From W.J.Murray@rl.ac.uk Wed Apr 12 16:18:56 2000 Date: Fri, 31 Mar 2000 17:00:43 +0100 From: W.J.Murray@rl.ac.uk To: Giulio.Dagostini@roma1.infn.it, harry@fsheb2.hep.fsu.edu Cc: [See mailing list in a separate file] Subject: RE: Conclusions of the CERN CLW Hi Giulio, I was sorry to hear at the FNAL workshop that you were not well - your contribution was missed. However, we got both the original ten points in FNAL from Fred James, and an extended version of of about 12 from Glen Cowan, I think. And no-one voiced any complaints. This is NOT to say that everone agreed with using Feldman+Cousins method for limits - just this list of agreed points. Which do you take issue with? 1) Civility 2) P(Hypothesis|data) requires a prior 3) Likelihood is not a PDF in the unknown parameters 4) Answers assuming Uniform prior depend upon the metric 5) Consistent treatment of UL requires automatic 2-sided CL 6) Bayesian intervals do not have frquentist coverage 7) Publishing L function is encouraged 8) Chi2 does not exist naturally in Bayes statistics 9) Classical CI construction has no prior 10) Any argument for objective decisions ignores the subjective utility function. I might question 5), which I think is too strong, but I would like to know which you disagree with? Cheers, Bill Murray > -----Original Message----- > From: Giulio D'Agostini [mailto:Giulio.Dagostini@roma1.infn.it] > Sent: 30 March 2000 22:49 > To: Harrison B. Prosper > Cc: Yves Perrin; Giulio D'Agostini; Alan.Norton@cern.ch; > alex.read@fys.uio.no; alexander.oh@desy.de; alfredo.cocco@cern.ch; > Andre.Holzner@cern.ch; andrea.perrotta@bo.infn.it; > Andrei.Kounine@cern.ch; anna.lipniacka@cern.ch; Anna.Okpara@cern.ch; > arik@idc.ctbto.org; biron@ifh.de; bityukov@mx.ihep.su; > borut.kersevan@cern.ch; bostjan.golob@cern.ch; > bouchez@hep.saclay.cea.fr; Brigitte.Vachon@cern.ch; > byronroe@umich.edu; > caria@ca.infn.it; carlino@cern.ch; carlo.dionisi@roma1.infn.it; > Catia.Grimani@pg.infn.it; celso.martinez.rivero@cern.ch; > Chris.Tully@cern.ch; claudia.cecchi@cern.ch; clifford@stats.ox.ac.uk; > conway@pion.Rutgers.EDU; cousins@physics.ucla.edu; d37@nikhef.nl; > daniel.lellouch@weizmann.ac.il; daniel.zer-zion@cern.ch; > danielle.moraes@cern.ch; deg@lbl.gov; degrassi@padova.infn.it; > dgc@lns.cornell.edu; dicredico@lngs.infn.it; > Dimitri.Bourilkov@cern.ch; > Donatella.Lucchesi@pd.infn.it; eilam.gross@cern.ch; > enrico.piotto@cern.ch; Erica.Polycarpo@cern.ch; f.james@cern.ch; > Fabrizio.Parodi@cern.ch; Fancesco.Anselmo@cern.ch; > Federica.Mazzucato@cern.ch; federica.strumia@cern.ch; > feldman@physics.harvard.edu; g.cowan@rhbnc.ac.uk; > Gaston.Wilquet@hep.iihe.ac.be; geoffrey.morton@cern.ch; > giles.barr@cern.ch; giunti@to.infn.it; gustavo.wolf@cern.ch; > hongbo.hu@cern.ch; Jacques.Goldberg@cern.ch; James.Letts@cern.ch; > Jason.Nielsen@cern.ch; Jean-Jacques.Blaising@cern.ch; jeitler@cern.ch; > jin@wisconsin.cern.ch; john.holt@cern.ch; kafka@tuhep3.phy.tufts.edu; > kapusta@in2p3.fr; Kara.Hoffman@cern.ch; klaus@ik1.fzk.de; > kuze@mail.desy.de; l.lyons@physics.ox.ac.uk; lebrun@in2p3.fr; > luc.pape@cern.ch; Madjid.Boutemeur@cern.ch; Maneesh.Wadhwa@cern.ch; > marcello.messina@cern.ch; Marco.Pieri@cern.ch; > marco.verzocchi@cern.ch; > marta.felcini@cern.ch; Martin.Grunewald@cern.ch; > massimo.corradi@bo.infn.it; Mathieu.Doucet@cern.ch; > Matts.Roos@Helsinki.fi; michaelw@umich.edu; > miguel.angel.falagan@cern.ch; muanza@ipnl.in2p3.fr; > navarria@bo.infn.it; > nicolas.delerue@desy.de; Niels.Kjaer@cern.ch; nolty_r@caltech.edu; > p.litchfield@rl.ac.uk; Pablo.Garcia.Abia@cern.ch; > paolo.bonifazi@roma1.infn.it; pasquale.migliozzi@cern.ch; > patricia.goncalves@cern.ch; pedrotd@physics.gla.ac.uk; > peter.bock@physi.uni-heidelberg.de; Peter.Igo-Kemenes@cern.ch; > peter.mcnamara@cern.ch; Peter.Wienemann@cern.ch; > Philip.Seager@cern.ch; > Philippe.Charpentier@cern.ch; pia.astone@roma1.infn.it; > Piero.Zucchelli@cern.ch; Pierre.Lutz@cern.ch; punzi@pisa.infn.it; > ridky@cern.ch; Robert.Clare@cern.ch; Robert.McPherson@cern.ch; > roberto.contri@ge.infn.it; roger.barlow@cern.ch; > Roumen.Tzenov@cern.ch; > S.Vlachos@cern.ch; Salvatore.Mele@cern.ch; > salvatore.sorrentino@cern.ch; > santoni@clrhp4.in2p3.fr; schwier@physics.umn.edu; > Serguei.Shevchenko@cern.ch; shvorob@cern.ch; > Silvia.Costantini@cern.ch; > simonetta.gentile@cern.ch; Stefania.Ricciardi@cern.ch; > stephane.keller@cern.ch; tatjana.unverhau@cern.ch; teyssier@cern.ch; > thomas.alderweireld@cern.ch; thomas.jannakos@bk.fzk.de; > Thomas.Speer@cern.ch; Thorsten.Kuhl@cern.ch; Tim.Christiansen@cern.ch; > Tom.Junk@cern.ch; volker.blobel@desy.de; w.murray@rl.ac.uk; > wes@hef.kun.nl; wilbur.venus@cern.ch; wolfgang.adam@cern.ch; > yorck@avalon.lngs.infn.it; Yves.Perrin@cern.ch; > zech@physik.uni-siegen.de > Subject: Conclusions of the CERN CLW > > > > > Dear participants to the CERN CLW, > > if you want to get an idea on how one > `tells the truth with statistics', > I would recommend you to give a look at > http://home.cern.ch/~pubxx/www/delsec/forum/010200/intro.html Did you realize that YOU agreed on the following "Apart from a few "outliers", there was general agreement on a rather extensive list of points proposed by Bob Cousins."? Best wishes, Giulio