Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

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

Re: st: Re: Coding Question

From   "Joseph Coveney" <>
To   <>
Subject   Re: st: Re: Coding Question
Date   Mon, 15 Aug 2011 13:04:13 +0900

> You definitely want the data in long form here . . .

Yeah, that was my first inclination, too.  But the IDs are eight characters
long.  Things like -reshape-, -sort- -egen-, -by id:-, and perhaps even compare
var[_n] to var[_n-1], require a few minutes' patience when surveys get large.
Keeping it wide often scales better in these circumstances.

All of the missing values in the OP's excerpt listing are monotonically missing
on the right.  I took the liberty of construing that as indicating a natural
termination of the run sooner in some individuals than in others.  But a
missing-in-the-middle would mean that missing is an unobserved state.  If that's
what missing means in this dataset, then all of our suggestions are wrong.

Joseph Coveney

*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index