Re: st: RE: Random start to random number sequence

["Clyde Schechter" <clyde.schechter@einstein.yu.edu>]

My approach to setting seeds overcomes most of the pitfalls that Bill
Gould points out with respect to times and dates, etc.

I take out my wallet and examine the first currency note in it.  I strip
off any letters from the serial number, and use that as the seed.  I put
the note at the back of my wallet so I won't reuse that serial number.  (I
spend currency notes at a faster rate than I start new pseudo-random
sequences!)

My main reason for using this approach is that I sometimes have to
generate randomization sequences for studies carried out by collaborators
who also use Stata.  To keep these collaborators from figuring out the
next random assignment coming up, I need to keep them from knowing what
seed I started with.  This method serves the purpose.  And it's simple to
carry out.


Clyde Schechter, MA MD
Associate Professor of Family & Social Medicine

Please note new e-mail address: clyde.schechter@einstein.yu.edu

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/