Message-ID: <30855819.1075856359059.JavaMail.evans@thyme>
Date: Tue, 17 Oct 2000 13:11:00 -0700 (PDT)
From: chris@lacima.co.uk
To: vkaminski@aol.com, julie@lacima.co.uk
Subject: Re: Comments
Cc: les@lacimagroup.com, vkamins@enron.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Bcc: les@lacimagroup.com, vkamins@enron.com
X-From: "Chris Strickland" <chris@lacima.co.uk>
X-To: <VKaminski@aol.com>, <julie@lacima.co.uk>
X-cc: <les@lacimagroup.com>, <vkamins@enron.com>
X-bcc: 
X-Folder: \Vincent_Kaminski_Jun2001_2\Notes Folders\Discussion threads
X-Origin: Kaminski-V
X-FileName: vkamins.nsf

Hi Vince,

Sorry to have missed you in Paris. Many thanks for your comments - they've
now been incorporated and sent to EPRM. Things are crazy at the moment, but
hopefully will calm down in a couple of weeks and we'll have time to catch
up better.

Best regards.

Chris.



----- Original Message -----
From: <VKaminski@aol.com>
To: <julie@lacima.co.uk>
Cc: <les@lacimagroup.com>; <vkamins@enron.com>; <chris@lacima.co.uk>
Sent: Sunday, October 15, 2000 11:06 AM
Subject: Comments


> Julie,
>
> Sorry for the delay. Here are he comments.
>
> Vince
>
> ************************************
>
> Sorry for long delay in responding. I have a few comments. Most are
focused
> on the third article as here is till time to make modifications.
>
> 1.  In the second article, I would mention that the formulation of the
mean
> reversion process represents one of several possible equations that
capture
> the same type of market evolution of prices over time.
> 2.  One comment that applies to both articles. The problem is how one
defines
> the time series of energy prices. The numbers used for Australian NSW pool
> prices seem to correspond to chronological prices. One alternative
approach
> is to build different time series for the corresponding time intervals for
> each day. This would result in different price behavior and estimates of
> jump. The choice is one of convenience and depends on actual problem under
> investigation. One could argue that volumes of electricity traded during
> different time slots represent different economic commodities.
> Figure 3a (Jump Frequency) has units on the vertical axis that require
> explanation. Are we talking about an expected number of jumps in the total
> number of half hourly periods in a year? The same goes for f in Table 2
> (article number 3).
>
>