On Sat, 7 Jun 2003, Dennis Roberts wrote in part: > [quoring Herman Rubin] > >The role of the statistician is to advise the person with > >the statistical problem on how to treat it, often devising > >new algorithms in the process. It is also to question the > >investigator about the assumptions, and to point out what > >assumptions make little difference. > > you sure put the role of the statistician down towards the bottom > of the barrel ...
Yes, well, "at the bottom" is where the foundation is built ... > sometimes in fact, the stat person is a co equal participant in the > research or questions being explored ... stat people can have ideas > too Which, as I recall, was precisely one of Herman's points, although his choice of language was "coauthor". Why do you present this idea as though you were disagreeing with him? > you make it sound like the statistician is merely a passive ingredient Dennis you HAVE to be reading that in by projection. 'Tain't in what Herman wrote, so far as I can see. DR>You can't expect every person who has a legitimate interest in "data" DR>to be a "true" statistician ... just like we can't expect every DR>person who has a valid interest in weather phenomena ... to know all DR>the intricate facts and "history" about weather ... > HR>I never claimed this. The investigator, however, is the one HR>who must make the probability assumptions about the data. > > well, i would reinterpret this as ... it is the investigator who is > primarily responsible for trying to outline and detail as much as > possible ... WHAT he/she is trying to accomplish ... what he/she is > primarily interested in exploring ... OK so far ... > BUT, the stat person should not just sit idly by ... Projecting again? > they should try to HELP the party in seeing what might be reasonable > and unreasonable ways to define/collect/examine the data ... Including describing the alternatively nasty effects of making one set of assumptions or another. [ snip, some material with which Dennis wasn't arguing ] > >My "commandments" bear repeating. > > > > I am often requested to repost my five commandments. These are > > posted here without exegesis. > > > > For the client: > > > > 1. Thou shalt know that thou must make assumptions. > > ok ... makes sense > > > 2. Thou shalt not believe thy assumptions. > > then why make assumptions? The obvious reason is because one cannot proceed to any useful result without doing so. > > For the consultant: > > > > 3. Thou shalt not make thy client's assumptions for him. > > well, the consultant should not do the client's project ... THAT i > agree with > > > 4. Thou shalt inform thy client of the consequences > > of his assumptions. > > but, in #2 ... you said for the client not to believe their > assumptions ... so, does the client make assumptions or not? Of course s/he must. One just shouldn't believe them. (One is reminded of George Box's comment (it was Box, wasn't it?) that "All models are wrong; some models are useful." Same principle.) > if the client makes a stupid assumption ... that you said he/she > must make ... shouldn't the consultant speak up and help the client > reshape or consider assumptions that seem to make more sense? That would certainly appear to be a part of "informing thy client of the consequences of his assumptions". [ snip ] DR> I do agree that software makes "output" easy to come by but, that is DR> a totally different matter ... > > HR> Not really. The oracle only answers the questions asked, HR> not the real questions. > > how can we know ad hoc ... that this is the case? How can it NOT be the case? The assertion is true for all oracles -- it's the nature of oracles -- whether the oracle is delivered by a human agent or by a computer program. As it is written, GIGO. Same thing. > i would say that many questions are about as fully answered by > standard output ... as one can get ... others, not so ... Only for those who are quite clear about (1) what questions they WANT to ask of their data and (2) what questions the "standard output" is giving them answers to. These are seldom the same. > one can't make a blanket statement that applies in all (or even > necessarily the majority) cases Depends on the statement, one would have thought. > > One does not just approach the > >altar, pay the priest his fee, present the sacrifice, and > >expect a miracle to provide the state of the universe. > > depends on the religious convictions you hold ... Really? What religious convictions involve the EXPECTING of miracles of any kind, let alone miracles expounding the state of the universe? Don't know of any myself; I suspect this is a figment of your imagination, Dennis. (The nature of a miracle is surprise: that's what the word means. To "expect surprises" is close to an oxymoron; certainly, at any rate, in the complacent form burlesqued by Herman in the metaphor above.) ----------------------------------------------------------------------- Donald F. Burrill [EMAIL PROTECTED] 56 Sebbins Pond Drive, Bedford, NH 03110 (603) 626-0816 . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
