First, don't apologize for not knowing all of Stata. None of us do
(well, maybe with the exception of Nick Cox and Bill Gould).
If my understanding of Stata is correct, there is no distinction between
any type of numeric variable on read-in. They are just integers, bytes,
longs, etc. How they are used in the analysis determines their
categories.
If you have a dichotomy, summarizing it gives a proportion, although the
standard deviation is off a little (divide by n-1), I think the
proportion command will take care of that.
If you create a 2 way table, this implies the variable is categorical,
unless you do as I sometimes do and try to create a 2 way table with a
continuous variable (try not to do this with the client in the room!).
For various other applications, the xi prefix is quite handy - it
creates indicator variables for you automatically. Some people don't
like it because the variable names are a bit ugly, especially with
interactions.
Anyway, good luck on your journey using Stata. The Statalist is a
terrific resource. Read some of the basic introductions to Stata such
as those by Acock, Juul, Kohler and Kreuter, or Hamilton. (disclosure:
I'm a close friend of Alan Acock)
Tony
Peter A. Lachenbruch
Department of Public Health
Oregon State University
Corvallis, OR 97330
Phone: 541-737-3832
FAX: 541-737-4001
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Ian C Zink
Sent: Tuesday, January 13, 2009 3:50 PM
To: [email protected]
Subject: Re: st: Re: (no subject)
Hello statalisters,
Please pardon the new kid on the block for not asking a question in a
more respectable and succinct in my question. One should approach such
things with humility if they are to expect a response. The original
question was not thought out with enough forethought before posting.
I am very new to STATA and would like to ensure that while running a
model, STATA understands that a certain variable is categorical
(actually binary response, either yes or no). It seems from the
response post that as long as the values I have entered for the variable
are binary, that STATA will understand the variable as categorical.
Thank you for all that may be inclined to assist me,
Most humbly,
Ian
Martin Weiss wrote:
> Hard to tell what your question is as your post is way too terse, but
> just -tabulate- the variable and see whether there are only two values
> or more. Or even better -inspect- the thing and Stata tells you how
> many unique values there are...
>
> HTH
> Martin
> _______________________
> ----- Original Message ----- From: "Ian C Zink"
<[email protected]>
> To: <[email protected]>
> Sent: Wednesday, January 14, 2009 12:08 AM
> Subject: st: (no subject)
>
>
>> How do ensure Stata reads my variables that I want to be categorical
>> (binary) as such?
>> Thank you...
>>
>> --
>> Ian C. Zink
>> Aquaculture Department - Division of Marine Affairs U. of Miami -
>> Rosenstiel School of Marine and Atmospheric Science
>> 4600 Rickenbacker Causeway
>> Miami, FL 33149
>> office: 305-421-4915
>> fax: 305-421-4675
>> email: [email protected]
>>
>> *
>> * 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/
>>
>
>
> *
> * 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/
--
Ian C. Zink
Aquaculture Department - Division of Marine Affairs
U. of Miami - Rosenstiel School of Marine and Atmospheric Science
4600 Rickenbacker Causeway
Miami, FL 33149
office: 305-421-4915
fax: 305-421-4675
email: [email protected]
*
* 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/
*
* 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/
