Today I will look at regular season home attendance in MLB. To do so I grabbed the data from ESPN.
First thing to note is that overall regular season attendance has
decreased by 488,645 fans from the 2016 regular season and the 2016 regular season dropped by about 600,000 fans from the 2015 season. Yes, that is a million fewer people attended a MLB game in 2017 as compared to 2015.
The three largest attendance declines were Kansas City (-337,342), Pittsburgh (-329,574) and the New York Mets (-328,980), and the three largest attendance increases were Atlanta (484,338), Cleveland (456,471) and Colorado (351,126).
While total
attendance and average attendance are lower this regular season as compared to the 2016 regular
season, is it statistically different from the previous regular season? We need a statistical tool to determine if attendance is different between the two regular seasons with some degree of confidence. The statistical tool I use is a t-test
as the means to perform the analysis.
A t-test looks at the
differences
between attendance for two regular seasons average home attendance and
allows us to judge the difference between their means
relative to the variability of their regular season average home
attendance. You can quickly perform a t-test in Microsoft Excel
=t.test(...). I choose to use a two tailed test, since regular season
average home attendance can increase and decrease as compared to the
previous regular season.
I am going to look at regular season average home attendance for
the 2016 and 2017 MLB season, just like I did for the 2016 MLB regular season. The reason I am looking at average
attendance is that not all teams play the same number of home games from
one season to the next and using the average is a much more accurate
for comparing one season to another.
So after running the t-test between the 2016 and 2017 regular season home attendance using a paired t-test, a t-tests
where the sample variance is assumed to be equal, and a t-test where the sample variance is not assumed to be unequal; in each case, the
result of the t-test is that it fails to accept (rejects) that regular
season average home attendance is different between the two seasons.
That might not be much consolation to the Royals, Pirates and Mets, but the decline in attendance is not significant as compared to the prior regular season.