Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: bootstrap a test linear hypotheses
From
Nick Cox <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: bootstrap a test linear hypotheses
Date
Wed, 5 Jun 2013 00:32:29 +0100
The problem is in the idea. How do you bootstrap a time series? Once
you have sampled a set of observations with replacement, how do you
then define the time order for such a sample, with typically some
observations repeated and some missing? There are ideas in the
literature on how to do it, but -bootstrap- does not implement them.
Nick
[email protected]
On 5 June 2013 00:23, Thierry Hounsa <[email protected]> wrote:
> Hi all.. How to bootstrap a test linear hypothese after the estimation of a Vectorial Autoregressive Model?
> Indeed, I perform these commands:
>
> *** estimate a VAR of 2 lags on the variables Y1 and Y2***
> var Y1 Y2
> *** Perform a test on the coefficients of Y1***
> test ([Y1]: L.Y2 L2.Y2)
> *** bootstrap the previous test***
> bootstrap, reps(50) : test ([Y1]: L.Y2 L2.Y2)
> But I get the following error message: "time-series operators are not allowed with bootstrap without panels, see tsset, r(198)"
> What's wrong with my commands? What should I do?
> Thanks in advance
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/faqs/resources/statalist-faq/
> * http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/