Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Re: Making Cohorts

From   Maarten buis <[email protected]>
To   [email protected]
Subject   Re: st: Re: Making Cohorts
Date   Thu, 28 Oct 2010 11:50:23 +0100 (BST)

--- On Thu, 28/10/10, ajjee <[email protected]> wrote:
> But I am still confused about COHORT. When I create this by
> cohort=year-age, now it gives me year of birth of each
> respondent. Now I want to group each respondent in a unique
> cohort.  I'm quoting procedure from a paper
> "Define C cohorts, which are groups of individuals sharing
> some common characteristic like sex or date of birth. These
> groups are defined in such a manner that each individual is
> a member of exactly one cohort, and remains a member of this
> cohort for all periods. For example, a particular cohort may
> consist of all male individuals born in 1945–1949."

So, year of birth is one form of cohort: it defines groups that
are born in a given year.  The fact that this confuses you is 
an example of common mistake: Just because something has its 
own name does not mean that it is special or difficult.  A 
cohort, as you defined it, is just another name for a variable 
that you want to treat as categorical.

If you want another categorization, then you need to tell us
exactly what you want. As the definition you quoted above says
there are an extremely large number of ways in which you can 
group observations.

Hope this helps,

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen


*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index