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, statalist.org is already up and running.


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

Re: st: confidence intervals for IRFs


From   Joerg Luedicke <joerg.luedicke@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: confidence intervals for IRFs
Date   Wed, 19 Sep 2012 10:06:58 -0500

It seems that the user-written package -clarify- (Gary King, see:
http://econpapers.repec.org/software/bocbocode/s355501.htm) contains
capabilities of drawing from inverse Wishart distributions. Have a
look at the program -_simsig2-, a sub-program within -estsimp.ado-
which is part of the -clarify- package.

J.



On Wed, Sep 19, 2012 at 8:19 AM, ulio Glogowsky <ulioglogowsky@gmail.com> wrote:
> Sorry! I'm going to reformulate the problem:
>
> I estimated a system of equations with a vector autoregressive model
> for two variables y1 and y2 and one lag.
> What I ultimately want to do is to construct confidence intervals for
> impulse response functions of this model. One way to do this is by
> Monte Carlo Integration. Doan explains in the "RATS User's Guide" how
> this can be done.
>
> When I try to write a program with the same procedure in STATA I start
> by calculating the covariance matrix of the estimated system of
> equations (here: "sigma" with dimension 2x2). This is not a problem.
> Now the inverse of sigma is decomposed by cholesky (lets call the new
> sigma sigmad) and based on sigmad and the degrees of freedom
> covariance matrices are drawn from an inverse Wishart Distribution.
> So, in order to use the same procedure in Stata, I would also have to
> draw from the inverse Wishart distribution. However I cannot find a
> way to do this.
>
> Is there a way to draw from the Wishart distribution in Stata similar
> to drawnorm()?
>
> 2012/9/19 Maarten Buis <maartenlbuis@gmail.com>:
>> On Wed, Sep 19, 2012 at 10:29 AM, ulio Glogowsky wrote:
>>> I want to use the method outlined by Doan (1990) to construct
>>
>> The Statalist FAQ exists to help you ask answerable questions. Please
>> use that service.
>>
>> -- Maarten
>>
>> ---------------------------------
>> Maarten L. Buis
>> WZB
>> Reichpietschufer 50
>> 10785 Berlin
>> Germany
>>
>> http://www.maartenbuis.nl
>> ---------------------------------
>> *
>> *   For searches and help try:
>> *   http://www.stata.com/help.cgi?search
>> *   http://www.stata.com/support/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/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/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index