Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Help for 3rd tier users of stata

From   n j cox <>
Subject   Re: st: Help for 3rd tier users of stata
Date   Wed, 19 Jul 2006 14:04:08 +0100

I am not at all familiar with this terminology of
tiers of users (is a high number complimentary or
not? are tiers like floors?) and I detest the term
"power user", which is too redolent of testosterone
and very large motor cycles for my taste. (Apologies
to all my Statalist friends who will now turn out to have,
or to admire, very large motor cycles. Stata's Angels,
Harvard Chapter, perhaps.) But terminology
aside, Woody seems to be echoing Suzy Scott, who
on 3 July asked

----------------------------------- Suzy Scott
Off the beaten track somewhat, but something that might be helpful in
the long run for encouraging new Stata users, which I've suggested once
before and I'll bring it up again. It might be nice to also have a
beginner/student Stata listserv - something just a bit more
newbie/student friendly. By that I mean a little more easy-going, not
too protocol intensive, a place where perhaps more basic questions can
be just asked and answered without too much fuss or concern. I truly
believe that many students simply can't afford the manuals, don't know
where to look for information, and truly do not have the time to spend
looking for an answer that is perhaps easy to find (for those with
extended exposure to the world of Stata). Since younger people tend to
use the Internet and listservs quite a bit, their first exposure to
Statalist might be a bit of a shocker - I know it was for me and I'm
not that young. Nonetheless, I got over it, learned the basic rules, and
try to follow them as best as I can. However, not all students may be so

So, we have been round this before. In the same thread various people
expressed, in effect, sympathy but also scepticism, and Suzy admitted
later that when she had raised the same suggestion a while back she
got more or less the same responses.

To give what appear to be the standard comments, and a few more,

1. If someone set up a list for Stata/statistics learners, no doubt
many people would be interested. The demand, I imagine, like Suzy,
is strongly there.

(An odd thing that no-one is explaining is that the number of
Statalist members keeps climbing, and the proportion who go for
the digest keeps increasing, so Statalist is booming by acquiring
more and more relatively inactive members. Why is this silent majority joining? Perhaps some fraction of members join
on a "nothing to lose" basis, but never get round to reading the digests
arriving daily.)

Anyway, at least some people on Statalist would enjoy the lower
traffic and shift in level of the list that might result from a
new learner list.

2. Indeed various people do this _locally_ at their own institution.

3. It seems unlikely that many Statalist "experts" would be very interested in joining a new learner list. (I don't much like the term
"expert" either.) So, a list aimed at learners would depend on
questions being answered by other learners or a few altruistic experts joining the list. This could happen. I would like to think that
it would.

4. They should speak for themselves, but I can't see either StataCorp
or Marcello Pagano having much interest in running another list.
StataCorp don't want to _run_ any list, not least because they
already run technical support. They have always been supportive
of Statalist, but very keen on its being independent of StataCorp.

5. Are people forgetting about technical support from StataCorp?

6. If two lists existed, double postings would need to be discouraged,
in my view. I can just sense all sorts of wily people sending their
questions to both lists on a "nothing to lose" basis.

7. Any new list would have to decide how nice it is going to be.
This is not my problem, but I would advise anyone who might want
to set up such a list to think very carefully about it. In all these threads, there are two related but distinct issues, the kinds of questions encouraged or discouraged, and how nice the list should be (meaning, patient, gentle, etc.). The Statalist FAQ is linked to

which has a great deal of relevant material here, including the comment

There have been hacker forums where, out of some misguided sense of hyper-courtesy, participants are banned from posting any fault-finding with another's posts, and told “Don't say anything if you're unwilling to help the user.” The resulting departure of clueful participants to elsewhere causes them to descend into meaningless babble and become useless as technical forums.

A learner list will have the same problem as Statalist, whether
questions of various kinds are, regrettably, to be discouraged or even banned. What if someone writes in, and if elementary questions are encouraged this really will happen,

When should I use a median and when a mean?

I am told that I need to transform my data. What does this mean?

What is a syntax error?

How do I draw a histogram in Stata?

Are there going to be users who will want to answer these questions?
(Are there going to be users who will want even to plough through these
in their inbox?)

The simple fact is that everyone's favourite list has questions very
like those you have or will have, or ones a bit more difficult, and also people willing and able to answer them.


--------------------------------------- Woody (
Not being a power user of Stata, and not even being a
second tier user, I sympathize with the plight of
those questioners who ask really basic questions
about things like statistical tests for medians. I
learn a lot from these questions. And, to be honest,
I am completely flummoxed by searching the archives
and would not know enough to use "median test" as my
search phrase.

If it is not good to waste the time of the power and
second tier users on such matters, could we have a
separate listserv or a SUBJECT line warning that
would allow us to move along up to those levels
eventually through learning from each other? Or is
there some other way to build a community for us?
* For searches and help try:

© Copyright 1996–2021 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index