22 Nov 2022

146

Multiple Regression Analysis: Definition, Methods, Applications

Format: APA

Academic level: Master’s

Paper type: Coursework

Words: 559

Pages: 2

Downloads: 0

Task #1. Examine performance measures (i.e., putting, driving yard, driving accuracy, greens in regulation, sand save percentage) and identify important predictors of Earnings per Round AND Top-10s. 

Multiple Regression 

Multiple regression analysis was carried out for the performance measures and predictors of Earnings per Round and results shown in table 1. Analysis was also performed for the performance measures and predictor of Top-10s and results were shown in table 2.

It’s time to jumpstart your paper!

Delegate your assignment to our experts and they will do the rest.

Get custom essay

Table 1. Multiple Regression for putting, driving yard, driving accuracy, greens in regulation, sand save percentage vs. earnings per round. 

Model Summary - Earnings per Round 
 

Durbin-Watson 

Model 

R² 

Adjusted R² 

RMSE 

Autocorrelation 

Statistic 

H₀  

0.000

 

0.000

 

0.000

 

21037.799

 

0.869

 

0.118

 

< .001

 
H₁  

0.659

 

0.434

 

0.417

 

16069.150

 

0.495

 

0.937

 

< .001

 
 
ANOVA 

Model 

 

Sum of Squares 

df 

Mean Square 

H₁   Regression  

3.282e +10

 

5

 

6.564e +9

 

25.419

 

< .001

 
    Residual  

4.286e +10

 

166

 

2.582e +8

         
    Total  

7.568e +10

 

171

             
 
Note.  The intercept model is omitted, as no meaningful information can be shown.
Coefficients 

Model 

 

Unstandardized 

Standard Error 

Standardized 

H₀   (Intercept)  

22637.552

 

1604.117

     

14.112

 

< .001

 
H₁   (Intercept)  

312336.800

 

119073.293

     

2.623

 

0.010

 
    Putting Average  

-428752.084

 

56542.827

 

-0.474

 

-7.583

 

< .001

 
    Yards/Drive  

920.506

 

206.201

 

0.405

 

4.464

 

< .001

 
    Driving Accuracy  

706.181

 

362.162

 

0.171

 

1.950

 

0.053

 
    Greens in Regulation  

2088.410

 

671.358

 

0.237

 

3.111

 

0.002

 
    Sand Save Pct  

401.193

 

221.685

 

0.111

 

1.810

 

0.072

 
 

Residuals vs. Predicted 

Standardized Residuals Histogram 

Q-Q Plot Standardized Residuals 

Table 2. Multiple Regression for putting, driving yard, driving accuracy, greens in regulation, sand save percentage vs. Top 10s 

Model Summary - Top 10s 
 

Durbin-Watson 

Model 

R² 

Adjusted R² 

RMSE 

Autocorrelation 

Statistic 

H₀  

0.000

 

0.000

 

0.000

 

2.407

 

0.747

 

0.414

 

< .001

 
H₁  

0.654

 

0.428

 

0.411

 

1.847

 

0.378

 

1.212

 

< .001

 
 
ANOVA 

Model 

 

Sum of Squares 

df 

Mean Square 

H₁   Regression  

424.341

 

5

 

84.868

 

24.868

 

< .001

 
    Residual  

566.520

 

166

 

3.413

         
    Total  

990.860

 

171

             
 
Note.  The intercept model is omitted, as no meaningful information can be shown.
Coefficients 

Model 

 

Unstandardized 

Standard Error 

Standardized 

H₀   (Intercept)  

2.919

 

0.184

     

15.901

 

< .001

 
H₁   (Intercept)  

24.435

 

13.689

     

1.785

 

0.076

 
    Putting Average  

-44.320

 

6.500

 

-0.428

 

-6.818

 

< .001

 
    Yards/Drive  

0.098

 

0.024

 

0.377

 

4.129

 

< .001

 
    Driving Accuracy  

0.080

 

0.042

 

0.170

 

1.925

 

0.056

 
    Greens in Regulation  

0.320

 

0.077

 

0.317

 

4.146

 

< .001

 
    Sand Save Pct  

0.049

 

0.025

 

0.118

 

1.911

 

0.058

 
 

Residuals vs. Predicted 

Standardized Residuals Histogram 

Q-Q Plot Standardized Residuals 

Stepwise Regression Analyses 

Stepwise regression analysis was carried out for the performance measures and predictors of Earnings per Round and results shown in table 3. The analysis was also performed for the performance measures and predictor of Top-10s and results were shown in table 4.

Table 3. Stepwise Regression for putting, driving yard, driving accuracy, greens in regulation, sand save percentage vs. earnings per round. 

Model Summary - Earnings per Round 
 

Durbin-Watson 

Model 

R² 

Adjusted R² 

RMSE 

Autocorrelation 

Statistic 

1  

0.000

 

0.000

 

0.000

 

21037.799

 

0.869

 

0.118

 

< .001

 
2  

0.438

 

0.192

 

0.187

 

18965.731

 

0.705

 

0.502

 

< .001

 
3  

0.590

 

0.348

 

0.340

 

17086.795

 

0.542

 

0.843

 

< .001

 
4  

0.642

 

0.412

 

0.401

 

16277.891

 

0.500

 

0.936

 

< .001

 
 
ANOVA 

Model 

 

Sum of Squares 

df 

Mean Square 

2   Regression  

1.453e +10

 

1

 

1.453e +10

 

40.406

 

< .001

 
    Residual  

6.115e +10

 

170

 

3.597e  +8

         
    Total  

7.568e +10

 

171

             
3   Regression  

2.634e +10

 

2

 

1.317e +10

 

45.112

 

< .001

 
    Residual  

4.934e +10

 

169

 

2.920e  +8

         
    Total  

7.568e +10

 

171

             
4   Regression  

3.117e +10

 

3

 

1.039e +10

 

39.209

 

< .001

 
    Residual  

4.451e +10

 

168

 

2.650e  +8

         
    Total  

7.568e +10

 

171

             
 
Note.  The intercept model is omitted, as no meaningful information can be shown.
Coefficients 

Model 

 

Unstandardized 

Standard Error 

Standardized 

1   (Intercept)  

22637.552

 

1604.117

     

14.112

 

< .001

 
2   (Intercept)  

726067.912

 

110671.743

     

6.561

 

< .001

 
    Putting Average  

-396791.372

 

62422.446

 

-0.438

 

-6.357

 

< .001

 
3   (Intercept)  

640072.569

 

100620.260

     

6.361

 

< .001

 
    Putting Average  

-480689.362

 

57764.898

 

-0.531

 

-8.321

 

< .001

 
    Greens in Regulation  

3577.114

 

562.482

 

0.406

 

6.360

 

< .001

 
4   (Intercept)  

461874.016

 

104556.105

     

4.417

 

< .001

 
    Putting Average  

-449993.656

 

55498.295

 

-0.497

 

-8.108

 

< .001

 
    Greens in Regulation  

2724.835

 

571.857

 

0.309

 

4.765

 

< .001

 
    Yards/Drive  

612.396

 

143.494

 

0.270

 

4.268

 

< .001

 
 
Note.  The following covariates were considered but not included: Driving Accuracy, Sand Save Pct.

Residuals vs. Predicted 

Standardized Residuals Histogram 

Q-Q Plot Standardized Residuals 

Table 4. Stepwise Regression for putting, driving yard, driving accuracy, greens in regulation, sand save percentage vs. Top 10s. 

Model Summary - Top 10s 
 

Durbin-Watson 

Model 

R² 

Adjusted R² 

RMSE 

Autocorrelation 

Statistic 

1  

0.000

 

0.000

 

0.000

 

2.407

 

0.747

 

0.414

 

< .001

 
2  

0.389

 

0.152

 

0.147

 

2.224

 

0.592

 

0.747

 

< .001

 
3  

0.529

 

0.280

 

0.271

 

2.055

 

0.483

 

1.000

 

< .001

 
4  

0.637

 

0.405

 

0.395

 

1.873

 

0.427

 

1.121

 

< .001

 
 
ANOVA 

Model 

 

Sum of Squares 

df 

Mean Square 

2   Regression  

150.259

 

1

 

150.259

 

30.388

 

< .001

 
    Residual  

840.602

 

170

 

4.945

         
    Total  

990.860

 

171

             
3   Regression  

277.401

 

2

 

138.700

 

32.855

 

< .001

 
    Residual  

713.460

 

169

 

4.222

         
    Total  

990.860

 

171

             
4   Regression  

401.665

 

3

 

133.888

 

38.176

 

< .001

 
    Residual  

589.195

 

168

 

3.507

         
    Total  

990.860

 

171

             
 
Note.  The intercept model is omitted, as no meaningful information can be shown.
Coefficients 

Model 

 

Unstandardized 

Standard Error 

Standardized 

1   (Intercept)  

2.919

 

0.184

     

15.901

 

< .001

 
2   (Intercept)  

-26.766

 

5.388

     

-4.968

 

< .001

 
    Yards/Drive  

0.101

 

0.018

 

0.389

 

5.513

 

< .001

 
3   (Intercept)  

40.288

 

13.194

     

3.054

 

0.003

 
    Yards/Drive  

0.097

 

0.017

 

0.374

 

5.720

 

< .001

 
    Putting Average  

-37.148

 

6.769

 

-0.359

 

-5.488

 

< .001

 
4   (Intercept)  

42.007

 

12.029

     

3.492

 

< .001

 
    Yards/Drive  

0.063

 

0.017

 

0.242

 

3.802

 

< .001

 
    Putting Average  

-46.933

 

6.385

 

-0.453

 

-7.351

 

< .001

 
    Greens in Regulation  

0.392

 

0.066

 

0.388

 

5.952

 

< .001

 
 
Note.  The following covariates were considered but not included: Driving Accuracy, Sand Save Pct.

Residuals vs. Predicted 

Standardized Residuals Histogram 

Q-Q Plot Standardized Residuals 

Summary and Analyses of Results 

For the multiple regression using the forced entry method, the value of R-squared increased when the given performance measures were added one a time. The signs in the coefficient had the expected positive and negative values. The value of R-squared for earnings per round were 0.434 and for Top 10s was 0.428. The values showed that the given performance measures were good predictors of Earnings per Round and Top-10s. Violations of the assumptions were checked using Durbin-Watson value and the plot functions showed that there were no violations.

The equation for performance measures and earnings per round was given as:

Earnings per round = 312,336.800 + (-428,752.084*Putting average) + (920.506*Driving yard) + (706.181*driving accuracy) + (2088.410*Greens in regulation) + (401.193*Sand save percentage).

The equation for performance measures and Top-10s was given as:

Top-10s = 24.435 + (-44.320*Putting average) + (0.098*Driving yard) + (0.080*driving accuracy) + (0.320*Greens in regulation) + (0.049*Sand save percentage).

The step-wise regression provided a model for the values that were significant i.e. values that had p<0.01. The values of R-squared were similar but slightly lower than the forced entry method. Also, the Durbin-Watson score for the step-wise regression was higher than the forced entry method. For earnings per round, the values that were significant were putting average, greens in regulation, and yard drive. Therefore, when focusing on improving the earnings per round, young PGA players should prioritize these performance measures to improve their earnings per round. For Top-10s, the values that were significant were similar to that of the earnings per round. Therefore, young PGA players should focus on improving the performance measures of drive yards, putting average, and greens in regulation to improve their earnings per round and top-10s.

The equation for performance measures and earnings per round using the stepwise method was given as:

Earnings per round = 312,336.800 + (-449,993.656 *Putting average) + (612.396 *Driving yard) + (2724.835 *Greens in regulation).

The equation for performance measures and Top-10s using the stepwise method was given as:

Top-10s = 42.007 + (-46.933 *Putting average) + (0.063 *Driving yard) + (0.392*Greens in regulation).

Illustration
Cite this page

Select style:

Reference

StudyBounty. (2023, September 16). Multiple Regression Analysis: Definition, Methods, Applications.
https://studybounty.com/multiple-regression-analysis-definition-methods-applications-coursework

illustration

Related essays

We post free essay examples for college on a regular basis. Stay in the know!

17 Sep 2023
Statistics

Scatter Diagram: How to Create a Scatter Plot in Excel

Trends in statistical data are interpreted using scatter diagrams. A scatter diagram presents each data point in two coordinates. The first point of data representation is done in correlation to the x-axis while the...

Words: 317

Pages: 2

Views: 187

17 Sep 2023
Statistics

Calculating and Reporting Healthcare Statistics

10\. The denominator is usually calculated using the formula: No. of available beds x No. of days 50 bed x 1 day =50 11\. Percentage Occupancy is calculated as: = =86.0% 12\. Percentage Occupancy is calculated...

Words: 133

Pages: 1

Views: 150

17 Sep 2023
Statistics

Survival Rate for COVID-19 Patients: A Comparative Analysis

Null: There is no difference in the survival rate of COVID-19 patients in tropical countries compared to temperate countries. Alternative: There is a difference in the survival rate of COVID-19 patients in tropical...

Words: 255

Pages: 1

Views: 251

17 Sep 2023
Statistics

5 Types of Regression Models You Should Know

Theobald et al. (2019) explore the appropriateness of various types of regression models. Despite the importance of regression in testing hypotheses, the authors were concerned that linear regression is used without...

Words: 543

Pages: 2

Views: 175

17 Sep 2023
Statistics

The Motion Picture Industry - A Comprehensive Overview

The motion picture industry is among some of the best performing industries in the country. Having over fifty major films produced each year with different performances, it is necessary to determine the success of a...

Words: 464

Pages: 2

Views: 86

17 Sep 2023
Statistics

Spearman's Rank Correlation Coefficient (Spearman's Rho)

The Spearman’s rank coefficient, sometimes called Spearman’s rho is widely used in statistics. It is a nonparametric concept used to measure statistical dependence between two variables. It employs the use of a...

Words: 590

Pages: 2

Views: 309

illustration

Running out of time?

Entrust your assignment to proficient writers and receive TOP-quality paper before the deadline is over.

Illustration