st: Re: coding

["Michael Blasnik" <michael.blasnik@verizon.net>]

I'm not sure I understand, but if you want to create a single categorical 
variable for each case based on 8 years of data and you have a categorical 
variable that takes on one of three possible values (possibility=1,2,3) for 
each year (year= 1,2,3,4,5,6,7,8), then you could::

gen score=possibility*10^(year-1)
collapse (sum) score, by(caseid)

This will give you an 8 digit number (score) for each caseid with each digit 
representing the value of possibility for each year.  One advatage of this 
approach is that the resulting number can be directly interpreted.  If you 
had more years than you might need to create the score variable as a double.

Michael Blasnik
michael.blasnik@verizon.net

----- Original Message ----- 
From: "Alexander Nervedi" <alexnerdy@hotmail.com>
To: <statalist@hsphsun2.harvard.edu>
Sent: Friday, January 27, 2006 7:30 PM
Subject: st: coding



> Hi List users,
>
> I am having a tough time getting my head around this.
>
> I have data on households which goes for 8 years and in each year i can 
> observe 3 possibilities. Thus a total of 8^3 possible histories exist.
>
> How would I go about creating a variable that classifies the data into 
> each of these possibilities?
>
> I have 800 households that I need to classify in this form.
>
> thanks!
>
> Al
*
*   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/