The technique of joint likelihood …

I almost spat out my cereal this morning when reading this conference proceedings by Anderson et al. (2015) presenting “the technique of joint likelihoods“.  What’s the technique of joint likelihoods, you ask?  Just the most obvious thing that you’ve been doing since forever: when you have N separate datasets with individual likelihood functions, L_i(\theta,\phi_i), for common parameters of interest, \theta, and nuisance parameters, \phi_i, the technique of joint likelihoods suggests that to perform inference on \theta you multiply the likelihood functions together (as opposed to blowing them out your arse, I presume).

This entry was posted in Uncategorized. Bookmark the permalink.

6 Responses to The technique of joint likelihood …

  1. lukebarnes says:

    Statisticians and your fancy-pants “multiplication”!

  2. Fantastic advance! Now we can analyse data sets that are more than a single number.

  3. You still eat cereal? You should read a little from this blog for a change from astro and stats; it will surely do a lot more for your health and your ability to continue reading astro and stats for years to come:

  4. Phillip Helbig says:

    There was a biology paper a while back which introduced the “new” concept of Riemann integration.

    • True, that paper came up a number of times in my conversations with bioinformaticians last week at the Wellcome Trust … though in each case they themselves brought up this embarrassing example!

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 )

Twitter picture

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

Facebook photo

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

Google+ photo

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

Connecting to %s