Dear all, Given the discussions and issues of d.f., p-values and mcmcsamp-CIs in mixed models, I wonder if anyone could recommend one or two papers (or other citable sources for that sake) that summarizes the arguments for/against P-values/mcCIs. I have followed the discussions on R-help and have learnt a lot (in my naive non-statistician way). With all respect to all great contributions, I may need published articles (if there are any), that could be suitable to use in the Methods-section of a manuscript, to motivate a no-p-values-but-some-nice-mcmcsampCIs-instead-approach! Thanks in advance! Henrik -- ************************ Henrik P?rn Department of Biology NTNU 7491 Trondheim Norway +47 735 96282 (office) +47 909 89 255 (mobile) +47 735 96100 (fax)
Henrik Parn <henrik.parn <at> bio.ntnu.no> writes:> > Dear all, > > Given the discussions and issues of d.f., p-values and mcmcsamp-CIs in > mixed models, I wonder if anyone could recommend one or two papers (or > other citable sources for that sake) that summarizes the arguments > for/against P-values/mcCIs. > > I have followed the discussions on R-help and have learnt a lot (in my > naive non-statistician way). With all respect to all great > contributions, I may need published articles (if there are any), that > could be suitable to use in the Methods-section of a manuscript, to > motivate a no-p-values-but-some-nice-mcmcsampCIs-instead-approach! >Book (Bayesian Data Analysis) by Gelman et al. is very good source of this and much more. You might also find his papers and blog interesting http://www.stat.columbia.edu/~gelman/ http://www.stat.columbia.edu/~gelman/blog/ Gregor