ltr

Top speed H1 : mean ≠ 140 km/hr Top speed H1 : mean ≠ 210 km/hr
Q-2) In order to comment on whether the design specifications are being
matched or not, perform relevant hypothesis tests and calculate the p-value for
each. What will you conclude? Assume you are performing the tests at 95%
confidence level.
For Rocinante36: Conclusion
Rocinante36:
p-value for mileage = 0.082 The p value is not less than 0.05,
p-value for top speed = 0.432 hence we "Fail to reject Ho” for both
For Marengo32: mileage and Top speed.
Marengo32:
p-value for mileage = 0.134 The p value is not less than 0.05,
p-value for top speed = 0.373 hence we "Fail to reject Ho” for both
mileage and Top speed.
Q-3) You have learnt about the possible errors that might result from the
hypothesis tests. What type of error is more expensive for Random motors
based on the hypothesis they are testing? Why? Assume that you need to
refund all your customers if your cars deviate from specifications.
The type of error which is more Reason:
expensive: In case of type 2 error, Random
Type 2 error: where in we fail to reject motors will end up its selling
null hypothesis while null hypothesis customers vehicles promising wrong
is not true specifications which will result in
e.g.: mileage is not actually 22, it is complaints -> bad reputation and
less than 22, but we fail to reject the losses to cover refund claims.
Type 1 error also will result in additional manufacturing cost,
hypothesis that mileage is 22 however, the losses are not as high as type 2 where there will
be losses such as reputation loss which impacts brand image
Q-4) Develop a regression equation for each model at 95 percent confidence
level. From the regression equation predict the sales of the two models.
Develop the regression equation for the Develop the regression equation for the
Rocinante models and Predict the number Marengo models and Predict the number of
of unit sales of Rocinante36 model? unit sales of Marengo32 model?

Regression coefficients Regression coefficients

Price: -0.7950 (significant) Price: -0.1867 (significant)

Mileage: 8.3063 (significant) Mileage: 0.04130 (insignificant)

Top speed: -0.0185 (insignificant) Top speed: 0.2208 (significant)

Equation: Sales = 50.723 - 0.795*Price + 8.306*Mileage Equation: Sales = 0.220*Top Speed - 0.186*Price - 13.447

Predicted Sales(in units): 227.897 Predicted Sales(in units): 25.265

Q-5) Based on sales prediction, what is the overall predicted profit for
Rocinante36 model and Marengo32 model ?

Overall predicted profit

Rocinante36 Model: Rs. 2,27,89,722.61

Marengo32 Model: Rs. 2,02,11,879.42

Q-6) As a CEO, you wish to invest only in the model which is predicted to be
more profitable. Which model among Rocinante36 and Marengo32 will you
invest in?

Which model you will invest in?

With Rocinante36 Model giving a profit of Rs. 2,27,89,722.61 which is Rs. 25,77,843.18
higher than the Marengo32 Model, I will invest in Rocinante36 Model.
Q-7) Now you must have derived the regression equation for both models, Rocinante and
Marengo. Now if you increase the price of Rocinante36 and Marengo32 by 1 lac rupees
each, which car will have a higher impact on the sales due to increase in price? Give proper
logic for your answer. You can consider that all other specifications such as mileage and top
speed remain the same for both models.

Which car is most affected by a price increase? Why?

Rocinante36: #Unit Sales (@7 lakh selling price): 227.897
Rocinante36: #Unit Sales (@8 lakh selling price): 227.102
Marengo32 : #Unit Sales (@41 lakh selling price): 25.265
Marengo32 : #Unit Sales (@42 lakh selling price): 25.078

The (negative) impact is higher for Rocinante36 with a drop of 0.8 unit sales vs. only a drop of 0.19 in
case of Marengo32.
Reason: As we observe the regression equations for Rocinante36 and Marengo32, we see that the
weightage (regression coefficient) for price in case of Rocinante36 is higher than that for Marengo32
and hence the impact.
Q-8) After developing the regression equation for both models (Rocinante and Marengo), if you
analyse the p values for coefficients in the regression results, you will notice that some of the
regression variables (top speed, mileage and price) are insignificant. Remove the insignificant
regression variables from your selection and rebuild the regression model using only significant
variables. Compare the Adjusted R square value for the new and old regression model. Do you
notice any change in Adjusted R square value? If yes, explain the reason for the change.

Is there a change on Adjusted R square Value? If so, Why?

For the R-square, any new nonzero terms must improve the fit. Removing insignificant variable
Adjusted R-square will get better if the new terms improve the fit,
and will get worse if the new terms make no difference Before After

R Square 0.99576 0.99503

In case of Rocinante36, both R square and adjusted R square
Rocinante36
reduces slightly as the insignificant variable is dropped which means Adjusted R Square 0.99535 0.99468
although the dropped variable was insignificant, there must be
some interaction effect which contributed to the overall goodness of R Square 0.86308 0.86288
fit. Marengo32
Adjusted R Square 0.84787 0.85309
In case of Marengo32, with the drop of insignificant variable, R
square drops, however, the adjusted R square increases which
indicates that the insignificant variable which was dropped had no
contribution to the model goodness of fit.