1

Chapter 15 Case 2

Student’s Name

Course Name & Number

Institutional Affiliation

Date
 2

Chapter 15 Case 2

Introduction

The acronym NASCAR stands for National Association for Stock Car Auto Racing.

NASCAR is the sanctioning body for stock-car racing in North America. NASCAR was

founded in 1948 in Daytona Beach, Florida and has become a widely popular sport in the

United States. In 2011 Matt Kenseth finished fourth out of 35 drivers for the season and his

success carried over into 2012 when he won the most important race of NASCAR’s season,

the Daytona 500. The earnings for drivers in NASCAR is based of their performances during

each race. The more races won, or higher finishes entitles the driver to more winnings. This

case will examine how significant each of the variables (poles won, wins, top 5 finishes and

top 10 finishes) are to the amount of winnings that each driver will collect.

Problem & Analysis

Problem 1

Suppose you wanted to predict Winnings ($) using only the number of poles won

(Poles), the number of wins (Wins), the number of top five finishes (Top 5), or the number of

top ten finishes (Top 10). Which of these four variables provides the best single predictor of

winnings?

Problem 1 Analysis

NASCAR bases their annual championship on a point system that awards points to

the drivers based on their finish in each race as well as the number of laps led during a race.

For example, a driver will obtain forty-three points for winning a race and each driver

finishing after the winner will receive one less point than the driver in front of them based on

their finish (Anderson et al, 2020). The drivers are also awarded a bonus point for leading a
 3

lap during a race and the driver who leads the most laps of a race will receive an additional

bonus point (Anderson et al, 2020). The winner of the race also receives three additional

bonus points for winning the race. At the end of the racing season, the driver with the most

accumulated points wins championship for the year. Winning a championship is great, but it

does not mean that the champion will receive the most winnings.

Using the independent variables – the number of poles won (Poles), the number of

races won (Wins), the number of top 5 finishes (Top 5), and the number of top 10 finishes

(Top 10) – a regression analysis can be performed to predict the winnings for a driver. Upon

performing the regression analysis, the independent variable with the highest correlation

coefficient is the best single predictor of winnings. In this case, the best single predictor of

winnings is the independent variable Top 10 because it has the highest correlation coefficient

of 0.898. The higher the correlation coefficient is the better the variable fits the equation.

Problem 2

Develop an estimated regression equation that can be used to predict Winnings ($)

given the number of poles won (Poles), the number of wins (Wins), the number of top five

finishes (Top 5), and the number of top ten (Top 10) finishes. Test for individual significance

and discuss your findings and conclusions.

Problem 2 Analysis

The most accurate estimated regression equation would consist of the top 2-5 racers

and top 6-10 racers as the variables. The following equation would be the best estimated

regression equation to use.

Winnings(Y)= 3140367 – 12939 *Poles + 202245 *Wins + 188700 *Top 2-5 + 117071 *Top

6-10
 4

The estimated regression equation using the top 2-5 and top 6-10 racers as the variable is the

best option because the maximum correlation within the variables is less than 50% (Keele et

al., 2020). In addition to this, with the exception of the pole variable, all other variables are

significant and contain at least a 5% level of confidence. Within the top 6-10 finishers, we

can expect a $117,071 increase between each place. Within the top 2-5 finishers, we can

expect a $188,700 increase between each place. For each additional win a driver has, we can

expect a $202,245 increase. Number of wins and the place that is won are in direct relation to

the amount of winning dollars received.

Variable DF Estimate Error t Value Pr > |t|

Intercept 1 3140367 184229 17.05 < .0001

Poles 1 -12939 107205 -0.12 0.9047

Wins 1 202245 90226 2.24 0.0325

Top 2-5 1 188700 34586 5.46 < .0001

Top 6-10 1 117071 33433 3.5 0.0015

Table 1: Regression output (Source: Author)

Determining the significance of each individual independent variable will show which

independent variable are significant in relation to the dependent variable. Based on the data

given, a multiple regression was performed to aid in determining the individual significance

of each independent variable. A value of t0.025 = 2.042 was used to compare t Stat of each

individual independent variable. Based on the t Stat of the data in the poles column being -

0.1207 and the p-value of 0.9407, the null hypothesis cannot be rejected for this variable.

The t Stat of -0.1207 is not less than the t value of -2.042, therefore, the independent variable

related to the number of poles a race car driver won is not significant. While performing the

same t-test on the number of wins that a race car driver had during the season the t Stat is

0.1218 and the p-value is 0.9039. The null hypothesis cannot be rejected for this variable
 5

because the t Stat of 0.1218 is not greater than the t value of 2.042. The independent variable

related to the number of races a race car driver won during the season is not significant. The

variable representing the number of top 5 finishes by a driver is not significant either because

the t-test reveals a t Stat of 1.4137 and a p-value of 0.1677. The null hypothesis cannot be

rejected because the t Stat of 1.4137 is not greater than the t value of 2.042. Finally, a t-test

was performed on the independent variable representing the number of top 10 finishes by a

race car driver during the season reveals a t Stat of 3.5017 and a p-value of 0.0015. When

compared to the t value of 2.042, the t Stat of 3.5017 is greater and the null hypothesis is

rejected. The rejection of the null hypothesis indicates that the independent variable is

significant.

Problem 3

Create two new independent variables: Top 2–5 and Top 6–10. Top 2–5 represents the

number of times the driver finished between second and fifth place and Top 6–10 represents

the number of times the driver finished between sixth and tenth place. Develop an estimated

regression equation that can be used to predict Winnings ($) using Poles, Wins, Top 2–5, and

Top 6–10. Test for individual significance and discuss your findings and conclusions.

Problem 3 Analysis

The addition of two new independent variables (Top 2-5 and Top 6-10 finishes) have

an effect on the regression model. The independent variable, poles has the same t Stat and p-

value as before when Top 5 and Top 10 were used as independent variables. The null

hypothesis cannot be rejected and the independent variable, poles, is not significant.

However, the independent variable, wins, becomes significant with the addition of Top 2-5

and Top 6-10 and the removal of Top 5 and Top 10 as independent variables. The t Stat for

these variable changes to 2.2415 with a p-value of 0.0325. The null hypothesis can be
 6

rejected because the t Stat of 2.2415 is greater than the t value of 2.042. The first of the new

independent variables, Top 2-5, has a t Stat of 5.4559 and a p-value of 0.000006. Based on

the comparison of the t Stat and the t value of 2.042 the null hypothesis can be rejected.

Thus, the independent variable Top 2-5 is significant. The second new independent variable,

Top 6-10, reveals a t Stat of 3.5017 with a p-value of 0.0015. Based on these calculations the

null hypothesis can be rejected and the independent variable is significant because the t Stat

is greater than the t value of 2.042.

Conclusion

At 0.05 level of significance, number of top ten finishes is significant. In problem 3,

at 0.05 level of significance, the relationship of Top2-5 and Top6-5 and number of wins are

significant (p value being 0.032541535, 6.43028E-06 and 0.001470314 respectively).

Therefore, the estimated regression equation comprising Top 5 and Top 10 finishes is

appropriate for the model.

Recommendations

After performing the test for individual significance for each of the independent

variables it is determined that poles are not a significant independent variable while, the

remaining three independent variables are in fact significant. Therefore, considering the

results of the regression analysis on NASCAR data, they should focus on stock racing car

models that;

1. Have high number of wins

2. Appear in top 5 (2-5) and 10 (6-10) finishes.

References

Anderson, D. R., Sweeney, D. J., Williams, T. A., Camm, J. D., Cochran, J. J., Fry, M. J., &

Ohlmann, J. W. (2020). Modern business statistics with Microsoft® Excel®. 7th

Edition. Cengage Learning.

Keele, L., Stevenson, R. T., & Elwert, F. (2020). The causal interpretation of estimated

associations in regression models. Political Science Research and Methods, 8(1), 1-

13. [Link]