Thursday, December 31, 2015

2015 Early Season Power Rankings - The Results

In which we rank the rankings...

Power rankings are everywhere, but how do we know if they are any good? If they are intended to be predictive, we can test them for their predictive value. So, for the past three years, I have archived a cross section of power rankings from early in the NFL season (after week four). Then, once the season is done, I assess each ranking's accuracy in predicting future wins in that same season.

Each team's win percentage for weeks 5-16 (week 17 excluded) is rank ordered. This is then tested for agreement with each power ranking. I use the Spearman Rank Correlation coefficient for this purpose. A Spearman value of 100% would indicate perfect agreement between two rankings (e.g. if 1-32 in win percentage lined up identically with the power ranking in question). A value of -100% would indicate complete disagreement between the two lists, meaning 1-32 in win percentage lines up with 32-1 in the power ranking. A value of 0% would mean, roughly, no correlation between the two rankings.

I archived the week 4 power rankings in this post from October. As a reminder, the rankings I evaluate are: Football Outsiders DVOA, ESPN's FPI (as a replacement for Brian Burke's AFA efficiency rankings), the Simple Ranking System, ESPN's official NFL power rankings, FiveThiryEight's Elo rankings, and the Betting Market Rankings published here at inpredictable.

Sunday, December 27, 2015

The Colts are alive, but play a virtually meaningless game today

Owing to a strange confluence of tiebreaker scenarios, the Colts' game today against the Dolphins has virtually no impact on its playoff chances. According to my simulations, the Colts make the playoffs in 6.7% of the simulations in which they win, and in 6.1% of the simulations in which they lose., a swing of just 0.6%.

Contrast that to the impact the Texans-Titans game has on the Colts' playoff odds: The Colts make the playoffs in 18.7% of the simulations in which the Texans lose, and just 0.2% of the simulations in which the Texans win.

Saturday, December 26, 2015

NFL Playoff Implications Week 16

Here are the playoff implications for the NFL's week 16 games. The purpose of this feature is to highlight games that have a significant impact on the playoff picture (see this post for background).

The playoff implications below are derived from a 50,000 round simulation of the remainder of the NFL season. I use my daily NFL rankings to simulate future games. I can group the simulation runs by the outcome of each game and then see how a team's playoff chances vary between the two groups. The interactive table at the bottom of the post will allow you to see corresponding results for any game or team. The results of the three Thanksgiving games have already been taken into account in the tables below.

Ranking Week 16 Games by Leverage

The table below ranks the week 16 games by total leverage. Leverage in this context is a measure of both how uncertain a game's outcome is (games between evenly matched teams have higher leverage) and how much the playoff picture swings as a result of that outcome.

Turnover Index Week 16

Here are the Turnover Index picks and results for week 16. The Turnover Index is a simple betting strategy based on the theory that the market overvalues defensive turnovers when judging team strength. See here and here for more background.

Of our two picks from week 15, one pushed and the other lost. But due to bet size, the net effect on bankroll amounted to a rounding error (for the second week in a row).

Here are the season to date results:

weekbetswonstarting
bankroll
amount betprofitsending
bankroll
6 1 1 $1,000 $40 (4.1%) $37 $1,037
7 3 1 $1,037 $79 (7.7%) ($29) $1,008
9 2 1 $1,008 $66 (6.6%) ($51) $956
10 3 1 $956 $43 (4.6%) $3 $959
11 1 1 $959 $11 (1.2%) $10 $970
12 3 2 $970 $45 (4.7%) ($34) $935
13 1 1 $935 $13 (1.4%) $12 $948
14 1 1 $948 $0 (0.1%) $0 $948
15 2 0.5 $948 $12 (1.3%) ($0) $948


Thursday, December 24, 2015

In the AFC, Strength of Victory Could Determine the Postseason

Professional sports tiebreaking procedures tend to be an exercise in multiple redundancy. In the NFL, to break a tie within a division, there are 12 potential steps, starting with head to head record, progressing through divisional and conference records, strength of schedule metrics, various scoring margin measures, and ultimately culminating in step 12, a coin flip.

In a previous analysis, I found that this tiebreaking system was sufficiently redundant. Based on 10,000 simulations of the 2013 season, I found that there was just a 0.01% chance of the 8th tiebreaker, net points scored and allowed, needed to break a tie. That left a 3 tiebreaker buffer before the last resort coin flip was needed.

With just two weeks remaining in the 2015 regular season, we are still in no danger of a coin flip determining the postseason participants. However, there does appear to be a good chance that both the AFC North and AFC South will need one of the more esoteric tiebreakers to determine their respective division winners.

Saturday, December 19, 2015

NFL Playoff Implications Week 15

Here are the playoff implications for the NFL's week 15 games. The purpose of this feature is to highlight games that have a significant impact on the playoff picture (see this post for background).

The playoff implications below are derived from a 50,000 round simulation of the remainder of the NFL season. I use my daily NFL rankings to simulate future games. I can group the simulation runs by the outcome of each game and then see how a team's playoff chances vary between the two groups. The interactive table at the bottom of the post will allow you to see corresponding results for any game or team. The results of the three Thanksgiving games have already been taken into account in the tables below.

Ranking Week 15 Games by Leverage

The table below ranks the week 15 games by total leverage. Leverage in this context is a measure of both how uncertain a game's outcome is (games between evenly matched teams have higher leverage) and how much the playoff picture swings as a result of that outcome.

Turnover Index Week 15

Here are the Turnover Index picks and results for week 15. The Turnover Index is a simple betting strategy based on the theory that the market overvalues defensive turnovers when judging team strength. See here and here for more background.

Our sole pick from week 14 was successful. However, the edge was so small that the Kelly Criterion dictated that we bet just 0.1% of our bankroll, so the impact on overall results was negligible.

Here are the season to date results:

weekbetswonstarting
bankroll
amount betprofitsending
bankroll
6 1 1 $1,000 $40 (4.1%) $37 $1,037
7 3 1 $1,037 $79 (7.7%) ($29) $1,008
9 2 1 $1,008 $66 (6.6%) ($51) $956
10 3 1 $956 $43 (4.6%) $3 $959
11 1 1 $959 $11 (1.2%) $10 $970
12 3 2 $970 $45 (4.7%) ($34) $935
13 1 1 $935 $13 (1.4%) $12 $948
14 1 1 $948 $0 (0.1%) $0 $948


Sunday, December 13, 2015

NFL Playoff Implications Week 14

Here are the playoff implications for the NFL's week 14 games. The purpose of this feature is to highlight games that have a significant impact on the playoff picture (see this post for background).

The playoff implications below are derived from a 50,000 round simulation of the remainder of the NFL season. I use my daily NFL rankings to simulate future games. I can group the simulation runs by the outcome of each game and then see how a team's playoff chances vary between the two groups. The interactive table at the bottom of the post will allow you to see corresponding results for any game or team. The results of the three Thanksgiving games have already been taken into account in the tables below.

Ranking Week 14 Games by Leverage

The table below ranks the week 14 games by total leverage. Leverage in this context is a measure of both how uncertain a game's outcome is (games between evenly matched teams have higher leverage) and how much the playoff picture swings as a result of that outcome.

Saturday, December 12, 2015

Stephen Curry is No Stat-Padder

Stephen Curry close up.jpg It's been kind of under the radar, but Stephen Curry is having quite the season. He leads the league in a variety of box score stats, both traditional and advanced. He is #1 in points per game, field goals made, and three pointers made (the latter by a ridiculous margin). He also leads the league in PER (34.0), True Shooting Percentage (0.692), Win Shares (6.3), Box Plus/Minus (12.7) and Real Plus Minus (10.90).

As defenders play him tighter near the three point line, he simply extends the topology of the court, knocking down 26, 28, 30 foot shots with better accuracy than DeAndre Jordan makes free throws.

Another stat in which Curry is dominant is Win Probability Added (WPA), which I publish here on my site. Win Probability Added, as I've defined it, takes all field goal attempts, free throw attempts, and turnovers for each player, and weights them according to the impact those plays had on team win probability. This is the "anti-stat padder" stat, as it effectively ignores performance during garbage time. And with the Warriors playing the way they are this season, garbage time cometh, and that right soon. This stat also places much more emphasis on clutch shooting, with higher rewards for a made clutch shot, and stiffer penalties for a miss.

Turnover Index Week 14

Here are the Turnover Index picks and results for week 14. The Turnover Index is a simple betting strategy based on the theory that the market overvalues defensive turnovers when judging team strength. See here and here for more background.

Our sole week 13 pick was successful, with the Saints covering in a wild game against the Panthers.

Here are the season to date results:

weekbetswonstarting
bankroll
amount betprofitsending
bankroll
6 1 1 $1,000 $40 (4.1%) $37 $1,037
7 3 1 $1,037 $79 (7.7%) ($29) $1,008
9 2 1 $1,008 $66 (6.6%) ($51) $956
10 3 1 $956 $43 (4.6%) $3 $959
11 1 1 $959 $11 (1.2%) $10 $970
12 3 2 $970 $45 (4.7%) ($34) $935
13 1 1 $935 $13 (1.4%) $12 $948


Sunday, December 6, 2015

NFL Playoff Implications Week 13

Here are the playoff implications for the NFL's week 13 games. The purpose of this feature is to highlight games that have a significant impact on the playoff picture (see this post for background).

The playoff implications below are derived from a 50,000 round simulation of the remainder of the NFL season. I use my daily NFL rankings to simulate future games. I can group the simulation runs by the outcome of each game and then see how a team's playoff chances vary between the two groups. The interactive table at the bottom of the post will allow you to see corresponding results for any game or team. The results of the three Thanksgiving games have already been taken into account in the tables below.

Ranking Week 13 Games by Leverage

The table below ranks the week 13 games by total leverage. Leverage in this context is a measure of both how uncertain a game's outcome is (games between evenly matched teams have higher leverage) and how much the playoff picture swings as a result of that outcome.

Saturday, December 5, 2015

Turnover Index Week 13

Here are the Turnover Index picks and results for week 13. The Turnover Index is a simple betting strategy based on the theory that the market overvalues defensive turnovers when judging team strength. See here and here for more background.

The good news is that our week 12 picks went 2-1 against the spread. The bad news is we lost the wrong bet. The betting strategy dictated we bet a combined 0.7% of our bankroll on the two winning bets. But we had 4.1% bet on the Cowboys to cover against the Panthers on Thanksgiving.

In what was practically a single game refutation of the Turnover Index, the Panthers, who led the league in defensive turnovers, refused to regress to the mean. Instead, they continued their greedy ways, picking off Tony Romo three times, two of which were returned for touchdowns.

Saturday, November 28, 2015

NFL Playoff Implications Week 12

Here are the playoff implications for the NFL's week 12 games. The purpose of this feature is to highlight games that have a significant impact on the playoff picture (see this post for background).

The playoff implications below are derived from a 50,000 round simulation of the remainder of the NFL season. I use my daily NFL rankings to simulate future games. I can group the simulation runs by the outcome of each game and then see how a team's playoff chances vary between the two groups. The interactive table at the bottom of the post will allow you to see corresponding results for any game or team. The results of the three Thanksgiving games have already been taken into account in the tables below.

Ranking Week 12 Games by Leverage

The table below ranks the week 12 games by total leverage. Leverage in this context is a measure of both how uncertain a game's outcome is (games between evenly matched teams have higher leverage) and how much the playoff picture swings as a result of that outcome.

Tuesday, November 24, 2015

Turnover Index Week 12

Here are the Turnover Index picks and results for week 12. The Turnover Index is a simple betting strategy based on the theory that the market overvalues defensive turnovers when judging team strength. See here and here for more background.

The sole week 11 pick was successful, with the Ravens just barely covering a 2.5 point spread (note: my point spread data comes from sportsdatabase.com).

Saturday, November 21, 2015

NFL Playoff Implications Week 11

Here are the playoff implications for the NFL's week 11 games. The purpose of this feature is to highlight games that have a significant impact on the playoff picture (see this post for background).

The playoff implications below are derived from a 50,000 round simulation of the remainder of the NFL season. I use my daily NFL rankings to simulate future games. I can group the simulation runs by the outcome of each game and then see how a team's playoff chances vary between the two groups. The interactive table at the bottom of the post will allow you to see corresponding results for any game or team.

Ranking Week 11 Games by Leverage

The table below ranks the week 10 games by total leverage. Leverage in this context is a measure of both how uncertain a game's outcome is (games between evenly matched teams have higher leverage) and how much the playoff picture swings as a result of that outcome.

Wednesday, November 18, 2015

Turnover Index Week 11

Here are the Turnover Index picks and results for week 11. The Turnover Index is a simple betting strategy based on the theory that the market overvalues defensive turnovers when judging team strength. See here and here for more background.

The week 10 picks went 1-2 against the spread, but we eked out a net positive return. One of the losing bets, Seahawks over Cardinals, had just the slightest edge, and thus the Kelly criterion only dictated a small fraction of our bankroll to be bet.

Sunday, November 15, 2015

Live Ball vs Dead Ball Turnovers

Last season, I added a new feature to the site which allowed for a deeper dive into NBA team per possession efficiency. Per possession efficiency has long been a staple of advanced metrics. It allows for a more precise measure of offensive and defensive skill. While traditionally a box score stat, I used the detailed play by play data to break out efficiency based on how each possession began. With rare exceptions, a possession can begin in one of the following ways:
  • After an opponent made shot
  • After a defensive rebound
  • After a turnover
As one would expect, possessions after a turnover are the most efficient, due to their opportunities for fast breaks. However, several people pointed out that the turnover bucket includes both "live ball" turnovers (bad passes, steals, etc.) as well as "dead ball" turnovers (out of bounds, offensive fouls, etc.). If turnover efficiency is driven by fast break opportunities, then possessions off of dead ball turnovers should have a much lower efficiency than their live ball counterparts. Here are the results, aggregated over the past four full NBA seasons (2011-2014):

Saturday, November 14, 2015

NFL Playoff Implications Week 10

Here are the playoff implications for the NFL's week 10 games. The purpose of this feature is to highlight games that have a significant impact on the playoff picture (see this post for background).

The playoff implications below are derived from a 50,000 round simulation of the remainder of the NFL season. I use my daily NFL rankings to simulate future games. I can group the simulation runs by the outcome of each game and then see how a team's playoff chances vary between the two groups. The interactive table at the bottom of the post will allow you to see corresponding results for any game or team.

Ranking Week 10 Games by Leverage

The table below ranks the week 10 games by total leverage. Leverage in this context is a measure of both how uncertain a game's outcome is (games between evenly matched teams have higher leverage) and how much the playoff picture swings as a result of that outcome.

Turnover Index Week 10

Here are the Turnover Index picks and results for week 10. The Turnover Index is a simple betting strategy based on the theory that the market overvalues defensive turnovers when judging team strength. See here and here for more background.

Despite the week nine picks going 1-1 against the spread. we lost about 5% of our bankroll, due to the majority of funds being placed on the losing bet. The model had the underdog Cowboys to cover the three point spread at home against the Eagles. Dallas couldn't leave a perfectly good push alone, and kicked a field goal at the end of regulation to force overtime. The Eagles won the coin toss (or did they?) and scored a touchdown on their opening possession to win the game and, alas, cover the spread.

With the NFL's new overtime rules that prevent a team from winning with a field goal on their opening possession, one would think that the frequency of overtime games finishing with a six point margin (as opposed to 3 points) would increase. However, based on the 65 games that have gone to overtime since 2012 (when the rule change went into effect), the percentage of games ending with a six point margin is largely unchanged relative to pre-2012:

Sunday, November 8, 2015

NFL Playoff Implications Week 9

Unfortunately, weekly playoff implications will not be featured on FiveThirtyEight this season. But, I was able to dust off the code from the "classic" version I originally created for this site. It lacks the bells and whistles of the FiveThirtyEight version, but it gets the job done. The purpose of this feature is to highlight games that have a significant impact on the playoff picture (see this post for background).

The playoff implications below are derived from a 50,000 round simulation of the remainder of the NFL season. I use my daily NFL rankings to simulate future games. I can group the simulation runs by the outcome of each game and then see how a team's playoff chances vary between the two groups. The interactive table at the bottom of the post will allow you to see corresponding results for any game or team.

Ranking Week 9 Games by Leverage

The table below ranks the week 9 games by total leverage. Leverage in this context is a measure of both how uncertain a game's outcome is (games between evenly matched teams have higher leverage) and how much the playoff picture swings as a result of that outcome.

Wednesday, November 4, 2015

Turnover Index Week 9

In the week 7 writeup of the Turnover Index, I flagged the Jets as a team that may regress from its strong 4-1 start. Since that time, the Jets have dropped two straight. Granted, the first was to the undefeated Patriots, and the 2nd loss came after an early injury to starting quarterback Ryan Fitzpatrick.

But the most telling stat is defensive turnovers. Over their first five games, the Jets led the league in defensive turnovers, averaging three per game. In their two games since? Zero turnovers created on defense. It's only two games, but it makes for a nice illustration of the principle behind this betting strategy: turnovers "created" by the defense are largely random.

There were no week 8 bets, but there is one more correction to the historical results table (I promise this is the last one).

Saturday, October 31, 2015

New Live Feature: The "SO" calculator

You were so preoccupied with whether or not you could,
you didn't stop to think whether you should.
Depending on your perspective, you may consider this a neat feature or an abomination.

Continuing work from last year's playoffs, I am sharing live win probability graphs on my site for all regular season games (although I'm still working out some kinks in the implementation).

In addition to the standard win probability metrics from last year, there is a new table that accompanies each graph, which I'm calling the "SO" Calculator ("SO" being short for Significant Other).

Most of us have been in the position where our wife/boyfriend/child/etc. does not care about a game we are watching and simply wants to know when it's going to be done. And most of us lie. If there is 4:55 on the clock, well say "about five minutes". And with a straight face too.

Thursday, October 29, 2015

Turnover Index Week 8

Unfortunately, there are no bets this week that satisfy our wagering criteria, but here are the week seven results:

Wednesday, October 21, 2015

Turnover Index Week 7 - Expect the Jets to Regress

We're off to a good start for the 2015 season. Our first bet against the spread was successful, with the Browns covering (just barely) against the Broncos as a 4 point underdog. Here are the results (we'll add a row to this table each week):

weekbetswonstarting
bankroll
amount betprofitsending
bankroll
6 1 1 $1,000 $49 (5.0%) $45 $1,045

There have been no shortage of surprising starts this NFL season (it's been positively weird). Among those surprises are the New York Jets, who have won four of their first five, despite an offseason marred by coaching changes, bad debt, and sucker punches.

Over those first five games, the Jets have averaged three turnovers per game on defense, which currently leads the league. But turnover success on defense is fleeting, and history suggests the Jets are unlikely to maintain this pace throughout the season. Going back to the 1989 season, here is how teams have fared after racking up at least 15 defensive turnovers in their first five games (48 teams in total):

Teams with at least 15 Defensive Turnovers in their 1st 5 Games
turnovers/gmwin percentagainst the spread
Games 1-53.272%68%
Games 6-162.052%45%


Wednesday, October 14, 2015

The Return of the Turnover Index

Make money betting on the NFL with this one simple trick!

For the past three NFL seasons, I have been publishing picks against the spread based on a simple betting strategy. That strategy, in a nutshell, is to bet on teams with a much lower defensive turnover total (season-to-date) than their opponent.

In the NFL, turnovers are largely random events. They correlate somewhat with team offense, but hardly correlate at all with team defense. However, the betting public has been slow to recognize this fact. Teams that have amassed strong records by "forcing" defensive turnovers may be overvalued by the market.

That's the theory, anyways. In practice, results have been modest. Over three seasons, my picks have gone 40-34-2 against the spread. That's enough to eke out a slight profit, but nothing spectacular. And it is somewhat below the 59% cover rate implied by my original analysis.

Sunday, October 11, 2015

NFL Week Four Power Ranking Roundup

This time last year, nobody was quite sure what to make of the 2-2 Patriots. In my power ranking roundup post from last year, here is where six different ranking systems placed them:
  • Simple Ranking System - #26
  • Football Outsiders' DVOA - #23
  • FiveThirtyEight Elo - #7
  • ESPN Power Rankings - #16
  • Inpredictable Market Rankings - #14
  • Advanced Football Analytics' Efficiency Rankings - #27
As we know, the Patriots went on to win 10 of their 12 remaining regular season games en route to another Superbowl title - an outcome predicted with eerie prescience by Skip Bayless (of all people):
The New England Patriots will rise like the phoenix from the ashes of Monday night's 41-14 loss in Kansas City and land at the University of Phoenix Stadium in Glendale, Arizona, playing in Super Bowl XLIX.
This year, however, there is no confusion, only consensus. The New England Patriots are the #1 team across all six power rankings after week four of the season. As a reminder, I archive these week four rankings and then test their accuracy in predicting future wins, once the season is finished.

Saturday, October 10, 2015

PitchF/x for the NBA

One of sports analytics' first "big data" moments came with Major League Baseball's introduction of PitchF/x in 2006. With the help of cameras installed in each stadium, each pitch is now tracked at an obsessive level of detail. Where once we had just "ball" or "strike", pitches can now be classified according to pitch type, velocity, release point, and movement.

In addition, strike zone position is also tracked for every pitch, and can then be converted into nifty looking scatter plots, such as those found on Fangraphs. The chart below is the scatter plot for Max Scherzer's recent no-hitter, his second of the season.
Earlier this year, I rolled out my attempt at PitchF/x-style analysis for the NBA. "ShotF/x" would have been a snappy name, but probably a trademark violation. So, I called it ShArc instead, short for Shot Arc Analysis. In that initial post, I used a simple physics model to examine the finer details of player free throw shooting - shot angle, release height, peak height, and accuracy. The raw data came from SportVU, the NBA's version of the PitchF/x system. Because the data was noisy, I applied some basic physics to tease out the most likely trajectory from the scatter of data points.

Monday, September 7, 2015

NFL Market Rankings and the Inequities of Playoff Seeding

The Top Five
With the regular season just a few days away, my market based NFL rankings are now up and running. These update daily and are designed to reflect the betting market's ranking of all 32 NFL teams. The rankings themselves use the betting point spreads and over/unders from each game. A simple weighted linear regression is used to reverse engineer a ranking from these pairwise numbers.

The key metric here is Generic Points Favored, or GPF, and it is what you would expect the team to be favored by against a league average opponent on a neutral field. By using the point spreads in conjunction with the over/under, GPF can be further decomposed into its offensive and defensive components (oGPF and dGPF).

For now, there is just a week's worth of point spreads and totals to work with, which is insufficient to create a proper regression analysis amongst the 32 NFL teams. To get enough connections between the teams, you need at least three weeks of data. To fill in the gaps in the meantime, I have used the full season point spreads as published by Cantor Gaming.

This will be my fourth year publishing these rankings for the NFL. When it comes to predicting future wins, they have outperformed a variety of other ranking systems. I am curious to see how they stack up this year against ESPN's revamped Football Power Index.

Saturday, August 22, 2015

Kind of a Drag

Just a heads up that this post is pretty heavy on math and physics: differential equations, integrals, drag coefficients, air density at varying altitudes, etc. You know, in case you're into that kind of thing.

Most physics problems, especially the undergraduate variety, require simplifying assumptions in order to make them workable - frictionless surfaces, perfect vacuums, spherical cows. This past May, I employed some simple physics to analyze the shooting trajectories of NBA players. The raw location data came from the SportVU location tracking system, and is somewhat noisy. To tease signal from that noise, I assumed the ball's path followed a simple trajectory, the kind which physics majors cut their teeth on as freshman. I then used linear regression to pick a path that best matched the raw data.

One key simplifying assumption made was to ignore the impact of drag on the flight of the ball. As the ball moves through the air, it is pushing that air out of the way, and the air pushes back, slowly degrading the ball's velocity. As it turns out, this effect, while small, was not negligible, and its omission was creating persistent bias in the modeling of free throws and field goals.

In this post, I'll outline my attempts to incorporate drag into my model of a basketball's trajectory, and then test that model's predictions against the raw SportVU data (science!). As a bonus project of sorts, I will also examine whether drag effects are noticeably different for thin air arenas such as those of the Denver Nuggets and Utah Jazz.

Thursday, August 20, 2015

Vegas Never Doubted Clayton Kershaw

Baseball diamond marines.jpg
San Diego's Petco Park
The most "pitcher friendly" park in the
league according to the market
After a long hiatus, betting market rankings for major league baseball are now available and will update daily for what's left of the season. Similar to my rankings for the NFL, NBA, College Football, and College Basketball, these attempt to reverse engineer an implied power ranking from the betting lines and totals for each game. I now have all five sports on a common mathematical framework and intend to share the technical underpinnings of the methodology in a future post.

The Los Angeles Dodgers currently sit atop the market based rankings, despite having just the sixth best record in the league.


Ranking Starting Pitchers

In addition to the standard team rankings, I can also derive a ranking of starting pitchers. Each MLB team is more like 5 to 6 distinct teams, depending upon who takes the mound to start. According to the market, the best pitcher in the league is, and has been, the Dodgers' Clayton Kershaw. Teams facing Kershaw are expected to score 1.27 less runs on average when compared to a league average starter. And despite Kershaw's early season bout with mediocrity, the market didn't blink. Kershaw has remained the top ranked pitcher throughout the season according to my Vegas rankings (check the sparkline next to each starter in the ranking table for a snapshot of their season progression).

Sunday, June 14, 2015

How Much Actual Time is Left in the Game?

The Persistence of NBA Game Time
Close games in the NBA can somewhat of a mixed blessing. As the drama increases, the pace tends to drag, as teams call timeouts to draw up set plays, players are fouled to stop the clock, and officials await decisions from the NBA's centralized review office in New Jersey. On average, the final minute of an NBA game takes over 5 minutes of real time to complete, and that number gets much larger if the game is close.

Here are some cheat sheets I put together that give you a sense as to how much real time is left in an NBA game, as a function of scoring margin and game time remaining. I had hoped to build a real time view of this into my live win probability graphs, but that will likely have to wait for the offseason.

Monday, June 8, 2015

New article at FiveThirtyEight: A Win Probability Guide to US vs. Australia

I have a new article up at FiveThirtyEight: A Win Probability Guide to US vs. Australia. Continuing my rather unhealthy obsession with in-game/in-match win probability, I took last year's work on mens soccer probability and applied it to the womens game. The US is a heavy favorite against Australia, and will be for all three of its so-called "Group of Death" matches. Win probabilities for mismatches evolve very differently than for evenly matched teams, and the post is a guide to how the US outlook evolves in the event they don't establish an early lead.

Data for womens sports is not exactly abundant, and soccer was no exception. The data for the model was culled from recent seasons of top league play. It took some effort, as well as some tedious cleaning to compile the data, and in the end, my final dataset consisted of just 950 matches (compared to the 3,000+ matches that all but fell in my lap for mens soccer). So, the model built here may be somewhat more prone to noise (or overly smoothed) than models built from a more robust dataset.