Re: st: new problem with table display

[Steven Joel Hirsch Samuels <sjhsamuels@earthlink.net>]

I agree with Maarten on this.  When I present estimated  totals, I  
don't ordinarily use scientific notation, but I do round to the  
nearest 10, 100, 1,000, 10,000,... depending on the size of the  
standard error.  I want the readers to see that the numbers are  
estimates.

-Steven

On Oct 31, 2007, at 8:15 AM, Maarten buis wrote:


> --- Richard Ohrvall <richard.ohrvall@gmail.com> wrote:
> > Regarding Maartens comment, well I disagree, I often have weights
> > calibrated to known population totals (eg. from a census). It
> > therefore makes sense to have the exact population total in tables
> > instead of a scientific notation with rounded figures. Of course
> > these figures are usually a bit uncertain, but they are often treated
> > as certain (eg. the population in the Netherlands at a certain date)
> > and consistency in this aspect can help to avoid confusion.
> Sometimes we have to conform to the prevailing practice in our
> discipline, but that does not mean we have to forget that that  
> practice
> is actually bad practice. Reporting numbers we know are nothing more
> than random noise seems like bad practice to me.
Steven  Samuels

sjhsamuels@earthlink.net
18 Cantine's Island
Saugerties, NY 12477
Phone: 845-246-0774
EFax: 208-498-7441




*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/