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: mgarch with daily data
From
Nick Cox <[email protected]>
To
[email protected]
Subject
Re: st: mgarch with daily data
Date
Wed, 21 Nov 2012 15:56:03 +0000
I don't know what advice you are seeking here.
1. Aggregating to weekly misses the fine structure of daily
variations. Perhaps this fine structure would be important to your
project, perhaps not; we really can't tell.
2. Aggregating to weekly -- whether taking averages, or totals, or
whatever -- still requires a decision about your zeros. As William
Buchanan also stressed, you need to be clear on what they mean, which
will have an implication for how best they are aggregated.
Nick
On Wed, Nov 21, 2012 at 3:28 PM, Hiroshi kameyama
<[email protected]> wrote:
> Thank you so much.
> What about to use weekly base by converting daily to weekly ?
>
> Kame
>
> 2012/11/21 Nick Cox <[email protected]>:
>> If I understand you correctly, these zeros are not really zeros, but
>> codes for missing values. I've never used -mgarch- at all, but I would
>> try recoding to missing.
>>
>> See -help mvdecode-.
>>
>> Nick
>>
>> On Wed, Nov 21, 2012 at 2:28 PM, Hiroshi kameyama
>> <[email protected]> wrote:
>>
>>> I am not new for Stata, but new for MGARCH.
>>>
>>> I would like to apply MGARCH.
>>> The dataset is as follows, daily data.
>>> But not all days have actual value, "0" means no trade for this day.
>>> Can I proceed to apply MGARCH?
>>>
>>> Your suggestion would be greatly appreciated.
>>> Thank you in advance.
>>>
>>> Hiroshi KAMEYAMA
>>> KAGAWA Univ., Japan
>>>
>>>
>>> t soymeal soybean corn time
>>> 1 0 6.7998916 5.857933 02jul2007
>>> 2 0 6.7824755 5.823046 03jul2007
>>> 3 5.462984 0 0 04jul2007
>>> 4 5.4493202 6.7872811 5.836272 05jul2007
>>> 6 5.4506092 0 0 07jul2007
>>> 7 5.4548937 0 0 08jul2007
>>> 8 0 6.8046145 5.858647 09jul2007
>>> 9 0 6.824917 5.877736 10jul2007
>>>
>>> to
>>> 1895
*
* 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/