Wednesday, June 14, 2017

Religion in the United States

Last night I had the pleasure of presenting a talk for the PyData Boston Meetup.  I presented a project I started earlier this summer, using data from the General Social Survey to measure and predict trends in religious affiliation and belief in the U.S.

The slides, which include the results so far and an overview of the methodology, are here:

And the code and data are all in this Jupyter notebook.  I'll post additional results and discussion over the next few weeks.

Thanks to Milos Miljkovic, organizer of the PyData Boston Meetup, for inviting me, and to O'Reilly Media for hosting the meeting.


  1. Professor Downey,

    I just want to write a message of appreciation for you and your work. By studying your books on my own, I went from working a pretty crappy job chopping carrots in a kitchen to working a great job as a data engineer at a startup. I now feel like my opportunities are endless.

    You're books are amazing. They are accessible, yet not-watered-down. They are fun and pertinent. By doing the example problems, and by building my own projects using your libraries, I not only learned a ton about object oriented programming in python and statistics, I was inspired by things like "the relationship between fractals and pink noise" (which I read about in ThinkComplexity and which led me to read ThinkDSP) and Bayesian decision science, which I never would have been exposed otherwise.

    These books are an incredible gift to the world. Thank you.

  2. So, I am wondering about the likelihood that what you're seeing in those data amounts to, "people without a religion (in America) used to all say they were Protestant, but now some of them say they have no religion." Trying to think of a statistical way of testing this theory, and I'm not coming up with much...

  3. Very interesting article. I think there is a missing piece to the analysis though. The rise of the "nones" tends to undo itself. Specifically, as individuals and groups become less religious, their birthrates tend to plummet and fall below replacement rate. Religious cultural groups like Mormons, Muslims, etc. tend to have very high birthrates comparatively, so each generation less "Nones" are born than die, while highly religious groups see their populations increase from generation to generation. There may be some religious individuals who become "nones" later in life, but gain, they will tend to may later, have children later and have less children overall. So while we might see a temporary rise in the number of non-religious individuals, over the long-term religion is here to stay for the simple reason that religious people have a lot of kids and non-religious people don't. I've always thought it a great irony that so many religious people don't like evolution, when it's clear that evolution really likes them.