GARCHKIT was originally written for research that became my dissertation. The primary feature that differentiates GARCHKIT from other GARCH implementations in Matlab is its ability to incorporate covariates into the second moment. The current version of GARCHKIT, 1.0b3, allows univariate ARMA(P,Q)-GARCH(R,S) estimation and simulation using maximum likelihood. The conditional distribution may be normal, student’s t or a mixture of two normals.

Version 1.1 now estimates and simulates FIGARCH and GARCH-in-Mean models.

Let me know if you have any questions.

Download GARCHKIT 1.2

Read the Release Notes

very brief GARCHKIT Tutorial:

>> % First, specify the options for GARCH estimation
>> % For a MA(1)-GARCH(1,1) model:
>> MA1=garchoptset(‘MALag’,1,’GARCHLag’,1,’ARCHLag’,1);
>> % For a t-GARCH model:
>> t=garchoptset(‘Distn’,’tgarch’);
>> % For other options, type “help garchoptset”
>> % If the data to be modeled is in a column vector ‘Y’
>> % The model is estimated with a call to garchest.m:
>> outMA1 = garchest(Y,[],[],MA1);
>> outt   = garchest(Y,[],[],t);
>> % If no options are given, a normal, GARCH(1,1) model will be estimated
>> out    = garchest(Y);
>> % Use garchresults.m to view the estimation results:
>> garchresults(out)
>> % To simulate the GARCH process, use garchsim.m