<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:georss="http://www.georss.org/georss" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:media="http://search.yahoo.com/mrss/"
		>
<channel>
	<title>Comments for Commodity Models</title>
	<atom:link href="http://commoditymodels.com/comments/feed/" rel="self" type="application/rss+xml" />
	<link>http://commoditymodels.com</link>
	<description>A blog on the mathematical modelling of energy and other commodities by Will Smith.</description>
	<lastBuildDate>Sat, 12 Feb 2011 13:26:16 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.com/</generator>
	<item>
		<title>Comment on About This Blog by Imonike</title>
		<link>http://commoditymodels.com/2009/11/28/4/#comment-1297</link>
		<dc:creator><![CDATA[Imonike]]></dc:creator>
		<pubDate>Sat, 12 Feb 2011 13:26:16 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.wordpress.com/?p=4#comment-1297</guid>
		<description><![CDATA[Hi Will, thanks very much for your response. I think I might say a bit about myself. I am a software engineer working in Ghana. I have been teaching myself statistics,econometrics and R in my spare time. I haven&#039;t traded commodities before, I had just studied to the point where I felt confident enough to try something like this. When you say that I should create a &#039;front month&#039; contract, are you saying that for example if I start with the March 2007 contract for white maize as my white maize front month contract, that I should take all the data I have for this contract to start building my time series for white maize, drop the last few days to avoid roll-over effects, continue to build my time series with the next contract for example April 2007 contract for white maize, ignoring all data that exists for the April 2007 contract before the roll over point and proceed in that fashion, doing like wise for yellow maize?

Thank you for your time.

Imonike]]></description>
		<content:encoded><![CDATA[<p>Hi Will, thanks very much for your response. I think I might say a bit about myself. I am a software engineer working in Ghana. I have been teaching myself statistics,econometrics and R in my spare time. I haven&#8217;t traded commodities before, I had just studied to the point where I felt confident enough to try something like this. When you say that I should create a &#8216;front month&#8217; contract, are you saying that for example if I start with the March 2007 contract for white maize as my white maize front month contract, that I should take all the data I have for this contract to start building my time series for white maize, drop the last few days to avoid roll-over effects, continue to build my time series with the next contract for example April 2007 contract for white maize, ignoring all data that exists for the April 2007 contract before the roll over point and proceed in that fashion, doing like wise for yellow maize?</p>
<p>Thank you for your time.</p>
<p>Imonike</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on About This Blog by commoditymodels</title>
		<link>http://commoditymodels.com/2009/11/28/4/#comment-1283</link>
		<dc:creator><![CDATA[commoditymodels]]></dc:creator>
		<pubDate>Tue, 08 Feb 2011 09:26:39 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.wordpress.com/?p=4#comment-1283</guid>
		<description><![CDATA[Why not make a &#039;front month&#039; contract, but avoid roll-over effects by rolling what you consider to be &#039;front month&#039; a few days before expiry.  It&#039;s the standard way to do it.  Or, more advanced, construct a weighted average of the 1st and 2nd month contracts, with the weights recalculated each day, to build a &#039;constant maturity&#039; contract with some duration, say 45 days.

Then do the same for both commodities and run the cointegration over the full time period.

To remove biases, you will have to correctly account for the rebalancing trade as you sell front month and buy 2nd month.  Put yourself in the position of a fund, sell some 1 month (at say the closing price), work out how much money you get, and buy 2nd month on the same day, again at the closing price.]]></description>
		<content:encoded><![CDATA[<p>Why not make a &#8216;front month&#8217; contract, but avoid roll-over effects by rolling what you consider to be &#8216;front month&#8217; a few days before expiry.  It&#8217;s the standard way to do it.  Or, more advanced, construct a weighted average of the 1st and 2nd month contracts, with the weights recalculated each day, to build a &#8216;constant maturity&#8217; contract with some duration, say 45 days.</p>
<p>Then do the same for both commodities and run the cointegration over the full time period.</p>
<p>To remove biases, you will have to correctly account for the rebalancing trade as you sell front month and buy 2nd month.  Put yourself in the position of a fund, sell some 1 month (at say the closing price), work out how much money you get, and buy 2nd month on the same day, again at the closing price.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Commodity Futures Curves Visualisation &#8211; &#8220;The Movie&#8221; by commoditymodels</title>
		<link>http://commoditymodels.com/2010/03/18/commodity-futures-curves-visualisation-the-movie/#comment-1282</link>
		<dc:creator><![CDATA[commoditymodels]]></dc:creator>
		<pubDate>Tue, 08 Feb 2011 09:23:13 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.com/?p=205#comment-1282</guid>
		<description><![CDATA[Hi Tom

Actually a lot of the coding effort for these graphs WAS in the scaling of the axes.  If it doesn&#039;t ever jump, I need a really wide y axis to show the whole time range, and you cannot see in detail the &#039;shape&#039; of the curve, which is my emphasis.

If the axis jumps constantly (every frame), the axis becomes a blur and the line remains constant, with only its shape changing.

Glad to know other people are studying and profitiing the roll yield and arbitraging the by-necessity fully-declared-up-front trading strategies of the index funds.]]></description>
		<content:encoded><![CDATA[<p>Hi Tom</p>
<p>Actually a lot of the coding effort for these graphs WAS in the scaling of the axes.  If it doesn&#8217;t ever jump, I need a really wide y axis to show the whole time range, and you cannot see in detail the &#8216;shape&#8217; of the curve, which is my emphasis.</p>
<p>If the axis jumps constantly (every frame), the axis becomes a blur and the line remains constant, with only its shape changing.</p>
<p>Glad to know other people are studying and profitiing the roll yield and arbitraging the by-necessity fully-declared-up-front trading strategies of the index funds.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on About This Blog by Imonike Mohammed</title>
		<link>http://commoditymodels.com/2009/11/28/4/#comment-1278</link>
		<dc:creator><![CDATA[Imonike Mohammed]]></dc:creator>
		<pubDate>Mon, 07 Feb 2011 19:56:29 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.wordpress.com/?p=4#comment-1278</guid>
		<description><![CDATA[Hello Will,
           I was browsing and I came across your blog. I was wondering whether you could give me a few pointers to a problem I am having. Here is the problem:

I am trying to do cointegration analysis of commodity futures data downloaded from the Johannesburg Stock Exchange. I am specifically testing for the presence of a cointegration relationship between the white maize and yellow maize futures. I have commodity futures data starting from November 2006 to mid-April 2010 in my database. When testing I pick a specific contract say &quot;White Maize May 2007&quot; and its yellow maize equivalent, create a time series of each and test. I was wondering if there was a way I could use all the data I have for the 2 commodities to create each commodity&#039;s time series without introducing any biases. I suspect this would give more accurate results if this were possible.
Any ideas will be greatly appreciated.

Thank you for your time.

Imonike]]></description>
		<content:encoded><![CDATA[<p>Hello Will,<br />
           I was browsing and I came across your blog. I was wondering whether you could give me a few pointers to a problem I am having. Here is the problem:</p>
<p>I am trying to do cointegration analysis of commodity futures data downloaded from the Johannesburg Stock Exchange. I am specifically testing for the presence of a cointegration relationship between the white maize and yellow maize futures. I have commodity futures data starting from November 2006 to mid-April 2010 in my database. When testing I pick a specific contract say &#8220;White Maize May 2007&#8243; and its yellow maize equivalent, create a time series of each and test. I was wondering if there was a way I could use all the data I have for the 2 commodities to create each commodity&#8217;s time series without introducing any biases. I suspect this would give more accurate results if this were possible.<br />
Any ideas will be greatly appreciated.</p>
<p>Thank you for your time.</p>
<p>Imonike</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on CV by Aaron</title>
		<link>http://commoditymodels.com/cv/#comment-1259</link>
		<dc:creator><![CDATA[Aaron]]></dc:creator>
		<pubDate>Mon, 31 Jan 2011 07:21:21 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.wordpress.com/?page_id=11#comment-1259</guid>
		<description><![CDATA[Hi Will,

I&#039;d like to learn commodity risk management model coding in matlab and VBA, Like VaR calculation for commodity holder. I&#039;m looking for some basic code in this area to start my study. But I can&#039;t find much resource through internet. Could you give me some tips about that?

Thanks!

Aaron]]></description>
		<content:encoded><![CDATA[<p>Hi Will,</p>
<p>I&#8217;d like to learn commodity risk management model coding in matlab and VBA, Like VaR calculation for commodity holder. I&#8217;m looking for some basic code in this area to start my study. But I can&#8217;t find much resource through internet. Could you give me some tips about that?</p>
<p>Thanks!</p>
<p>Aaron</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Commodity Futures Curves Visualisation &#8211; &#8220;The Movie&#8221; by Tom</title>
		<link>http://commoditymodels.com/2010/03/18/commodity-futures-curves-visualisation-the-movie/#comment-1250</link>
		<dc:creator><![CDATA[Tom]]></dc:creator>
		<pubDate>Fri, 28 Jan 2011 13:02:55 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.com/?p=205#comment-1250</guid>
		<description><![CDATA[Hi,

Nice graphs indeed, might be worth fixing the axis scale to improve the visualisation, not very nice when it jumps about.

You underestimate the CTA universe. The vast majority already account for and model commodity roll down in extremely sophisticated ways. There are CTA’s whose entire purpose is to trade this by arbitraging the dislocations which occur when large ETF’s, funds and commodity indices roll their futures.]]></description>
		<content:encoded><![CDATA[<p>Hi,</p>
<p>Nice graphs indeed, might be worth fixing the axis scale to improve the visualisation, not very nice when it jumps about.</p>
<p>You underestimate the CTA universe. The vast majority already account for and model commodity roll down in extremely sophisticated ways. There are CTA’s whose entire purpose is to trade this by arbitraging the dislocations which occur when large ETF’s, funds and commodity indices roll their futures.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Key Papers in Commodities Finance by Immo</title>
		<link>http://commoditymodels.com/2010/02/25/key-papers-in-commodities-finance/#comment-947</link>
		<dc:creator><![CDATA[Immo]]></dc:creator>
		<pubDate>Thu, 25 Nov 2010 10:04:52 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.com/?p=126#comment-947</guid>
		<description><![CDATA[Hi,

I am really fascinated about your homepage, tons of useful information, very cool!

I am wondering whether you know any good paper on a business cycle model of commodities which describes the return of different commodity groups (energy, base metals, precious metals, agriculture) in the different business cycles.

I just read that you are quite familiar with those academic papers, maybe you know some useful stuff!

thx
Immo]]></description>
		<content:encoded><![CDATA[<p>Hi,</p>
<p>I am really fascinated about your homepage, tons of useful information, very cool!</p>
<p>I am wondering whether you know any good paper on a business cycle model of commodities which describes the return of different commodity groups (energy, base metals, precious metals, agriculture) in the different business cycles.</p>
<p>I just read that you are quite familiar with those academic papers, maybe you know some useful stuff!</p>
<p>thx<br />
Immo</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Commodity Futures Curves Visualisation &#8211; &#8220;The Movie&#8221; by Jez Liberty</title>
		<link>http://commoditymodels.com/2010/03/18/commodity-futures-curves-visualisation-the-movie/#comment-802</link>
		<dc:creator><![CDATA[Jez Liberty]]></dc:creator>
		<pubDate>Wed, 13 Oct 2010 18:13:29 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.com/?p=205#comment-802</guid>
		<description><![CDATA[Thanks for the feedback on the hedge fund looking at using roll yield - that&#039;s interesting. I feel it is a topic that has been hotting up lately. 
I have actually been talking to another CTA who is looking into this also and he seemed to confirm this (ie lots of CTAs he talks to are using/looking into similar methodologies).

The stockcharts yield curve chart has actually been up for a good few years (I started watching it in 07)

Understand the license issue with data...]]></description>
		<content:encoded><![CDATA[<p>Thanks for the feedback on the hedge fund looking at using roll yield &#8211; that&#8217;s interesting. I feel it is a topic that has been hotting up lately.<br />
I have actually been talking to another CTA who is looking into this also and he seemed to confirm this (ie lots of CTAs he talks to are using/looking into similar methodologies).</p>
<p>The stockcharts yield curve chart has actually been up for a good few years (I started watching it in 07)</p>
<p>Understand the license issue with data&#8230;</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Commodity Futures Curves Visualisation &#8211; &#8220;The Movie&#8221; by commoditymodels</title>
		<link>http://commoditymodels.com/2010/03/18/commodity-futures-curves-visualisation-the-movie/#comment-801</link>
		<dc:creator><![CDATA[commoditymodels]]></dc:creator>
		<pubDate>Wed, 13 Oct 2010 18:01:37 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.com/?p=205#comment-801</guid>
		<description><![CDATA[2nd comment, Jez, I was actually talking to a large hedge fund recently about the possibility of using roll yield to enhance commodity returns, in a more dynamic way than the DB Enhanced Yield.   I agree that it&#039;s not widely used yet, at least publicly.]]></description>
		<content:encoded><![CDATA[<p>2nd comment, Jez, I was actually talking to a large hedge fund recently about the possibility of using roll yield to enhance commodity returns, in a more dynamic way than the DB Enhanced Yield.   I agree that it&#8217;s not widely used yet, at least publicly.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Commodity Futures Curves Visualisation &#8211; &#8220;The Movie&#8221; by commoditymodels</title>
		<link>http://commoditymodels.com/2010/03/18/commodity-futures-curves-visualisation-the-movie/#comment-800</link>
		<dc:creator><![CDATA[commoditymodels]]></dc:creator>
		<pubDate>Wed, 13 Oct 2010 17:54:50 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.com/?p=205#comment-800</guid>
		<description><![CDATA[Hi Jez

That animated yield curve looks suspiciously like my movies!  Maybe just coincidence, not sure how long their site has been up.  
The trouble with putting the data on the internet is that I don&#039;t have a license to use the prices for anything other than personal research use.  So I can&#039;t take this concept too far.]]></description>
		<content:encoded><![CDATA[<p>Hi Jez</p>
<p>That animated yield curve looks suspiciously like my movies!  Maybe just coincidence, not sure how long their site has been up.<br />
The trouble with putting the data on the internet is that I don&#8217;t have a license to use the prices for anything other than personal research use.  So I can&#8217;t take this concept too far.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Commodity Futures Curves Visualisation &#8211; &#8220;The Movie&#8221; by Jez Liberty</title>
		<link>http://commoditymodels.com/2010/03/18/commodity-futures-curves-visualisation-the-movie/#comment-799</link>
		<dc:creator><![CDATA[Jez Liberty]]></dc:creator>
		<pubDate>Wed, 13 Oct 2010 17:46:41 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.com/?p=205#comment-799</guid>
		<description><![CDATA[Will, glad I found your blog (well actually one my reader pointed me to that post as I have done a bit of work on commodity yield curves - with the aim of enhancing a typical Trend Following strategy using the yield curve to enhance the roll yield. I talked about it here: http://www.automated-trading-system.com/better-trend-following-improved-roll-yield/ )

Your method of visualisation is great - better than my static snapshot one &quot;built&quot; in Excel (as per there: http://www.automated-trading-system.com/roll-yield-commodity-yield-curve/ )

If you ever look to improve it though, a design idea that I quite like is this interactive player for the yield curve on the stockcharts website: 

http://stockcharts.com/charts/YieldCurve.html

Cheers,
Jez]]></description>
		<content:encoded><![CDATA[<p>Will, glad I found your blog (well actually one my reader pointed me to that post as I have done a bit of work on commodity yield curves &#8211; with the aim of enhancing a typical Trend Following strategy using the yield curve to enhance the roll yield. I talked about it here: <a href="http://www.automated-trading-system.com/better-trend-following-improved-roll-yield/" rel="nofollow">http://www.automated-trading-system.com/better-trend-following-improved-roll-yield/</a> )</p>
<p>Your method of visualisation is great &#8211; better than my static snapshot one &#8220;built&#8221; in Excel (as per there: <a href="http://www.automated-trading-system.com/roll-yield-commodity-yield-curve/" rel="nofollow">http://www.automated-trading-system.com/roll-yield-commodity-yield-curve/</a> )</p>
<p>If you ever look to improve it though, a design idea that I quite like is this interactive player for the yield curve on the stockcharts website: </p>
<p><a href="http://stockcharts.com/charts/YieldCurve.html" rel="nofollow">http://stockcharts.com/charts/YieldCurve.html</a></p>
<p>Cheers,<br />
Jez</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Bloomberg&#8217;s Commodity &#8220;Plunge&#8221; Misreporting by Dr. Duru</title>
		<link>http://commoditymodels.com/2010/06/03/bloombergs-commodity-crash-misreporting/#comment-650</link>
		<dc:creator><![CDATA[Dr. Duru]]></dc:creator>
		<pubDate>Mon, 13 Sep 2010 02:57:25 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.com/?p=246#comment-650</guid>
		<description><![CDATA[Thank you for this important rebuttal and clarification. I causally read the Bloomberg article and was almost fooled. Glad I decided to do some research into just what in the world this index really measures.]]></description>
		<content:encoded><![CDATA[<p>Thank you for this important rebuttal and clarification. I causally read the Bloomberg article and was almost fooled. Glad I decided to do some research into just what in the world this index really measures.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Commodity Prices and Data Sources by commoditymodels</title>
		<link>http://commoditymodels.com/2010/08/17/commodity-prices/#comment-599</link>
		<dc:creator><![CDATA[commoditymodels]]></dc:creator>
		<pubDate>Sun, 05 Sep 2010 06:48:31 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.com/?p=269#comment-599</guid>
		<description><![CDATA[Thanks Nicolas R.  Very useful.  I have updated the collection above.]]></description>
		<content:encoded><![CDATA[<p>Thanks Nicolas R.  Very useful.  I have updated the collection above.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Commodity Prices and Data Sources by commoditymodels</title>
		<link>http://commoditymodels.com/2010/08/17/commodity-prices/#comment-577</link>
		<dc:creator><![CDATA[commoditymodels]]></dc:creator>
		<pubDate>Thu, 02 Sep 2010 05:23:03 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.com/?p=269#comment-577</guid>
		<description><![CDATA[Sorry, I don&#039;t know.  I got all my data from Thompson-Datastream.]]></description>
		<content:encoded><![CDATA[<p>Sorry, I don&#8217;t know.  I got all my data from Thompson-Datastream.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Commodity Futures Curves Visualisation &#8211; &#8220;The Movie&#8221; by commoditymodels</title>
		<link>http://commoditymodels.com/2010/03/18/commodity-futures-curves-visualisation-the-movie/#comment-576</link>
		<dc:creator><![CDATA[commoditymodels]]></dc:creator>
		<pubDate>Thu, 02 Sep 2010 05:22:33 +0000</pubDate>
		<guid isPermaLink="false">http://commoditymodels.com/?p=205#comment-576</guid>
		<description><![CDATA[?In response to Jonathan DePiri: 

Sorry, no, I don&#039;t want to post the source code.   My career history is about 15 years of working in finance and IT, now moving to commodities.  As well as studying for a PhD, some of my time is spent on commodity-related consultancy.  My personal commodity-based software library written in Matlab is a big part of my consultancy, so I don&#039;t wish to give it out for free.  

If you mention a commodity I may already have the data and be able to build the movie.  Or if you have the historical futures data, I could convert it into a suitable format (often not a trivial task) and render it as a movie for a small fee.]]></description>
		<content:encoded><![CDATA[<p>?In response to Jonathan DePiri: </p>
<p>Sorry, no, I don&#8217;t want to post the source code.   My career history is about 15 years of working in finance and IT, now moving to commodities.  As well as studying for a PhD, some of my time is spent on commodity-related consultancy.  My personal commodity-based software library written in Matlab is a big part of my consultancy, so I don&#8217;t wish to give it out for free.  </p>
<p>If you mention a commodity I may already have the data and be able to build the movie.  Or if you have the historical futures data, I could convert it into a suitable format (often not a trivial task) and render it as a movie for a small fee.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

