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

Re: st: Categorical variable

From   Katarina Sikavica <[email protected]>
To   [email protected]
Subject   Re: st: Categorical variable
Date   Fri, 22 Jul 2005 15:18:52 +0200

hi again,

thanks a lot for answering this quickly .... and sorry for the imprecision (I just subscribed to statalist :-))
actually: I've collected data on reported reasons for CEO turnover (as stated in newspaper articles); my dummy variables look like this:

- poor performance (1/0)
- retirement (1/0)
- policy differences (1/0)
- ....

Now I would like to create a single new variable called "reason" that looks like this:

one and only variable "reason" coded as follows:

1 poor performance
2 retirement
3 policy differences
4 ....


Inactive hide details for Richard Williams <>Richard Williams <[email protected]>


[email protected]



Re: st: Categorical variable

At 02:43 PM 7/22/2005 +0200, Katarina Sikavica wrote:

>Hi Alice,
>hi all,
>I have the same problem.... in addition to the below question I would like
>to know whether and how I can generate a string variable out of say 3 or
>more dummy variables.

Katy, could you be more specific as to what you have in mind?  Anyway, one
way might be

gen x = 100 *  dummy_1 + 10 *  dummy_2 +  dummy_3
tostring x, gen(xstring)

I suspect that isn't what you have in mind though, e.g. maybe you want a
string variable with values like "high" "medium" "low" ?  Perhaps something

. gen y = "high" if dummy_1 == 1
. replace y = "medium" if dummy_2 == 1
. replace y = "low" if dummy_3 == 1

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):
WWW (department):

*   For searches and help try:

GIF image

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