Correlation Matrix
Locked
 
|
Hello. I am trying to compute the correlation matrix, from a set of time series (say 3 seperate series for simplicity). I am a new user to quantlib, and I cannot seem to figure out how to do this exactly using the library. It seems like I should be using the GenericSequenceStatistics class, bit I am unsure how. Can anyone provide me with a few pointers? A simple, yet complete example would be extremely appreciated.
Please let me know if you need additional information.
Thanks
-a
------------------------------------------------------------------------------ This SF.net email is sponsored by Sprint What will you do first with EVO, the first 4G phone? Visit sprint.com/first -- http://p.sf.net/sfu/sprint-com-first _______________________________________________ QuantLib-users mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-users |
|
|
Hi, try this two methods (they are part of a larger class called financial time series), they should work Cheers Simone inline shared_ptr<SequenceStatistics> createsequence(TimeSeries<vector<Real>>jointds)
{ boost::shared_ptr<SequenceStatistics> gss(new SequenceStatistics);
for (it = jointds.begin();it !=jointds.end();++it) { p = it->second;
gss->add(p.begin(),p.end()); }
return gss; } inline Disposable<Matrix> getCorrelation(boost::shared_ptr<SequenceStatistics> g)
{ return g->correlation(); }
On 1 July 2010 20:50, Andrew Hill <[hidden email]> wrote:
------------------------------------------------------------------------------ This SF.net email is sponsored by Sprint What will you do first with EVO, the first 4G phone? Visit sprint.com/first -- http://p.sf.net/sfu/sprint-com-first _______________________________________________ QuantLib-users mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-users |
|
|
In reply to this post by digiplant
Try this; in C# .Net SWIG env.
public QuantLib.Matrix CalculateCorrelation(DataSet MarketPriceChanges) // this dataset has series you want to correlate { uint UInstrumentCount = Convert.ToUInt32(MarketPriceChanges.Tables.Count); int InstrumentCount = MarketPriceChanges.Tables.Count; QuantLib.SequenceStatistics priceValuesCorreration = new QuantLib.SequenceStatistics(0); QuantLib.Matrix CorrelationMatrix = new QuantLib.Matrix(UInstrumentCount, UInstrumentCount); for (int i = 1; i < MarketPriceChanges.Tables[0].Rows.Count; i++) { QuantLib.DoubleVector vector = new QuantLib.DoubleVector(); for (int j = 0; j < UInstrumentCount; j++) { vector.Add(Convert.ToDouble(MarketPriceChanges.Tables[j].Rows[i]["PRICE_CHANGE"])); } priceValuesCorreration.add(vector); } CorrelationMatrix = priceValuesCorreration.correlation(); return CorrelationMatrix; } 2010/7/1 Andrew Hill <[hidden email]>
------------------------------------------------------------------------------ This SF.net email is sponsored by Sprint What will you do first with EVO, the first 4G phone? Visit sprint.com/first -- http://p.sf.net/sfu/sprint-com-first _______________________________________________ QuantLib-users mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-users |
|
|
Hello,
I believe there might be a small mistake in Quantlib 1.01 sobolrsg.cpp SobolRsg::skipTo method. The method starts with: void SobolRsg::skipTo(unsigned long skip) { unsigned long N = skip+1; unsigned int ops = (unsigned int)(std::log((double)N)/M_LN2)+1; It should be: void SobolRsg::skipTo(unsigned long skip) { unsigned long N = skip<<1; unsigned int ops = (unsigned int)(std::log((double)N)/M_LN2)+1; Regards, Fabien Le Floc'h. ------------------------------------------------------------------------------ Special Offer-- Download ArcSight Logger for FREE (a $49 USD value)! Finally, a world-class log management solution at an even better price-free! Download using promo code Free_Logger_4_Dev2Dev. Offer expires February 28th, so secure your free ArcSight Logger TODAY! http://p.sf.net/sfu/arcsight-sfd2d _______________________________________________ QuantLib-users mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-users |
|
|
Sorry for the annoyance, it's a mistake in my test, QL code is correct.
Le 01/02/2011 18:37, Fabien Le Floc'h a écrit : > Hello, > > I believe there might be a small mistake in Quantlib 1.01 sobolrsg.cpp > SobolRsg::skipTo method. The method starts with: > void SobolRsg::skipTo(unsigned long skip) { > unsigned long N = skip+1; > unsigned int ops = (unsigned int)(std::log((double)N)/M_LN2)+1; > > It should be: > void SobolRsg::skipTo(unsigned long skip) { > unsigned long N = skip<<1; > unsigned int ops = (unsigned int)(std::log((double)N)/M_LN2)+1; > > Regards, > > Fabien Le Floc'h. > > ------------------------------------------------------------------------------ > Special Offer-- Download ArcSight Logger for FREE (a $49 USD value)! > Finally, a world-class log management solution at an even better price-free! > Download using promo code Free_Logger_4_Dev2Dev. Offer expires > February 28th, so secure your free ArcSight Logger TODAY! > http://p.sf.net/sfu/arcsight-sfd2d > _______________________________________________ > QuantLib-users mailing list > [hidden email] > https://lists.sourceforge.net/lists/listinfo/quantlib-users -- Fabien LE FLOC'H Financial Engineer ................................................. C A L Y P S O 106-108 rue de la Boétie 75008 Paris OFFICE +33 (0)1 44 50 01 84 FAX +33 (0)1 44 50 12 84 ................................................. ------------------------------------------------------------------------------ Special Offer-- Download ArcSight Logger for FREE (a $49 USD value)! Finally, a world-class log management solution at an even better price-free! Download using promo code Free_Logger_4_Dev2Dev. Offer expires February 28th, so secure your free ArcSight Logger TODAY! http://p.sf.net/sfu/arcsight-sfd2d _______________________________________________ QuantLib-users mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-users |
«
Return to quantlib-users
|
1 view|%1 views
| Free forum by Nabble | Edit this page |