MLS Attendance 2010: Getting the statistics right

This is what 36,000 fans each week looks like. Not every club is so lucky.

I am focused on World Cup like everyone else, and I am working on a nice little spreadsheet and post to accompany my viewing experience. But I must take this opportunity to provide some statistical commentary.

As a US soccer fan, I am all for the sport's growth and Major League Soccer plays a key part in that growth. Everyone is hoping for a big bounce in MLS's profile this year due to the World Cup, so I was naturally excited when MLS Daily came out with a post trumpeting 10.8% growth at MLS match attendance. The problem is that after a closer examination of their numbers, I find that their calculation method is wrong and that the actual attendance growth is far less. Let me explain.

MLS Daily's method is simple, straightforward, and one that the average fan might make. They take the 2010 average attendance through 93 games (16,472) and divide it by the 2009 average attendance through 91 games (14,862) to get the 10.8% growth in attendance. The problem is that this violates the basic rule of statistics: it's not the average that matters, but the distribution around the average. The correct way to calculate the average increase in 2010 MLS attendance vs. 2009 MLS attendance is to answer the following two questions:

• Is 2010 MLS attendance statistically significantly higher than 2009 MLS attendance?
• If so, by how much?

To answer those two questions, we must look at each individual team's difference and not the league average.

The Statistics

To answer the first question, I first must develop the 2009 and 2010 attendance figures by club. This is easy if I trust the MLS Daily numbers by club. In this case I do trust them, and I divide the 2010 numbers they have published by (1 + % change from 2009) for the respective clubs. That gives me this breakdown of 2009 and 2010 attendance (deleting Philly, of course). We're now ready to make some comparisons.

What's the first rule of any statistical analysis? That's right: check for normality. Neither data set tested normal (which is the key assumption the MLS Daily analysis relies upon yet violates), so I looked to see if I could get both data sets to be normal via a common recommended Box-Cox transform. No luck again. It's time to turn to the Mann-Whitney parametric analysis.

The Mann-Whitney test uses medians, not means, to evaluate the difference in two populations - in this case, 2009 and 2010. That allows it to evaluate non-normal distributions. Using the Mann-Whitney test can allow us to understand whether or not a statistical difference exists and how big it is.

The Results

Running the Mann-Whitney test yields some interesting results. Figure 1 shows the results of the test.

Figure 1: Mann-Whitney test results for 2009 vs. 2010 MLS attendance

As the last line of the test indicates, the difference between the two seasons is significant which means the 2010 season has seen an increase in attendance. However, the difference is only 802 people which yields a 5.5% increase in attendance - nearly half of what MLS Daily claims. What's astonishing is that if you look at the likely spread in differences (95% spread to be exact), almost 2/3's of the likely difference is negative. That means that while the observed values indicate a likely attendance growth, they don't rule out a possible attendance drop given the poor showings in some cities.

Getting these statistics right is very important. MLS is on an expansion plan the next several years - Vancouver and Portland in 2011, and Montreal in 2012. Expansion is important, but key established teams are suffering: New England and San Jose are both down double digits versus last year. Expanding too quickly can hurt the existing teams, and stunt league growth. It's important that MLS and its fans have a realistic view of its growth from one year to the next to ensure club and league viability.

That's Why They Play the Games

The ghosts of World Cup 1950 that will stalk England on Saturday

The Rematch is almost upon us, and it's only appropriate that I turn to the Soccernomics model for national team performance to provide a prediction of the possible outcome. If two teams, i and j, face each other the Soccernomics model uses the following equation to predict goal differential:

GD(ij) = 0.137 ln[pop(i)/pop(j))] + 0.145 ln[GDP(i/GDP(j))] + 0.739 ln[exp(i)/exp(j)] + 0.657 for home team

In the case of England and the US, no one is the home team so we can drop the final term in the equation. Now we turn to the population, GDP, and experience terms.

Population

• England: 51,456,400
• US: 309,449,000

GDP

• England: $35,334
• United States: $46,381

Experience:

• England: 780 matches
• United States: 403 matches

Plugging these variables into the above equation yields a 0.203 goal differential advantage for England. England greatly benefits from their nearly 2-to-1 advantage in international experience that counts nearly six times as much as the other variables. For all the smack talk from English fans, this is hardly an advantage in the World Cup.

This match will likely be far more even than some would think. It's certainly within the United State's capability to win it. Both teams are in top form, and everyone is hoping for an outstanding clash worth the 60 year wait.

I have only one thing left to say.

"DON'T FIRE UNTIL YOU SEE THE WHITES OF THEIR EYES, BOYS! BEAT ENGLAND!!!"

Two quick links

I know this is probably late, but if you haven't got a World Cup tracking service or document yet and are in to Excel, you might find this blog post by a friend very interesting. Diego Oppenheimer at Microsoft has put together an outstanding template for all you World Cup junkies - essentially you watch the games, fill in the results as they happen, and the spreadsheet gives you real time results of who makes it out of group play and who doesn't. Diego has done a great job of both providing the finished product and what he started with and the instructions to get to the finished product for all you people looking to learn more about how Excel functions. I'd highly recommend checking it out, and seeing what you can do to expand the spreadsheet or improve it.

Secondly, I got a nice few links at a regular reader's blog. Brett and I have been conversing a good bit the last week or two about Soccernomics, soccer statistics, and the possibility of a player metric like +/- from hockey being applied to soccer. He's been pushing me to think hard about how to improve statistics as they relate to soccer, and I appreciate it. Of course I also appreciate the links. If you have time, check out his personal blog as well as his business intelligence blog. BI, when done right, is basically business statistics. The same could be said of soccer statistics applied in a professional setting.

Four More Matches

There are only four more matches until MLS heads into its World Cup 2010 break. I will wait until those games are complete to update my MLS table and golden boot competition standings. In the meantime, here's the impact of those last four matches on the teams' playoff chances listed in W/D/L format. All data is from Sports Club Stats.

• Chicago Fire (9.4/-4.2/-10.7) at Colorado Rapids (3.9/0.5/-2.7)
• LA Galaxy (-0.05/0.05/0.01) at Real Salt Lake (1.7/0.1/-1.7)
• DC United (0.4/0/-0.1) at Seattle Sounders FC (5.7/-6.2/-11.4)
• Philadelphia Union (8.1/0.3/-2.9) at Kansas City Wizards (3.5/-3.0/-5.6)

My Seattle Sounders could really move up if they win their second game in a row. The quick six points they will have picked up if they beat DC United will have improved their playoff chances from 13.5% to 36.3% in just two matches. They will still have a long way to go in the second half of the season, but they will have moved up to fourth in the Western Conference with a win against DC.

What's also amazing is how little impact DC United and LA Galaxy's matches have on their likely chances of making the playoffs. DC is a truly dangerous team, having nothing left to play for except pride. Meanwhile, LA could be coasting without Landon Donovan and Edson Buddle, but they continue to outperform the whole rest of the league in their absence. Is this MLS's version of The Invincibles?

Statistics are just numbers

Cultural anthropology through Dutch soccer

I spent the weekend in Portland at a friend's wedding, and one of the side benefits was catching up with two friends and their new born son. The husband and I are always chattering about soccer whenever we get together (especially Arsenal as we are both supporters), and the topic of my blog came up. He's a regular reader, and while he enjoys the blog he did feel compelled to mention the change in tone just prior to my recent trip to Europe. He singled out this post for comment, inquiring why I moved away from statistical commentary and spoke with a different voice in asking for readers' recommended books. I think such inquiry provides a perfect opportunity for me to clarify my purpose for this blog and comment on one of those recommended books.

First, this blog is an outgrowth of my belief that statistics can illuminate unseen relationships, but they cannot be dealt with independently of the wider context of the subject area they are being used within. As my Portland friend commented earlier in that visit, we Americans are obsessed with statistics compared to other nations. Our obsession often leads us to look for patterns or significance where there are none. The mark of a good statistician is one who, in their normal course of study of a subject, stumble upon a question that may be best addressed with statistical analysis - that is, the use of statistics should be a rare occurrence in most fields. The same should be no different in soccer.

The challenge comes in building a blog around soccer statistics when my stated goal is to not be in search of patterns that don't actually exist. To me, this blog is a journey in understanding the many facets of the world's most popular sport. Statistics will greatly aid in that journey - to make sense of some larger truths in the sport. However, statistics often only describe the most likely outcome of an average event and not the actual outcome of a specific one, which is why we play each and every match to determine the actual outcome. In the same manner, I see statistics only being part of my journey through the world of soccer. Statistics related to the latest happenings in the soccer world will make up the bulk of my posts, but I also don't want to lose touch with the human element of the game. Soccer shapes our human experience, and to a greater degree our human experience shapes the game of soccer. I want to understand the humanity that produces the numbers I study. With that explanation, I now dive into one of those recommended books from my previous post.

At the urging of a regular reader/re-tweeter I picked up Brilliant Orange: The Neurotic Genius of Dutch Soccer by David Winner. It was a late addition to my reading material for my trip, and I was a bit sad I couldn't get it on the Kindle as it would have kept my bag weight down. Nonetheless, it came highly recommended and had the side benefit of helping describe the culture from which many of my co-workers come. After completing this book, I only wish I had read it earlier. It would have made my nearly three years of working with the Dutch much easier.

The book, more than anything, is a fascinating study of how such a small nation that outperforms expectations copes with the inevitable defeat it faces in major tournaments. This over performance has been quantified in the Soccernomics model, where the Dutch score a half goal more per match than the model predicts and they sit 9th out of 49 European teams in this category used to gauge over-performance (see Figure 14.4 in Soccernomics). The book starts at the beginning of post-war Dutch soccer to explain how coping with over-achievement became a Dutch soccer challenge.

To younger fans like me, Dutch soccer can be found everywhere today. Even Brilliant Orange acknowledges this, singling out Arsene Wenger's Arsenal squads as one of the professional embodiments of Dutch "Total Football" outside of the Eredivisie. This wasn't the case in the early 1970's. At that time, the Dutch were perfecting their version of soccer and unleashed it upon the world in Germany in 1974. At that World Cup the Netherlands began its run of over achievement. The heartbreaking loss in 1974 and the expected loss of 1978 set up the Dutch soccer story and was dealt with in the Dutch psyche as something to be accepted, largely tolerated, and in some ways celebrated.

The book goes through and weaves compelling stories of Dutch cultural impact on their style of soccer. Chapter 14 explains how Dutch land constraints and use lead to a different visualization of the soccer pitch, while Chapter 25 explains how their strategies of multiple uses of the same space on the pitch are also reflected in the unique layout and use of space at Schipol International Airport. In Chapter 18, the author explains how Dutch collaborative democracy is a handicap for their soccer team, and how the atheistic Dutch are still shamed about outstanding achievement based upon their Calvinist cultural mores. Such belief structures make accepting failure to win a championship all that much easier, and Chapter 6 explains how such democratic tendencies doomed the great national team of the 70's. Chapter 15 details the Dutch struggle with their role in the Holocaust, and how the adoption of the Jews by Ajax as a way to cope with that past has bred modern anti-Semitic chants from rival clubs. Chapter 13 explains how anti-German feelings, which were largely absent in the Netherlands until the late-70's, rose and fell in the 80's and 90's via the heated battles between the two nations' soccer clubs.

One of the final chapters plays right into one of the themes from Soccernomics. In the chapter entitled "5 out of 6: Frank, Patrick, Frank, Jaap, Patrick, Paul... and Gyuri" (read the book to understand the chapter numbering system), author David Winner takes us behind the scenes of a debate within Dutch soccer: to win, or not to win, by penalty kicks. It seems that in their pursuit of playing their beautiful game, Dutch teams of the 80's and 90's felt winning by penalty kicks was beneath them. If they couldn't win in 90 or 120 minutes playing their game, they felt it was better to leave winning up to the chance of penalty kicks rather than a system for taking them. While other teams were analyzing goalie behavior before matches and devising systems for taking penalty kicks, the Dutch weren't even practicing penalty kicks let alone doing any preparation like the other teams. They were convinced of the Soccernomics conclusion that penalty kicks didn't change the likely outcome of the match based upon certain predictors before Soccernomics was ever published. The problem is that they came to the wrong conclusion.

We know that the conclusion in Chapter 6 of Soccernomics is that penalty kicks don't have a statistically significant impact on the outcome of a soccer match vs. the predicted outcome from the Soccernomics model that looks at home pitch advantage, GDP, and population size of the two countries playing each other. The simplification behind that statement is that the statistical test says penalty kicks have no impact on the average outcome - it doesn't say much about specific outcomes. In the case of the Dutch team, we already know they punch way above their belt when it comes to international competitions. In their case, each game won on penalty kicks would have been another notch in their belt of over-achievement. The fact that they have likely conceded a number of matches due to lack of practice or respect for winning via penalty kicks means their over-achievement is likely higher than measured in Soccernomics. I'd be interested to see if the Dutch team itself would have shown a statistically significant shift in wins or losses based upon matches that went to penalty kicks. Luckily, David Winner outlines the ongoing battle by many in the Dutch soccer program to emphasize penalty kick practice and strategies.

In summary, I'd highly recommend this book to anyone. It's well written, very conversational, and strikes an outstanding balance between soccer and cultural material. To read this book is to begin to understand both Holland and its soccer team.

Golden Boot Update: June 2, 2010

In a recent post I showed how the leaders in the MLS golden boot race can be compared to the distribution of goal scorers in MLS's 15 year history. I was also able to show how good Edson Buddle was playing - in the top 1% of all goal scorers in MLS history. Here's an update on the Top 5 goal scorers nearly a month later.

Figure 1: 2010 Top 5 goal scorers as of June 2, 2010

Edson Buddle played one more match without notching another goal, so he has now fallen to the second percentile. On the opposite end, Dwayne De Rosario has scored a goal in each of his last two matches, slightly improving him to the fourth percentile. Juan Pablo Angel continues to fall, giving up eight percentile points from a month ago. Jeff Cunningham dropped out of the top 5, and was replaced by Alvaro Saborio who was MLS's player of the month for May. Chris Wondolowski has also regressed, giving up 13 percentile points.

The golden boot competition is shaping up to be a real contest between Edson Buddle and Dwayne De Rosario - all others are starting to regress towards historical averages. De Rosario will likely pass Buddle while he is playing for the United States in the World Cup, but if both can stay in top form we may get to see two of the best single season goal scorers duke it out for the boot.

MLS Predicted Finish: June 1, 2010

Predicted Finish as of June 1, 2010 (click to enlarge)

It's been several weeks since my last post, so there's a lot of movement and catching up to do.

Galaxy Domination Continues

Since I last wrote, the Galaxy have picked up another two wins and a tie. One of those wins, a 2-0 defeat of then second ranked Columbus, was accomplished without the duo of Buddle and Donovan. Overall the team's projected goal differential and point totals have come down just a bit, but are still on pace to shatter the records in each category in the 15 year history of MLS.

The Galaxy have now played slightly over a third of there season and have yet to be defeated. They looked very good in their first game without their World Cup players. Is this team good enough to go undefeated?

Real Salt Lake is proving Championship was not a fluke

I was one of the biggest detractors of RSL's championship last season. I am not a fan of the MLS playoff system, where a team playing .500 soccer has a shot to knock off a much better team with one good game. RSL's play, as of late, may be a hint of what they were capable of all last season. Three wins in as many matches has moved them up from fifth to second in this week's standings. Let's see if this run is an aberration or signs of RSL making a push the last 2/3's of the season to prove their championship wasn't a fluke.

West Continues to Dominate

The Western Conference occupies six of the eight playoff spots. New York Red Bulls, with their -4 goal differential, have now dropped three spots since May 10th and are out of the Top 8. The competitiveness of the West is going to make it very hard for the bottom two teams, Chivas USA and Seattle Sounders FC, to make a move into the playoffs. According to Sports Club Stats, the bottom six teams each have less than a 20% chance of making the playoffs. Four out of those six clubs are from the Eastern Conference.

Seattle's Sophomore Slump Continues

The most popular franchise in the league, at least by home attendance, has had a very disappointing start to its second season. In it's last three league matches it has gone 1-2. Not even a dominating 3-0 win in a friendly against Boca Juniors could get the team in the right frame of mind, as they followed it up with a 1-0 loss to Colorado. That loss dropped their chances of qualifying for the playoffs down to 13.5%.

The team's Achilles heel? It's offense. Seattle has the third lowest goal differential at -5, ahead of only DC United and Philadelphia. They've scored one goal over that three games stretch, but only given up two goals over the same period. As my friendly soccer-crazed bartender suggests, the problem may lay in the coaching strategy. Seattle should be scoring plenty of goals with Freddy Montero and Steve Zakuani, but both seem to be blanketed all the time by opposing defenders. My bartender chalks it up to unimaginative play calling on the part of Sigi Schmid. He may be right. He may not be. I just know that the team better start producing some goals soon if it wants to even threaten for a playoff spot in its sophomore year.

Biggest Movers

Gaining ground: Real Salt Lake (+3), Colorado Rapids (+3), and New England Revolution (+3)

Losing ground: Kansas City Wizards (-5), New York Red Bulls (-3), and three teams at (-2)

Biggest Matches This Week

According to Sports Club Stats, the following matches will have the biggest impact on teams' playoff chances:

• New York Red Bulls vs. Houston Dynamo
• New York Red Bulls vs. Chivas USA
• FC Dallas vs. San Jose Earthquakes
• Chicago Fire vs. Philadelphia Union

Tomorrow I will provide an update on the Golden Boot race and where it sits versus MLS goal scorers of season's past.