KenFSU get ready for a "nu-uh" type arguement littered with with sarcasm
Thanks for your great contribution to the thread, and for your grasp of irony (in your defense, this sentence is
littered with sarcasm), but not uh!
Whoa, Ken, that's pretty interesting.
I actually conducted a pretty in-depth regression analysis on Jaguars attendance last year, examining regular season games played from 2005 onward (after stadium capacity was reduced to 67,164), omitting that bizarre stretch of six consecutive home games at the beginning of the 2009 season that saw attendance drop by nearly 20,000 per game due to a sharp economic downturn coupled with widespread rumors that Weaver was in talks to move the franchise to Los Angeles.
I looked at every (non-economic) variable I could think of, from winning percentage, to past season winning percentage, to opponent attributes, to game day temperature, to national television coverage, all the way down to chance of rain, in an attempt to identify factors that affected attendance (keeping in mind changes in how attendance was reported over various seasons).
To strip some of the economic influence from attendance numbers, I modeled the data with the belief that mean annual attendance was roughly representative of what the market could support in that particular economy in that particular year. And conversely, any deviation from that mean was largely a reflection of consumer taste or distaste for each weekâ€™s particular game based on our multitude of independent variables. Thus, in order to roughly normalize attendance data against much broader economic effects, instead of using actual attendance as my dependent variable, I used actual attendance relative the seasonal mean (actual attendance for the game minus mean attendance for that yearâ€™s season). This calculation output the number of fans over or under that yearâ€™s mean that attended each game based on the given set of variables.
Of all of these many factors, I found exactly three variables that had a pronounced effect on attendance.
I"ll copy and paste from my findings:
"The first statistically significant independent variable is opponent's winning percentage, which has a beta of 1,302.14. Holding all other variables constant, attendance will increase by approximately 1,300 fans over seasonal mean if the opponent is undefeated (seasonal and prior-10 game records yielded similar results), increase by 650 fans for a team with an equal number of wins and losses (b1 x 0.5), all the way down to an increase of zero fans for a team that has not yet won a game (b1 x 0.00). This indicates that city residents have a preference for watching winning opponents play.
The second significant independent variable was relative popularity of opponent. Every year, Harris Interactive â€“ a market research firm headquartered in New York City â€“ releases a popularity ranking of NFL teams, listing each franchise from the most popular to the least. Using this variable allowed me to examine how the overall popularity of the visiting team impacted home game attendance here in Jacksonville. This variable yields a beta of 30.62. For the sake of a clearer equation, I inverted the popularity rankings before running regression analysis. By inverting the popularity rankings (most popular team =31, least popular =0), a positive rather than negative beta is produced. This beta demonstrates that for each additional tick upwards in opponent popularity, approximately 31 additional fans will attend a game. For example, the 10th most popular team in the league (inverted to 31-10 = 21) would draw approximately 651 additional fans (31 x 21) to the Jaguarsâ€™ stadium.
The final statistically significant independent variable tested was national television coverage, which yielded a beta of 479.17. Because this independent variable is binary and either switched off (0 for no national television) or on (1 for national television), the beta simply states that 479 residents will make their decision on whether to attend the game based on if it is or isn't on national television.
What was most surprising is that the independent variable that I initially felt would show the strongest correlation with attendance (Jaguars winning percentage) actually showed no statistically relevant correlation. In fact, Jaguars attendance seems far more correlated with characteristics of the visiting team than the performance of the home team. Jacksonville â€“ like other large cities in Florida â€“ has a large population of transplants from other areas of the country. Perhaps these transplants, along with a desire to "see the stars come to town' may factor into consumer preference appearing to be so opponent-driven."
Of course you can never isolate every variable, and things like marketing and advertising expenditure certainly can increase attendance, but the point is, it's realllly hard to show any statistical correlation between winning and attendance here in Jacksonville.
Couple of questions:
-Did you look at day of week and time of day for the games. I imagine some of that effect can get conflated with the nationally-televised binary variable, but that is one that I would initial think to have some effect.
-I am always so curious about the national games. It does seem anecdotally that more people are interested in attending them. Do you think this is due to simply the fact that they are televised more widely, or because of why they were scheduled to be nationally-televised in the first place (division rival game, replay of the prior season's super-bowl, two teams that are expected to be good before the season)? I feel like there are so many factors that go into the nationally-televised game. Perhaps its a desire to be part of the event, or to fill the seats to project a better image of the Jags nationally, or the reasons discussed above for which the network wants to televise it nationally.
-For winning percentage, is "seasonal" the end-of-season or the season to that point?
-Do you have anything like pre-season rankings in there, or some variable that measures the "hype" (media coverage, big pickups/trades, etc)?
-I would think it might be more telling to measure the relative popularity by a weighted variable (fan base, population in home market, merchandise sales, local fans even [I bet you could get data on that]) rather than ranking. I would expect that to give this variable more resolution.
-I don't know about removing 3/4 of the 2009 season from the equation. Perhaps an additional dummy variable thrown in so that you could differentiate what you believe to be an outlier, but there is still differences between the data for those 6 games that might be of interest. Plus, those games were coming off a very bad season, so your trailing-10 percentage may actually show some movement in addition to the "recession" variable.
-I wonder, does your seasonal normalization for economic effects also remove any annual effects from changes in the team (hype, pre-season rankings, previous season record, hirings/firings, etc)? If every game is normalized by the average attendance that season, then there would be nothing to show for changes between seasons, right?
This is good stuff. You should do it for every season AND every team.
Can metrojax fund some research?