Quantitative equity portfolio management (Chincarini & Kim)

Covers both financial theory and real-world practice.

Interesting chapters on factor models, taxes, leverage.

Closet index funds

Is a closet index fund hiding in your portfolio ?

This would be costly! These funds mimic indexes, yet they have higher expense fees (typically between 1% and 2%) than index funds or index ETFs (0.1% to 0.5%). The accumulation of expense fees compounded over the years is significant. If you hold a closet index fund in your portfolio, you could -at no additional risk – increase your return by replacing this fund with a mutual index fund, or an ETF.

Fortunately, closet index funds can be exposed using simple statistical analysis. Closet index funds are likely to show:

  • A high correlation with the index
  • A lower performance relative to the index

In Kwanti Portfolio Lab, define a portfolio with a single holding (that of the fund to analyze), and select the ‘index correlation’ function, which will correlate the fund to a broad range of standard indexes.

Evidence-based technical analysis (Aronson)

This book explains how a scientific approach can be used to determine if a technical analysis (TA) rule is worth using or not. If you are looking for a recipe book, this is not it. There is no specific TA rule or approach which is promoted here.

The author first point is that TA – as is generally practiced today – is subjective and lacks discipline. Yet it is widely used, because it successfully exploits the fallacies of the human mind (for example: overconfidence, hindsight bias, the predilection to find patterns where none exist). For example, technical analysts always seem to have a ‘good story’ about what is happening on a chart, and the mind tends to fall for a good story. Another example is the Eliott Wave Principle, one of TA most enduring theories (and a good story too) because of its ability to minutely curve-fit historical data.

The author advocates a more scientific, objective approach to TA, grounded in statistics. A clear and well-illustrated introductory statistics section is included. More than mathematics, it is rigor and logic which is required from the reader. Eventually the author presents a statistical significance test for trading rules found via data mining and the results of testing 6400 simple rules (the result is that no rule is found to have statistically significant returns).

A great contribution of this book is its layman explanation of the data mining problem. An insidious problem with multiple forms, data mining explains why it is easy to devise a strategy that was a winner in the past, but will fail miserably going forward. There are many software platforms available to backtest strategies and optimize them. It has become easier than ever to fall in the data mining trap. However, designing and testing a strategy – and in particular backtesting – requires great rigor and discipline. If you are inclined to believe this, then this book is a must-read.

The intelligent asset allocator (Bernstein)

A classic investment book! Asset allocation decisions have high impact on long term portfolio returns. Bernstein introduces portfolio theory, the efficient frontier (and its shortcomings), and outlines a practical approach that any investor can follow.

This relatively short book is easy read, and touches on important topics beyond asset allocation: index investing, value investing, small vs. large stocks. A must read.

Correlation: using time weights

Most correlation calculators use an ‘equal weights’ formula: each data point is given the same weight, whether they are recent or long past. This is an easy calculation that is used for example in the CORREL function in Excel.

In the ‘exponential weights’ formula, the more recent data points are given more weight in the calculation, making it more responsive to recent events and less sensitive to past ones.

The Microsoft and Yahoo stocks recently provided an example of the advantage of the exponentially weighted formula over the equally weighted formula. On Feb 1st, 2008, Microsoft announced a bid over Yahoo stock. Immediately, the daily correlation of returns became negative as the two stocks started moving in opposite directions.

The equally weighted calculation (in the example above, based on 50 days window) takes longer to register the shock, and it has a major flaw: on Apr 14th the the Feb 1st data point is no longer part of the 50 days window, and the correlation surges upwards.

The exponentially weighted calculation on the other hand, is able to better incorporate the Feb 1st shock, because it assigns higher weights to the more recent data points. It reacts more promptly, then absorbs the shock gradually, avoiding any artificial surge.

The above is meant to illustrate the correlation calculation formulas; it does not suggest any trading idea. As a matter of fact, correlation is only a starting point for pairs trading. Cointegration is preferred (and the two stocks have indeed been cointegrated in the last 90 days).