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

st: Re: conditioning reset at each gap

From   Kit Baum <[email protected]>
To   [email protected]
Subject   st: Re: conditioning reset at each gap
Date   Thu, 17 Jan 2008 06:54:03 -0500

You should

gen t = _n
tsset t

if your daily return data are missing on weekend days and holidays. Put them in 'business daily' context.

For more detail on this issue please see Stata Tip 40, "Taking care of business"

Kit Baum, Boston College Economics and DIW Berlin
An Introduction to Modern Econometrics Using Stata:

On Jan 17, 2008, at 2:33 AM, Bulent wrote:

I have daily return data and want to estimate a garch(1,1) model as below.

.arch r, arch(1) garch(1) het(d1990) nolog

- ----results---
Number of gaps in sample: 427
(note: conditioning reset at each gap)

What does "conditioning reset at each gap" exactly imply?
When I generated a new time variable with
.egen t=fill (1 2)

and used this linear variable as the time variable, I don't get
"conditioning ..." message and the results are a little different.

I have daily data. Should I use the "daily date variable" or the t
above for my time variable?
*   For searches and help try:

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