home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!charon.amdahl.com!pacbell.com!ames!saimiri.primate.wisc.edu!zaphod.mps.ohio-state.edu!uwm.edu!spool.mu.edu!nigel.msen.com!ilium!rphroy!kocrsv01!c23st
- From: c23st@kocrsv01.delcoelect.com (Spiros Triantafyllopoulos)
- Newsgroups: rec.autos
- Subject: Re: Before Buying Japanese.
- Message-ID: <1993Jan25.130831.13729@kocrsv01.delcoelect.com>
- Date: 25 Jan 93 13:08:31 GMT
- References: <1993Jan22.142044.20423@magnus.acs.ohio-state.edu> <1993Jan22.220535.10804@leland.Stanford.EDU> <1993Jan22.234608.11303@magnus.acs.ohio-state.edu>
- Sender: news@kocrsv01.delcoelect.com (Usenet News Account)
- Distribution: na
- Organization: Delco Electronics Corp.
- Lines: 38
-
- In article <1993Jan22.234608.11303@magnus.acs.ohio-state.edu> jnielsen@magnus.acs.ohio-state.edu (John F Nielsen) writes:
- >> [...consumer reports stats]
- >>ratings. if the sample size is too small, it's not going to be much
- >>more reliable than asking one or two people. the information they
- >>give may still be useful, but it will be lacking in authoritativeness.
- >>
- >How can you say their sample size is too small. Do you know what
- >tolerances they are willing to accept?
-
- They *won't* tell.
-
- If they could prove, one way or the other, that they have a sufficient
- sample size (representative of the population) and that the distribution
- of cars in the sample is more or less indicative of the population,
- they may have a case.
-
- The methods required are very simple; any junior level stat textbook
- has the methods for verifying distributions and checking sample sizes.
-
- But the issue is that it all depends on voluntary returns of questionmarks,
- and, that the responses do not take into account at all driving conditions.
- Give me any car and I can beat the living crap out of it by driving it in,
- say, Chicago, for a year. Take the same car and drive it for a year in
- Sarasota, FL. and see if you get different results. Substitute Chicago
- for 'aggresive under 25 year old driver', 'mom with 4 kids and stuff on
- a small car', 'older driver driving 3 miles a day', etc and you'll see
- what I'm talking about.
-
- If you have this information also it is quite easy to see what is going on.
- Otherwise it ends up sounding too much like the link between coffee and
- heart disease (there isn't one, yet CR style statistics convinced quite
- a few people that there is one. A classic stat textbook example).
-
- Spiros
- --
- Spiros Triantafyllopoulos c23st@kocrsv01.delcoelect.com
- Software Technology, Delco Electronics (317) 451-0815
- GM Hughes Electronics, Kokomo, IN 46904 [A Different Kind of Disclaimer]
-