|
From: Peter C. <pca...@gm...> - 2015-06-27 18:41:14
|
I messed it up, right. A is the event to default until t2. B is the event to survive until t1. Hopefully. Peter On 27 June 2015 at 18:20, Peter Caspers <pca...@gm...> wrote: > Bonjour Francois, > > the value that is returned (i.e. p2-p1) is the probability to default > between t1 and t2. > > Your expression simplifies to (p2-p1) / ( 1-p1 ) and is the > probability to default between t1 and t2 *given that* (or *conditional > on* to speak more mathematically) you survive until p1. I.e. it is P( > A | B ) = P( A and B) / P( B ), where A is the event to default until > t1 and B likewise the event to default until t2. Whereas the first > expression is P( A and B ). > > Sometimes I get spontaneous headaches to spot the difference between > the two (anybody else, too ?). But say you are likely to default until > t1 (p1=90%) already and certain to die until t2 (p2=100%), then the > value p2-p1 returned in QL is 10% (since until t1 a lot might happen > already ...). Your expression is 100% on the other hand, i.e. if you > are lucky and survive until t1, then you are really doomed and just > heading for your final destintation on t2 for sure. > > Does it make sense that way ? > > Best regards and a beautiful weekend for you > Peter > > > On 27 June 2015 at 16:31, Francois Botha <ig...@gm...> wrote: >> Hi, >> >> Shouldn't the calculation of the default probability between 2 dates ( see >> https://github.com/lballabio/quantlib/blob/master/QuantLib/ql/termstructures/defaulttermstructure.cpp#L117 >> ) be: >> return 1.0 - (1.0 - p2) / (1.0 - p1); >> >> Survival probabilities are cumulative / multiplicative, right? >> >> Francois Botha >> >> ------------------------------------------------------------------------------ >> Monitor 25 network devices or servers for free with OpManager! >> OpManager is web-based network management software that monitors >> network devices and physical & virtual servers, alerts via email & sms >> for fault. Monitor 25 devices for free with no restriction. Download now >> http://ad.doubleclick.net/ddm/clk/292181274;119417398;o >> _______________________________________________ >> QuantLib-dev mailing list >> Qua...@li... >> https://lists.sourceforge.net/lists/listinfo/quantlib-dev >> |