Bookmark and Share

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]

st: Problems when estimating GARCH(1,1) in STATA


From   Pawel Smietanka <[email protected]>
To   "[email protected]" <[email protected]>
Subject   st: Problems when estimating GARCH(1,1) in STATA
Date   Fri, 2 Aug 2013 16:29:36 +0100

Hi,

I estimate a simple GARCH(1,1) model in STATA with two lags in the main equation. Here are my results:

. arch grr L.grr L2.grr, arch(1) garch(1)

(setting optimization to BHHH)
Iteration 0:   log likelihood =   -251.345  
Iteration 1:   log likelihood = -249.86249  
Iteration 2:   log likelihood = -248.02976  
Iteration 3:   log likelihood = -244.96328  
Iteration 4:   log likelihood = -243.46113  
(switching optimization to BFGS)
Iteration 5:   log likelihood =  -243.1621  
Iteration 6:   log likelihood = -242.87726  
Iteration 7:   log likelihood = -242.75897  
Iteration 8:   log likelihood = -242.74415  
Iteration 9:   log likelihood = -242.72715  
Iteration 10:  log likelihood = -242.72279  
Iteration 11:  log likelihood =   -242.721  
Iteration 12:  log likelihood = -242.72072  
Iteration 13:  log likelihood = -242.72072  

ARCH family regression

Sample: 3 - 169                                    Number of obs   =       167
Distribution: Gaussian                             Wald chi2(2)    =      7.45
Log likelihood = -242.7207                         Prob > chi2     =    0.0241

------------------------------------------------------------------------------
             |                 OPG
         grr |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
grr          |
         grr |
         L1. |    .096067   .0706532     1.36   0.174    -.0424107    .2345448
         L2. |   .2064248   .0846426     2.44   0.015     .0405284    .3723211
             |
       _cons |   .5485593   .0975064     5.63   0.000     .3574502    .7396684
-------------+----------------------------------------------------------------
ARCH         |
        arch |
         L1. |   .0695062   .0191442     3.63   0.000     .0319843     .107028
             |
       garch |
         L1. |   .9419905   .0168409    55.93   0.000     .9089829    .9749982
             |
       _cons |  -.0169108   .0067299    -2.51   0.012    -.0301011   -.0037205
------------------------------------------------------------------------------

Here are the results if I estimate the same model with EViews:


Dependent Variable: GRR				
Method: ML - ARCH (BHHH) - Normal distribution				
Date: 08/02/13   Time: 15:59				
Sample (adjusted): 1955Q4 1997Q2				
Included observations: 167 after adjustments				
Convergence achieved after 21 iterations				
Presample variance: backcast (parameter = 0.7)				
GARCH = C(4) + C(5)*RESID(-1)^2 + C(6)*GARCH(-1)				
				
Variable	Coefficient			Std. Error			z-Statistic			Prob.  
				
C		0.7337004912934016		0.1096705613724465		6.690040445783071		2.231089246054068e-11
GRR(-1)		-0.02404062885934711	0.0966189012756239		-0.2488191082898637		0.8035007095852133
GRR(-2)		0.05643336253467177	0.0821454687954468		0.6869930059708879		0.4920871358180699
				
Variance Equation			
				
C		0.2488161343870002		0.1361285274433679		1.827803026007994		0.06757911892732735
RESID(-1)^2	0.3116928064545641		0.1281005882690402		2.433187939776972		0.01496653021627075
GARCH(-1)	0.531066612689561		0.180428222951572		2.943367750355234		0.003246625031072093
				
R-squared	0.005976020314715446	    Mean dependent var		0.6752610952095809
Adjusted R-squared	-0.006146223339983159	    S.D. dependent var		1.102947684190452
S.E. of regression	1.106331973406644	    Akaike info criterion		3.017883281072389
Sum squared resid	200.7311514026217	    Schwarz criterion		3.129907010859818
Log likelihood	-245.9932539695445	    Hannan-Quinn criter.		3.063351247210276
Durbin-Watson stat	2.04819433712679			
				
As seen from the tables, the values of the coefficients are very different. Do happen to know what may be the reason for such great differences in values?

Kind regards,

Pawel Smietanka
This message and any attachment are intended solely for the addressee and may contain confidential information. If you have received this message in error, please send it back to me, and immediately delete it.   Please do not use, copy or disclose the information contained in this message or in any attachment.  Any views or opinions expressed by the author of this email do not necessarily reflect the views of the University of Nottingham.

This message has been checked for viruses but the contents of an attachment
may still contain software viruses which could damage your computer system, you are advised to perform your own checks. Email communications with the University of Nottingham may be monitored as permitted by UK legislation.





*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index