New revision of How to become a Bayesian in eight easy steps

Quentin, Fabian, Peter, Beth and I recently resubmitted our manuscript titled “How to become a Bayesian in eight easy steps: An annotated reading list” that we initially submitted earlier this year. You can find an updated preprint here. The reviewer comments were pleasantly positive (and they only requested relatively minor changes), so I don’t expect we’ll have another revision. In the revised manuscript we include a little more discussion of the conceptual aspect of Bayes factors (in the summary of source 4), some new discussion on different Bayesian philosophies of how analysis should be done (in the introduction of the “Applied” section) and a few additions to the “Further reading” appendix, among other minor typographical corrections.

This was quite a minor revision. The largest change to the paper by far is our new short discussion on different Bayesian philosophies, which mainly revolve around the (ever-controversial!) issue of hypothesis testing. There is an understandable desire from users of statistics for a unitary set of rules and regulation–a simple list of procedures to follow–where if you do all the right steps you won’t piss off that scrupulous methods guy down the hall from you. Well, as it happens, statistics isn’t like that and you’ll never get that list. Statistics is not just a means to an end, as many substantive researchers tend to think, but an active scientific field itself. Statistics, like any field of study, is a human endeavor that has all sorts of debates and philosophical divides.

Rather than letting these divides turn you off from learning Bayes, I hope they prepare you for the vast analytic viewpoints you will likely encounter as Bayesian analyses become more mainstream. And who knows, maybe you’ll even feel inspired to approach your own substantive problems with a new frame of mind.  Here is an excerpt from our discussion:

Before moving on to our final four highlighted sources, it will be useful if readers consider some differences in perspective among practitioners of Bayesian statistics. The application of Bayesian methods is very much an active field of study, and as such, the literature contains a multitude of deep, important, and diverse viewpoints on how data analysis should be done, similar to the philosophical divides between Neyman–Pearson and Fisher concerning proper application of classical statistics (see Lehmann, 1993). The divide between subjective Bayesians, who elect to use priors informed by theory, and objective Bayesians, who instead prefer “uninformative” or default priors, has already been mentioned throughout the Theoretical sources section above.


A second division of note exists between Bayesians who see a place for hypothesis testing in science, and those who see statistical inference primarily as a problem of estimation. ….

You’ll have to check out the paper to see how the rest of this discussion goes (see page 10).   🙂

3 thoughts on “New revision of How to become a Bayesian in eight easy steps

  1. I’m sorry, I have none of the tools to understand this series, try as I have with earlier episodes, and I have no right to ask you, but I do intuit that is is somehow important in my own train of thought . . . so, sorry, I’m sure this series is already as brief as an introduction to such a thing can be, but . . .

    how many sentences, how many paragraphs would it take to lay out the specific difference between the Bayesian, uh, attitude? Philosophy and the sort of paradigm you’re set against? Sorry again: I mean, in English, in words. I can’t glean anything from numbers, I literally think in words, or I think I do – I sure don’t think in math, although I have a general appreciation for numbers. Can you give me a brief layout of the primary older assumption you’re correcting? That might tell me if I like your general bent and if should try to learn this stuff.

    No right to pester you, I know, just putting my hand out and hoping for something for free. I don’t really dream it, I think you’re writing for statisticians, right? I hope you don’t think this is any slam on you, that you’re not being understood. Honestly, I don’t have the capacity, especially today to even attempt to read this one, I’m just remembering my impressions from previous posts. It seems like great stuff, for what I know about it.

    I have a very simple, almost certainly erroneous complaint I would like to make regarding the twin/adoption study analyses, their use of statistics and their assumptions, and I wonder if my crackpot interpretation would resonate with the direction you’re working in. Wow. I didn’t understand a word, but you made an impression on me, I haven’t forgotten. On better days, I’ll keep trying.


  2. Hello Alexander, thanks for the modifications.
    @Jeff/neighsayer – I am not a statistician either. But, if you take the time to dive into the posts and papers that Alexander has written or collected, you will get a grasp on it.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s