Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Daniela Witten Profile picture
Daniela Witten
@daniela_witten
dorothy gilford endowed chair and prof of stat/biostat @uw. all views my own.
6 subscribers
Feb 9, 2022 • 4 tweets • 4 min read
****Big news for fans of ISLRv2!!**** #RStats #ISLR #ISL

A TORCH VERSION OF THE DEEP LEARNING LAB (CHAPTER 10) IS NOW AVAILABLE!!! 🎆🤩💯🍾🥳🎉🪅

The original deep learning lab made use of keras, which requires a python installation, and is very finicky.

1/3 Image @dfalbel and @zkajdan translated the Chapter 10 lab into torch, a deep learning library from @rstudio that **doesn't require a python installation**.

It's available here: statlearning.com/resources-seco…

2/3
Dec 26, 2021 • 5 tweets • 2 min read
My daughter and I have been sitting on the tarmac at SeaTac for 6 hours waiting for our flight to take off.

@alaskaair what is going on?! 6 hours is way too long to have a 7yo sitting on a plane, especially without snacks, water, or updates about flight status Also, thankful for our n95s, I can’t see a covered nose anywhere
Oct 2, 2021 • 6 tweets • 2 min read
What I’ve learned during this pandemic… a 🧵

1/ 2/
Aug 5, 2021 • 6 tweets • 3 min read
Finally --- the 2nd edition of ISLR is out!!!!🥳🎉🪅🍾

Well, sort of. 🙄It's "published", but due to shortages in the global paper supply, hard copies won't be available for a bit longer 😢😭🤦‍♀️

You can pre-order a hard copy from Springer/Amazon, & **download the pdf today**! 1/ Image Purchase from Springer: link.springer.com/book/10.1007/9…

Purchase from Amazon: amazon.com/Introduction-S…

Download the pdf today: statlearning.com
2/
Apr 14, 2021 • 7 tweets • 2 min read
A lot of people have reached out to check in on me after this article came out --- in which I use a very colorful analogy to describe the current situation that many mothers in academia face during the pandemic 1/ nytimes.com/2021/04/13/hea… If you reached out, then thank you for the concern. I have been very fortunate: since late Spring 2020, I have had the good fortunate of consistent high-quality childcare for my 3 small children. (Not to mention that I'm senior faculty w/ job security.) 2/
Mar 16, 2021 • 6 tweets • 2 min read
I am loving these recent threads from @j_l_godwin on ADHD + academia. Thank you for sharing your experiences, Jessica --- I have learned a lot, and this new knowledge will help me be a better teacher/mentor for students in the future. Another one:
Jan 17, 2021 • 6 tweets • 3 min read
Since you asked, yes, I will write a thread about the SVD.

The SVD solves the optimization problem in the screenshot (X is nxp).

The k columns of U and V are the 1st k left and right singular vectors of X, and the diagonal elements of D are the 1st k singular values

1/4 Image "Nonnegative matrix factorization" is a bit broad but it is most often used to refer to the optimization problem in this screenshot, which -- as you can see -- is like a distant cousin of the SVD. Sometimes an orthogonality constraint may be placed on the columns of V.

2/4 Image
Oct 29, 2020 • 16 tweets • 5 min read
The new cover article in @NautilusMag is about the sordid history of eugenics in the field of statistics.

I had a conversation with @aubreyclayton a few months ago, when he was beginning his work on this article.

1/🧵 I think this article has a lot of value, as it brings to sharp focus the very racist views of some of the founders of our field: Galton, Pearson, Fisher, in particular. I applaud Aubrey for his very careful research about this topic.

Some screenshots from the article:

2/
Oct 3, 2020 • 5 tweets • 1 min read
WHY DID I SAY A P-VALUE IS A TEST OF SAMPLE SIZE?

THREAD 🧵



Suppose we want to test whether the mean of some random variable X is zero. To keep it simple, X1,...,Xn are i.i.d. N(mu, 1). Testing if mu=0.

1/🧵 Now suppose that IRL mu=0.001 (remember- IRL the null hypothesis never exactly holds!)

The z-test for testing mu=0 involves computing

Z=sqrt(n)*Xbar/sigma

and comparing to a N(0,1) distribution. And sigma=1 by my earlier assumption that X_1,...,X_n are i.i.d. N(mu,1).

2/
Oct 3, 2020 • 13 tweets • 2 min read
FOUR CARDINAL RULES OF STATISTICS 📈📊📉

A thread

1/🧵 ONE: CORRELATION DOES NOT IMPLY CAUSATION.

Yes, I know you know this, but it’s so easy to forget!

Yeah, YOU OVER THERE, you with the p-value of 0.0000001 — yes, YOU!! That’s not causation.

2/
Oct 2, 2020 • 4 tweets • 1 min read
Last week, a paper came out that received a lot of very harsh criticism from the scientific community. First things first: I 100% agree with a lot of that criticism.

Criticizing a paper (or agreeing with others' criticisms of a paper) is okay. That's how science works.

1/ HOWEVER, after seeing the paper, I shot off a careless tweet. It was meant to be lighthearted, but it missed the mark!!!! It came across as a personal attack on the authors.

It was a mistake to have posted it, and I have since deleted it.

2/
Sep 19, 2020 • 4 tweets • 2 min read
Hi scientists, could you please help me understand why this Harvard site says that the FPR of PCR can be as high as 5%?

Is this just due to the risk of sample/lab contamination (hopefully << 5%), or do they consider it a FP if someone who recovered has trace amounts of virus? 1/ Image By contrast this website from MIT is in line with what I thought to be true- virtually no FP from PCR
2/ Image
Sep 11, 2020 • 4 tweets • 2 min read
today my husband said “in a normal year we’d be in air conditioned offices all day and we wouldn’t even notice the horrible air quality”

and that’s the moment I discovered that my husband thinks my office for the past literally 10 years has air conditioning even though it doesn’t have A/C, i do miss it so— for one thing, my office has a door that I can close.

also, who wouldn’t love an office in a building that is ambiguously inspired by either a monastery or a prison? ImageImage
Aug 21, 2020 • 4 tweets • 2 min read
Pre-covid Image And this with @aristeinberg Image
Aug 9, 2020 • 23 tweets • 6 min read
The Bias-Variance Trade-Off & "DOUBLE DESCENT" 🧵

Remember the bias-variance trade-off? It says that models perform well for an "intermediate level of flexibility". You've seen the picture of the U-shape test error curve.

We try to hit the "sweet spot" of flexibility.

1/🧵 This U-shape comes from the fact that

Exp. Pred. Error = Irreducible Error + Bias^2 + Var

As flexibility increases, (squared) bias decreases & variance increases. The "sweet spot" requires trading off bias and variance -- i.e. a model with intermediate level of flexibility.

2/
Aug 7, 2020 • 8 tweets • 2 min read
When I teach cross validation in my Intro to Statistical Learning course, I literally spend a class on “potential pitfalls of CV” and this is the main error I talk about. Happens all the time in published biology literature- not just for methylation data

1/ This error is particularly stressful to me as a statistician, because it means that my data analysis can be totally wrong due to data pre-processing that may have been performed before I ever saw the data and that I don’t know about

2/
Aug 4, 2020 • 4 tweets • 3 min read
It is such an honor to receive the 2021 Breiman Award from @AmstatNews for "outstanding contributions to statistical learning, computational statistics, and their practical applications".

1/4 Image This honor would 100% not have been possible without the mentoring and support that I have received over the years from colleagues @UWBiostat and @UW Stat as well as elsewhere (special shout-out to the one and only @robtibshirani)....

2/4
Jul 24, 2020 • 6 tweets • 1 min read
This is how I feel 99.9% of the time that I watch people cook pasta. Guys this is not that hard.
- Salt the water
- Sauce gets mixed in right away
It isn't rocket science.
Unless you're making soup, do NOT put oil in the water.
I've lost friends over this & I feel OK about that. This tweet proudly brought to you by the daughter of a Neapolitan
Jun 29, 2020 • 5 tweets • 1 min read
I wouldn’t worry - getting COVID under control will be a sinh!!

Or possibly a tanh Actually the issue is asympto(ma)tic
Jun 24, 2020 • 16 tweets • 4 min read
The Fisher Lecture: an epilogue.

I am delighted that COPSS decided to retire the name of the Fisher Award and Lecture, and to create a new COPSS Distinguished Achievement Award and Lecture.

A lot has happened during the past 3 weeks since I posted this original thread.

1/ In the world . . . well, read the news, I can’t give you a recap.

But in case you've been living under a rock . . it’s been a lot.

I’ll focus on just two news items.

2/
Jun 20, 2020 • 4 tweets • 1 min read
When I finished my PhD I told a female statistician (a few years senior to me) that I’d be starting a job @UW.

Her first Q: who will your postdoc advisor be? (A: I was going to be faculty)

Her 2nd Q: what department is your husband’s faculty appointment? (A: 😳 😳 😳) It cuts both ways tho because my husband’s co-workers at the time we’re like “you’re moving all the way to Seattle to go to grad school?!”