Wednesday, September 19, 2007

The Value of Homefield Advantage, 2007 Week 2

One of the things I've learned in my football research is that the value of home-field advantage varies pretty widely from year to year, especially with interconference games. Because prediction systems tend to have a big bias towards the home team, this can have a large impact on accuracy. So throughout the season, I'll be keeping track of home team winning percentage and average final score margin (home team points - away team points) for interconference, interdivision, and intradivision matchups. If you're interested in that sort of thing, it can help you with betting on the spread (hint).

All Games
Home Team Win %: 62.5000%
Avg. Final Score Margin: 2.3438

Home Team Win %: 62.5000%
Avg. Final Score Margin: 2.0000

Interdivision, Intraconference
Home Team Win %: 70.0000%
Avg. Final Score Margin: 7.2000

Home Team Win %: 57.1429%
Avg. Final Score Margin: -0.9286


Brian Burke said...

Derek, do you think that certain years have different HFA rates because there is something systematic about the particular season, or do you think it's random variation?

Let's say it's week 12. Does the HFA rate for weeks 1-11 have an effect on what it will likely be for week 12? Just curious what your thoughts are on this.

Derek said...

I think it has a lot to do with the new scheduling algorithm. So you might not see the effect within a particular week, but you will see it over a few weeks time. It's not entirely intuitive because if Good Division plays Crappy Division, then the Good Division would win nearly all of the games and there'd be an equal effect on home and away games.

That the effect becomes more noticable after 2002 makes me think that more strongly.

This theory, though, is still far from being worked out thoroughly. And I don't know why it'd be so different for interconference games. Length of travel? Lack of familiarity? Opponent quality mismatches?