Publications by Pat

A look at historical Value at Risk

17.12.2012

Historical Value at Risk (VaR) is very popular because it is easy and intuitive: use the empirical distribution of some specific number of past returns for the portfolio. Previously “The estimation of Value at Risk and Expected Shortfall” included an R function to estimate historical VaR. Generating portfolios A useful tool to explore risk mo...

4666 sym R (557 sym/6 pcs) 8 img

Miles of iles

24.12.2012

An explanation of quartiles, quintiles deciles, and boxplots. Previously “Again with variability of long-short decile tests” and its predecessor discusses using deciles but doesn’t say what they are. The *iles These are concepts that have to do with approximately equally sized groups created from sorted data. There are 4 groups with quartil...

4883 sym R (2342 sym/11 pcs) 14 img

Market predictions for year 2013

07.01.2013

Calibrations of 2013 predictions for 18 equity indices — plus some publicly available predictions. Orientation The distributions are an attempt to see the variability if there were no market-driving news for the whole year. Another way of thinking: mentally moving the distribution to center on a prediction gives a sense of the variability of re...

4183 sym R (70 sym/1 pcs) 38 img

Clustering and sector strength

21.01.2013

An exploration of the usefulness of sectors. Previously This subject was discussed in “S&P 500 sector strengths”. Idea Stocks are put into groups based on the sector that the company is considered to be in.  Cluster analysis is a statistical technique that finds groups.  If sectors really move together, then clustering should recover sector...

4815 sym R (1747 sym/7 pcs) 8 img 1 tbl

The components garch model in the rugarch package

28.01.2013

How to fit and use the components model. Previously Related posts are: A practical introduction to garch modeling Variability of garch estimates garch estimation on impossibly long series Variance targeting in garch estimation The model The components model (created by Engle and Lee) generally works better than the more common garch(1,1) model....

3476 sym R (2459 sym/11 pcs) 6 img

An infelicity with Value at Risk

04.02.2013

More risk does not necessarily mean bigger Value at Risk. Previously “The incoherence of risk coherence” suggested that the failure of Value at Risk (VaR) to be coherent is of little practical importance. Here we look at an attribute that is not a part of the definition of coherence yet is a desirable quality. Thought experiment We have a dis...

4312 sym R (1604 sym/4 pcs) 12 img

Variability of predicted portfolio volatility

11.02.2013

A prediction of a portfolio’s volatility is an estimate — how variable is that estimate? Data The universe is 453 large cap US stocks. The variance matrices are estimated with the daily returns in 2012. Variance estimation was done with Ledoit-Wolf shrinkage (shrinking towards equal correlation). Two sets of random portfolios were created.  ...

6086 sym R (1482 sym/10 pcs) 12 img

R for finance and other upcoming events

12.02.2013

Featured R for Finance Workshop 2013 March 5-6 in London. The target audience are professionals and academics, who wish to learn the basics of the statistical software R and its use in Finance. The workshop is led by Ron Hochreiter, Pat Burns and Michael Sun. Details are on the Unicom website.  Please reference Burns Statistics when you register...

3734 sym 2 img

Simple tests of predicted returns

18.02.2013

Some ways to explore how good a method of predicting returns is. Data and model The universe is 443 large cap US stocks that have data back to the beginning of 2004.  The daily (adjusted) close was used. The model that is used as an example is the default signal from the MACD function of the TTR package in R.  As we’ll see, this works sometim...

6588 sym R (5387 sym/11 pcs) 22 img

Portfolio tests of predicted returns

25.02.2013

Exploring the quality of predictions using random portfolios and optimization. Previously “Simple tests of predicted returns” showed a few ways to look at expected returns at the asset level.  Here we move to the portfolio level. The previous post focused on correlation.  Win Vector Blog points out that gauging prediction quality using corr...

5752 sym R (2493 sym/7 pcs) 18 img