Author Archives: Pat

Volatility estimation and time-adjusted returns

Posted on 2011/12/15 by Pat

Do non-trading days explain the mystery of volatility estimation? Previously The post “The volatility mystery continues” showed that volatility estimated with daily data tends to be larger (in recent years) than when estimated with lower frequency returns. Time adjusting One of the comments — from Joseph Wilson — was that there is a problem with … Continue reading →

Posted in Quant finance, R language | Tagged , , , | Leave a comment

Searching for inspiration on financial risk

Posted on 2011/12/13 by Pat

Two people, two sources. Planes Deus ex Macchiato has a post called “Planes not bridges” in which it is suggested that learning from air traffic investigators makes sense.  The logic is that a large component of plane accidents is caused by human (mis)beliefs.  So perhaps finance can imitate air safety in reducing the frequency of … Continue reading →

Posted in Risk | Leave a comment

News analytics

Posted on 2011/12/12 by Pat

Last week was the news analytics workshop at Birkbeck College. The idea There is room in news analytics for a large range of approaches.  The leading model runs along the lines of: something happens a journalist (possibly a machine) creates a news item the news item is captured, time-stamped and given an id the news … Continue reading →

Posted in Quant finance | Tagged | 4 Comments

LondonR recap

Posted on 2011/12/10 by Pat

The biggest and perhaps best meeting yet. The talks James Long: “Easy Parallel Stochastic Simulations using Amazon’s EC2 & Segue”.  This was a lively talk about James’ package to use Amazon’s cloud to speed up a (huge) call to lapply.  The good part is that if you want to use Amazon as your cloud provider, … Continue reading →

Posted in R language | Leave a comment

The volatility mystery continues

Posted on 2011/12/05 by Pat

How do volatility estimates based on monthly versus daily returns differ? Previously The post “The mystery of volatility estimates from daily versus monthly returns” and its offspring “Another look at autocorrelation in the S&P 500” discussed what appears to be an anomaly in the estimation of volatility from daily versus monthly data. In recent times … Continue reading →

Posted in Quant finance, R language | Tagged , , , | 13 Comments

Alpha decay in portfolios

Posted on 2011/11/30 by Pat

How does the effect of our expected returns change over time?  This is not academic  curiosity, we want to know in the context of our portfolio if we can.  And we can — we visualize the effect of expected returns in situ. First step The idea is to look at the returns of portfolios that … Continue reading →

Posted in Quant finance, R language, Random portfolios | Tagged , , , | 5 Comments

The carry trade — almost wordless

Posted on 2011/11/28 by Pat

The idea Borrow in a currency with low interest rates, lend in a currency with high interest rates. The image Photo by Patti via stock.xchng The question Am I wrong? Subscribe to the Portfolio Probe blog by Email

Posted in almost wordless, Fund management in general | Tagged , | 2 Comments

Upcoming events

Posted on 2011/11/27 by Pat

New events QWAFAFEW-NYC 2011 November 29 5:30PM Midtown: Barry Feldman on “Stability – A New Dimension of Equity Style” and Dan diBartolomeo on “Five Easy Steps to Fixing the Credit Ratings Agencies” Abstract: Russell’s new defensive and dynamic indexes identify a new dimension of equity style Russell calls Stability. Russell has just launched global Stability … Continue reading →

Posted in Events | Leave a comment

A quant finance group on LinkedIn

Posted on 2011/11/23 by Pat

Room with a view. A problem Most groups concerning finance on LinkedIn are full of garbage.  Lots of items that don’t pertain to the real subject of the group, including lots that don’t pertain to much of anything. The “Quant Finance” group was an exception — it was almost completely on-target.  However, it seems to … Continue reading →

Posted in Quant finance | Tagged | Leave a comment

Asynchrony in market data

Posted on 2011/11/21 by Pat

Be careful if you have global daily data. The issue Markets around the world are open at different times.  November 21 for the Tokyo stock market is different from November 21 for the London stock market.  The New York stock market has yet a different November 21. The effect The major effect is that correlations … Continue reading →

Posted in Quant finance, R language | Tagged , , | 3 Comments