case problem 4 by a. haris awang & m. zaini zakariah

7
MBA 6073 BUSINESS STATISTICS Case Problem 4: Major League Baseball Team Values By A. Haris Awang (MBA2016041001) & Mohd Zaini Zakariah (MBA2016041025) Presented on 24 th July, 2016 Submitted to: Mr. Demudu Naganaidu Senior Vice President Operations Tel: 03-9080 5888 27 th July, 2016

Upload: haris-awang

Post on 13-Jan-2017

75 views

Category:

Data & Analytics


0 download

TRANSCRIPT

Page 1: Case Problem 4 by A. Haris Awang & M. Zaini Zakariah

MBA 6073 – BUSINESS STATISTICS

Case Problem 4: Major League Baseball Team Values

By

A. Haris Awang (MBA2016041001) & Mohd Zaini Zakariah (MBA2016041025)

Presented on

24th July, 2016

Submitted to:

Mr. Demudu Naganaidu

Senior Vice President Operations

Tel: 03-9080 5888

27th July, 2016

Page 2: Case Problem 4 by A. Haris Awang & M. Zaini Zakariah

MBA 6073 – BUSINESS STATISTICS

1

MANAGERIAL REPORT

1. Develop numerical and grapical summaries of the data.

The scatter plot for value vs income does not show any trend or correlation between value &

income. There is zero correlation between these variables. It can be concluded that the variables

are not related to one another. Increases or decreases in income have no effect on increases or

decreases in value.

Page 3: Case Problem 4 by A. Haris Awang & M. Zaini Zakariah

MBA 6073 – BUSINESS STATISTICS

2

As for value vs revenue, there a positive trend in this scatter plot. There is a positive correlation

between these variables. Increases in revenue are correlated with increases in value. Similarly,

decreases in revenue are correlated with decreases in value.

2. Use regression anlaysis to investigate the relationship between value and income. Discuss

your findings.

Based from the above results, p-value = 0.163 > α = 0.05 at 95% confidence interval. So the

relationship between value and income is not significant.

R Square = 0.034 means that the model only explains 3.4% of the data.

Page 4: Case Problem 4 by A. Haris Awang & M. Zaini Zakariah

MBA 6073 – BUSINESS STATISTICS

3

The scatter plot for residual analysis for homoscedasticity shows that the residual variance is constant

and the residual statistics shows that residuals are linear with 0.000 mean and not cyclical or non-

linear.

Residuals Statisticsa

Minimum Maximum Mean Std. Deviation N

Predicted Value 213.89 323.16 286.30 24.509 30

Std. Predicted Value -2.954 1.504 .000 1.000 30

Standard Error of Predicted

Value

24.098 76.313 32.186 11.385 30

Adjusted Predicted Value 102.84 333.83 281.57 39.191 30

Residual -165.040 407.066 .000 129.685 30

Std. Residual -1.250 3.084 .000 .983 30

Stud. Residual -1.279 3.270 .016 1.042 30

Deleted Residual -172.533 457.571 4.729 146.750 30

Stud. Deleted Residual -1.294 4.084 .049 1.146 30

Mahal. Distance .000 8.729 .967 1.759 30

Cook's Distance .000 1.059 .073 .221 30

Centered Leverage Value .000 .301 .033 .061 30

a. Dependent Variable: Value ($millions)

Page 5: Case Problem 4 by A. Haris Awang & M. Zaini Zakariah

MBA 6073 – BUSINESS STATISTICS

4

3. Use regression analysis to investigate the relationship between value and revenue. Discuss

your findings.

Based from the above results, p-value = 0.000 < α = 0.05 at 95% confidence level. It indicated that

there is a significant relationship between value and revenue.

The adjusted R square obtained was 0.928, indicating that 92.8% of the variance in value was

explained by revenue.

Page 6: Case Problem 4 by A. Haris Awang & M. Zaini Zakariah

MBA 6073 – BUSINESS STATISTICS

5

The scatter plot for residual analysis for homoscedasticity shows that the residual variance is constant

and the residual statistics shows that residuals are linear with 0.000 mean and not cyclical or non-

linear.

Residuals Statisticsa

Minimum Maximum Mean Std. Deviation N

Predicted Value 72.61 648.17 286.30 127.323 30

Std. Predicted Value -1.678 2.842 .000 1.000 30

Standard Error of Predicted

Value

6.495 19.752 8.747 2.669 30

Adjusted Predicted Value 67.30 611.09 285.21 124.771 30

Residual -89.630 81.826 .000 34.753 30

Std. Residual -2.534 2.314 .000 .983 30

Stud. Residual -2.671 2.789 .014 1.052 30

Deleted Residual -99.530 118.913 1.093 40.161 30

Stud. Deleted Residual -3.038 3.223 .018 1.130 30

Mahal. Distance .011 8.078 .967 1.520 30

Cook's Distance .000 1.763 .089 .324 30

Centered Leverage Value .000 .279 .033 .052 30

a. Dependent Variable: Value ($millions)

4. What conclusions and recommendations can you derive from your analysis?

Conclusions & Recommendations:

a. Based on the above table, the revenue contributed strongly (96.5%) to the variation in value

of the team but the income has no significant relationship to the value. The results show

that income is not significantly related to value of the team since the p-value is more than

.05.

Page 7: Case Problem 4 by A. Haris Awang & M. Zaini Zakariah

MBA 6073 – BUSINESS STATISTICS

6

b. The final model used to describe this case is the Simple Linear Regression Model,

Yi = β0 + β1Xi + εi

Where

Yi is dependent variable,

β0 is population Y intercept,

β1 is population slope coefficient,

Xi is independent variable,

εi is random error.

c. The results suggested that $1 million increase in revenue was followed by $3.787 million

increase in value of the team and can be estimated by the Simple Linear Regression

Equation, ŷi = b0 + b1xi

Where

ŷi is estimated (or predicted) y value for observation i,

b0 is estimate of the regression intercept,

b1 is estimate of the regression slope,

xi is value of x for observation i.

d. The estimated value of the team is only valid for any given revenue between $63 million

(min) and $215 million (max).

END