Things about analytics every newcomer should know

(Feel free to add your own)

⬇⬇⬇
Raw data will almost always be messy and cleaning will be a big part of any project.

If you expect that, you'll be less frustrated with the amount of time you spend cleaning.
Relatedly: Data Engineers are important and if you don't have one, you'll probably wish you did.
Statistical significance is arbitrary & can be abused.
Many organizations (in and out of sports) still have very limited or no analytics infrastructure.

There's a *lot* of low-hanging fruit.
The term "AI" is overused.
Statistics is not purely objective.

Humans decide what goes into models & how those models are built.
The process of communicating quantitative insights is as important as the process of generating those insights.
Visualizations should as as simple as possible while still conveying the underlying information.
Constantly looking things up on Stack Overflow is not only OK, it's an essential part of programming.
Quantitative analysis is often most effective when *combined* with qualitative analysis.

Each genre of analysis can keep the other's gaps & biases in check.

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Brendan Kent

Brendan Kent Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @brendankent

23 Mar
Why is sports analytics valuable?

Because humans have mental & situational constraints.

A thread 👇
1/ Sports analytics has been able to provide value beyond traditional qualitative judgments because humans have limits that can be generally classified as:

- Mental constraints
- Situational constraints
2/ Let's start with the mental constraints.

Perhaps the most obvious mental constraint is that our memory is limited.

We don't have the capacity to remember and process everything that happened on every play.
Read 20 tweets
11 Feb
Descriptive vs. Predictive

What's the difference between a descriptive metric & a predictive metric? Why does it matter?

A thread 👇
1/ Generally speaking:

- Descriptive metrics are intended to describe what has happened in the past

- Predictive metrics are intended to provide insight into what might happen in the future
2/ Let's look at an example of each type.

A 🏀 player's Free Throw % is a descriptive metric because it quantifies the efficiency with which a player shot free throws in the past.
Read 14 tweets
28 Jan
New to sports analytics?

These are the programming languages and tools to learn & the order to prioritize learning them in.

A thread 👇
Priority 1️⃣: Get comfortable with Excel

Most high-level modeling is not done in Excel, however, it’s still important to know your way around a spreadsheet.

If you don’t have access to Excel, Google Sheets (which is free) will do the trick.
Priority 2️⃣: Learn either R or Python

R & Python are the core languages of sports analytics, & most roles will require that you know at least 1 of them.

Don’t worry about learning both at first. They’re similar languages and if you know one, it'll be easy to learn the other.
Read 10 tweets
12 Jan
Win Probability, Explained 📈

What is win probability? How does it work? Is it ever "correct"?

If you ever find yourself asking these questions, this thread is for you 🧵
1/ Win probability (abbreviated "WP") is the likelihood that a team will win a particular game, expressed as a percentage.

50% WP: If the game is played 1000 times, the team will win ~500

10% WP: If the game is played 1000 times, the team will win ~100
2/ Importantly, WP is not a statement about whether a team WILL or WON'T win a game. A team having a 30% WP means they're MORE LIKELY TO LOSE THAN WIN but not that THEY'RE GOING TO LOSE.
Read 20 tweets
16 Oct 20
Thread: There are a variety of online statistics, computer science, and data science courses that can be audited for free.

Here are a few I'd recommend to those interested in developing a technical skill set for sports analytics ⬇
"Intro to Statistics" from Stanford

Gotta build the foundation!

udacity.com/course/intro-t…
"Introduction to Computer Science & Programming Using Python" from MIT

These days, virtually every job in sports analytics requires some programming experience.

edx.org/course/introdu…
Read 7 tweets
14 Oct 20
There aren't many better ways to get exposure to teams (that are hiring) than to perform well in this. Also, sports analytics is fun.
More specifically to this year's topic (the secondary), many football analytics folks I've spoken to (including on @MeasurablesPod) agree this is perhaps the most difficult area of the game to quantify.

Excited to see how people tackle this problem (pun intended, obviously).
Read 6 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!

:(