Statalist The Stata Listserver

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

Re: Re: st: BTSCS ad-on for xtprobit?

From   "Austin Nichols" <>
Subject   Re: Re: st: BTSCS ad-on for xtprobit?
Date   Thu, 1 Feb 2007 16:59:16 -0500

I did not intend to close the thread myself, but to invite someone
else to close the thread by publishing the program, and I did mean for
that someone to obtain the author's permission. In other words, I
agree with point (3): the author should maintain all reasonable
control over distribution.  On point (1) however, I may have to
disagree--the authors want people running logits to include a set of
dummies to test for duration dependence.  Not having the ado file,
however, I cannot be sure of what the file does...

On 2/1/07, n j cox <> wrote:
I am going to re-open a thread that Austin has just closed
with three comments on different levels.

1. I don't think there is a close relation between this paper
and the program named. They both use the name BTSCS or -btscs-:
that's all. Nor, as said before, has it anything to do with -xtprobit-.

2. I can't recollect how I got hold of my copy of this program,
beyond a clear recollection that I and others helped the author
write it, and a suspicion that it was direct personal email. So I am
really not clear that it was ever published, even in the weak sense of
being made public. If it had been published in the STB or SJ or
distributed via SSC that would be evident. Other people evidently
have copies, but I can't speak for them.

3. In the absence of such evidence, my own standard is that
_public_ redistribution of this program requires the approval of
the author. As with published papers and unpublished papers I see
a difference between two kinds of interaction:

(a) If someone gives you a copy of something not yet published
on the basis that it might be interesting or useful, you presumably
feel entitled to pass it on to others in the same way, unless
you were explicitly asked to keep quiet about it. That's in terms
of reading it; citing it is a different story.

(b) However, publishing someone else's paper even under their name
is just unacceptable except in extreme circumstances: for example,
the person is long since dead, or recently dead and it is clear
that whoever is handling their affairs is happy about the idea.

Programs I feel to be intellectual property. The fact that many
people are generous and/or relaxed about distributing their programs
doesn't change this principle. Nor does the fact that lack of respect
for use of programs as intellectual property is widespread.

For all I know, the original author would just be pleased at the
thought that his program is interesting or useful to others, but
to assume that he would have no reservations about other people
distributing it is just that: an assumption.

This is, therefore, a long explanation of why I have no intention of
making my copy of this program public. It is also a requeat for the
Stata user community to consider what kind of behaviour is ethical
in these circumstances.


Austin Nichols

To close this thread, will you post the ado file somewhere where
anyone can see it when you get it?  This might include pasting the
text into an email to Statalist, if the file is not too big.  Also,
the original ref seems to be
Beck, Nathaniel, Jonathan N. Katz and Richard Tucker. 1998. Taking
Time Seriously: Time-Series-Cross-Section Analysis with a Binary
Dependent Variable. American Journal of Political Science, 42:
or the web-friendly

Jason Yackee

 > Thank you all.  My friend has lost his copy the program he was
talking about in one of his computer moves.  I will email the original
*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index