[Gretl-users] Forecasting variance of a GARCH model

Sven Schreiber svetosch at gmx.net
Mon Sep 29 12:13:53 EDT 2014


Please keep the communication on the list. [See below for Karthik's
message.]

-sven

Am 29.09.2014 um 15:46 schrieb Karthik Raju:
> Hello Sven,
> 
> First, I wish to congratulate you for organizing the 4th GRETL
> conference to be held at Berlin on 12 & 13 June 2015.
> 
> Now, I will cite you a literature related to what I intend to do.
> 
> Please refer to the article in the link http://goo.gl/zwhzS7. In this
> article, the author compare the predicted variance from different models
> to the realized variance and evaluates the performance of those models
> by using loss functions to choose a best model.
> 
> Similarly, I have a dataset comprising 5 years of stock index returns
> for which I want to estimate the conditional variance using models like
> TARCH, EGARCH, APARCH etc. Then, I want to forecast/predict the models
> for 1 year ahead and measure the forecasting/predicting ability of the
> models used.
> 
> Best,
> Karthik Raju
> 
> Sven Schreiber wrote on 2014-09-29 10:50 AM +0530:
>>> Please show us some example from the literature where this is done, in
>>> order to address the conceptual difficulties that Jack mentioned. Only
>>> afterwards could we possibly move to the stage of formulating code.
>>>
>>> thanks,
>>> sven
>>
>> Am 28.09.2014 um 10:26 schrieb Karthik Raju:
>> I am a beginner in time series analysis. So, please can you guide me how
>> to formulate the code for unique models like EGARCH, TARCH etc.
>>
>>
>> _______________________________________________
>> Gretl-users mailing list
>> Gretl-users at lists.wfu.edu
>> http://lists.wfu.edu/mailman/listinfo/gretl-users
> 
> 



More information about the Gretl-users mailing list