1
00:00:02,254 --> 00:00:04,742
Today I am joined by Jacob.

2
00:00:07,874 --> 00:00:14,957
Buffa, the senior director of performance science and player development for the Houston
Astros.

3
00:00:14,957 --> 00:00:18,389
Growing up with a deep -rooted passion for sports in St.

4
00:00:18,389 --> 00:00:29,974
Louis, Missouri, Jacob's journey from aspiring baseball player at Missouri State
University to leading player development and performance science is nothing short of

5
00:00:29,974 --> 00:00:30,625
inspiring.

6
00:00:30,625 --> 00:00:37,898
Jacob discusses the critical role of nutrition and conditioning in athlete development,
emphasizing the innovative

7
00:00:37,898 --> 00:00:47,076
of education and visual communication tools to help athletes understand how their dietary
choices impact performance.

8
00:00:47,076 --> 00:00:59,306
He also explains how Bayesian stats play a pivotal role in analyzing player performance
and managing injury risks, and delves into how complex concepts like Bayesian analysis are

9
00:00:59,306 --> 00:01:02,769
communicated effectively to coaches and players,

10
00:01:03,662 --> 00:01:08,782
they understand the uncertainties and limitations of the models used.

11
00:01:08,782 --> 00:01:18,482
Finally, Jacob and I discuss emerging trends in baseball science, such as biomechanical
analysis and the application of computer vision algorithms.

12
00:01:18,482 --> 00:01:25,342
This is Learning Basics Statistics, episode 114, recorded June 20, 2024.

13
00:01:27,884 --> 00:01:36,039
Welcome Bayesian Statistics, a podcast about Bayesian inference, the methods, the
projects, and the people who make it possible.

14
00:01:36,039 --> 00:01:38,201
I'm your host, Alex Andorra.

15
00:01:38,201 --> 00:01:42,243
You can follow me on Twitter at alex -underscore -andorra.

16
00:01:57,452 --> 00:01:58,272
like the country.

17
00:01:58,272 --> 00:02:02,504
For any info about the show, learnbasedats .com is Laplace to be.

18
00:02:02,504 --> 00:02:09,686
Show notes, becoming a corporate sponsor, unlocking Bayesian Merge, supporting the show on
Patreon, everything is in there.

19
00:02:09,686 --> 00:02:11,596
That's learnbasedats .com.

20
00:02:11,596 --> 00:02:21,949
If you're interested in one -on -one mentorship, online courses, or statistical
consulting, feel free to reach out and book a call at topmate .io slash alex underscore

21
00:02:21,949 --> 00:02:22,630
and dora.

22
00:02:22,630 --> 00:02:24,140
See you around, folks.

23
00:02:24,140 --> 00:02:26,013
and best patient wishes to you all.

24
00:02:26,013 --> 00:02:33,126
And if today's discussion sparked ideas for your business, well, our team at PIMC Labs can
help bring them to life.

25
00:02:33,126 --> 00:02:35,589
Check us out at pimc -labs .com.

26
00:02:39,022 --> 00:02:47,102
Hello my dear fans, I'm coming to you with fantastic news because Learn Based Ads is going
live.

27
00:02:47,102 --> 00:02:52,042
We're indeed going to have the two first live shows of Learn Based Ads history.

28
00:02:52,042 --> 00:02:57,652
It's going to happen very soon in Stankham 2024 in Oxford, UK.

29
00:02:57,652 --> 00:03:00,302
We're going to have two panel discussions.

30
00:03:00,302 --> 00:03:08,270
We're going to kick things off amazingly on September 10 with Charles Margossian, Steve
Bronder and Brian Ward.

31
00:03:08,270 --> 00:03:11,470
talking about the past, present and future of Stan.

32
00:03:11,470 --> 00:03:22,970
And then on September 11, Elizaveta Semenova and Chris Wyman are gonna make science look
really cool because we're gonna talk about how Bayesian stats are used in the very

33
00:03:22,970 --> 00:03:26,010
important field of computational biology.

34
00:03:26,010 --> 00:03:37,010
So if that sounds like fun, if you wanna ask us embarrassing questions, if you wanna meet
us in person, if you wanna have exclusive LBS stickers, well, get your StanCon tickets now

35
00:03:37,010 --> 00:03:37,550
and...

36
00:03:37,550 --> 00:03:42,430
Honestly, I can't wait to meet you all on September 10 and 11.

37
00:03:42,430 --> 00:03:44,976
See you very soon, my dear patients.

38
00:03:48,302 --> 00:03:52,184
Jacob Buffa, welcome to Learning Bayesian Statistics.

39
00:03:52,205 --> 00:03:53,786
Hey Alex, how are you doing?

40
00:03:55,147 --> 00:04:01,511
I am doing very well, thank you so much for being on the show Jacob.

41
00:04:01,792 --> 00:04:12,999
So as I said in the introduction, you work for the Houston Astros, which I'm sure the
American listeners know about for non -baseball listeners.

42
00:04:13,800 --> 00:04:16,442
Houston Astros is a big MLB...

43
00:04:16,536 --> 00:04:25,128
team so baseball and thanks a lot actually to JJ Robbie for putting us in contact.

44
00:04:25,128 --> 00:04:31,090
JJ was here on the show damn a few years ago.

45
00:04:31,270 --> 00:04:43,213
I don't even remember the number of the episode but for people curious about what JJ is
doing at the Astros he was not at the Astros at the time but you'll get an idea of what

46
00:04:43,213 --> 00:04:46,442
he's doing he's doing absolutely tremendous job.

47
00:04:46,442 --> 00:04:48,263
in the R &D department.

48
00:04:48,804 --> 00:04:50,324
So yeah, I referred to that episode.

49
00:04:50,324 --> 00:04:57,151
I put in the show notes the link to the sports analytics playlist.

50
00:04:57,151 --> 00:05:02,835
And I'm sure if you're into sports, that's going to be worth your time.

51
00:05:02,835 --> 00:05:12,953
But today we have Jacob with us and I'm having you on the show because you're doing a lot
of different things and your background is actually super interesting.

52
00:05:12,953 --> 00:05:15,745
So yeah, maybe

53
00:05:16,503 --> 00:05:31,085
Tell us what you're doing nowadays, but mainly how you ended up working on these because I
know your path is marked by a passion for baseball, sure, but it was still a bit senior in

54
00:05:31,085 --> 00:05:31,435
random.

55
00:05:31,435 --> 00:05:32,686
So I love that.

56
00:05:33,207 --> 00:05:34,708
Yeah.

57
00:05:34,708 --> 00:05:41,493
So currently I serve as the senior director of player development and performance science
for the Houston Astros.

58
00:05:42,134 --> 00:05:45,736
My path to here was definitely unique.

59
00:05:46,913 --> 00:06:01,480
I played baseball in high school and then actually went to Missouri State University for
baseball as well, but wound up very quickly realizing that I was much smarter than I was

60
00:06:01,480 --> 00:06:02,900
good at baseball.

61
00:06:05,081 --> 00:06:12,324
so wound up actually pursuing an interest in just overall human performance.

62
00:06:12,324 --> 00:06:14,345
I was very passionate about

63
00:06:14,765 --> 00:06:18,719
basically, you know, training to be bigger, faster, stronger.

64
00:06:18,719 --> 00:06:31,069
so, you know, wound up spending a lot of time around the strength and conditioning staff
there, you know, wound up doing some, some internships and really learning as much as I

65
00:06:31,069 --> 00:06:32,751
could actually outside of school.

66
00:06:32,751 --> 00:06:40,757
You know, I chose my, my degree is actually marketing and then wound up adding economics
in there.

67
00:06:40,757 --> 00:06:41,848
But

68
00:06:43,147 --> 00:06:46,320
was never really big on learning like inside the classroom.

69
00:06:46,320 --> 00:06:50,523
It was just something that was not a passion of mine.

70
00:06:50,784 --> 00:07:01,032
So through college, you know, was able to gain a lot of knowledge around just general
kinesiology, strength and conditioning principles.

71
00:07:01,412 --> 00:07:11,949
And actually, I think it was like my junior year, I was approached by a friend of mine
named Denton McRomey, who was like, hey, man, like,

72
00:07:11,949 --> 00:07:17,029
we should start a gym, you know, after college, like that's what we should do.

73
00:07:17,029 --> 00:07:23,449
And actually at first I was like, you're crazy, like starting a business, like that's, I
don't know how to do that.

74
00:07:23,569 --> 00:07:26,589
But he kind of talked me into it.

75
00:07:26,589 --> 00:07:31,379
And so that's, you know, after graduating in 2016, moved back to St.

76
00:07:31,379 --> 00:07:32,669
Louis, Missouri.

77
00:07:32,869 --> 00:07:35,269
And, you know, we had some connections.

78
00:07:35,269 --> 00:07:36,979
We played baseball together in high school.

79
00:07:36,979 --> 00:07:40,379
He went off to play at Rockhurst, but we had some connections in the St.

80
00:07:40,379 --> 00:07:42,017
Louis area with

81
00:07:42,017 --> 00:07:54,852
baseball teams and we wound up leveraging those to be able to start training some kids and
got a building and basically kind of step by step, you know, figured out, you how to do

82
00:07:54,852 --> 00:07:56,563
it, how to run the business.

83
00:07:56,563 --> 00:08:07,347
And one of the things that we did that turned out to be relatively unique there was, you
know, I was very, we were very passionate about identifying what underlying physical

84
00:08:07,347 --> 00:08:11,233
qualities we, you know, were truly being impacted.

85
00:08:11,233 --> 00:08:12,784
to help improve on field performance.

86
00:08:12,784 --> 00:08:24,518
Because deadlifting more or squatting more is definitely important, but there's not
necessarily like a causal relationship to throwing five miles an hour harder.

87
00:08:25,959 --> 00:08:28,640
But there are certain first principles that we're trying to impact.

88
00:08:28,640 --> 00:08:37,273
So this is where I started to learn a lot about force plate research and just general
linear physics.

89
00:08:37,273 --> 00:08:41,325
And we purchased a set of force plates ourselves.

90
00:08:41,399 --> 00:08:48,734
started jumping athletes, really diving into the movement signatures, the force velocity
profiling.

91
00:08:49,395 --> 00:08:57,140
And we started testing guys' bat speed, their throwing velocity, and just started keeping
all this information with players.

92
00:08:57,741 --> 00:09:08,509
And over the course of a couple years, know, wound up, you know, being able to have some
research around why we do what we do, and we're really enjoying it.

93
00:09:08,621 --> 00:09:14,241
And then the Houston Astros in 2019 opened up a job called a performance coach.

94
00:09:14,401 --> 00:09:25,521
And this was traditionally what baseball would call a fourth coach or a development coach,
which coaches first base, know, maybe coaches defense and base running.

95
00:09:25,921 --> 00:09:31,961
But this role, they actually expanded to help in performance science.

96
00:09:31,961 --> 00:09:37,579
So the Astros were actually the first organization to have a sports scientist in baseball.

97
00:09:37,741 --> 00:09:40,323
So they were very passionate about this.

98
00:09:40,323 --> 00:09:54,753
part of this role was helping to do the sports science testing, helping to do the workload
monitoring, a lot of the grunt work, quite frankly, but it was definitely insights into

99
00:09:54,753 --> 00:09:56,494
multiple departments.

100
00:09:56,534 --> 00:10:07,101
it was something that I, given I never had actually a formal degree in kinesiology or
anything like that, I actually felt like this was my first shot.

101
00:10:07,543 --> 00:10:14,455
to actually work professionally or work for someone, work for an organization or in sport.

102
00:10:14,835 --> 00:10:17,706
So I applied and wound up getting the job actually.

103
00:10:17,706 --> 00:10:29,479
I actually remember Bill Fricke, Pete Petilla and Jose Fernandez were the three who I
interviewed with and who wound up hiring me and I'm forever grateful to all three of them

104
00:10:29,820 --> 00:10:34,121
for taking a chance on me because my resume was nothing spectacular.

105
00:10:35,309 --> 00:10:38,729
And so I wound up doing that for 2019.

106
00:10:39,268 --> 00:10:45,969
In 2020, they actually are after that season, they offered me a position as a sports
science analyst.

107
00:10:45,969 --> 00:10:58,109
So I accepted that role, moved down to West Palm Beach with my wife, where the spring
training complex is, and was a sports science analyst for two years.

108
00:10:58,109 --> 00:11:03,789
And then in 2022, you know, the Astros decided that they wanted to make a bigger

109
00:11:03,789 --> 00:11:07,449
more formal investment in biomechanics and sports science.

110
00:11:07,449 --> 00:11:15,229
So they started a performance science department and they asked me to be the director and
build it out.

111
00:11:15,229 --> 00:11:18,089
So I was very grateful for that opportunity.

112
00:11:18,089 --> 00:11:26,829
In 2022 and 2023, I was the director of performance science, building out that team and
trying to get that research off the ground.

113
00:11:26,829 --> 00:11:33,649
then just this past year, at the end of the year, they

114
00:11:33,833 --> 00:11:37,401
as to expand my responsibilities again to oversee player development.

115
00:11:37,401 --> 00:11:43,303
So that is the long story of how I wound up where I'm at.

116
00:11:45,517 --> 00:11:46,328
Yeah, I love it.

117
00:11:46,328 --> 00:11:46,758
I love it.

118
00:11:46,758 --> 00:11:48,970
It's absolutely, absolutely fantastic.

119
00:11:48,970 --> 00:11:52,523
that's also why I wanted to have you on the show.

120
00:11:52,984 --> 00:12:03,382
Because as you were saying, also you did quite a lot of weightlifting, which I am
personally very interested about.

121
00:12:03,382 --> 00:12:07,335
I do that very amateurly in my local gym.

122
00:12:08,277 --> 00:12:13,080
But something I discovered when digging into the science of weightlifting is

123
00:12:13,781 --> 00:12:26,872
And that was surprising to me because like, I didn't know anything about that before doing
that myself, diving into the science of it and basically conducting small RCTs on me at

124
00:12:26,872 --> 00:12:34,018
the gym and, know, coming up with my own macro cycles and so on.

125
00:12:34,018 --> 00:12:43,117
So something I was really, really surprised by is by the importance of nutrition.

126
00:12:43,117 --> 00:12:52,677
actually, you know, because when you're like, when you start a training like that, you're
like, yeah, the training is like 90 % of the results, right.

127
00:12:52,677 --> 00:13:02,097
But actually, I discovered nutrition is extremely important and is an integral part of the
training program.

128
00:13:02,097 --> 00:13:09,297
So I'm also curious if that's the case in sports teams.

129
00:13:09,685 --> 00:13:20,719
like baseball and then like, yeah, basically how do you apply that kind of knowledge that
we have from a much more controlled sport like weightlifting?

130
00:13:20,719 --> 00:13:24,871
How does that help you in your job today?

131
00:13:25,831 --> 00:13:28,743
Yeah, that's a really good question.

132
00:13:28,743 --> 00:13:39,697
absolutely, like nutrition plays a huge role in, I think all professional sport, but
definitely within our organization, we do take it very seriously.

133
00:13:41,077 --> 00:13:49,440
And yeah, I think that there are, you interesting parallels, you you talked about
weightlifting specifically, you know, I did spend probably three, three, four years

134
00:13:50,000 --> 00:13:52,160
competitively weightlifting.

135
00:13:52,861 --> 00:14:00,463
And, you know, like one example of something that is, it's just a staple in weightlifting
is you have to make a weight class.

136
00:14:00,463 --> 00:14:07,915
And so, you know, one of things that you have to do is you have to be able to manipulate
your body weight to essentially be

137
00:14:07,915 --> 00:14:13,969
the lowest body weight that you can possibly be while like lifting the most weight that
you can possibly lift.

138
00:14:13,969 --> 00:14:24,947
And, you you have weigh ins at a certain time and, you know, so you wind up needing to
basically weigh in at a certain time and then understanding this is what I need to eat and

139
00:14:24,947 --> 00:14:32,802
when to be able to, you know, lift at my fullest capacity, you know, over X number of
hours later.

140
00:14:32,883 --> 00:14:36,533
And while the exact scenario is

141
00:14:36,533 --> 00:14:38,865
significantly different than baseball, right?

142
00:14:38,865 --> 00:14:41,276
There's no weight classes or anything like that.

143
00:14:42,037 --> 00:14:53,645
The general principle of being able to understand essentially, you know, what your body
needs to perform at its highest level and how long that takes to get in your system and

144
00:14:53,645 --> 00:14:57,257
get out of your system is extremely valuable, right?

145
00:14:57,257 --> 00:15:06,663
And so, you know, on like something like that, that is certainly applicable is, you know,
even something as simple as like caffeine intake.

146
00:15:06,697 --> 00:15:14,984
You know, we play night games and so we know how important sleep is for overall
performance.

147
00:15:14,984 --> 00:15:25,842
And it could be very easy for someone to take extreme amounts of caffeine before the game,
you know, because they don't know how long it takes for caffeine to actually get through

148
00:15:25,842 --> 00:15:26,363
their system.

149
00:15:26,363 --> 00:15:31,497
And so they wind up actually it not being that useful, you know, for the first portion of
the game.

150
00:15:31,497 --> 00:15:35,880
And then they wind up basically not being able to sleep for several hours post game.

151
00:15:36,501 --> 00:15:45,823
So I think even basic principles like that, understanding what to put in your body and
when is extremely impactful.

152
00:15:46,564 --> 00:15:47,244
Yeah.

153
00:15:47,244 --> 00:15:47,504
Yeah.

154
00:15:47,504 --> 00:15:49,465
That's a very good example.

155
00:15:49,465 --> 00:15:51,165
I'm actually very curious.

156
00:15:51,165 --> 00:15:53,446
How do you follow that?

157
00:15:53,446 --> 00:15:57,087
Because like, you cannot be behind the players all the time, right?

158
00:15:57,087 --> 00:16:05,867
So here you have to also rely, I guess, own professional, professional character of the
player.

159
00:16:05,867 --> 00:16:08,338
So I'm guessing there is variation on that.

160
00:16:08,338 --> 00:16:10,558
How do you guys handle that?

161
00:16:10,558 --> 00:16:22,071
Because, yeah, in the end, we know about that stuff, but also there is a lot of personal
variation, not only as you were saying on caffeine intake and the timing, but also effect

162
00:16:22,071 --> 00:16:24,503
of caffeine on people.

163
00:16:24,503 --> 00:16:28,443
I'm personally very sensitive to caffeine.

164
00:16:28,984 --> 00:16:33,229
So that's cool because it wakes me up in the morning.

165
00:16:33,229 --> 00:16:42,289
But definitely I know that if I take caffeine after more or less 12 p I'm gonna have
troubles at night.

166
00:16:42,309 --> 00:16:55,329
I'm wondering how, yeah, how do you implement that stuff once, like how do you implement
the science on the players?

167
00:16:55,989 --> 00:17:03,285
Yeah, you know, I'm not gonna lie and say that we have it down perfectly or that all of
our players, you know, follow

168
00:17:03,641 --> 00:17:05,301
everything to a T.

169
00:17:05,482 --> 00:17:07,702
We largely rely on education.

170
00:17:07,962 --> 00:17:11,853
And I think that that's something that resonates with me.

171
00:17:11,853 --> 00:17:25,087
you know, I think for anyone that has kids, it's not significantly different in that you
can tell them the right thing over and over and over again, but until they believe it

172
00:17:25,087 --> 00:17:28,248
themselves, they may not do it.

173
00:17:28,248 --> 00:17:32,729
And so, yeah, to your point, we don't have oversight over these guys.

174
00:17:32,863 --> 00:17:35,714
all the time, nor do we want to have to.

175
00:17:36,175 --> 00:17:47,841
So the best thing that we can do is essentially educate them on why it's important for
their performance, why it's important for their careers, and trying to distill complex

176
00:17:47,841 --> 00:18:01,479
science into very simple but impactful infographics and try and communicate things
visually and essentially get them to believe and understand that if they want to improve

177
00:18:01,479 --> 00:18:02,603
their performance.

178
00:18:02,603 --> 00:18:04,853
this is something that they should do.

179
00:18:05,474 --> 00:18:17,597
And definitely when players do that, you can definitely see it because they take ownership
over their careers and we definitely see changes on the field as well.

180
00:18:17,857 --> 00:18:18,868
Okay, yeah, I see.

181
00:18:18,868 --> 00:18:20,558
That must be super interesting.

182
00:18:20,558 --> 00:18:30,281
So you basically get the players somewhere together and you go through the application of
the science.

183
00:18:30,953 --> 00:18:40,237
I don't know, like today is about caffeine, tomorrow is about sleep, and next week is
going to be about meal timing, stuff like that.

184
00:18:40,237 --> 00:18:41,317
Is that how that works?

185
00:18:41,317 --> 00:18:42,528
Yeah, essentially.

186
00:18:42,528 --> 00:18:54,943
You know, we have the draft coming up here, July 14th to the 16th, and that's a great
example of like after the draft, we have an onboarding process for all of our players.

187
00:18:54,943 --> 00:18:59,845
And so they will learn about the Astros' philosophies.

188
00:18:59,989 --> 00:19:04,352
In many areas, they'll learn about what our hitting philosophy is.

189
00:19:04,352 --> 00:19:07,273
They'll learn about what our defensive philosophy is.

190
00:19:07,813 --> 00:19:10,155
They'll learn about what our strength and conditioning philosophy is.

191
00:19:10,155 --> 00:19:14,557
And one of the things that they'll learn about is our nutrition philosophy.

192
00:19:14,557 --> 00:19:18,459
And it's definitely on the education side.

193
00:19:18,459 --> 00:19:20,941
It's why are carbs important?

194
00:19:20,941 --> 00:19:22,161
Why are fats important?

195
00:19:22,161 --> 00:19:23,722
Why is protein important?

196
00:19:23,722 --> 00:19:26,264
How much of that should you intake?

197
00:19:26,264 --> 00:19:28,164
What are the proper sources?

198
00:19:29,159 --> 00:19:35,224
And ultimately, you know, we always try and tie it back to on -field performance, you
know.

199
00:19:35,224 --> 00:19:47,383
So, you know, for example, you know, we can educate players that if, you know, if you're
playing in the field, know, carbs are important for essentially like high bouts of energy,

200
00:19:47,383 --> 00:19:47,863
right?

201
00:19:47,863 --> 00:19:55,581
And if you, one of the key performance indicators of basically being a good defender in
the outfield is how fast you can run.

202
00:19:55,581 --> 00:19:57,442
and how much ground you can cover.

203
00:19:57,442 --> 00:20:00,685
if multiple balls hit you, can you do that multiple times?

204
00:20:00,685 --> 00:20:11,652
And so, it's a non -trivial thing to be able to fuel your body correctly for maximum
effort sprints multiple times over several hours.

205
00:20:12,133 --> 00:20:19,057
And so, if we can tie it back to basically what they value, I think it has a better chance
of landing.

206
00:20:19,438 --> 00:20:22,350
Okay, yeah, that's definitely super interesting.

207
00:20:22,350 --> 00:20:23,460
I love that.

208
00:20:23,661 --> 00:20:24,541
And yeah, that...

209
00:20:24,541 --> 00:20:30,303
Also, personally, that timing of things is, I can see very interesting.

210
00:20:30,303 --> 00:20:42,258
You have also to understand, know, like there are definitely some moments of the days of
the day where I'm more efficient at the gym than like I'm definitely much more efficient

211
00:20:42,258 --> 00:20:43,799
in the morning than in that at night.

212
00:20:43,799 --> 00:20:44,239
Right.

213
00:20:44,239 --> 00:20:49,711
So I never now I almost never train at night or the evening if I don't have to.

214
00:20:50,071 --> 00:20:52,512
And I much rather do that in the morning.

215
00:20:52,512 --> 00:20:54,273
Also, because I have the caffeine.

216
00:20:54,273 --> 00:20:59,357
boost, you know, some like, and going to the gym after a full day of work is just like,
that's hard.

217
00:20:59,357 --> 00:21:03,980
You know, I much prefer go for a walk, or something like that.

218
00:21:04,881 --> 00:21:09,525
But definitely something I resonated with, and that's like, that's very anecdotal.

219
00:21:09,525 --> 00:21:14,829
But you're saying that there are some late night games, right?

220
00:21:14,829 --> 00:21:20,493
And so you have to take your caffeine at the right moment so that it

221
00:21:20,673 --> 00:21:24,694
gives you the boost for the game, but at the same time doesn't disturb your sleep.

222
00:21:25,274 --> 00:21:27,615
So it's a completely different field.

223
00:21:27,615 --> 00:21:31,216
But I do some stand up from time to time.

224
00:21:31,636 --> 00:21:34,137
And stand up shows are at night.

225
00:21:34,137 --> 00:21:36,358
And so I actually have the same issue.

226
00:21:36,358 --> 00:21:48,361
I I came up with that, that timing stuff, like very nerdy caffeine timing the other day,
just before a show because I wanted to have that but I knew if I if I

227
00:21:48,481 --> 00:21:56,547
took my caffeine too late, I would have like I would not sleep for instance, before like
three or 4am which happened to me before.

228
00:21:56,547 --> 00:22:07,354
So like that that made me that made me laugh when you talked about that because I was
like, well, not only you know, high sports professional have that issue.

229
00:22:07,354 --> 00:22:11,277
So thank you so much, Jacob for for all the work you do.

230
00:22:11,277 --> 00:22:15,799
And that's that's actually useful to much, much more people than you thought.

231
00:22:17,857 --> 00:22:19,478
That's good to know.

232
00:22:20,038 --> 00:22:20,579
You see?

233
00:22:20,579 --> 00:22:23,100
Well, that's actually the same issue.

234
00:22:23,100 --> 00:22:30,504
I mean, for any people who have to do some stuff at night where they need to be alert, I
guess that will be useful to them.

235
00:22:32,845 --> 00:22:44,122
Now, I'm curious also about what you do, the kind of work you do for analyzing player
performance and injury risk, because I know these two topics are extremely important for a

236
00:22:44,122 --> 00:22:45,712
professional sports team.

237
00:22:46,795 --> 00:22:52,859
I'm wondering how Bayesian stats are applied here and how they can be helpful.

238
00:22:54,475 --> 00:23:03,949
Yeah, I think that there's a significant way that just the overall Bayesian framework is
applied.

239
00:23:03,949 --> 00:23:20,906
And I think if we think about the components of professional sports, being successful in
professional sports, some of them being skill acquisition, cognitive processing, in -game

240
00:23:20,906 --> 00:23:24,121
strategy, and then obviously kinesiology.

241
00:23:24,121 --> 00:23:26,523
you know, injury risk.

242
00:23:26,663 --> 00:23:32,868
Kinesiology is probably the most publicly researched area, you know, of all of them.

243
00:23:32,868 --> 00:23:44,568
If anyone wants some answers, it's easiest, you know, to Google how to make a player
bigger, faster, stronger, or, and you'll get dozens of research articles that are

244
00:23:44,568 --> 00:23:49,171
applicable, which, you know, in my area means that

245
00:23:49,311 --> 00:24:02,945
we can leverage that information as priors and then be able to apply our observations from
our population to both improve the resolution of the insights that we glean from the data

246
00:24:02,945 --> 00:24:13,405
that we have, but also to be able to infer maybe where our specific processes or our
specific population might differ from the research population.

247
00:24:15,513 --> 00:24:17,454
Okay, okay, I see.

248
00:24:17,634 --> 00:24:26,008
That's in what's the what would you say is the state of the science on these on on these
fronts?

249
00:24:26,008 --> 00:24:30,260
My are we somewhat confident?

250
00:24:30,260 --> 00:24:34,602
Or is that something that's really at the frontier and that's evolving almost every year?

251
00:24:34,602 --> 00:24:40,065
I think that there there are aspects of it that we are very confident in.

252
00:24:41,261 --> 00:24:43,292
And there are aspects of it that are definitely evolving.

253
00:24:43,292 --> 00:24:56,467
So an example of aspects that we are confident in is like we are very confident in how
specific musculature and their functions apply to injuries and human performance.

254
00:24:57,508 --> 00:24:59,119
Very confident in the static state.

255
00:24:59,119 --> 00:25:09,693
You know, I think that we are one area that we that the research is improving in is
understanding maybe how these function in a

256
00:25:10,059 --> 00:25:11,590
in a dynamic state.

257
00:25:11,590 --> 00:25:27,321
And an example of that would be, know, it's maybe easy to take a look at hamstring
strength, right, and player's hamstring strength and then track that over a season and

258
00:25:27,321 --> 00:25:30,523
see, okay, who hurts their hamstring more or less, right?

259
00:25:30,523 --> 00:25:39,169
But it's, you know, there are certainly aspects to like sprint mechanics, that impact
that.

260
00:25:39,617 --> 00:25:49,424
that maybe are less obvious because there's not quite as much quantifiable information on
it right now.

261
00:25:49,905 --> 00:25:56,371
It also requires essentially getting more nuance and understanding what is the muscle
doing at the time of injury.

262
00:25:56,371 --> 00:26:05,288
And given that injuries are relatively sparse in nature when compared to non -injured
instances, that type of information is tough to come by.

263
00:26:05,288 --> 00:26:09,771
But there are definitely people doing good work and trying to understand how

264
00:26:09,783 --> 00:26:13,555
coordination fits into injury mitigation.

265
00:26:13,555 --> 00:26:14,995
So that's one area that we're improving.

266
00:26:14,995 --> 00:26:27,440
But I do think it's very good and we're very confident in overall, how does musculature
impact injury risk?

267
00:26:27,440 --> 00:26:29,461
Okay.

268
00:26:29,941 --> 00:26:39,245
What is a question or topic in particular in that realm that you'd love to see answered in
the coming month?

269
00:26:39,361 --> 00:26:41,284
that you're really curious about.

270
00:26:48,117 --> 00:26:52,389
Well, I guess, you know, don't know if this is specific enough.

271
00:26:52,389 --> 00:26:54,099
It's definitely not in the coming months.

272
00:26:54,099 --> 00:27:06,565
But you know, one thing that like we are always pursuing in the baseball industry is one
of the things that is most important to a pitcher being successful on the field is how

273
00:27:06,565 --> 00:27:07,665
hard they throw.

274
00:27:07,665 --> 00:27:10,306
That's, that's like pretty common.

275
00:27:10,907 --> 00:27:14,388
The harder you throw, generally, the better the results are going to be.

276
00:27:14,768 --> 00:27:16,729
However, we also know from

277
00:27:17,513 --> 00:27:25,880
external research that how hard you throw is pretty much the driving factor to whether or
not you're going to get hurt.

278
00:27:26,441 --> 00:27:35,009
You you put more torque on the elbow and more strain and that winds up essentially
escalating your injury risk a ton.

279
00:27:35,790 --> 00:27:42,996
And so like one of the things that I think we've been trying to look at is

280
00:27:43,831 --> 00:28:02,124
tendon and ligament adaptations and trying to understand, can we periodize workload of a
pitcher to be able to maximize their in -season performance and mitigate their injury

281
00:28:02,124 --> 00:28:02,364
risk?

282
00:28:02,364 --> 00:28:09,258
Because ultimately, the answer of throw the ball slower is not gonna work.

283
00:28:09,899 --> 00:28:13,451
I think baseball has tried to take the approach of

284
00:28:13,591 --> 00:28:19,423
just throw less overall and injuries continue to increase.

285
00:28:19,463 --> 00:28:23,215
So, you know, I think that there's, I don't know the answer to the question.

286
00:28:23,215 --> 00:28:25,966
I don't think external research will get to it.

287
00:28:25,966 --> 00:28:29,407
Hopefully, you know, we're able to get to it internally.

288
00:28:29,688 --> 00:28:30,248
Yeah.

289
00:28:30,248 --> 00:28:30,538
Yeah.

290
00:28:30,538 --> 00:28:35,130
I guess that's, that would be quite, be quite interesting, I'm guessing.

291
00:28:35,850 --> 00:28:42,673
And what about the, so I guess you talked a bit, a bit about that right now, but what do
you,

292
00:28:43,273 --> 00:28:54,778
See like how to Bayesian models help in predicting the impact of training loads on the
athletes Well -being and performance in general like not only injury.

293
00:28:54,919 --> 00:29:07,305
Yeah You know, I think when it comes to training loads, you know, we we know that there
are broad truths About how stress, you know impacts the human body

294
00:29:08,479 --> 00:29:14,091
We also know that there are nuances around how specific people or players adapt to
stresses.

295
00:29:14,091 --> 00:29:26,014
So we can essentially use those broad truths to overcome sparse data where we may not have
a whole lot of information on any specific player.

296
00:29:26,034 --> 00:29:28,154
But we do have a few observations.

297
00:29:28,275 --> 00:29:37,067
And then if we combine that with something like a multi -level model where we can

298
00:29:37,067 --> 00:29:44,553
then really glean some robust insights where maybe robust data actually doesn't exist.

299
00:29:49,225 --> 00:29:49,786
I see.

300
00:29:49,786 --> 00:29:50,706
Yeah.

301
00:29:50,946 --> 00:29:51,787
Yeah, for sure.

302
00:29:51,787 --> 00:29:58,271
I mean, that's definitely where, where hierarchical models would definitely be super
helpful.

303
00:29:58,492 --> 00:30:08,058
Like if you can relate the different, the different positions and the different players
and the different population of players, definitely super powerful.

304
00:30:09,320 --> 00:30:16,865
And what about the, so what you do also some, like you also work on, on

305
00:30:16,873 --> 00:30:18,425
athlete conditioning, right?

306
00:30:18,425 --> 00:30:26,403
And you, you, you do that, like you use the science of that to improve the training of the
players that right?

307
00:30:26,403 --> 00:30:26,983
Yes.

308
00:30:26,983 --> 00:30:27,664
Yeah.

309
00:30:27,664 --> 00:30:28,445
Okay.

310
00:30:28,445 --> 00:30:31,578
So how do you use how do you use, like, how do you do that?

311
00:30:31,578 --> 00:30:33,510
And how do you use Bayesian approaches here?

312
00:30:33,510 --> 00:30:35,031
Yeah.

313
00:30:35,111 --> 00:30:36,512
Good question.

314
00:30:38,775 --> 00:30:54,355
So I mean, I think it's not unrelated to the last answer that I gave, but one of the
limitations of overall injury prevention is the amount of data that can be collected.

315
00:30:54,656 --> 00:31:03,161
We only have so many players that come through our system in any given year or even
through a couple of years.

316
00:31:04,482 --> 00:31:08,905
And then we only have so many samples even within a given player.

317
00:31:09,117 --> 00:31:13,089
And especially on an injured population, right?

318
00:31:13,089 --> 00:31:27,115
The injured population is significantly less than the healthy population to the point
where, you know, if you have one or two players who maybe got injured with what looks like

319
00:31:27,115 --> 00:31:31,446
healthy data, you know, it can be difficult to discern.

320
00:31:32,167 --> 00:31:37,759
you know, even we go back to leveraging previous research, you know, I think

321
00:31:37,961 --> 00:31:42,344
If we take the example, stick with hamstring strength and hamstring injuries.

322
00:31:43,605 --> 00:31:56,674
If we have hamstring strength information on players, we can absolutely take information
from research and say, we believe within a certain degree of certainty that this is what a

323
00:31:56,674 --> 00:32:02,517
healthy hamstring signature or force profile would actually look like.

324
00:32:03,398 --> 00:32:08,051
And we can play around with how confident we are in that.

325
00:32:08,149 --> 00:32:13,190
you know, to basically see what gets us closest to the actual outcomes.

326
00:32:13,190 --> 00:32:17,842
And then that allows us to, you know, obviously be more confident in what we're looking
at.

327
00:32:17,842 --> 00:32:20,333
Yeah, yeah, that makes sense.

328
00:32:20,333 --> 00:32:27,595
That, I mean, that sounds pretty challenging, but that does make sense.

329
00:32:27,595 --> 00:32:36,397
So from all that you're seeing here, really something I can see is that, yes, if you look
at the

330
00:32:36,715 --> 00:32:42,490
You know, like one question in particular, the data can be limited.

331
00:32:42,490 --> 00:32:52,257
But if you look at the overall amount of data, and definitely in comparison to other
sports, baseball is quite rich in data.

332
00:32:53,139 --> 00:33:05,949
Because you have inputs from game statistics, you have player tracking systems, have
physiological data, you have a lot of these sources, how, so how do you integrate these

333
00:33:06,219 --> 00:33:12,172
diverse data sources to then provide interesting insights?

334
00:33:14,694 --> 00:33:28,841
Yeah, I think it, from my perspective or just my opinion on it, I think it starts by
layering the data properly, which I think to me means understanding what level of

335
00:33:28,841 --> 00:33:35,544
information is important depending on the question being asked or what level of
information do we need to start with.

336
00:33:36,757 --> 00:33:44,019
And so, for example, if we want to know, let's say how we can make someone a better
outfielder, right?

337
00:33:44,019 --> 00:33:58,033
First, we jump right to, well, what's their reactive strength index from the force plates
and, the reactive strength index is low, hamstring strength is low, I think we're going to

338
00:33:58,033 --> 00:33:59,254
lose a lot of people, right?

339
00:33:59,254 --> 00:34:03,915
There's not going to be a whole lot of people that will immediately make that connection
and say,

340
00:34:03,979 --> 00:34:05,490
yeah, that makes sense.

341
00:34:05,490 --> 00:34:07,892
We fixed that, he'll be a better outfielder.

342
00:34:08,213 --> 00:34:15,949
But if we start with maybe asking the question, how many runs is this player worth as a
defender?

343
00:34:15,949 --> 00:34:19,021
How many runs has he saved as a defender?

344
00:34:19,582 --> 00:34:21,884
Which may come from our ball tracking data, right?

345
00:34:21,884 --> 00:34:26,747
That may come from understanding which balls were hit to them, were hit to him.

346
00:34:26,968 --> 00:34:31,091
How many other defenders would have actually made that play on average?

347
00:34:31,091 --> 00:34:32,772
Something simple like that.

348
00:34:33,623 --> 00:34:44,819
you know, then we can maybe work backwards to the next level of information and say, well,
it looks like maybe he doesn't catch quite as many balls as the average outfielder because

349
00:34:44,819 --> 00:34:45,719
he's not as fast.

350
00:34:45,719 --> 00:34:48,321
Like he's slower than average as well.

351
00:34:48,321 --> 00:34:52,243
And we know that the amount of ground that you can cover is certainly important.

352
00:34:52,603 --> 00:35:01,838
Then I think you can make the next step to the physiological data and say, he's like,
doesn't produce a whole lot of force and he's not super strong.

353
00:35:01,838 --> 00:35:03,649
So now,

354
00:35:03,649 --> 00:35:12,553
people start to actually link the two and say, okay, now I can see how improving his
hamstring strength and his force production qualities makes him a better outfielder.

355
00:35:12,973 --> 00:35:14,444
Okay, yeah, that's fascinating.

356
00:35:14,444 --> 00:35:20,756
it's like, yeah, different hints basically that you're picking up from the data.

357
00:35:20,756 --> 00:35:28,159
Yeah, yeah, essentially, and making sure that basically each one is applied at the right
time.

358
00:35:28,460 --> 00:35:32,001
Yeah, yeah, And well, I think that's...

359
00:35:32,339 --> 00:35:42,415
And a question I have that's related to that also is then what what do you think are the
most significant challenges that you face?

360
00:35:42,415 --> 00:35:53,901
Not only you, but the whole, you know, science team that which are these challenges that
you face when you're applying patient stats in baseball science?

361
00:35:53,901 --> 00:35:56,562
And how do you address them?

362
00:35:58,023 --> 00:35:59,464
really good question.

363
00:35:59,464 --> 00:36:02,425
I mean, actually, I, I think that

364
00:36:03,862 --> 00:36:14,629
The largest challenge is actually getting people that are extremely familiar with Bayesian
methods and fluent in Bayesian methods.

365
00:36:14,629 --> 00:36:23,675
And I would not consider myself a Bayesian expert by any means.

366
00:36:24,035 --> 00:36:28,238
And the field of sports science doesn't teach this.

367
00:36:29,739 --> 00:36:32,513
It's very limited in the statistical methods.

368
00:36:32,513 --> 00:36:33,674
that it actually teaches.

369
00:36:33,674 --> 00:36:46,558
so I actually think one of the, I guess maybe another tangent, like it's related, is
people in the field of sports science tend to be very tied to what previous research,

370
00:36:46,558 --> 00:36:48,671
methods that previous research have done, right?

371
00:36:48,671 --> 00:36:54,657
So they'll come in and they'll say, I want to do project X and...

372
00:36:54,657 --> 00:36:58,059
this paper, these two papers were written on this project and they did it this way.

373
00:36:58,059 --> 00:36:59,991
So this is exactly how I want to do it.

374
00:36:59,991 --> 00:37:02,743
These are the statistical methods that were used.

375
00:37:02,743 --> 00:37:13,460
And a lot of times these papers are written by very, very intelligent strength
conditioning coaches or, you know, exercise physiologists, but they're, they're very,

376
00:37:13,460 --> 00:37:17,713
they're not written by people with strong stats backgrounds.

377
00:37:17,713 --> 00:37:24,557
So I think getting people in the field that are actually familiar with this type of
approach.

378
00:37:25,406 --> 00:37:26,947
is the largest obstacle.

379
00:37:26,947 --> 00:37:37,313
But I do think once we get people with that skill set, there's actually very few barriers
to it, just given, I think, two things.

380
00:37:37,634 --> 00:37:52,324
The first one being the amount of tools that are available to use Bayesian methods across
both Python and R with very simple syntax and are computationally fast has expanded

381
00:37:52,324 --> 00:37:53,544
tremendously.

382
00:37:54,091 --> 00:37:58,143
you know, just over the last six or seven years since I've been paying attention.

383
00:37:59,704 --> 00:38:07,808
And I also think that how we communicate, how we communicate Bayesian stats generally
aligns with how people think.

384
00:38:07,808 --> 00:38:12,241
People know that there are uncertainties around every decision that is made.

385
00:38:12,241 --> 00:38:16,593
And we know that some uncertainties are wider than others.

386
00:38:16,593 --> 00:38:23,356
And depending on our risk tolerance, you know, that may factor in more so than just a
single point estimate.

387
00:38:24,157 --> 00:38:30,481
And so I do think that overall, communicating them, I think that's actually one of the
strengths of Bayesian approaches.

388
00:38:30,481 --> 00:38:30,942
Okay.

389
00:38:30,942 --> 00:38:31,882
I see.

390
00:38:31,882 --> 00:38:33,433
Yeah, that's very interesting.

391
00:38:33,433 --> 00:38:49,374
it's like, it's a mix of like not only the data and the availability of those, and also,
guess, the importance of having at least a part of the organization focused on that, but

392
00:38:49,374 --> 00:38:53,429
it's also a technical side in the sense that

393
00:38:53,429 --> 00:39:07,211
You definitely need people who are able to work on these with these kind of methods that
you're using a lot and Bayesian stats are definitely a very important part of that

394
00:39:07,211 --> 00:39:07,721
workflow.

395
00:39:07,721 --> 00:39:09,443
Yeah, yeah, absolutely.

396
00:39:09,443 --> 00:39:10,024
Yeah.

397
00:39:10,024 --> 00:39:21,073
And actually how, like, because you have to communicate, as you were saying, your findings
and the results of your models to a lot of different stakeholders.

398
00:39:21,073 --> 00:39:22,694
So how do you do that?

399
00:39:22,694 --> 00:39:26,455
I know from experience that it can be challenging.

400
00:39:26,455 --> 00:39:39,741
So how do you communicate these complex statistical concepts like those from Bayesian
analysis to coaches and players to ensure that they are effectively utilized?

401
00:39:39,821 --> 00:39:45,924
Yeah, that's a non -trivial task as well.

402
00:39:45,924 --> 00:39:49,125
I do think one of the things that we try and do is

403
00:39:49,931 --> 00:39:53,763
we do communicate it in different ways to different groups of people, right?

404
00:39:53,763 --> 00:40:07,568
I think when talking with JJ's group and R &D, we're actually gonna wanna be as technical
as possible because we actually want their input on the methods and they're gonna wanna

405
00:40:07,568 --> 00:40:14,071
know, I trust these results based off of the process?

406
00:40:14,311 --> 00:40:18,213
If I'm communicating with a coach or a scout,

407
00:40:19,241 --> 00:40:20,883
they don't care about that, right?

408
00:40:20,883 --> 00:40:33,333
If I'm communicating with them, it's actually more so like one of the general approaches
that we take is, we distill the information that we have down to as few dimensions as

409
00:40:33,333 --> 00:40:33,884
possible?

410
00:40:33,884 --> 00:40:46,645
So, oftentimes what that looks like is maybe at most three or four dimensions where
obviously if we're relaying it in a graph, we have our X, Y axis and then maybe it's

411
00:40:46,977 --> 00:40:52,450
you know, gradiented with a specific color and faceted by different positions, right?

412
00:40:52,450 --> 00:41:07,028
So, you know, for example, if we're trying to communicate injury risk of a elbow injury
risk of a pitcher, you know, we might take a look at, we might take a look at the, you

413
00:41:07,028 --> 00:41:15,681
know, x axis being shoulder strength, the y axis maybe being lower body strength or
something like that, it may be gradiented out.

414
00:41:15,681 --> 00:41:20,604
by injury risk or probability and it may be faceted by how hard you throw.

415
00:41:20,744 --> 00:41:30,949
So that way, we can communicate four different variables, but very, very simply put and
hopefully easy to distill down.

416
00:41:31,930 --> 00:41:32,991
see.

417
00:41:32,991 --> 00:41:43,557
And what do you, in your experience, what are the most common challenges of consumers of
these models?

418
00:41:43,713 --> 00:41:49,077
be players, be coaches, be people from the business side.

419
00:41:49,478 --> 00:41:56,143
What do you see as the main difficulties and what would you recommend?

420
00:41:56,203 --> 00:42:01,527
What would you your advice to listeners who have to do the same at the work?

421
00:42:02,068 --> 00:42:13,587
Maybe not for coaches and players, but for other stakeholders who are not part of the
model building team, but have to use the models.

422
00:42:13,587 --> 00:42:15,037
in their own work?

423
00:42:16,878 --> 00:42:23,940
Yeah, so I think that there are two obstacles and they're actually kind of probably
competing obstacles.

424
00:42:24,420 --> 00:42:30,722
I mean, the first one is, you know, we want to be as concise, as quick as possible, right?

425
00:42:32,222 --> 00:42:39,674
We don't want to say, okay, you know, look at this visual, then this visual, then this
visual, then this visual to make your decision, right?

426
00:42:39,674 --> 00:42:43,063
If we can encompass it all in a single visual or

427
00:42:43,063 --> 00:42:47,035
you know, a single pillar of philosophy, that's what's going to resonate.

428
00:42:47,035 --> 00:42:53,181
Otherwise, you know, they may forget or if it gets too complex, they may not even try and
use it.

429
00:42:53,482 --> 00:43:06,432
The second obstacle is actually, you know, related to that is when we do that, I think we
run the risk of glossing through or like smoothing through a lot of information, maybe

430
00:43:06,432 --> 00:43:12,197
meaningful information and maybe nuanced, but nuanced cases do come up, right?

431
00:43:12,393 --> 00:43:19,318
And so we don't want to overgeneralize in an effort to simplify too much.

432
00:43:19,898 --> 00:43:31,206
so, you know, like one of the things that we have tried to do, and I'm not saying that we
are great at it, so maybe other people have better approaches, but we have tried to keep

433
00:43:31,206 --> 00:43:40,933
the information or the philosophy or the tagline as simple as possible, but then try and
highlight, you know, these scenarios.

434
00:43:40,991 --> 00:43:50,887
maybe possible scenarios where it's worth, if the results don't look intuitive to you, ask
a question.

435
00:43:50,968 --> 00:43:58,713
And we just try and highlight where these possible scenarios could go wrong, where
certainly we want people to actually think through it.

436
00:43:58,713 --> 00:44:08,130
And if they see a result that says, I don't think this is right, this doesn't make any
sense to me, as an expert in their field, just ask the question, or please just don't take

437
00:44:08,130 --> 00:44:10,341
these at face value all the time.

438
00:44:10,719 --> 00:44:12,400
Hmm, yeah, definitely.

439
00:44:12,400 --> 00:44:14,793
think it's something very useful.

440
00:44:14,793 --> 00:44:23,780
So in my experience, making sure to communicate not only what the model can do, but also
and maybe most importantly, what it cannot do.

441
00:44:23,901 --> 00:44:31,607
And that way, that will mitigate a lot of these issues of over or under confidence in the
model.

442
00:44:31,607 --> 00:44:38,613
Because I mean, we definitely as humans and it's well documented in the science that

443
00:44:38,867 --> 00:44:49,160
And humans have a different way of handling uncertainty around algorithm decisions, right?

444
00:44:49,160 --> 00:45:05,904
We tolerate much more the fact that a human is gonna underperform and be wrong in a
special case, but algorithms, when they are wrong in just one instance, then people will

445
00:45:05,904 --> 00:45:08,149
lose trust extremely fast.

446
00:45:08,149 --> 00:45:09,530
in the algorithm.

447
00:45:10,611 --> 00:45:26,572
yeah, I can think it's something to be very careful of when we communicate our model
because well, people will be way more, will be way harsher on the model than on a scout,

448
00:45:26,572 --> 00:45:27,843
for instance, right?

449
00:45:27,843 --> 00:45:37,729
A scout can be wrong much many more times than a model for recruiting players can be
because of that.

450
00:45:37,729 --> 00:45:39,380
bias that humans have.

451
00:45:39,380 --> 00:45:48,815
So I think it's very important to communicate that as you were saying, and also to
communicate that the model is not just a machine.

452
00:45:48,815 --> 00:45:50,956
The model is made by humans.

453
00:45:52,077 --> 00:45:54,278
be a bit kinder to it, Yeah.

454
00:45:54,658 --> 00:45:55,738
Yeah.

455
00:45:55,819 --> 00:46:01,662
I I think a good example of that, least for us, you put it well, communicating what the
model can't do.

456
00:46:02,182 --> 00:46:07,245
For us, that's actually our injury risk models, I think,

457
00:46:07,745 --> 00:46:18,328
for a lot in that category where like, you know, if we were to actually communicate, if we
actually communicated the exact probabilities that the model outputs of someone getting

458
00:46:18,328 --> 00:46:25,070
hurt, it's almost always going to say that the odds are they don't get hurt because those
are the true odds, right?

459
00:46:25,070 --> 00:46:30,311
That at any given time, if someone goes out there and plays, the odds are that they won't
get hurt.

460
00:46:31,152 --> 00:46:36,033
And so then, you know, we can communicate that like this, model that we're using is,

461
00:46:36,493 --> 00:46:42,133
not necessarily to make the prediction whether or not that this player is going to get
hurt.

462
00:46:42,153 --> 00:46:52,973
It's to infer what physical qualities or what features are actually important that we can
impact that lead to more or less risk.

463
00:46:52,973 --> 00:46:58,193
And so maybe it's less about is this player at 45 % risk or 35 % risk.

464
00:46:58,193 --> 00:47:06,053
It's more about what do we deem as important that would put that player at more or less
risk and then is that worth it?

465
00:47:06,241 --> 00:47:06,681
Yeah.

466
00:47:06,681 --> 00:47:06,992
Yeah.

467
00:47:06,992 --> 00:47:13,947
So basically communicating all the uncertainties around the decision to make.

468
00:47:13,947 --> 00:47:14,337
Nice.

469
00:47:14,337 --> 00:47:14,717
Yeah.

470
00:47:14,717 --> 00:47:15,077
Cool.

471
00:47:15,077 --> 00:47:22,713
Well, I think I've already asked you about a lot of that, like very precise, you know,
science questions.

472
00:47:22,713 --> 00:47:28,808
So maybe now to play us out a bit more looking towards the future.

473
00:47:28,808 --> 00:47:33,881
Are there any emerging trends?

474
00:47:33,889 --> 00:47:44,637
that you see in baseball science that you believe will significantly impact how teams
manage training and performance in the near future.

475
00:47:45,738 --> 00:47:55,706
And yeah, are there also some breakthroughs that you would really want to see?

476
00:47:55,706 --> 00:47:56,327
Yes.

477
00:47:56,327 --> 00:47:58,908
So actually, as far as future,

478
00:47:59,681 --> 00:48:04,423
you know, I guess, more or less like innovations in this field.

479
00:48:04,584 --> 00:48:13,939
One of the things that makes me very excited about my role is I actually do believe like
performance science in general fits into that category.

480
00:48:13,939 --> 00:48:19,152
And I guess more specifically as it relates to biomechanical information.

481
00:48:19,152 --> 00:48:24,364
So like we've talked a lot about just general kinesiology and physiology in this
conversation.

482
00:48:24,364 --> 00:48:29,617
you know, the last I think was three or four years ago, you

483
00:48:29,653 --> 00:48:37,346
Major League Baseball rolled out Hawkeye information, which is tracking the individual
joints of every single player.

484
00:48:37,346 --> 00:48:47,680
And that is where a lot of injury research comes from, especially in baseball field around
the torque of the elbow and things like that.

485
00:48:48,141 --> 00:48:54,303
So I do believe, like I, I'm very excited at that data set.

486
00:48:54,303 --> 00:48:58,589
And I believe that that's where, that's where the arms race.

487
00:48:58,589 --> 00:49:03,272
is in baseball is who can leverage that information the best.

488
00:49:03,973 --> 00:49:12,799
As far as breakthroughs that I'm hoping for, I don't know, maybe I could probably change
my answer if you would like me to change it.

489
00:49:12,799 --> 00:49:26,769
But I actually think that not necessarily on the research side, but the quality of the
computer vision algorithms and the player, the tracking, I'm hoping that

490
00:49:27,281 --> 00:49:35,486
breakthroughs occur there and maybe even more specifically the speed at which those
algorithms or those models are processed.

491
00:49:35,486 --> 00:49:38,188
And I guess that's for two reasons.

492
00:49:38,188 --> 00:49:52,976
First of all, when we're talking about elbow torque, the difference of one inch of the
wrist placement is exponentially more in degrees, which is exponentially more in force or

493
00:49:52,976 --> 00:49:53,396
torque.

494
00:49:53,396 --> 00:49:55,017
And so

495
00:49:55,093 --> 00:50:00,375
if a model misses by an inch, that's significant.

496
00:50:00,636 --> 00:50:03,877
And that's a very high standard for a computer vision model.

497
00:50:03,877 --> 00:50:05,798
It's a high standard for the human eye.

498
00:50:07,039 --> 00:50:14,332
But ultimately, if you want to get the most precise information possible, that's where I
think some of the innovation will come from.

499
00:50:14,332 --> 00:50:20,585
And then in a practice setting, there's a lot of research around

500
00:50:21,221 --> 00:50:31,017
feedback loops and skill acquisition and basically being able to provide a target and then
just providing that player with feedback of whether or not they hit that target and how

501
00:50:31,017 --> 00:50:32,147
far they were.

502
00:50:33,428 --> 00:50:45,965
And just given the complexity of the computer vision models and the size and the compute
power, those results, those biomechanical results don't come back for an hour or two,

503
00:50:45,965 --> 00:50:48,957
which is fast, but it's not, you

504
00:50:49,289 --> 00:50:51,590
we could use it inside of a minute, right?

505
00:50:51,590 --> 00:50:55,552
To really get to apply it in a practice setting.

506
00:50:55,552 --> 00:51:06,857
And so, yeah, those are maybe not specific kinesiology or physiology innovations, but I'm
hoping that somebody can figure that out in the next several years.

507
00:51:06,857 --> 00:51:08,927
Yeah, mean, yeah, for sure.

508
00:51:08,927 --> 00:51:13,239
That's like, I agree, that sounds absolutely amazing.

509
00:51:13,519 --> 00:51:17,281
So listeners, you've heard Jacob like...

510
00:51:18,145 --> 00:51:24,347
get going on that if you're if you're a fan of computer vision algorithms in baseball.

511
00:51:24,628 --> 00:51:27,569
Definitely that would be used by the Astros.

512
00:51:27,589 --> 00:51:30,530
And I'm guessing a lot of other teams.

513
00:51:30,850 --> 00:51:31,891
Yeah, that's super cool.

514
00:51:31,891 --> 00:51:33,311
I completely agree.

515
00:51:33,311 --> 00:51:39,674
And, well, I think that's that's the show, Jacob.

516
00:51:39,674 --> 00:51:45,416
I mean, that's I think we've already covered a lot of topics.

517
00:51:45,917 --> 00:51:47,487
Before we close up,

518
00:51:47,733 --> 00:51:51,754
I have the last two questions I ask everybody, of course, at the end of the show.

519
00:51:51,754 --> 00:52:00,486
But is there a topic you would have liked to mention but I failed to ask you about?

520
00:52:01,797 --> 00:52:05,548
I actually think that we covered it.

521
00:52:05,548 --> 00:52:12,830
mean, these are probably my three favorite topics of baseball, human performance, and
maybe statistical methods.

522
00:52:12,830 --> 00:52:15,660
So I think we hit on it all.

523
00:52:16,361 --> 00:52:17,687
Well, I'm glad.

524
00:52:17,687 --> 00:52:19,058
to hear that.

525
00:52:19,420 --> 00:52:21,863
So then, let's play a sandwich.

526
00:52:21,863 --> 00:52:28,413
First question, if you had unlimited time and resources, which problem would you try to
solve?

527
00:52:28,413 --> 00:52:29,714
Yeah, I...

528
00:52:30,796 --> 00:52:34,471
Is this specific to my field or just in general?

529
00:52:36,395 --> 00:52:37,865
Now, Justin Shanerl.

530
00:53:05,239 --> 00:53:07,730
Yeah, at a limited time and resources, I'd probably dive into that.

531
00:53:07,730 --> 00:53:23,289
But then more specifically, like in my field, I would absolutely love to be able to solve
the elbow injury risk with pitchers.

532
00:53:23,289 --> 00:53:27,761
I think it's something that is just an extremely complex problem.

533
00:53:27,761 --> 00:53:30,522
And I very much enjoy complex problems.

534
00:53:30,623 --> 00:53:35,157
And there's an extremely high return on investment.

535
00:53:35,157 --> 00:53:38,048
I think for someone I can help with that.

536
00:53:38,048 --> 00:53:46,190
Yeah, I mean, I'm really impressed at because the players play such an amount of games per
year.

537
00:53:46,190 --> 00:53:48,240
It's absolutely incredible.

538
00:53:49,241 --> 00:53:55,703
Me, like honestly, my I was anchored with European sports teams.

539
00:53:55,743 --> 00:53:58,413
So like in football, they play.

540
00:53:58,413 --> 00:54:04,205
I mean, soccer, they will play like on tops.

541
00:54:04,205 --> 00:54:10,945
let's say 50, 60 games per season, rugby is less.

542
00:54:11,605 --> 00:54:30,125
So like, yeah, when I started working in baseball and I saw the number of games that these
guys play per year at such a high level, I'm honestly surprised that they don't get

543
00:54:30,125 --> 00:54:32,105
injured more often.

544
00:54:33,107 --> 00:54:44,192
And yeah, like I understand why you're saying the elbow injury because like, yeah, that
was one of my first, that was one of my first questions when I started looking today.

545
00:54:44,192 --> 00:54:51,465
It was like, damn, but the pitchers must throw, I don't know how many thousand balls in
each season.

546
00:54:51,465 --> 00:54:54,926
And that's not even counting the training.

547
00:54:54,926 --> 00:55:02,169
So the amount of joint pain and risk that you have with that is absolutely incredible.

548
00:55:02,509 --> 00:55:06,989
I really don't know how they don't get injured more often, to be honest.

549
00:55:07,169 --> 00:55:08,469
Yeah, I agree.

550
00:55:08,469 --> 00:55:11,769
What they do and what they go through is impressive.

551
00:55:12,189 --> 00:55:16,289
Yeah, 162, that's a lot of games.

552
00:55:17,249 --> 00:55:18,249
damn.

553
00:55:18,468 --> 00:55:31,329
And is that actually, so maybe last question before the very last question, do you see
any, like is the pitcher position really the one that's the most at risk for injury or is

554
00:55:31,329 --> 00:55:32,435
that pretty much

555
00:55:32,435 --> 00:55:39,027
will widespread across the positions or do you have some positions that are much more
prone to injury?

556
00:55:39,027 --> 00:55:45,078
No, mean, it's pretty centralized at the pitcher position.

557
00:55:45,078 --> 00:55:58,792
There are definitely injury risks all over the field, but in terms of the biggest, mean,
the injury risk on the mound is exponentially higher than any other injury.

558
00:55:58,792 --> 00:56:01,413
I think if we look at the

559
00:56:01,975 --> 00:56:09,449
the game of baseball, the throwing motion is probably the only one that like truly pushes
the limits of the human body.

560
00:56:09,909 --> 00:56:16,433
know, sprinting, you know, no offense to any of my baseball players, love you guys, but
they're not the fastest in the world.

561
00:56:16,433 --> 00:56:19,194
You know, they're not pushing that barrier.

562
00:56:19,575 --> 00:56:28,139
They're not the strongest, you know, in the world, but that right or left arm and the
delivery is moving, you the fastest in the world.

563
00:56:28,139 --> 00:56:32,001
And so I think that's the one that pushes the boundaries the most.

564
00:56:32,001 --> 00:56:32,682
Yeah.

565
00:56:32,682 --> 00:56:33,072
Okay.

566
00:56:33,072 --> 00:56:33,612
Interesting.

567
00:56:33,612 --> 00:56:33,982
Yeah.

568
00:56:33,982 --> 00:56:40,327
I mean, I'm not, I'm not surprised, but that's, that's good to, to, to hear say that.

569
00:56:40,327 --> 00:56:40,657
Yeah.

570
00:56:40,657 --> 00:56:47,162
I mean, the, you amount of pitches they have, they have to make is just like, can't, I
can't believe that.

571
00:56:47,162 --> 00:56:49,473
It's just, it's just absolutely incredible.

572
00:56:49,794 --> 00:56:54,877
and also like, if you have any baseball players listening to that episode, well done.

573
00:56:54,897 --> 00:56:57,679
that's like, that's impressive.

574
00:56:57,679 --> 00:57:00,781
Like, you let me know if you have some.

575
00:57:00,811 --> 00:57:03,603
Houston Astros players listening to that episode.

576
00:57:03,603 --> 00:57:05,755
That's like great publicity.

577
00:57:05,755 --> 00:57:10,449
We need to like, you know, advertise that and then on the social media.

578
00:57:11,850 --> 00:57:12,521
It's like that.

579
00:57:12,521 --> 00:57:14,732
That'd be quite amazing.

580
00:57:16,995 --> 00:57:29,409
actually, you know, do you have do we have any study about then pitchers who retire and
how their joints age?

581
00:57:29,409 --> 00:57:39,998
Because I know for US football, for instance, that can be quite a big, they can still be
at a high injury risk even after their professional career.

582
00:57:39,998 --> 00:57:41,979
Is that the case also in baseball?

583
00:57:41,979 --> 00:57:44,241
Or do we not know about that?

584
00:57:44,261 --> 00:57:45,502
You know, that's a good question.

585
00:57:45,502 --> 00:57:47,704
I'm not gonna say that there's not research.

586
00:57:47,704 --> 00:57:50,366
haven't, know, there could be something that I'm not aware of.

587
00:57:50,366 --> 00:57:55,150
But I haven't read personally, you know, any, any research on it.

588
00:57:55,150 --> 00:57:58,313
So, yeah, I'm not aware of any.

589
00:57:58,313 --> 00:57:59,233
Okay, yeah.

590
00:57:59,233 --> 00:58:01,754
Yeah, I'd be interested in that.

591
00:58:01,874 --> 00:58:06,755
If anybody in the audience knows about that, let us know.

592
00:58:08,195 --> 00:58:11,976
And well, finally, last question for you, Jacob.

593
00:58:12,457 --> 00:58:19,998
If you could have dinner with any great scientific mind, dead, alive, or fictional, who
would it be?

594
00:58:20,099 --> 00:58:20,979
man.

595
00:58:22,099 --> 00:58:24,940
You know, I'm to go with fictional.

596
00:58:24,940 --> 00:58:29,077
And I'm going to go with Tony Stark as Iron Man.

597
00:58:29,077 --> 00:58:32,419
I'm a big fan of the Marvel movies.

598
00:58:32,719 --> 00:58:36,421
And so I think he's the one that I'd like to have dinner with.

599
00:58:37,002 --> 00:58:38,663
That's a great answer.

600
00:58:38,663 --> 00:58:41,044
I have never had that one on the show.

601
00:58:41,044 --> 00:58:43,046
So yeah, you're the first one.

602
00:58:43,046 --> 00:58:44,486
But I understand.

603
00:58:44,687 --> 00:58:51,100
That's definitely my favorite of all the Marvel superheroes.

604
00:58:51,100 --> 00:58:53,451
So yeah, I love that.

605
00:58:54,412 --> 00:58:55,755
Yeah, that would

606
00:58:55,755 --> 00:58:56,755
Definitely be super cool.

607
00:58:56,755 --> 00:59:01,667
Would you ask him if you can fly the iron suit?

608
00:59:01,867 --> 00:59:02,787
Definitely.

609
00:59:02,787 --> 00:59:05,608
And I'd hope that he would say no, but I would have to ask.

610
00:59:05,608 --> 00:59:07,608
Yeah, I mean, yeah, for sure.

611
00:59:07,909 --> 00:59:09,649
Yeah, I would definitely ask.

612
00:59:09,649 --> 00:59:14,391
Like you should probably also ask if you could play baseball with the iron suit.

613
00:59:14,391 --> 00:59:16,201
That'd be probably super fun.

614
00:59:16,201 --> 00:59:20,272
Yeah, that might be my only chance to make it professionally.

615
00:59:20,272 --> 00:59:23,371
Yeah, mean, with the iron suit.

616
00:59:23,371 --> 00:59:25,982
You must throw pretty fast.

617
00:59:25,982 --> 00:59:29,923
you like you should think about that, Jacob.

618
00:59:29,963 --> 00:59:32,403
That would mitigate injury risk a lot.

619
00:59:33,644 --> 00:59:35,984
Yeah, probably.

620
00:59:37,445 --> 00:59:41,506
Well, on that note, I think it's the perfect time to close.

621
00:59:41,506 --> 00:59:44,287
So thank you so much, Jacob.

622
00:59:44,287 --> 00:59:47,388
That was a pleasure to have you on the show.

623
00:59:47,388 --> 00:59:50,609
Thanks again, JJ, for putting us in contact.

624
00:59:50,669 --> 00:59:51,809
As usual.

625
00:59:51,937 --> 01:00:05,556
We'll add links to your website and socials and any resource that you think is interesting
for listeners who want to dig deeper and start learning about baseball science, sports

626
01:00:05,556 --> 01:00:09,448
science in general, and baseball analytics.

627
01:00:09,609 --> 01:00:13,231
Thanks again, Jacob, for taking the time and being on this show.

628
01:00:13,231 --> 01:00:14,832
Thank you very much, Alex.

629
01:00:14,832 --> 01:00:16,083
I really enjoyed it.

630
01:00:20,119 --> 01:00:23,812
This has been another episode of Learning Bayesian Statistics.

631
01:00:23,812 --> 01:00:34,321
Be sure to rate, review, and follow the show on your favorite podcatcher, and visit
learnbaystats .com for more resources about today's topics, as well as access to more

632
01:00:34,321 --> 01:00:38,404
episodes to help you reach true Bayesian state of mind.

633
01:00:38,404 --> 01:00:40,346
That's learnbaystats .com.

634
01:00:40,346 --> 01:00:45,210
Our theme music is Good Bayesian by Baba Brinkman, fit MC Lars and Megharen.

635
01:00:45,210 --> 01:00:48,352
Check out his awesome work at bababrinkman .com.

636
01:00:48,352 --> 01:00:49,557
I'm your host.

637
01:00:49,557 --> 01:00:50,518
Alex and Dora.

638
01:00:50,518 --> 01:00:54,741
can follow me on Twitter at Alex underscore and Dora like the country.

639
01:00:54,741 --> 01:01:02,026
You can support the show and unlock exclusive benefits by visiting Patreon .com slash
LearnBasedDance.

640
01:01:02,026 --> 01:01:04,408
Thank you so much for listening and for your support.

641
01:01:04,408 --> 01:01:13,515
You're truly a good Bayesian change your predictions after taking information and if
you're thinking I'll be less than amazing.

642
01:01:13,515 --> 01:01:16,853
Let's adjust those expectations.

643
01:01:16,853 --> 01:01:30,021
Let me show you how to be a good Bayesian Change calculations after taking fresh data in
Those predictions that your brain is making Let's get them on a solid foundation