[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: missing year in panel

From   "Nick Cox" <[email protected]>
To   <[email protected]>
Subject   RE: st: missing year in panel
Date   Wed, 23 Jan 2008 17:17:45 -0000

If you map your years 1991/1992 1994 on to times 1, 2, 3 on then you can

get Stata to -tsset- using those times. But you would be pretending that
a gap does not exist. Yet the alternative is an enormous block of

The choice is yours, and the consequences are yours, not Stata's. 

[email protected] 

Viktor Slavtchev

Maarten, you are right I should clarify the point.
There is yearly questionnaire I am relying on. However, for some reason,

this questionnaire was not performed in 1993. That is, the 1993 wave 
simply dies not exist. The data for 1991, 1992, 1994 and so on are 
available. My question is, whether this is problem in exploiting the 
panel structure of the data and how to deal with?

Maarten buis wrote:
> --- Viktor Slavtchev <[email protected]> wrote:
>> I have a panel with one missing year. For example the data is
>> available for 1991, 1992, 1994, 1995 and so on, but not for 1993.
>> That is not because the survey, I've got the data from, was not
>> performed in the year 1993. My question is how to use the panel
>> structure of the data, considering that particular break in the data?
> Do I understand you correctly that the survey was performed in that
> year but that year is missing for everyone? That to me seems to
> a serious problem in the data preparation (e.g. you appended the
> different waves to create a single file, but somehow the append for
> wave 1993 failed), and I would go back to that before trying to do any
> analysis.

*   For searches and help try:

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