I get it now. You have to find the difference between deviance and null deviance.There doesn't appear to be a simple formula based on counts that can do the trick. If someone knows, please let me know.BTW, is logistic regression used in finance?

<t>Suppose I have a case control study with the following numbers:x 0 1 2case 89 369 342control 56 250 266The logistic regression looks like this and x can only take the value of 0, 1 and 2logit(p) = alpha + beta*xThe answer for the likelihood ratio test for beta=0 is approximately 1.991But how do I...

<r>I want to model stochastic interest rate for my option pricing software. I think the simple Vasicek model should be good enough for my purpose.According to my understanding, I can obtain the spot rate r(t) for a particular date with these steps:1. obtain deposit rates and swap rates for that date...

My quant friend says I should calibrate to cap prices (ie sum of caplet prices) as oppose to caplet vols. I think I will give that a try.

<t>According to my understanding of the Hull book, the typical interest rate cap/floor quotes are the flat volatilities of cap/floor of different maturity.The caplets/floorlets of each cap/floor of the same maturity are assumed to have the same caplet/floorlet volatility.My derivation shows that suc...

You do need to do some dirty/petty things but so does lawyers. Still, docs are more respected in this society.

Thanks for your reply. I will give that a try. BTW, the B&M book is really a good read for a practioner. Thanks for your recommendation.

<t>Thanks for your reply. I finally get a hand on the Brigo & Mercurio's 2006 edition.In pp. 115, it says there are two ways to do MC:1. Sample at each time step the exact transition density from r(s_i) to r(s_i+1), i=0...q-1, under the T-forward-adjusted measure;2. Discretize the SDE for r, und...

<t>Thanks for your reply. I think I know how to bootstrap and then obtain a piece-wisely connected linear yield curve. But I think I only have the line to connect overnight rate and 1mos rate. Do I just use this slope as the slope for T=0? Also, what should be the slope when T hits the undifferentia...

<t>I was thinking the theta(t) (the time-varying function in the drift term) in Hull-White is to be expressed in terms of the instantaneous forward rate function and its derivative with respect to t. I thought I need a smooth yield curve for these two functions and this smooth yield curve can be the...

<t>I am thinking about implementing Hull-White model. I heard that Nelson-Siegel can be used to construct a twice differentiable yield curve and it also has some nice properties. I am planning to use Monte Carlo to simulate a process that involves short rate. I notice that there are two exponential ...

<r>ah. I find the answer to my question....<URL url="http://en.wikipedia.org/wiki/Yield_curve#Construction_of_the_full_yield_curve_from_market_data"><LINK_TEXT text="http://en.wikipedia.org/wiki/Yield_curv ... arket_data">http://en.wikipedia.org/wiki/Yield_curve#Construction_of_the_full_yield_curve_...

<t>Ho-Lee model is likedr = theta(t)*dt + sigma*dzSuppose I have zero-coupon yield curve that has these pointsmaturity(yr) zero rate (%)0.25 10.1270.5 10.4691.0 10.5361.5 10.6812.0 10.808Do I then fit a smooth bond price function P with these prices and then use the relationship f(0,t) = - d(log P(0...

Also keep pumping money to AIG is an indirect way of pumping money to GS....

<t>Thanks for your reply.I had experience calibrating for GARCH models. They use squared daily returns (actually it is the new daily vol assuming mean of daily return is 0) to evolve the processv_t = omega + alpha*u_t*u_t + beta*v_(t-1)The stochastic process for v can then be derived asdv = (1-alpha...