Re: st: RE: A modest proposal - missing data doesn't count

[Phil Schumm <pschumm@uchicago.edu>]

On Jun 15, 2010, at 12:08 PM, Nick Cox wrote:
> Paradoxical though it may seem, Allan has got to produce a stronger  
> argument before it can judged exactly how good his proposal is.


Indeed.  To quote Bill Gould (http://www.stata.com/statalist/archive/2008-01/msg00287.html 
):

> The last time we at StataCorp thought carefully about this problem,  
> we learned that it is not enough to write down the statements for  
> which the proposal better meets expectations. You have to go  
> searching for the statements that do the unexpected and then ask,  
> "How easy will that be to explain to users?"


I would suggest that there be some modest required reading here, to  
avoid wasting bandwidth.  For example:

1) http://www.stata.com/statalist/archive/2008-01/index.html#00257
   (everything under the subject "My last word on a strange world")

2) an introduction to missing values in SAS (sorry -- this link may  
not work for everyone)

http://support.sas.com/documentation/cdl/en/lrcon/62955/HTML/default/viewer.htm#/ 
documentation/cdl/en/lrcon/62955/HTML/default/a001292604.htm

3) an introduction to how NULL values are handled in SQL
   (e.g., http://en.wikipedia.org/wiki/Null_(SQL))

Item (2) is useful for those who don't use SAS, since it demonstrates  
that SAS is similar to Stata in this regard, except with missing  
values stored at the bottom instead of at the top.  Item (3) is useful  
for those who don't use SQL or are otherwise unfamiliar with multi- 
valued logic.

Others may be able to suggest additional references.


-- Phil

*
*   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/