Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Computers don't make mistakes, people do.

From   Marcello Pagano <>
Subject   st: Computers don't make mistakes, people do.
Date   Fri, 21 Jun 2002 10:31:16 -0400

Dear Listers,

If you have a few minutes to spare you may want to
look at,

Software Glitch Threw Off Mortality Estimates
    Jocelyn Kaiser
Science Jun 14 2002: 1945-1947.
(Because of our rule about attachments, I cannot
attach it.)

What is reported there is a very subtle mistake of
some consequence that took five years to discover.
It came about because the researchers accepted a
default value in a canned program without
investigating its effects.

I know this would never happen to a Stata user;)
but I am bringing it to your attention because it
is awfully close to home (General Additive Model
in S-plus) and I think we can all learn from it.
When we have an excellent program at our disposal,
we may forget how complex it is, and get lulled
into not being sufficiently discerning.

Enjoy the summer (even though Italy and the US lost!)



Marcello Pagano
Biostatistics Department			Tel: 1-617-432-4911
Harvard School of Public Health		        Fax: 1-617-739-1781
655 Huntington Avenue    
Boston, MA  02115         

eppur si muove

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index