Managerial Economics

BSNS 6130

December 13, 2012

By:

Morgan Thomas

Chad Goodrich

Jake Dodson

Austin Burris

Brittany Lutz

Abstract

As there are many who invest in athletic events, the ability to better predict attendance to such events, such as the Detroit Tigers games, could benefit many. The benefits include being able to better stock concessions stands, allocate advertising budgets, and staff security. Therefore, the aim of our study was better explain the variation in attendance to the Detroit Tigers home games. The variables we used included: * Opponent

* Detroit Tigers’ Winning Percentage

* Opponent Winning Percentage

* Ace Pitcher

* Temperature

* Promotional Days

We predicted each variable would have a positive relationship with attendance. However, our data proved that to be otherwise as you can see in our regression model:

Attendance = 29697.22 + 3524.993 (O) – 6723.86 (DTW%) + 691.2616 (OW%) + 936.4279 (AP) + 121.5826 (T) + 1810.263 (PD)

All variables except the opponents winning percentage had a positive relationship with attendance to each game. The R Squared also demonstrated that the variables used only explained 26.4% of the variation in attendance. Furthermore, P-Value of the F-Stat proved our model 99.9% level of confidence, meaning it is significant. Overall, three of our variables including temperature, opponent, and promotional days, were significant at the 90% level of confidence and three of them were not including opponent winning percentage, ace pitcher, and winning percentage. Introduction

Businesses are continuously looking at ways to maximize their advertising dollars. Major League Baseball teams are no different, with franchises being valued in the billions and players salaries in the hundreds of millions, ownership must find ways to maximize their return on investment. The purpose of this study is to determine the effect on attendance outside of ownership control. Such items in particular include team winning percentage, opposing team-winning percentage, popularity of the opponent, star players playing, weather, and promotional days, such as Father’s day or the Fourth of July. Using a sample from the 2012 Detroit Tigers home schedule variations in attendance were examined. A regression technique is employed in an effort to determine whether the examined selection criteria measures are predictors of attendance. Model Development

Because our group has an interest in sports, we chose to analyze the attendance at professional baseball games. We chose to limit our research to one team because most businesses limit their sponsorships to one team. We selected the Detroit Tigers due to their geographic proximity to Indianapolis and the Indianapolis market does not have a Major League Baseball team. We also believe that the two cities have similar business climates. Hypothesis/Variables

We conducted a multiple regression in order to determine which independent variables would have an impact on game attendance. The following are proxy variables we used in this regression:

* O: Opponent

* DTW%: Detroit Tigers’ Winning Percentage

* OW%: Opponent Winning Percentage

* AP: Ace Pitcher

* T: Temperature

* PD: Promotional Days

Our hypothesized equation is as follows:

Attendance = a + b(O) + c (DTW%) + d(OW%) + e(AP) + f(T) + g (PD)

Hypothesized Expectations

Mentioned above are the variables we hypothesize to be statistically significant in determining what affected attendance at 2012 Detroit Tiger’s home games. Our hypothesis and expectations for each variable are listed below.

Opponent Team: We anticipated that whenever the Tigers played either the New York Yankees or the Boston Red Sox that the attendance would be higher. A dummy variable was used when the Tigers were at home and played either of these teams. A one was used for the New York Yankees and Boston Red Sox...