Re: st: Re: Problem with combining sibling data

[daniel klein <klein.daniel.81@gmail.com>]

Annabel sent a follow up question to me privately. The FAQs clearely
state that in general you shoud not do so
(http://www.stata.com/support/faqs/resources/statalist-faq/#private).

I will try and answer as good as I can. If -1 and -2 represent missing
values of some kind, it seems natural to exclude those from the
calculation (that is before or while adding the variables up). You can
do so using -mvdecode- (see my first reply), -recode-, -replace-, or
some technique as demonstaretd in Nick's reply.

I do not underrstand why you want to only exclude -2 from the
calculations, as you already correctly noted, that we cannot "be sure
of what [any of the negative values] mean", in terms of the "true"
(underlying) value.

Best
Daniel
--

Thanks.

Sorry, Yes my first variable was using simple addition "+", i.e. gen
sib = var1 + var2 + var3 + var4 ....

I suppose what I should really have enquired about is how I deal with
the -1 and -2  because that was really what worries me, so adding up
the variables gives you this table.

siblings_16
Freq. Percent Cum.
-8 470 4.05 4.05
-6 8 0.07 4.12
-5 61 0.53 4.64
-4 5,669 48.81 53.45
-3 154 1.33 54.77
-2 260 2.24 57.01
-1 332 2.86 59.87
0 588 5.06 64.93
1 2,118 18.24 83.17
2 1,189 10.24 93.41
3 434 3.74 97.14
4 332 2.86 100.00
Total 11,615 100.00

It is my concern over what - 1 to -8 now mean. So clearly -8 is 4 of
the -2's but how can I be sure of what the others mean...

Can you use the simple addition generator whilst keeping the original
label/ code, so ask it to add but all those that are labelled -2 are
left out of the addition?

Otherwise, I'll just recode what it produces but I fear what I might
miss/ misuse.

Best Wishes
Annabel
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/