- August 27th, 2009, 3:22 pm
- Forum: Programming and Software Forum
- Topic: File opening progress bar in Excel
- Replies:
**1** - Views:
**35748**

<t>Dear all,Excel has the little progress bar on the bottom right corner that is used when opening a file.When I open a file that is rather large, say 10MB, another pop-up progress bar comes up after a few seconds, on which has the title 'opening' and says something like 'opening file C:\\blah\blah\...

- August 11th, 2009, 1:25 pm
- Forum: Technical Forum
- Topic: linear regression question
- Replies:
**7** - Views:
**37054**

Do you mean Panel Data or two step regressions a'la Fama + MacBeth?K

- August 6th, 2009, 7:50 am
- Forum: Technical Forum
- Topic: Is VECM useful for anything
- Replies:
**1** - Views:
**36451**

<r>I think you could have a look in the stat-arb literatureMy first Google hits were this firm:<URL url="http://www.yats.com/?topic=rapt&lang=enand">http://www.yats.com/?topic=rapt&lang=enand</URL> this paper:<URL url="http://papers.ssrn.com/sol3/papers.cfm?abstract_id=1404905&download=y...

- July 27th, 2009, 6:23 am
- Forum: Technical Forum
- Topic: GARCH Parameter estimation
- Replies:
**6** - Views:
**44122**

<t>QuoteOriginally posted by: droneEither ways not much point in fitting things to historical volatility!I love these blanket statements! Can u elaborate on that pls?Say that I am a risk manager measuring risk of equity portfolios. Where would you propose that I fit, if not historical vol?Say that I...

- July 26th, 2009, 5:29 pm
- Forum: Technical Forum
- Topic: Serial correlation in GARCH and OLS
- Replies:
**6** - Views:
**39611**

<t>AFAI remember Newey-West corrects for serial correlation, it does not remove it. So you would still find it in the residuals.But:1. Your serial correlation comes from a specific source, which is the overlapping interval. Since you know its source I would prefer to tackle it more explicitly [as in...

- July 24th, 2009, 10:50 pm
- Forum: Technical Forum
- Topic: Serial correlation in GARCH and OLS
- Replies:
**6** - Views:
**39611**

<t>1. Of course the standard errors of OLS and Garch will be different. The OLS standard errors assume homoscedastic normal residuals. You can see the impact by simulating Garch and estimating with OLS2. You should write down your model so we can understand what you do. As you describe it, it appear...

- July 20th, 2009, 10:43 am
- Forum: Technical Forum
- Topic: Distribution of weighted sum of Bernoulli random variables
- Replies:
**1** - Views:
**38840**

The characteristic function is straightforward, but from that point you would need some approximation, as I am not aware of such a distribution in closed formI would try to match that with a mixture of binomials or something similarKyriakos

- July 15th, 2009, 7:13 am
- Forum: Technical Forum
- Topic: CPI process with stochastic drift
- Replies:
**1** - Views:
**37097**

Apologies for the stupid question, but isn't the definition of the real rate r_r = r_n - p, for p the inflation, which gives dCPI/CPI = (r_n - r_r)dt? Where does the volatility of the CPI come from if it doesn't come from the real or the nominal rate?K

- July 14th, 2009, 3:41 pm
- Forum: Technical Forum
- Topic: Peculiar process option pricing
- Replies:
**3** - Views:
**37217**

<r>QuoteOriginally posted by: AnthisAssume an underlying price process with the following properties:1)Its identified by two distinct regimes a low level-low vol one where the process evolves fluctuating within certain limited boundaries and a high level-high vol. 2) The transition from the Low regi...

- July 10th, 2009, 8:49 am
- Forum: Technical Forum
- Topic: Excel bond price
- Replies:
**4** - Views:
**38138**

<t>Thanks for that.So essentially there is a switch in the formula as the second-to=last coupon is paid.My question is that Excel help does not actually point that out in their help file for PRICE, but they do in their help file for YIELD. I guess it is their omission but they still implement the ri...

- July 8th, 2009, 11:41 am
- Forum: Technical Forum
- Topic: help on Vasicek estimation
- Replies:
**1** - Views:
**37363**

<t>I am not sure what you mean by "using Garch to fit the sigma" since in your equation sigma seems to be constantBut anyway, if you want to use latent factors, then for estimation you should look into filters [depending on the structure candidates would be Kalman, particle, regime swhitching, etc]I...

- July 8th, 2009, 8:58 am
- Forum: Technical Forum
- Topic: Excel bond price
- Replies:
**4** - Views:
**38138**

<t>A quick question that perhaps I shouldn't ask...Excel help for PRICE says that it implements the bond price [for redemption 100] asbut wouldn't the correct one bewhere:c: coupon ratey: yield to maturityf: number of coupons per yearN: number of remaining coupon paymentsA: number of days from start...

- July 8th, 2009, 8:46 am
- Forum: Technical Forum
- Topic: standard problem with dupire
- Replies:
**5** - Views:
**38681**

<r>An decreasing total variance implies arbitrage opportunities using calendar spreadsYou can check chapter 6.4 of this doc <URL url="http://www.lulu.com/content/e-book/a-matlab-based-introduction-to-financial-mathematics/7268112K"><LINK_TEXT text="http://www.lulu.com/content/e-book/a-ma ... s/72681...

- June 30th, 2009, 8:12 pm
- Forum: Technical Forum
- Topic: My kalman filter's fit is too good
- Replies:
**4** - Views:
**39042**

residuals of what?If it is resids from the latent factor it might mean that the model is overidentified and therefore spurious.

- May 14th, 2009, 7:20 am
- Forum: Technical Forum
- Topic: Visalizing Probability Distribution of FX from volatility Skew
- Replies:
**6** - Views:
**42218**

<t>The simplest way is to use the Breeden-Litzenberger formulaJust fit a parametric curve through your points, like Gatheral's SVI form, and then take the second derivative accordinglyTo be more precise you will get the "risk-adjusted market expected probability distribution", rather than "market ex...

GZIP: On