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

Re: st: The philosophy behind storing missing values as very large positive numbers


From   Richard Williams <[email protected]>
To   [email protected]
Subject   Re: st: The philosophy behind storing missing values as very large positive numbers
Date   Sat, 03 Jul 2004 09:39:04 -0500

At 03:21 AM 7/3/2004 -0400, [email protected] wrote:
One thing in Stata that irks me is the treatment of missing values. Stata (IMO) does not handle missings consistenly. For example, if I issue a regression command, missings are recognised as missings and these values are not included in the regression. However, if I type

gen x=1 if (y>10)

then x has the value 1 even if y is missing. In other words, Stata treats as a real value. It's a problem that's easy to solve, but if you forget to include "& y!=.", you can create problems further down the line. Other statistical packages get this right.
As a sidelight, with the new extended MD codes "& y!=." is potentially problematic coding, as it will not exclude .a, .b, etc. Better is

gen x=1 if (y>10) & !missing(y)

or else

gen x=1 if (y>10) & (y < .)

And as another sidelight, as far as other packages go, SPSS gets it "right" (as you define it) but I think it was established in some other thread that SAS gets it "wrong". But, not being a SAS user, I can't confirm that.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX: (574)288-4373
HOME: (574)289-5227
EMAIL: [email protected]
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc

*
* 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/




© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index