I put together a season projection visualization that illustrates the playoff probabilities and win totals for each team. The numbers are based on the results of the season prediction project I did for ESPN The Magazine.
The method used to create the projections is explained here.
The viz is intended one-stop shopping for the season outlook. The top window shows the probabilities each team will make the playoffs. Dark green indicates a playoff berth by winning the division, lighter green indicates a wildcard berth.
The three windows below are team-specific. Hover the cursor over (or tap) a team's column in the top chart to see its details below. The window on the left is a chart of win totals. The bars represent the probability the selected team will finish with a corresponding number of wins. The second window shows the same information presented in a different way. It's the cumulative probability of each win total. In other words, it's the probability the selected team will win at least that many games. The third window is a pie chart. (Yes, I know pie charts are the unloved orphans of the chart world.) It illustrates the probability each team will win its division.
The biggest takeaways here are that the best teams from last year are probably going to be the best teams this year. Although SEA is ranked as the strongest team, they have a tougher division and conference than other contenders. DEN has the easiest path to the Super Bowl and NE has the second easiest. The NFC simply has more contenders at this point.
There are some teams that have solid postseason chances, but are stuck behind a dominant team in their division so are likely gunning for a wildcard. KC is a good example.
I was very surprised how well CLE came out in the wash, but I shouldn't be. Their defense is very solid and often overlooked. Their problem is that there are 3 slightly better teams in the AFC North. ARI is another example of a solid team with high projected win totals but relatively low playoff chances.
Unlike the ESPN Magazine article, the win totals here are true team-specific statistical estimates rather than a league-wide season "projection." Because of all the uncertainty and randomness inherent in the process, true win total estimates will tend to cluster tightly around 8 wins for almost every team. But we know that in any one single observed season, we'll see a 13-game winner, a couple 12-game winners, and we'll see a few teams with win totals under 5 as well. The win totals in the ESPN article reflect that observation, and were an attempt to capture the single most plausible observed season outcome, given the results of the season simulation model.
The one thing we know for sure is that these predictions will be wrong. I guarantee it.
Link to the viz.
- Home
- team analysis
- Season Projections Visualization
Subscribe to:
Post Comments (Atom)
is it possible that the team wins is mislabeled? Each teach is clustered near nine wins. the average win projection is nine across the entire league. presumably the x-axis is mislabeled by one win?
Yeah, there seems to be something fishy with the numbers. Look at teams like Washington, Cleveland or the Jets that seem to have projected means of less than 8 wins (based on their playoff odds). They all have distributions that say they have a better chance of winning 9 games than 7.
Any chance you would let us connect to your data using our own instances of Tableau?