Ian McKeague - Marginal screening and post-selection inference


277
views
0
9 months ago by
McKeague Slides (click here)
Community: WHOA-PSI 2017

2 Answers


0
9 months ago by
In the discussion of McKeague & Qian (2015), Shah & Samworth suggested calibration using permutations, since the global null had a particular simple form there. It seems the same argument applies here. Is that right?

I asked the same question about Judy's talk, but she explained that in her setting it wouldn't work.
0
9 months ago by
According to the simulation results on slide 21 of my talk, calibration using permutations is around 100 times slower (and less powerful) than the Monte Carlo calibration we develop.  
Please login to add an answer/comment or follow this question.

Similar posts:
Search »
  • Nothing matches yet.