LINK-Bayesian methods in drug development and regulatory review

post by polymathwannabe · 2014-04-04T14:58:04.476Z · LW · GW · Legacy · 5 comments

Contents

5 comments

This year's first issue of Pharmaceutical Statistics is all about Bayes. All the articles are free downloadable PDFs:

http://onlinelibrary.wiley.com/doi/10.1002/pst.v13.1/issuetoc?campaign=dartwol|42819650

5 comments

Comments sorted by top scores.

comment by ChristianKl · 2014-04-05T02:56:30.326Z · LW(p) · GW(p)

How about giving excerpts?

Replies from: buybuydandavis
↑ comment by buybuydandavis · 2014-04-05T23:40:49.552Z · LW(p) · GW(p)

Feel free to do so.

I'll take a useful notice without complaint. He did even post it as a LINK. Truth in advertising, and a useful notice. I'd rather have people post useful info than refrain for want of a write up.

Replies from: ChristianKl
↑ comment by ChristianKl · 2014-04-06T12:26:08.922Z · LW(p) · GW(p)

There a media thread for useful links.

I think that it's a good custom for discussion post to contain excerpts and by the time of my writing the post was at -2.

Replies from: buybuydandavis
↑ comment by buybuydandavis · 2014-04-06T23:43:56.204Z · LW(p) · GW(p)

IMO, omnibus continuing threads don't work in our date focused list software. I was completely unaware of those threads, and I've been here nearly 3 years.

I'd rather have people just post them with an appropriate tag, like the OP did.

comment by gwern · 2014-04-18T17:44:02.874Z · LW(p) · GW(p)

I enjoyed

  • "Bayesian methods for design and analysis of safety trials", Price et al 2013.

    Good overview, and I see many old friends like multi-level models & meta-analyses mentioned.

  • "Use of historical control data for assessing treatment effects in clinical trials", Viele et al 2013

    Informative priors are one of the major attractions of Bayesian and meta-analytic approaches for me (I'd much rather express my prior information directly than sweep it under the rug and play games of modus ponens/tollens with everyone), so I found this paper particularly interesting - all about how to draw upon previous clinical trials' results for running new experiments. It's a little dismaying how much effort seems to be going into approaches which strike me as completely unprincipled hacks like the 'power priors' rather than focusing on models which match the underlying facts, like hierarchical modeling or using covariates to directly estimate similarity of past & present data points, but at least people are working along those lines!