Worse still..at some stage you would have to change the zeroes back to
missing. How would you differentiate between genuine zeroes and
missings masquarading as zeroes? It could be done, but it'd be a lot
of work for little gain and a good chance of stuffing things up.
Joseph
On Thu, Apr 9, 2009 at 7:28 AM, Caleb Southworth <[email protected]> wrote:
> On Wed, 8 Apr 2009, Eldon Spackman wrote:
>
> :You could replace missing values with the value 0.
> :Eldon
>
> That is a poor practice. Zero often has real meaning. Changing missing
> to zero will alter the mean, if that were important. cf -mvencode- and
> -mvdecode-
> *
> * 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/
>
*
* 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/
