Trend Following

One of the primary challenges with stock selection is the identification of the best stock features to use for the selection of winning stocks. Typically, there are easily more than 50 variables that can be used for stock selection. Many stock investors prefer to keep stock selection as simple as possible and therefore are interested in identifying a few stock variables to use for the identification of winning stocks. Principal Component Analysis is a statistical technique that reduces a large number of inputs of data to a few factors. Once the factors are established, they are displayed in a perceptual map. The perceptual map provides a clear picture of the winning stocks that should be selected for trading.

In the past 20 years, momentum or trend following strategies have become an established part of the investor toolbox. We introduce a new way of analyzing momentum strategies by looking at the information ratio (IR, average return divided by standard deviation). We calculate the theoretical IR of a momentum strategy, and show that if momentum is mainly due to the positive autocorrelation in returns, IR as a function of the portfolio formation period (look-back) is very different from momentum due to the drift (average return). The IR shows that for look-back periods of a few months, the investor is more likely to tap into autocorrelation. However, for look-back periods closer to 1 year, the investor is more likely to tap into the drift. We compare the historical data to the theoretical IR by constructing stationary periods. The empirical study finds that there are periods/regimes where the autocorrelation is more important than the drift in explaining the IR (particularly pre-1975) and others where the drift is more important (mostly after 1975). We conclude our study by applying our momentum strategy to 100 plus years of the Dow-Jones Industrial Average. We report damped oscillations on the IR for look-back periods of several years and model such oscilations as a reversal to the mean growth rate.

This paper studies trend filtering methods. These methods are widely used in momentum strategies, which correspond to an investment style based only on the history of past prices. For example, the CTA strategy used by hedge funds is one of the best-known momentum strategies. In this paper, we review the different econometric estimators to extract a trend of a time series. We distinguish between linear and nonlinear models as well as univariate and multivariate filtering. For each approach, we provide a comprehensive presentation, an overview of its advantages and disadvantages and an application to the S&P 500 index. We also consider the calibration problem of these filters. We illustrate the two main solutions, the first based on prediction error, and the second using a benchmark estimator. We conclude the paper by listing some issues to consider when implementing a momentum strategy.

We show that combining momentum and trend following strategies for individual commodity futures can lead to portfolios which offer attractive risk adjusted returns which are superior to simple momentum strategies; when we expose these returns to a wide array of sources of systematic risk we find that robust alpha survives. Experimenting with risk parity portfolio weightings has limited impact on our results though in particular is beneficial to long-short strategies; the marginal impact of applying trend following methods far outweighs momentum and risk parity adjustments in terms of risk-adjusted returns and limiting downside risk.Overall this leads to an attractive strategy for investing in commodity futures and emphasises the importance of trend following as an investment strategy in the commodity futures context.

Moving average trading strategies are examined for trading ten major currencies during the 1997-2001 time period. Both a traditional trend-following moving average cross over strategy and a contrarian strategy are tested. Following a simple moving average cross over out performed, on average, the contrarian strategy. However, neither strategy consistently outperformed a simple strategy of holding U.S. dollars during the four-year

See http://ssrn.com/author=1530815
ABSTRACT The objective of this technical analysis study was to test the profitability of 80 related trend following algorithms applied to closing prices for India's Nifty index over periods of rising, falling, mixed trend and nearly trendless markets. Daily closing prices for the Nifty index were divided into four periods covering trading days from 2005 through 2012. Trend following rules were used that employed no leverage and no short positions. Only investments in the Nifty index or in cash at India's MIBOR rate were permitted with no transaction costs or dividends assumed. For each period all 80 related trend following algorithms were statistically examined for significance against return distributions created using a Levich-Thomas bootstrapping process. We conclude from this technical analysis study that the family of 80 algorithms investigated worked well in a sharply declining market, but far less so or not at all well in markets that were more gradually rising, mixed trend or nearly trendless. Other papers available at http://ssrn.com/author=1530815
Key Words: Trend Following, Algorithms, Nifty Index, India, Technical Analysis
JEL Classification: G10, G11, G12, G14, G15 Available at http://ssrn.com/abstract=2381236