The age of the stadium can be appealing if the stadium is rich with history, or if it is new and equipped with the most modern features. However, middle-aged stadiums may have neither appeal and could result in depressed attendance figures. The number of wins that the team has in the season impacts fan interest, as does the team's salary (which is a good way to operationalize a team's star power).
Each of these variables is already quantified, so is fully operationalized. This avoids the trap of using spurious proxies in a study. There are three possible outcomes that can result from this research. The null hypothesis can be proven within significant confidence limits or it may be disproved. The third option is that the null hypothesis may be proven, but there is reason to suspect that some of the variables are closely related to one another and that this has an impact. For example, it is possible that while both salary and wins are shown to be correlated with attendance, that this is only because they are strongly correlated with one another. Thus, the third option is that evidence may be found of cross-correlations that casts doubt about the findings that either support or fail to support the null hypothesis.
The level of measurement for the age of the stadium will be years. One year will be used as the scale, as partial years are significant in assets that could be decades old. The level of measurement for the teams' salaries will be millions of dollars...
So for example, the salary of the Toronto Blue Jays in 2005 was $45.7 million. The size of the stadium will be measured in seats, and the level will be 1 seat. Thus, it will be recorded that in 2005 Shea Stadium had a capacity of 55,775. The level of measurement for wins will be one win.
Each of these variables is ordinal in nature, with a numeric value that represents an ordinal level wherein a salary level of $50.0 million is exactly half of a salary level of $100.0 million and an age of 24 years is double an age of 12 years. Using ordinal variables lends greater value to the study than the use of other forms of variables, because ordinal variables provide a direct and specific measure. For example, the age of the stadium can be measured by its inception date, but that is a numeric variable with no ordinal attached to it; whereas age in years delivers the same information in ordinal fashion.
Works Cited:
Nightengale, B. & Boeck, S. (2010). Slight fall in baseball attendance no surprise. USA Today. Retrieved July 10, 2010 from http://www.usatoday.com/sports/baseball/2009-04-29-mlb-attendance_N.htm
Winfree, J., McCluskey, J., Mittelhammer, R. & Fort, R. (2004). Location and attendance in major league baseball. Applied Economics. Vol. 36 (19) 2117-2124.
Browning, R. & DeBolt, L. (2010). The effects of promotions on attendance in professional baseball. The…
