Golf Analytics

How Golfers Win

Tag Archives: billy horschel

How Real are Hot Streaks in Golf?

Whenever a golfer goes on a high profile hot streak – think Rickie Fowler since June, Billy Horschel for the FedEx Playoffs, Henrik Stenson at the end of last year – there’s always a ton of talk in the media and among fans about how their new swing/putting stroke finally clicked, or that player is returning to form, or they’re finally mature enough to win, etc. Humans love writing narratives to explain why things happen. The end result of all that talk is that a guy in the middle of a hot streak is considered to be much better than they would’ve been considered before the hot streak. No one thought Billy Horschel was deserving of a Ryder Cup pick a month ago, but now everyone thinks we should toss Webb/Mahan off to make room for him. No one thought Rickie Fowler was one of the 1-2 best American players in May, but now that’s almost assumed. Everyone around golf seems to think that hot streaks are real – that they actually predict who’s going to continue to play well. In this post I’ll provide evidence that shows that hot streaks are retained to a small degree – even months later – but that extreme performances still regress strongly to prior expectations.


I settled on using five week periods to measure performance. My sample was everyone who had recorded at least 8 rounds in a five week period and then recorded at least 8 rounds in the next five weeks. All my data is from the 2011-2014 seasons. The actual metric I used to measure performance was my z-score ratings, which are basically strokes better or worse than the field adjusted for the strength of the field. I compared each player’s z-score over that five week sample to my prior z-score rating. I have a prior rating for every player in my sample generated each week which mostly uses prior performance and very recent play to predict how well a player will play that week. They’re designed to be the most accurate prediction of performance. I subtract the prior expectation from the sample performance to get the change in performance which I’ll call the Initial Delta.

So my metric looks like this:

(Sample performance over 5 weeks) – (Prior expectation) = (Initial Delta)

I generated an Initial Delta for every player who qualified for my sample, generating over 27000 separate data points.

I then calculated a Subsequent Delta for every player using the same method only using the next five weeks as my Sample performance and the same Prior expectation used above (meaning I don’t consider any recent results). I then compare the Initial Delta to the Subsequent Delta. If players get hot and stay hot, the two should be strongly correlated. If whether a player has been hot or cold does not predict their subsequent performance, the two will not be correlated.

tl;dr of the above is I’m comparing how much better/worse a guy played over the first 5 or 10 weeks to how much better/worse he played over the next 5 weeks.


The results show that in general players retain only a small portion of their over or under-performance. Overall, about 20% of the Initial Delta is retained over the next five weeks. This means that if Billy Horschel played 1.8 strokes better than expected over the last five weeks, he should be expected to play about 0.36 strokes better than previously expected in the next five weeks. Now, 0.36 strokes is a large amount, but it’s not enough to bring him up to Bubba/Fowler/Keegan’s level (here is an example of the distribution of talent among the top 50 in the world). Right now, he should be considered slightly better than Mahan or Webb, but not to some ridiculous amount and certainly not to any degree that’s going to effect the outcome of the Cup.


Looking Further Ahead:

The above shows that hot streaks can be retained to some degree over a short period of time, but how much is retained further down the road? Is Billy Horschel going to be able to retain any of that ability he showed to win the FedEx Cup going into next season? I set-up the same study as above, only instead of looking at performance in the next five weeks, I looked over the next four months (16 weeks to be precise). Everything is calculated the same, though I only included players with at least 20 rounds over that four month span.

The results here showed that about 18% of the Initial Delta is retained over the next four months, a similar amount to what is retained over the next five weeks. Golfers who play significantly better than expected over five weeks should perform better than previously expected, but only to a small degree. To give you a sense of when recent performance becomes mostly insignificant, if a player performs 0.5 strokes better than expected over five weeks (basically what Chris Kirk has done in the FedEx Cup Playoffs), he is expected to retain only around 0.1 strokes (which is insignificant, basically a rounding error in predictive terms).


Adjusting Expectations:

I’ve attached a list of the top and bottom ten guys who have most over or under-performed over the last five weeks (PGA/European Tour only).


Obviously Horschel is at the top along with some FedEx Playoff stalwarts like Palmer/Fowler/Day. Ryder Cupper Jamie Donaldson has been killing it over in Europe as well. Among the trailers, Phil’s name sticks out like a sore thumb. The US team has to hope his multiple weeks off can help him rediscover his game before the next week. Probably the most terrifying thing is how close Ryan Moore came to making this team – he finished 11th in points, but was only a stroke away from jumping Zach Johnson in points at the PGA Championship. Moore is dead last of 339 pro golfers in terms of his performance relative to expectation.

The Most Overrated Golfers at the US Open

Golfers get overrated in Majors by the media in very predictable ways; good not great players who win Majors will be permanently over-hyped in subsequent events (Graeme McDowell), elite guys will still get a ton of attention even when their careers have taken them from the top to merely very good (Phil Mickelson), and a guy who comes out of nowhere with a good tournament will still receive attention a couple years later even though they’re not good (Ricky Barnes). Below are a few players who are being given entirely too much attention this week.

Billy Horschel:

Horschel was a great collegiate golfer at Florida, but stumbled around on the PGA Tour his first few years playing well below Tour average. Last year he supposedly arrived, riding an anomalous putting fueled surge to his first PGA Tour victory and a T4 at the US Open at Merion. Horschel faded fast down the stretch though; he had one top ten in thirteen post-US Open events in 2013. Horschel’s season so far hasn’t been particularly inspiring  – he’s 87th in the world by my numbers – though I’ve seen people claim his T15/T6 the last two weeks are signs of him rounding into form. He’s the classic case of a guy putting out of his mind for a few months and then losing the “magic” completely. He had never posted a strokes gained putting season better than average before putting up an awesome +0.60 in 2013 up to the US Open. He’s been exactly average since.

Horschel doesn’t exactly fit into the Ricky Barnes role of contending in their first Major and struggling to stay on Tour two years later because he’s a bit better than Barnes ever was, but a guy of Horschel’s ability will top ten at a Major only once every four years or so. He’s going off at 80/1 – possibly the worst bet on the board.

Graeme McDowell:

G-Mac’s victory at Pebble Beach placed him permanently on the list of guys who have “it” to win US Opens, whatever that “it” is. There’s a huge portion of the golf media that basically think an accurate driver with a solid all-around game like McDowell is the perfect antidote to the deadly US Open rough. Like I showed in my post Monday, that has no statistical support. Golfers certainly play poorly out of US Open rough – worse than on a generic PGA Tour set-up – but many US Open venues also are very long, requiring more >175 yard approach shots than normal aimed at fast and firm greens. It’s an advantage to avoid the rough, but not if it also means facing 20 yard longer approach shots to impossible greens.

McDowell was heavily touted going into Merion last year for the above reason; in the Open he hit 61% of his fairways, but finished +13 and MC’d. This year’s course doesn’t set-up any better for him – it’s ~25 yards longer/hole than Merion – and he’s going off at 50/1 instead of the 20/1 last year. G-Mac has the 28th best aggregate performance since 2012, but is going off at lower odds than Schwartzel (19th), Stricker (6th), Poulter (22nd), Haas (23rd), and Bradley (20th).

Phil Mickelson:

In many ways this week is about Phil and should be about Phil. He’s the only guy other than Tiger to tee it up for his first crack at the career Grand Slam since Ray Floyd played the British in 1986. What he’s accomplished is awesome and I’m glad his first crack will come without the oxygen stealing Tiger Woods show around. All that said, Phil can’t be considered the favorite to win this week and he’s probably not going to win. He’s declined a lot due to age from his early 2000s peak as one of the three best in the game. Right now, he’s more like the 15th best by my numbers.

That’s to be expected though; my aging research has shown that guys lose a lot of ability from 35 to 44 (Phil’s decline has been typical in this regard). That decline is largely concentrated in less driving distance and diminished iron play – both things Phil has suffered in the past two seasons. Curiously, Phil has posted two extremely anomalous putting seasons to go along with that decline in his long game. That hasn’t continued into this season. His season hasn’t been bad or disappointing this year, but it hasn’t been up there with the rightful favorites – McIlroy, Scott, or Bubba.

Phil’s only silver lining is that he typically over-performs his aggregate talent level in the US Open. Since 1999, Phil’s played around 0.5 strokes better per round in the US Open than in all other PGA Tour rounds. You can credit his preparation, focus, “clutch” ability, or randomness. Whether this represents reality or not, I can’t say for sure. It’s unlikely a player would perform that much better over 15 years of rounds just due to randomness, but that doesn’t mean Phil will continue to outperform his aggregate performance going forward. Only if you credit him for his full value of over-performance does Phil come close in expected performance to the favorites.

Regardless, so much of the touting of Phil by the media this week is total wish-casting. The media loves the idea of Phil winning, mainly so they can bask in the attention of the sports mainstream which will have its attention on the NBA Finals/World Cup without Tiger competing. Phil is actually more likely to miss the cut than he is to complete the career Grand Slam this week.

What’s Changed? – Billy Horschel

One of the most significant stories on the PGA Tour this year has been the emergence of Billy Horschel as one of the best golfers week in and week out.. After racking up only three top-tens in his first two largely mediocre seasons on Tour, Horschel’s earned a top-ten in seven of seventeen starts this year, missing only a single cut along the way, and earning his first Tour victory in New Orleans. His arrival to the general golf public came at the US Open where he was in the final group Saturday and finished T4.

The incredible thing about Horschel’s emergence has been how poor he played in his first two years on Tour. He entered the Tour in 2010 through Qualifying School after a brilliant collegiate career at Florida, but made only four starts due to an injury. He re-earned his card in Qualifying School again, but had a poor year (+0.14 by my Z-Score Method & only 140th on the Money List). His conditional status in 2012 only allowed him to finish 147th on the Money List (-0.12 by Z-Score for PGA and rounds), but he managed to again qualify for the Tour in Q-School. So through two full seasons, he had shown himself to be roughly PGA average. In 2013, though, he’s played to -0.50 – the 18th best performance in the world.

While it’s not completely unheard of for a player to improve as much as Horschel did, it is very rare. Horschel’s improvement from 2012 to 2013 was -0.39 standard deviations. That is the 19th largest improvement from one year to the next in the last five seasons, from a sample of over 800 pairs of seasons (I restricted my examination to golfers with 50+ rounds in each season). Many of the improvements ahead of him are from golfers with established high levels of performance regaining form, such as Jim Furyk in 2012, Adam Scott in 2010, Sergio Garcia in 2011, and Angel Cabrera  this season. Whether due to nagging injury, personal trouble, lack of focus/preparation, etc. those guys fell from performing at a high level, but were able to regain their form the next season. Other golfers went from being extremely bad (below Tour average), to just mediocre. Much rarer  are the genuine breakthroughs where a golfer goes from being quite average to very good. Among those ahead of Horschel, only Webb Simpson in 2011 improved from average or better to playing elite level golf.

So how is Billy getting it done? What has he improved on since last season that has allowed him to earn the top 10s and maiden victory? To examine this I’m going to use what I’ll refer to as Component Stats. These are stats measuring how well a player scrambles, drives the ball, hits approach shots, and putts. To measure performance, I’ve created three of my own stats plus I’ll be using the publicly available Strokes Gained – Putting. For the other three, I’ve already introduced Adjusted Scrambling and I’ll be introducing my Approach and Driving stats in the next few weeks. For now, just remember that the stats are measured in strokes above and below the field and try to isolate how well a golfer is performing in one area by adjusting for distance of shot, starting position, and what happens in subsequent shots.

By this method, in 2012, Horschel was only substantially better than PGA Tour average at driving – where he gained nearly half a stroke on the field. He was average at scrambling, slightly below average at putting, and slightly above average at hitting approach shots. In short, he was much like dozens of other Tour golfers who survive because they’re very good at one skill and good enough at everything else. What separates the elite from those golfers is the elite only have one weak spot in their game. Of the best 25 golfers by Z-Score in 2012, only Robert Garrigus ranked below average in more than one of the four statistical components. Only three of the top 50 (Ben Curtis and Lee Westwood also) ranked below average in more than one category. As long as Horschel could only rely on his driving, he was not going to be able to distinguish himself.

I have no particular insight into what Horschel changed in his preparation in 2013; people have credited maturity gained from working with a sports pyschologist. What I do know is that Horschel has delivered far better performances putting and hitting approach shots this season. His Strokes Gained Putting has improved from -0.09 to +0.50 strokes this season – one of the largest improvements year-to-year – and improved by almost a half a stroke on approach shots; a total improvement of a full stroke. Horschel’s driving has remained well above average, and though his scrambling has regressed by 0.20 strokes (he’s only successfully scrambling 59% of the time despite putting lights out overall and hitting from closer lies), that hasn’t hurt him much.










All in all, Horschel’s improvement has been worth 2/3rds of a stroke. A to-be-posted regression analysis shows that golfers a stroke better than PGA Tour average earn ~$65,000/tournament more than average golfers or about $1.5 million over a typical season, just to provide a financial benchmark to evaluate his improvement.

The question now is whether Horschel can maintain his performance going forward. My research has shown it’s correct to regress samples of around half a season by adding 25 rounds worth of average performance. That would expect Horschel to perform at around -0.36, equal to something like the 35th best player in the world. My weighted and regressed two year Z-Score method predicts something similar. However, if Horschel has made genuine changes to his preparation and mental approach to the game, we may not be seeing a golfer playing above his head, but rather one pushing his ceiling higher.