Scribd
Upload
21 views

Predicting Winnings for NASCAR Drivers

Uploaded by

timestruckme
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
21 views

Predicting Winnings for NASCAR Drivers

Uploaded by

timestruckme
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 7

Predicting Winnings for NASCAR Drivers

Abhilash Juluri

Master of Business Analytics

Concordia University, Wisconsin

Department of Business

DBA 9110 Business Intelligence and Predictive Analytics

Dr. Jim Eden


Predicting Winnings for NASCAR Drivers.

This paper uses the NASCAR season data to identify the number of winnings which can

be predicted by evaluating parameters like poles, wins, top 5 and top 10. Research techniques

used in the analysis are the descriptive analysis, multiple regression analysis and variable

construction to improve the predictive power.

This analysis aims at giving and predicting the aspects that could affect winnings for

NASCAR drivers through statistical means. The data used for the elaboration of the analysis

stems from the NASCAR performance and income statistics of drivers.

The 35 NASCAR drivers of the year for 2011 also depicted great differences in

performance. On average, drivers won 0.94 poles, 1 race, had 5.11 top 5 finishes, and 10.2 top 10

finishes. Winnings averaged $4.71 million, with a substantial range from $2.27 million to $8.49
million. This variation shows the nature of competition of the season and the way the

performance affects the money earnings.

Regression Analysis

The multiple regression analysis shows that 99.2% of the variance in winnings can be

explained by the model (R² = 0.992). Significant predictors include having 3 poles (p = 0.047), 3

or more wins (p < 0.05), and several top 5 finishes (e.g., 1–0 with p = 0.002, 2–0 with p = 0.003).

Gaining top 10 finishes has a positive and negative impact on winnings where some categories

are poorly affected. In a general sense, the paper shows that wins and top 5 results are by far the

best bet for enduring high earning, whereas the role of poles and top 10 finishes is inconclusive.

Single Predictor Analysis


The regression model explains 82% of the variance in winnings (R² = 0.820). The

intercept is statistically significant (p < .001). Among the predictors, only the number of top 10

finishes is statistically significant (p = 0.001), suggesting it has a significant positive impact on

winnings. Other predictors (poles, wins, and top 5 finishes) do not have significant p-values,

indicating they do not have a statistically significant impact on winnings in this model.
New Variables: Top 2–5 and Top 6–10

Created manually in Excel and loaded into JAMOVI.


R (Correlation Coefficient): 0.906

R² (Coefficient of Determination): 0.820

The R2 value of 0.820 indicates that 82% of the success ($) can be explained by the

predictors in the model. This indicates a very good fit of the model to the data.

The model shows a strong fit with an R2 of 0.820.

Number of wins, 2-5 finishes, and 6-10 finishes are important indicators of success.

Number of poles is not a significant factor in determining success.

Finishing in positions 2-5 and 6-10 significantly increases success, with positions 2-5

having a greater impact compared to positions 6-10

The recommended regression equation is:


Since the "Poles" predictor was not significant, the best simplified model would exclude

it:

Winnings ($) = 3.14e+6 + (202245 *Wins) + (188700 *Top 2-5) + (117071*Top 6-10)

Conclusion

Analysis of 2011 NASCAR season data showed that the model could explain up to 99.2%

of the variance in driver earnings, indicating a very good performance The main finding was that

drivers with three or more wins race, or secure three pole positions. They tend to make a lot more

money. More often finishing in the top 5 also increases earnings, but those finishing in the top 10

had mixed results. Other variables such as Top 2–5 and Top 6–10 have shown that a good

position in the top 10 results in higher returns. This study highlights the importance of consistent

driver performance to maximize revenue.

You might also like