Nicola Sartori - Median bias reduction of maximum likelihood estimates

22 months ago by

Sunday 2nd October 9:00-9:30am

Sartori Slides

Community: WHOA-PSI 2016

1 Answer

21 months ago by

For the 1-interest parameter logistic regression question, when the interest parameter has a finite estimate, you can reduce the regression problem to a simpler one with the same conditional distribution for the sufficient statistic associated with the interest parameter that removes sthe parameter estimated at infinity.  The conditional likelihood remains the same, and so you could use this to reduce median bias in a context that doesn't have to worry about the infinite estimate.  A reference is Kolasa (1997) Scand J Stat.  Have you considered this approach?

Please login to add an answer/comment or follow this question.