I have heard broadcast play by play announcers discussing on-base streaks. As you might imagine, it is much easier to earn your way on base than just by a hit. This list is a bit out of date, but the top remains the same. Twice hitters exceeded 70 games in a season. Joe DiMaggio set a record of 74 in 1941 as part of his hitting streak. Ted Williams blew that away in 1949 with an 84 game streak. I don’t think many people were award of the records at the time, as hits were paramount. Drawing a lot of walks can be detrimental to a hit streak, but they are great if you are trying to generate an on base streak.
The second thing I heard was in a recent Yankees broadcast, where they talked about Juan Soto providing protection for Aaron Judge by being on base so many times in front of him. I actually did a graphic about this at ESPN in 1992. George Bell joined the White Sox at season, near the end of his career, and he was driving in a lot of runs. Robin Ventura and Frank Thomas were batting in front of him, clogging up the bases. Bell saw the most runners on base that season, so opponents could not pitch around him. Bell was still good at generating power, and that led to lots of RBI. The takeaway is that there is more than one way to protect a power hitter.
The James ranking is more conservative, and I believe rightly so. How can you rank a pitcher or batter among the very best after just a couple of months of duty? Skenes’s rise was indeed impressive, but the league did not have a chance to adjust to the youngster.
Halfway through August, the meteoric rise has stalled. Today he ranks 80th. His last three starts don’t look all that legendary, good, but not great. He produced a 4.15 ERA in 17 1/3 innings, walking eight batters. He struck out batters at a good rate, but not exceptionally good.
The James ranking found a level that Skenes could sustain. I suspect the young star will adjust himself, and keep rising. For now, he appears to be where he belongs.
With two out in the bottom of the eighth inning, none on, in game one of the doubleheader between the Angels and the Yankess, LAnaheim manager Ron Washing issued an intentional walk to Aaron Judge. Here’s the data since 1974 on what base situations lead to an intentional walk:
Base Situation
Intentional Walks
000
140
001
134
010
27655
011
233
100
7818
101
1587
110
20893
111
3
1974 through August 6, 2024
The base situation corresponds to the three bases from the catcher’s perspective, with third base on the left and first base on the right. A one indicates the base was occupied.
So the IBB with the bases empty is on par with a man on first, but Judge’s recent collection of bases empty walks brought that situation a little farther ahead.
Justin Steele of the Cubs pitched a complete game two-hitter Friday afternoon to help defeat the Angels 5-1. He walked two and struck out seven.
That brings the complete game total for the season to 17. I thought that might be pretty good, but the CG rate is down again. The seventeen complete games came in 2621 starts, or in 0.64% of starts. Last season produced 35 CG, which worked out to 0.72%. That was down from 36 CG in 2022. CGs may disappear from the game faster than triples.
Steven Kwan of the Guardians went three four four Thursday afternoon to raise his batting average to .367. He also raised his BABIP to .379. One of those hits went for his eighth home run of the season. He hit eleven in total during his first two year in the majors.
Kwan right now provides a good example of how batting average is a combination of BABIP and what I call BABnIP, batting average on balls not in play. BABIP is approximately your BA if you never homer and never strike out (not quite, because BABIP includes sacrifice flies in the denominator). How runs raise your BA above your BABIP, strikeouts know your BA down. BABnIP is simply HR/(HR+K). What a batter should want for a higher BA is a BABnIP is higher than his BABIP.
Kwan struck out 21 times this season, giving him a BABnIP of 8/29, or .276.
Note that in 1941, Ted Williams owned a BABIP of .378. That season, he hit 37 home runs and struck out 27 times for BABnIP of .578. Power and contract is a rare skill, and it’s the big reason he was the last .400 hitter.
We have an odd situation in the AL. The Guardians own the best winning percentage at .653, but they are half a game behind the Yankees at .650.
I love these situations as it provides a moment to explain an important point in judging the standing of teams. First place is based on winning percentage, not on games back. Games back is a measure of the difference in games over .500. In almost all cases they agree on the ranking.
If you look at winning percentage as a long-term outcome, the Guardians would win 106 games at .653, the Yankees would win 105 games at .650. That’s why the Cleveland should be considered as having the best record in the AL.
Games back is 1/2*(Difference in games over .500). It’s a chase number. Right now, the Yankees are 24 games over .500 (52-28) while the Guardians are 23 games over .500 (49-26). 1/2(24-23) = 1/2. This came about because the Yankees played five more game that Cleveland. If the Guardians just made up the five games before the Yankees played again, we’d expect them to go 3-2 (.600) , gaining three half games for each win and lowing two half games for each loss, and the teams would be tied.
Andrew McCutchen hit the 50th triple of his career as his Pirates beat the Rays 4-3 on Saturday. For McCutchen it was a long wait. His 49th triple came on 4/7/2021. In between he played 446 games with 75 doubles, 66 homer runs, but no triples. Congratulations to McCutchen on holding on long enough to reach that milestone. It turns out that since 1920, not too many players hit 400 doubles, 50 triples, and 300 home runs. While there are a lot of Hall of Famers on the list McCutchen is closer to the ones who would be in the Ha
I really like how this captures the difference between Jose Altuve and Luis Arraez. Both keep their bats in the strike zone a long time (slow late acceleration). Altuve, however, gets the bat moving quickly at the beginning, and it looks like that allows him to generate more power.
MLB details new StatCast technology that measures bat speed. One of my favorite graphics here is the list of fastest and slowest average swing speed, and how both sets are full of good hitters:
Oh, no: Another reason that Statcast doesn’t respect Arraez, right? Not quite. Slower doesn’t always mean worse; sometimes it just means different, in the same way a pitcher with a below-average fastball might still find a way to succeed.
So why does any of this matter? After all, it’s not like very many people would prefer Stanton over Steven Kwan in their lineup, right? It’s sort of like fastball velocity, where you’d obviously prefer to have it than not have it — and in the aggregate, it’s much better to have it — but throwing 98 mph doesn’t automatically make you more productive than someone who throws 92. It’s a tool, not the answer.
Still, the data makes it pretty clear. If you’re not an outlier unicorn in terms of bat control like Kwan or Arraez, you’d probably like to swing hard if you could.
MLB.com
There are hitters who are known for keeping the bat in the zone longer, and they tend up to contact hitters. They start their hips to get their body moving, but they commit their hands very late. This allows them time to correct their swing if they misjudged the pitch. I’ve heard Tony Gwynn and Derek Jeter described this way, but I suspect hitters like Ty Cobb, Joe DiMaggio, Pete Rose, Rod Carew, and Wade Boggs fit the mold as as well.
If you look at this graph at Baseball Savant, what you see is that while Arraez’s swing is slow, he squares up the ball better than anyone. The graph also makes clear why Juan Soto is go good, as he combines bat speed with the ability to square up the ball.
It will be nice to see what that graph looks like when we have a couple of thousand of swings for each batter.
In looking at MLB batter splits for this season, two things stand out to me. The first is that the composite batting order is rather well constructed. The major put a lot of on-base percentage at the top, and given the stats so far, the fourth hitter is better than the third hitter in both OBP and slugging percentage. That makes sense, as the fourth hitter serves a dual role of cleaning the table, and setting the table for the rest of the order. After the fourth hitter, there is a steady decline in OBP and slugging. The worst hitters still bat ninth, and they are pretty awful this season.
The other thing that stands out is that designated hitters are the best hitters by position. That really hasn’t been true during the history of the DH, even though the defensive spectrum would predict that. It’s possible that with the universal DH, teams and players finally adopted the idea that it’s a real position, rather than a place holder for someone injured, or someone who needs a day off from the field.
It struck me that the six runs the Padres scored on fourteen walks Sunday night against the Dodgers seemed low. Looking at all games from 2021 on, the linear regression provides the formula runs = (0.55 * Walks) + 2.73. So normally we would expect 10 runs scored in such a game. For the most part, that has not been the case. In that time there were four games with 13 or 14 walks, and the runs scored in those games were 4. 5, 6, and 7. There was also a 17 walk game that led to 17 runs. This makes me wonder if sometimes high walk games are more about the defensive use of the outcome, walking tough hitters to reach one who are easier to put out.
Major League Games produced five shutouts on Monday. Days with lots of shutouts do seem to be connected to weather. In the 30 team era (1998-on), Sept-Oct produced 22 days with at least five shutouts, March-April 18, with May third at 17. Of the summer months, July produced 14 such days, August 12, and June 10.
This begs the question, how do you avoid extreme parks? Do you not allow teams to play at altitude? Mandate 30 foot fences in the outfield? Deaden the ball?
What if new buildings change the character of your static park? This happened to Wrigley Field. Before the NL built a number of new, fairly neutral stadiums in the 1960s and 1970s, Wrigley wasn’t that extreme. Then the Mets, Dodgers, Pirates, Reds, and Cardinals, and Giants all moved into stadiums that tended to favor pitchers, so Wrigley suddenly was an outlier.
A big part of the Cubs failure to win a World Series for so many years simply came from other teams lowering the bar for having an extreme stadium!
Teams do tinker with stadiums a lot more than in prior years. The best example recently was Baltimore moving fences back to prevent home runs. I suspect we’ll see more of this. It’s another way to suppress offense that MLB needs to counter.
Tom Tango uses data on the position of the left wrist of catchers to infer how the backstops set targets for various pitches. This first post in a series deals with inside pitches, and the differences in targeting are small compared to the difference in ball placement up and down.
I could this being useful to broadcasters. It would be fairly easy to build a model for each catcher, or even each catcher/pitcher combination. Then, if an analyst says, “He wanted that pitch up!” it would more likely be true.
One could also build reports on how often pitchers hit the intended targets, which I suspect would be very useful in evaluating talent, both for the future, but in season and in game as well. Along with spin rates, FIP, and barrels, hitting the target could add to the valuation of free agents. Within a season, target deterioration could indicate an injury before it becomes serious. Within a game, target deterioration might be a better indication of when to lift a pitcher rather than third time through the order.
For a while I thought it was possible to make an improvement to the Beat the Streak Picks by determining the current probability of the hotness or coldness of a hitter. It strikes me as a hidden Markov model (HMM). The idea would be to assign one of three states to a player at a given time; cold, normal, hot. Since it is difficult to know the current state of the player, these hidden states make up the hidden part of the model. On each sequence (a game), the model emits an observation, in this case, the quality of the game.
For example, if you are in the normal state and have a normal game, one would postulate that the player stayed in the normal state. But a high quality game or a low quality game might signify a transition to one of the other states.
Efficient algorithms exist to learn the probabilities of transitioning from one state to another, and also the probabilities of a particular observation given the current state. To train these models, however, we need games that are tagged with a good representation of the state.
Tagging can be difficult, however. One way would be to hire people to look at a game log for a player and find the hot, not, and normal areas of the sequence. I tried that myself, and found it rather difficult to eyeball.
Instead, I used my version of an offensive game score to do the tagging. I looked at a six day sequence going forward from a particular game and took the average game score. Average game scores less than 46 were considered Cold. Average game scores greater than 56 were considered Hot. Those in between were considered normal.
I ran the tagger for six players and generated a series of averages based on the state to see if the tagger worked decently. Here are the results:
There are four types of hitters represented here. Freeman and Trout are superstar batters. Owen and Bradley were known more for their defense, and they are seldom hot. They are in fact cold as much as they are normal. Ken Phelps is the power hitter who walks a lot. His profile is similar to the defensive specialist, seldom hot but very often cold. Finally, Arraez is the great hitter with little power, and the lack of power keeps him from being hot often. He is seldom cold, however.
Note that for each player, the hot state is associated with a low strikeout rate, while K rates don’t vary that much between normal and cold. It would seem that in hot states players are seeing the ball well and really driving it.
The column I’m most interested in would be the last one, percentage games with a hit. Note how even the weak hitters are well over 80% when they are hot. If one is trying to choose between Arraez and Freeman on a particular day, knowing if one is hot might make a big difference.
So the idea would be to used this automated tagging to train an HMM. Use the HMM to figure out the probability of a player being hot at a particular part of time, then train a new neural network to take advantage of that parameter.
Tom Tango compares the distributions of swing speeds for Luis Arraez and Ronald Acuna Jr. Arraez swings his bat much slower than Acuna, but for each they are most effective at the higher speed end of their distributions. As you might expect, Arraez makes more contact than Acuna, but Acuna’s power makes his high speed swings more valuable.
Tango:
That’s why you can’t just look at swing speed on its own: it really needs to be evaluated based on that batter’s swing distribution.
TangoTiger.com
This is also a very good example of how there are many ways in baseball to be successful. The consensus today seems to be that every hitter needs to be like Acuna. Therefore, one would think that some smart team might sign a bunch of Arraez like players cheaply and win. (See the Cardinals of the 1980s.) It could be, however, that those players are few and far between, since youngsters are taught to swing like a power hitter.
It’s not clear how we get to a better mix of Acunas and Arraezes. I think it would be a more interesting game if we did.
An old friend asked me over the weekend if Albert Pujols set a record for consecutive games without a triple, or if he set it for the end of a career. A couple of days testing queries resulted in this spreadsheet, which list every player with a tripleless streak of at least 300 games, all streaks starting from the 1920 season on.
Pujols did not set a record in either case. His streak of 977 games without a triple is the fourth longest in the time span, and the second longest to end a career. Mark McGwire holds the record with 1389 games. He tripled on June 20, 1988, and didn’t triple again until August 2, 1999. Paul Konerko is second with 1215 games. Third, and owning the longest streak to end a career is Victor Martinez at 981 games. Pujols is fourth at 977 games. Note that I only counted games in which the hitters earned a plate appearance. I threw out games in which they did not come to the plate.
If you look at the spreadsheet, the First Triple and Last Triple columns are dates with a double header indicator at the end. (0 for a single game, 1 for the first of two, 2 for the second of two.) If the Last Triple date starts with a 2200, that indicates the streak ended with the player’s career or the streak is still active. For example, Josh Donaldson is climbing the ladder at 742 games, ranking 11th all time. If the indicator ends in a 99, that’s was the start of the player’s career.
Note that among the streaks of at least 700 games, almost all of them started in the 21st century. It’s not until the streak get below 600 that you start seeing players from the pre-division era. I am fairly confident that the top 20 is really the top 20 of all time. Triples have been in constant decline, so the streaks keep growing.
I hope you enjoy pursing the list. You’ll find all three Molina brothers and both Giambi brothers. Cecil and Prince Fielder make the list. I was surprised to see Aaron Judge with a current streak of 440, because Judge strikes me a fast. John Olerud, a great doubles hitter, didn’t seem to try to stretch those hits.
The Bill James Pitcher Ranking provides a way to look at how much a particular pitcher dominated during his tenure in the majors. The following table show most days in first place during a career since 1940* during the competitive part of the year, April through October:
If Cole produces another dominant season in 2024, with 180 days in first place, he moves up to fourth on the list.
Note that many of the pitchers on the list are rather modern. Two reasons come to mind on this front:
Baseball became better over time at preventing injuries, especially serious shoulder injuries. Even with all the elbow blow outs, many good pitcher returns from TJ and pitch well.
It may be easier to be dominant during a high offensive era, as most pitchers get knocked around. See the long term domination of Clemens, Maddux, Martinez, and Johnson during and just after the PED era.
That makes Koufax’s domination even more impressive. A major injury shortened his career, and he pitched in a relatively low offensive era.
Keep your eye on Cole. He may wind up very close to the top of this list.
Major League Baseball, after consulting the Elias Sports Bureau, said Wednesday the score reverted to 1-0 under 7.02 (b) (4) (A) of the Official Baseball Rules, which deals with suspended games.
“If one team is ahead, the team that is ahead shall be declared the winner (unless the game is called while an inning is in progress and before the inning is completed, and the visiting team has scored one or more runs to take the lead, and the home team has not retaken the lead, in which case the score upon the completion of the last full inning shall stand,)” the rule states.
ESPN.com
I am awaiting an update to the Day by Day Database. If I were the commissioner, I would have let the game stand as a no decision with the top of the ninth’s stats counting.
Davis Schneider of the Blue Jays went one for two with two walks Wednesday afternoon to stay hot in his rookie season. He raised his batting average to .426. Given his statistics so far, he should have 94 AB if he plays all 28 of the Blue Jays remaining games. So 57 for 141 give him a .400 BA, or 37 for his last 94. Note that the highest number of AB for a .400 hitter since Ted Williams in 1941 is 134 by Bob Hazle in 1957, who went 54 for 134 for a .403 BA.
My very conservative estimate of Schneider’s probability of hitting .400 is 0.014. (.301 Is the highest batting average that has 20 hits as the highest end of the 95% confidence interval.) Maybe he’ll be the lucky one.
Harry Lewis, one of the best reasons to go to Harvard, and Kasey Uhlenhuth discuss the life of Arthur Augustus Johnson in Harvard Magazine. “Fats” Johnson, as he was known, developed one of the best Negro League teams in the Boston area, the Tigers:
As early as 1912, Johnson—an athletic 5’11”, 180 pounds before he earned his nickname—was playing baseball while off duty in Boston. The “Great Migration” of Southern blacks was bringing more African Americans to Roxbury, where several ball fields were available to all-black teams.
A decade later, Johnson was managing and promoting Boston’s most successful black baseball team, the Boston Tigers. He lined up opponents across New England and even in Canada. The “money man” for the team, he handled the business side of the games. The team was never fully professional, but as an allegedly amateur team, it could play games and collect receipts on Sundays, when professional games were banned. “Oh for the good ole Boston Tigers days when ole Carter Field was the haven of many a baseball classic,” “Sheep” Jackson told the Boston Chronicle in 1942, referring to what is now a Northeastern University athletic facility on Columbus Avenue.
Johnson made the transition from Pullman porter to baseball impresario with the help of connections he made at Harvard, where he became a celebrated figure for reasons unrelated to baseball.
HarvardMagzine.com
He also did a great business supplying Harvard undergraduates with liquor during prohibition. It’s a great story of a man who saw opportunities for business and seized them.
I also noticed in the latest issue of the magazine that a classmate of mine, Bruce Schoenfeld published a book on the rise of analytics in sports. Game of Edges is available at Amazon.
With Bill James Online going offline soon, Bill James graciously gave me permission to bring the Bill James Starting Pitcher Historical Rankings up to date. Both that and the rank logs will be updated on a daily basis. Thanks very much to Bill for the creation of this ranking system and allowing me to display the results.
Why are we still doing league stats? Justin Verlander of the Astros allowed four earned runs in five innings to the Marlins Wednesday night, and his ERA in the box score is listed as 4.50. His ERA for the year, however, stands at 3.36. If he had been traded inside the NL, that is the number we would see.
For most of baseball history, it made sense to separate stats by due to a players changing teams. Up until the late 1990s, the NL and AL never faced each other, so the stats reflected what went on within those disparate groups. In addition, the NL and AL played different styles and used different umpires. When the leagues added awards one would want to decide based on what players did in the league.
The designated hitter exacerbated the difference, especially for pitchers. Even when interleague play started, there were so few of those game that it made little difference, and the persistence of the DH really did make the league different.
That is totally blown away now. There is a universal DH. Every team in one league plays every team in the other league. The American League approach of power offense has now supplanted the NL approach of small ball. There is no difference between playing in the NL and playing in the AL today.
The only thing left is the awards, but are there really league awards when a over a quarter of the season is played against the other league? Maybe it’s time to admit we have a one league game, and adjust accordingly. One MVP, one Cy Young, one Rookie of the Year, and the stats in the boxes are always the total for the season.
Tom Tango notice that the Cy Young points for the league leaders were rather low this season. Here’s the lowest score total by the league leaders in full seasons since 1920:
Tom Tango starts work on quantifying swings and misses by pitch, but also by the reason for the swing and miss. One of the nice things is that the data matched expectations. Check it out.
“So we have to study that data now and decide where’s our right fielder’s going to play; here’s where our left fielder’s going to play. That’s what we do. There could be a more machine-oriented version of studying that to say, ‘Actually, for this pitcher, for this hitter, the right balance is actually here because of the way he throws his fastball, or because of the way he throws his breaking ball.
“There’s ways that we can’t even comprehend that’s so multi-dimensional. That could be how (AI) works in the future.”
