Skip to content
Prev 908 / 20628 Next

interpreting significance from lmer results for dummies (like me)

On Behrens-Fisher; see the Wikepedia article "Unsolved problems in  
statistics",
and references that are given there.

Linnik, Jurii (1968). Statistical Problems with Nuisance Parameters.
American Mathematical Society. ISBN 0821815709.

The link given to the

My reading of the literature is that this is not so much an unsolved
problem as one that has, within the p-value paradigm,  no satisfactory
theoretical solution.   I take this to be a problem with the p-value
paradigm.  For Bayesians there is no problem; all inference is
conditional on one or other choice of prior.  The various frequentist
"solutions" to the Behrens-Fisher problem involve one or other
more limited form of conditioning.

Others may be able to pronounce more authoritatively.

John Maindonald             email: john.maindonald at anu.edu.au
phone : +61 2 (6125)3473    fax  : +61 2(6125)5549
Centre for Mathematics & Its Applications, Room 1194,
John Dedman Mathematical Sciences Building (Building 27)
Australian National University, Canberra ACT 0200.
On 27 Apr 2008, at 2:06 PM, Andrew Robinson wrote: