Thursday, March 09, 2006
st: RE: differentiating missing values in codebook
Graham- If you are using Stata 7, 8, or 9, you can categorize missings very easily. Stata has 27 values for missing - ., .a, .b,...through .z, and they can be assigned using the -mvencode- command. If you do this first, and then run the tables with the 'missing' option, you should see everything you want. There's a great deal of information in the helpfiles under 'missing' - I know it generates a lot of hits when you ask it, but if you just select 'missing' from the hits it gives you a quick rundown that answers this question in clear detail.
Plus, the command - codebook - will give you condensed information about variables, in bulk or for one specific variable in the data. I'm not clear on what you want in terms of weighting, but Stata will even tell you patterns in the missing values for the whole dataset using the command/option combination - codebook,mv - so you might look at that.
Good luck. Jen Marino
* * 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/
Links to this post: