Live data from Hacker News

Bayesian Data Analysis, Third edition (2013) [pdf]

sites.stat.columbia.edu

21–30 of 71 posts

Re: Bayesian Data Analysis, Third edition (2013) [pdf]

#21
post #13

This is my favorite book on statistics. Full stop. The author Andrew Gelman created a whole new branch of Bayesian statistics with both his theoretical work on hierarchical modeling while also publishing Stan to enable practical applications of hierarchical models. It took me about a year to work through this book on the side (including the exercises) and it provided the foundation for years of fruitful research into…

What is a book / course on statistics that I can go through before this so that I can understand this?

I don’t mean for the bar to sound too high. I think working through khan academy’s full probability, calculus and linear algebra courses would give you a strong foundation. I worked through this book having just completed the equivalent courses in college.

It’s just a relatively dense book. There’s some other really good suggestions in this thread, most of which I’ve heard good things about. If you have a background in programming, I’d suggest Bayesian Methods for Hackers as a really good starting point. But you can also definitely tackle this book head on, and it will be very rewarding.

Re: Bayesian Data Analysis, Third edition (2013) [pdf]

#23
post #4

Looking for more self study statistics resources for someone with a CS degree, any other recs?

Start with statistics by David Freedman. It is very approachable as an introduction, not too theory heavy, can get a handle on all of the "main" issues. Afterwards, you have 2 options:

1) Do you want "theoretical" knowledge(math background required)? If so, then you need to get a decent mathematical statistics book like Casella-Berger. I think a good US CS degree grad could handle it, but you might need to go a bit slow and google around/ maybe fill in some gaps in probability/calculus.

2)Introduction to Statistical Learning is unironically a great intro to "applied" stats. You have most of the "vanilla" models/algorithms, theoretical background behind each but not too much, you can follow along with the R version and see how stuff actually works and exercises that vary in difficulty.

With regards to Gelman and Bayesian data analysis, I should note that in my experience the Bayesian approach is 1st year MS /4th year of a Bachelors in the US. It's very useful to know and have in your toolbox but IMO it should be left aside until you are confident in the "frequentist" basics.

Re: Bayesian Data Analysis, Third edition (2013) [pdf]

#24

Earlier quoted context omitted.

Is there a good book that covers statistics as it is applied to testing - like for medical research or as optimization or manufacturing or whatever?

The key insight to recognize is that within the Bayesian framework hypothesis testing is parameter estimation. Your certainty in the outcome of the test is your posterior probability over the test-relevant parameters. Once you realize this you can easily develop very sophisticated testing models (if necessary) that are also easy to understand and reason about. This dramatically simplifies. If you're looking for a spe…

I might checkout Statistical Rethinking given how frequently it is being recommended!

Edit: Haha I just found the textbook and I’m remembering now that I actually worked through sections of it back when I was working through BDA several years back.

Re: Bayesian Data Analysis, Third edition (2013) [pdf]

#25
post #13

This is my favorite book on statistics. Full stop. The author Andrew Gelman created a whole new branch of Bayesian statistics with both his theoretical work on hierarchical modeling while also publishing Stan to enable practical applications of hierarchical models. It took me about a year to work through this book on the side (including the exercises) and it provided the foundation for years of fruitful research into…

What is a book / course on statistics that I can go through before this so that I can understand this?

Bayesian Statistics the Fun Way is probably the best place to start if you're coming at this from 0. It covers the basics of most of the foundational math you'll need along the way and assumes basically no prerequisites.

After than Statistical Rethinking will take you much deeper into more complex experiment design using linear models and beyond as well as deepening your understanding of other areas of math required.

Re: Bayesian Data Analysis, Third edition (2013) [pdf]

#26
post #13

This is my favorite book on statistics. Full stop. The author Andrew Gelman created a whole new branch of Bayesian statistics with both his theoretical work on hierarchical modeling while also publishing Stan to enable practical applications of hierarchical models. It took me about a year to work through this book on the side (including the exercises) and it provided the foundation for years of fruitful research into…

What is a book / course on statistics that I can go through before this so that I can understand this?

Regression and Other Stories. It’s also co-authored by Gelman and it reads like an updated version of his previous book Data Analysis Using Hierarchical/Multilevel Models.

Statistical Rethinking is a good option too.

Re: Bayesian Data Analysis, Third edition (2013) [pdf]

#27
post #26

Earlier quoted context omitted.

What is a book / course on statistics that I can go through before this so that I can understand this?

Regression and Other Stories. It’s also co-authored by Gelman and it reads like an updated version of his previous book Data Analysis Using Hierarchical/Multilevel Models. Statistical Rethinking is a good option too.

Can second Regression and Other Stories, it's freely available here: https://users.aalto.fi/~ave/ROS.pdf, and you can access additional information such as data and code (including Python and Julia ports) here: https://avehtari.github.io/ROS-Examples/index.html

Re: Bayesian Data Analysis, Third edition (2013) [pdf]

#28
post #5
post #3

I'm a fan of the stats blog hosted by Columbia that Gelman is the main contributor to: https://statmodeling.stat.columbia.edu

Thanks for sharing, any particular articles that had last impact on you?

Beyond “power pose”: Using replication failures and a better understanding of data collection and analysis to do better science https://statmodeling.stat.columbia.edu/2017/10/18/beyond-pow...

You need 16 times the sample size to estimate an interaction than to estimate a main effect https://statmodeling.stat.columbia.edu/2018/03/15/need16/

Debate over effect of reduced prosecutions on urban homicides; also larger questions about synthetic control methods in causal inference. https://statmodeling.stat.columbia.edu/2023/10/12/debate-ove...

Bayesians moving from defense to offense: “I really think it’s kind of irresponsible now not to use the information from all those thousands of medical trials that came before. Is that very radical?” https://statmodeling.stat.columbia.edu/2023/12/23/bayesians-...

Re: Bayesian Data Analysis, Third edition (2013) [pdf]

#29
post #13

This is my favorite book on statistics. Full stop. The author Andrew Gelman created a whole new branch of Bayesian statistics with both his theoretical work on hierarchical modeling while also publishing Stan to enable practical applications of hierarchical models. It took me about a year to work through this book on the side (including the exercises) and it provided the foundation for years of fruitful research into…

What is a book / course on statistics that I can go through before this so that I can understand this?

Highly recommend Stats 110 from Blitzstein. Lectures and textbook are all online https://stat110.hsites.harvard.edu/

Re: Bayesian Data Analysis, Third edition (2013) [pdf]

#30
I can attest how useful Bayesian analysis is. My team recently needed to sample from many millions of items to test their qualities. The question is that given a certain budget and expectation, what's the minimum or maximum number of items that we need to sample. There was an elegant solution to this problem.

What was surprising, though, was how reluctant the engineers are to learn such basic techniques. It's not like the math was hard. They all went through the first-year college math and I'm sure they did reasonably well.

Post reply on HN