Search found 815 matches

by coalexander
Fri May 02, 2014 9:05 pm
Forum: Volume III
Topic: Analytic Moments for GARCH processes
Replies: 3
Views: 3204

Re: Analytic Moments for GARCH processes

I like mentoring more than anything else but have been taken away from it since returning to Sussex...but will resume asap, hopefully within a year. Thanks for your very kind words! Carol
by coalexander
Fri May 02, 2014 5:53 pm
Forum: Volume III
Topic: Analytic Moments for GARCH processes
Replies: 3
Views: 3204

Re: Analytic Moments for GARCH processes

Try asking Silvia Stanescu -- she's at Kent...sorry for being away so much this last year, my Job at Sussex is exhausting!
by coalexander
Thu Jul 25, 2013 8:36 pm
Forum: Volume I
Topic: Dealing with missing data and consistent parameters
Replies: 1
Views: 2662

Re: Dealing with missing data and consistent parameters

Hi Searle, Many apologies to you and other forum users for my absence. I have been overwhelmed with work. Regarding your first question you must always compute vols and corrs using the same data and methods, otherwise your covariance matrix may not be positive definite (giving you negative portolfio...
by coalexander
Thu Jun 13, 2013 5:51 pm
Forum: Volume II
Topic: Co integration beteweem historical volatilities series
Replies: 2
Views: 3618

Re: Co integration beteweem historical volatilities series

Hi, Long term co-movements can be determined by the behaviour of the spread even if the series are statistically I(0)...but in your case you have a problem because you say the spread is not I(0). The problem is that you do not account for jumps. Volatilities jump a lot, so you need to use the new ge...
by coalexander
Mon Jun 03, 2013 3:08 pm
Forum: Volume II
Topic: EWMA vs GARCH
Replies: 1
Views: 4081

Re: EWMA vs GARCH

Hi Jan I think I actually make the case that there are two way to view EWMA (a) as an estimator for unconditional variance, just a different (weighted, more complex) formula to the usual sample variance (b) as a conditional model, in which case it is like a baby GARCH model. A conditional variance m...
by coalexander
Thu Mar 21, 2013 9:30 pm
Forum: Volume IV
Topic: Exponentially Weighted Moving Average in Excel
Replies: 2
Views: 5241

Re: Exponentially Weighted Moving Average in Excel

You appear to be rather mixed up. EWMA std is for a normal (or student t) VaR formula. You cannot multiply this by -1 and take into a percentile calculation, which is for historical VaR. Column E should not be multiplied by -1. Just use normal VaR formula with this sigma. Percentile is applied to lo...
by coalexander
Sun Mar 17, 2013 1:15 pm
Forum: Volume III
Topic: The constant maturity con futures example
Replies: 1
Views: 2730

Re: The constant maturity con futures example

Hi Eduoard,

Sorry for late reply, I have been unbelievably busy lately! Also, I cannot be much help on your question.

The longer maturities were not liquid, but I am not sure about the missing data for 1mth. I guess there were data problems but I cannot recall from 5 years ago which they were.
by coalexander
Sun Mar 17, 2013 1:04 pm
Forum: Volume III
Topic: Black Scholes Formula
Replies: 2
Views: 2874

Re: Black Scholes Formula

Hi

apologies for l;ate reply, I have been really busy lately.

I can't help you intuition with Baxter and Rennie but I can answer your second question -- the answer is yes!
by coalexander
Sun Mar 17, 2013 1:02 pm
Forum: Volume III
Topic: Data filtering
Replies: 1
Views: 2421

Re: Data filtering

This paper should answer your question well, Carol
by coalexander
Sun Mar 17, 2013 12:51 pm
Forum: Volume II
Topic: Co-Integration and ECM to estimated correlation
Replies: 5
Views: 6216

Re: Co-Integration and ECM to estimated correlation

Hi I don't think you have quite understood the nature of cointegration and unit root tests. They are always done on integrated series, but returns are not integrated they are stationary. You can use price, or log price. Your choice. Even weekly data (usually taken on Wednesday) are not synchronous. ...

Go to advanced search