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: Polynomial in Time in an Unbalanced Panel

From   Maarten buis <>
Subject   Re: st: Polynomial in Time in an Unbalanced Panel
Date   Fri, 18 Jun 2010 07:55:39 -0700 (PDT)

--- On Fri, 18/6/10, natasha agarwal wrote:
> I tried
> egen t1=group(year)
> gen t2=t1^2
> gen t3=t1^3
> But am not sure if this is correct for an unbalanced
> panel?

The -egen- step sounds dangerous an un-necessary to me
(regardless of whether this balanced or un-balanced panel
data or cross sectional data). I would just substract 
some meaningfull timepoint from your year variable to 
make sure that 0 zero is located within the range of 
your data. Other than that it looks ok to me.

-- Maarten

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


*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index