HN user

AllenDowney

214 karma
Posts32
Comments20
View on HN
towardsdatascience.com 6y ago

The Inspection Paradox is Everywhere: a surprising statistical illusion

AllenDowney
33pts4
blogs.scientificamerican.com 9y ago

Programming is a tool for teaching, learning, exploring, and thinking

AllenDowney
2pts0
www.npr.org 11y ago

'Game of Thrones' Fans Develop Formula to Determine Who Might Survive Series

AllenDowney
1pts0
thinkdsp.blogspot.com 11y ago

Draft of Think DSP: a Python-based introduction to digital signal processing

AllenDowney
5pts0
allendowney.blogspot.com 11y ago

Bayesian election forecasting: a simple explanation

AllenDowney
2pts0
www.technologyreview.com 12y ago

Internet use is associated with non-religion

AllenDowney
8pts2
allendowney.blogspot.com 13y ago

Software engineering practices all grad students should adopt

AllenDowney
1pts0
allendowney.blogspot.com 13y ago

Excerpt from Think Bayes: statistical analysis of belly button bacteria

AllenDowney
3pts0
oreillynet.com 13y ago

Webcast on Friday: Intro to Bayesian Statistics using Python

AllenDowney
2pts0
allendowney.blogspot.com 14y ago

Internet use undermines religious affiliation.

AllenDowney
2pts0
allendowney.blogspot.com 14y ago

By 2030, None will be the second-largest religious affiliation in the US.

AllenDowney
8pts0
allendowney.blogspot.com 14y ago

What caused widespread religious disaffiliation in the 1990s?

AllenDowney
2pts0
allendowney.blogspot.com 14y ago

Secularization in America: fewer Protestants, more Nones

AllenDowney
2pts0
allendowney.blogspot.com 14y ago

GSS: Religion declining in U.S.; fraction of Nones increasing (fast).

AllenDowney
2pts0
allendowney.blogspot.com 14y ago

The passive voice is a hoax $100 if you can find a journal that requires it.

AllenDowney
1pts1
allendowney.blogspot.com 14y ago

Analysis of the original Bayesian inference (from 1763)

AllenDowney
4pts0
allendowney.blogspot.com 14y ago

Bayesian statistics tutorial: video from PyCon

AllenDowney
10pts0
allendowney.blogspot.com 14y ago

Self-organized criticality and the Great Man theory of history.

AllenDowney
1pts0
allendowney.blogspot.com 14y ago

Small world graphs and scale-free networks: excerpt from Think Complexity

AllenDowney
2pts0
allendowney.blogspot.com 14y ago

Third installment of Think Complexity, a new book about complex systems.

AllenDowney
2pts0
allendowney.blogspot.com 14y ago

25% of college freshmen have no religion, but the gender gap is growing.

AllenDowney
3pts0
allendowney.blogspot.com 14y ago

The philosophy of complexity: from a new O'Reilly book, Think Complexity.

AllenDowney
1pts0
allendowney.blogspot.com 14y ago

Excerpts from new O'Reilly book on Complexity Science.

AllenDowney
7pts0
allendowney.blogspot.com 14y ago

Crackpot science, Bayesian estimation and the Variability Hypothesis.

AllenDowney
1pts0
allendowney.blogspot.com 14y ago

Are first babies lighter? An example of multiple regression in Python and R.

AllenDowney
2pts0
allendowney.blogspot.com 14y ago

A Bayesian model to estimate the age of a renal tumor.

AllenDowney
2pts0
allendowney.blogspot.com 14y ago

New version of the Girl Named Florida: now with more Bayes.

AllenDowney
1pts0
allendowney.blogspot.com 14y ago

World's hardest probability problem: the red-haired girl named Florida

AllenDowney
2pts0
allendowney.blogspot.com 14y ago

Why red hair is funny: a Bayesian analysis.

AllenDowney
5pts0
allendowney.blogspot.com 14y ago

All your Bayes are belong to us: fun Bayes's Theorem problems.

AllenDowney
80pts5

That's true. I have the good fortune to work at a college (Olin College) that recognizes that my work developing textbooks is aligned with the mission of the institution, and can have as much external impact as research. But you are right -- most places give professors zero credit for writing textbooks.

I understand that "just write a book" might come off as glib, especially for profs who teach 3+ classes per semester. So I don't mean that everyone has to, or should, but

1. Writing 150 pages that are targeted for your class and your students is easier than writing "the bible" for your field.

2. The quality of the first draft might not be great, but if you are getting feedback and constantly improving, it's not long before you are better off than using one of the expensive tomes.

3. If you start with other free material, you can get off to a fast start (several people have now written books that started with my material, and then evolved beyond recognition).

This is very similar to my method. The first time I teach a class, I draft some notes. After the class, I fix the problems, or at least flag them for next time. The second time through, I add, remove, edit, refine, etc., based on feedback from students and my own observation (and, often, what I have learned since last time :)

Many of my examples start with code, so the first draft of the chapter is mostly explaining the worked example.

It's not very different from the work most profs do when they are developing a class, but at the end you have a book that has co-evolved to fit your students and the learning goals.

Hi All, Thanks for your interest in this book! It is a very rough draft, but I welcome comments and suggestions.

The code examples are not quite ready for prime time, but I will release them soon and update the (missing) link in the book.

Ignore the haters -- Think Bayes is going to be awesome!

Just kidding (mostly), but your point is correct: there is no book that is right for all audiences. But if you can program, and the mathematical approach to this material doesn't do it for you, this book might.

I need to write a preface to answer this question, but the most important prereq is Python programming. The premise of the series is that if you can program (in any language) you can use that skill as leverage to learn about other topics.

So I would recommend

1. Think Python 2. Think Stats 3. Think Bayes

I am coming around to the conclusion that this example is more trouble than it's worth. I think it's kind of fun, but it does seem to annoy people.

This kind of feedback is exactly why I like to post drafts early. Expect this example to magically disappear very soon :)

Yes, that's exactly what the objective of this book is! I am not using computation out of necessity, but rather because I think it provides leverage for understanding the concepts, and learning to (as you say) compose traditional models and build new ones.

As the book comes along, I am finding that many ideas that are hard to explain and understand mathematically can be very easy to express computationally, especially using discrete approximations to continuous distributions.

For example, I just posted a section on ABC

http://www.greenteapress.com/thinkbayes/html/thinkbayes008.h...

that (I think) really demonstrates the strength of this approach.

Of course, my premise only applies for people who are as comfortable with programming as with math, or more so.

Sorry! It's really not meant to be a trick. The book is under a CC license. I provide the PDF version at Green Tea Press, the LaTeX source for anyone who wants to make a modified version, and a not very good HTML version (some of the math is broken). O'Reilly provides the printed and Kindle versions.

Right now all versions have the same content, but I will continue to revise, so you can think of the version on Green Tea Press as the draft of the second edition.

I know it can be confusing, but I hope the benefits of the free license make up for it.

Thanks! I am hoping to get back to the Complexity book soon. I want to finish the section on agent-based modeling (and I need to remove some of the stats material that I poached for Think Stats).

Clojure looks interesting, but I don't know much about it, so I probably won't do anything with it soon. But part of the reason I use free licenses is so that other people can adapt my books.

Nicholas Monje is working on Think OCaml (http://thinkocaml.com); that might be the best version to translate into Clojure.

I tried to keep the code simple -- no Python esoterica, only a few objects. So it should be easy to pick up the Python as you go along.

But let me know whether that turns out to be true.

Thanks for the kind words about the book! If you are interested in this topic, there is a video of me giving a talk about it at greenteapress.com/semaphores. The thread simulator I demonstrate in the talk is available from allendowney.com/swampy. As always, comments are welcome.