Subject: Re: Looking for a good statistical analysis software for quality
From: harmonic@world.std.com
Date: Sat, 7 Dec 1996 00:09:20 GMT
In article <57i224$5mb@wagner.spc.videotron.ca>,
Jean-Luc Lemieux wrote:
>Hi!
>
>We are implementing process random sampling of different product we are manufacturing and
>I am looking for an easy (ie user friendly) software to record the result and draw graphs
>and/or charts of the sampling result (mean, variation, % of certainty, Mean comparison,
>ANOVA, etc.)
>
>Could you suggest any package that would meet this description?
>
>Thank again for the help.
>
>NB. I will post back the result of this enquiry to share with all.
>Jean-Luc Lemieux
You might try O-Matrix. You can get a free copy from
http://world.std.com/~harmonic
Subject: Re: UNIX OPERATING SYSTEM, WHICH ONE!!!!!!!
From: williamc@uclink2.berkeley.edu (William Chow)
Date: 7 Dec 1996 02:44:18 GMT
Alain Cardinal (cardinaa@sit.qc.ca) wrote:
: Evan Leibovitch wrote:
: >
: > In article <329CB17A.C9F@ucla.edu>, Bryan Austin wrote:
: >
: > >I am in the market for a UNIX operating system. I have narrowed the
: > >search down to three 3 prospects: SCO UNIX 2.1, Solaris x86 UNIX, and
: > >Lunix. My question is, which of the three is the best choice, and more
: > >importantly, Why? I will be using the operating system for business and
: > >personal use.
: >
: > >I am positive that all three OSs have some strengths and weaknesses.
: > >This has been my method of evaluation so far. If anyone can help please
: > >reply.
: For personal use: LINUX is good choice, the price is important.
: For business use: LINUX is dangerous.
Actually, in the recent PC Week, there were a couple of reports that
businesses were using Linux and Apache for stuff like WWW servers...
: SCO is most stable.
: Solaris is most stable and you can upgrade to better computer system.
Hmmmm.... How stable is Solaris anyway? I called tech support last time
(big mistake, Sun tech support is next to useless...) and it appears that
there's a list of some 150 known bugs? There's also a patch CD-ROM that
comes with Solaris (running this on a Sparc). Are these simply minor bugs?
(I haven't had a real crash with Solaris yet...)
: Why do you use UNIX system? for application, not for only UNIX system.
: Usually, in business, you should not restart your computer at each days.
: You should have stability of operating system.
: You have not the choice of Great application (Oracle, Informix, ...)
: with linux.
This is very true, the MOST damaging case against free OSes like Linux is
that they usually don't have a lot of end user apps. They do have access
to a lot of development tools because of GNU. (Hell, I use gnu stuff in
Solaris, not only because it's free, sometimes because it's better...)
It's hard to predict if this will change anytime soon.
: PC is not computer stable. When you have computer room with 20 servers
: (10 SGI and 10 PC). You should restart your PC at regular time. For
: SGI, you forget to shutdown your SGI one year after.
: SGI, SGI, OSF and AIX is very stable.
I've actually heard the opposite, that SGI wasn't terribly reliable (but
that's in relation to Sun).
: If you have any problem with Oracle product or Netscape. On SGI and SUN
: that's funny for support. With LINUX, The compagnie Oracle and other
: you respond "just select good machine and you will have good support".
Well, actually, there ARE firms that have pay-as-you-go support for Linux,
like Cygnus. I cannot comment on their effectiveness. The support I
received from Sun wasn't very impressive... I was also rather surprised at
the lack of a user manual included with Solaris, you have to print it out
(and who exactly has the time and money to print out a couple hundred
pages of documents?)... I guess customer service isn't a priority at Sun.
: Why do you want? UNIX PC for games and Words, or UNIX for business
: application.
: UNIX SYSTEM ADMINISTRATOR
: cardinaa@sit.qc.ca
Subject: pronunciation of statisticians' names
From: Desmond Allen
Date: Sat, 07 Dec 1996 17:38:27 +0000
I am presently trying to render the names of various statisticians into
Japanese. Unfortunately I don't know the national or linguistic origins
of many of them which makes it impossible to guess the pronunciaton of
their names particularly in regard to correct vowel sounds and their
length, the syllable stress, silent letters, v/w, ch/k etc.
Could anyone help me with the following please:
Sidak,Hochberg,Einot,Welsch,Tamhane,Waller,Breslow,Meyer,Olkin,Tarone,
Levene,Geisser,Cronbach,Mantel,Haenszel,Mauchly,Desu,Hamann,
Jaccard,Dice, Huynh, Feldt, Kaiser, Kulczynski, Theil, Prais.
Many thanks
Des Allen
Machida Shi, Japan
e-mail: dw6d-alln@asahi-net.or.jp
PS Thanks for the response re Wald = Woll
Subject: Re: Looking for a good statistical analysis software for quality
From: Johan Zietsman
Date: Sat, 07 Dec 1996 10:57:05 +0200
harmonic@world.std.com wrote:
>
> In article <57i224$5mb@wagner.spc.videotron.ca>,
> Jean-Luc Lemieux wrote:
> >Hi!
> >
> >We are implementing process random sampling of different product we are manufacturing and
> >I am looking for an easy (ie user friendly) software to record the result and draw graphs
> >and/or charts of the sampling result (mean, variation, % of certainty, Mean comparison,
> >ANOVA, etc.)
> >
> >You may try your normal spreadsheet as a first order tool. I know qpro has some very nice features in this regard.
Cheers,
Ziets
Subject: Re: UNIX OPERATING SYSTEM, WHICH ONE!!!!!!!
From: blove@mrinc.com (Dr. Buddy Love)
Date: Sat, 07 Dec 1996 19:37:53 GMT
>Actually, in the recent PC Week, there were a couple of reports that
>businesses were using Linux and Apache for stuff like WWW servers...
The last time I tried to use Linux and Apache (about a month ago), the
web server kept hanging up (kinda like they do in UW 2.1).
>Hmmmm.... How stable is Solaris anyway? I called tech support last time
>(big mistake, Sun tech support is next to useless...) and it appears that
>there's a list of some 150 known bugs? There's also a patch CD-ROM that
>comes with Solaris (running this on a Sparc). Are these simply minor bugs?
>(I haven't had a real crash with Solaris yet...)
At least they acknowledge that bugs exist, contrary to SCO's policy of
denial.
Subject: Re: Sequential Significance Testing
From: hrubin@b.stat.purdue.edu (Herman Rubin)
Date: 7 Dec 1996 14:34:54 -0500
In article <580q84$lcg@wnnews1.netlink.net.nz>,
David Hadorn wrote:
>I'm trying to ascertain the current "conventional wisdom" among
>philosophically minded statisticians concerning the validity of sequential
>significance testing. On the one hand are Bayesian statisticians, who condemn
>the whole notion of sequential testing as symptomatic of the fatal flaws in
>frequentist-based Fisherian significance testing (e.g., "why should what *I*
>believe depend on how often *he* peeked at the data [using an inevitably
>arbitrary set of stopping rules]?"), and who have sometimes called sequential
>testing "sampling to a foregone conclusion."
Bayesian statisticians may criticize some kinds of sequential procedures,
but I have had three PhD students write dissertations on this, and I consider
it an essential part of statistics.
In most standard situations, a Bayesian will state that the terminal action
should not depend on the stopping rule. This is the case if the probability
of stopping at the actual point does not depend on the state of nature, but
merely on the observations.
Now no Bayesian will consider sampling until the null hypothesis is rejected
at the .05 level and then stating that it is false as reasonable. It is
necessary to take into account both the probability of the various types
of error in the terminal decision and the cost of observation.
On the other hand are the
>classical statisticians who seem to see nothing wrong with sequential testing
>as long as the .05 probability "account" is "spent" a little at a time over
>the sequential tests. But doesn't Fisherian significance testing depend on
>*preassignment* of the experimental outcome space, and doesn't sequential
>testing violate this tenet?
>The issue has become quite an important one in the field of health outcomes
>research (which is where I'm coming from), because more and more studies are
>being stopped early because of the results seen during early peeking at the
>data. Combined with an unfortunate and increasing propensity to conduct
>studies without blinding (and without testing the inter-observer reliability
>of assessment of soft outcomes) it seems to me we are going to see more and
>more treatments given formal blessing without really being subjected to the
>full and rigorous testing we once aspired to.
Much more should be done in this direction. Bayesian sequential analysis,
somewhat more complicated than it is usually done, can be used to make
intelligent decisions on how to treat patients while trials are still
being done.
Do not go by simplistic Bayesian presentations; it is not an automatic
procedure, but takes input which must be provided by the user, not the
statistician. It is only when the user fully specifies all aspects of
the problem that the statistician can just take over.
>Any thoughts would be welcome. Please reply privately (or cc: me if posted to
>list) as my mail reader is unreliable over here.
>Thanks!
>David Hadorn
>david.hadorn@vuw.ac.nz
--
Herman Rubin, Dept. of Statistics, Purdue Univ., West Lafayette IN47907-1399
hrubin@stat.purdue.edu Phone: (317)494-6054 FAX: (317)494-0558
