Trend following with momentum versus moving averages: a tale of differences

Despite the ever-growing interest in trend following and a series of publications in academic journals, there is a dearth of theoretical results on the properties of trend-following rules. Our paper fills this gap by comparing and contrasting the two most popular trend-following rules, the momentum (MOM) and moving average (MA) rules, from a theoretical perspective. We provide theoretical results on the similarity between different trend-following rules and the forecast accuracy of trading rules. Our results show that the similarity between the MOM and MA rules is high and increases with the strength of the trend. However, compared to the MOM rule, the MA rules exhibit more robust forecast accuracy for the future direction of price trends. In this paper, we also develop a hypothesis about uncertain market dynamics. We show that this hypothesis, coupled with our analytical results, has far-reaching practical implications and can explain a number of empirical observations. Among other things, our hypothesis explains why the empirical performance of the MA rules is better than that of the MOM rule. We broaden the appeal and practical importance of our theoretical results by offering various illustrations and real-world examples.     

Testing moving average trading strategies on ETFs

The evidence for the profitability of MA strategies documented in the literature is usually based on non-tradable indices or portfolios/factors and the use of the zero return or risk-free rate as the benchmark. In this paper we implement MA strategies using ETFs and examine the performance of such strategies using a variety of risk-adjusted performance measures. We find that relative to the buy-and-hold strategy, MA strategies have lower average returns and Sharpe ratios, but fare better under factor-adjusted performance measures such as the CAPM alpha. We also find that MA strategies become less profitable when they are implemented using ETFs than using their underlying indices. In addition, we propose a quasi-intraday version of the standard MA strategy (QUIMA) that allows investors to trade immediately upon observing MA crossover signals. The QUIMA strategy outperforms the standard one that only trades at the close of a trading day, when the long-term MA lag length is no more than 50 days.     

Time series momentum trading strategy and autocorrelation amplification

This paper investigates why general Moving Average (MA) trading rules are widely used by technical analysts and others. We assume general stationary processes for prices and we derive the autocorrelation function for an MA trading rule. Based on our results, we conjecture that autocorrelation amplification is one of the reasons why such trading rules are popular. Using simulated results, we show that the MA rule may be popular because it can identify price momentum and is a simple way of assessing and exploiting the price autocorrelation structure without necessarily knowing its precise structure. This paper then, provides empirical evidence of autocorrelation amplification using 15-year daily price data for 11 major international stock indices.     

Trading rule profits in european currency spot cross-rates

The moving average (MA) trading rule is applied to six European spot cross-rates — JY/BP, DM/BP, JY/DM, SF/DM, SF/BP, and JY/SF — to see if opportunities for profitable trading exist. The results suggest that MA trading rules are marginally profitable only for the JY/DM and the JY/SF cross-rates, while trading rules are not profitable for the other four cross-rates. Bootstrapping and out-of-sample tests provide similar results. Examination of subsamples characterized by central bank intervention do not produce different results. Computation of Box-Pierce statistics adjusted for heteroscedasticity show that daily returns for all six cross-rates are serially uncorrelated. Overall, the results suggests that cross-rates are sufficiently transparent to eliminate MA trading rule profit.     

Chasing trends: recursive moving average trading rules and internet stocks

The recent rise and fall of Internet stock prices has led to popular impressions of a speculative bubble in the Internet sector. We investigate whether investors could have exploited the momentum in Internet stocks using simple moving average (MA) trading rules. We simulate real time technical trading using a recursive trading strategy applied to over 800 moving average rules. Statistical inference takes into account conditional heteroscedasticity and joint dependencies. No evidence of significant trading profits is found. Most Internet stocks behave as random walks; this, combined with high volatility, may be the reason for the dismal performance of the moving average rules.     

Home bias in portfolio choices: social learning among partially informed agents

Using an ‘incomplete information’ model, we explore the role of social learning in the global portfolio choices of stock market investors. When partially informed followers attempt to estimate true domestic (home) mean returns, they likely acquire private domestic signals from partially informed leaders. However, the calibration results indicate the existence of home bias when partially informed agents have poor quality information. Partially informed agents are prone to a learning bias; they overreact to new domestic information due to overconfidence in their domestic private signals, but they demonstrate a conservative response to new information in foreign markets. Links between the private signals of partially informed agents may lead to correlated foreign investment strategies among such agents through social learning. We suggest the acquisition of private signals, along with the dissemination of information, affect international portfolio decision rules and are determinants of the phenomenon of home bias.     

A Generalized Econometric Model and Tests of a Signalling Hypothesis with Two Discrete Signals

To test the major prediction of a signalling hypothesis-that the market price is monotonic in the signal-the price response to the signal must be measured. Since a signal is an outcome of a rational decision rule of the signaller, the market can infer the true type of the signaller from the signal. This necessitates estimation of the price response to the signal, conditional on the rational decision rule. Thus, the empirical models (e.g., event studies in corporate finance) that estimate the market price responses to signals without conditioning on the rational decision rules are misspecified if viewed as tests of the prediction of a signalling hypothesis. This paper builds a generalized econometric model with two possible discrete signals, derives the rational decision rules, presents a simple estimator of the price response to a signal, and illustrates its use in testing a recently expounded hypothesis that firms signal their true value by forcing or not forcing an outstanding convertible bond.     

Testing the profitability of moving-average rules as a portfolio selection strategy

One of the main difficulties in evaluating the profits obtained using technical analysis is that performance of trading rules depends upon the judicious choice of rule parameters. In this paper, popular moving-average (or cross-over) rules are applied to a cross-section of Australian stocks and the signals from the rules are used to form portfolios. The performance of the trading rules across the full range of possible parameter values is evaluated by means of an aggregate test that does not depend on the parameters of the rules. The results indicate that for a wide range of parameters moving-average rules generate contrarian profits (profits from the moving-average rules are negative). In bootstrap simulations the return statistics are significant indicating that the moving-average rules pick up some form of systematic variation in returns that does not correlate with the standard risk factors.     

Profitability of Nonlinear Dynamics Under Technical Trading Rules: Evidence from Pacific Basin Stock Markets

This paper explores a possible link between an asymmetric dynamic process of stock returns and profitable technical trading rules. Using Pacific Basin stock market indexes, we show that the dynamic process of daily index returns is better characterized by nonlinearity arising from an asymmetric reverting property, and that the asymmetric reverting property of stock returns is exploitable in generating profitable buy and sell signals for technical trading rules. We show that the positive (negative) returns from buy (sell) signals are a consequence of trading rules that exploit the asymmetric dynamics of stock returns that revolve around positive (negative) unconditional mean returns under prior positive (negative) return patterns. Our results corroborate the arguments for the usefulness of technical analysis.     

Time series reversal in trend-following strategies

This paper empirically studies the reversal pattern following the formation of trend-following signals in the time series context. This reversal pattern is statistically significant and usually occurs between 12 and 24 months after the formation of trend-following signals. Employing a universe of 55 liquid futures, we find that instruments with sell signals in the trend-following portfolio (‘losers’) contribute to this type of reversal, even if their profits are not realised. The instruments with buy signals in the trend-following portfolio (‘winners’) contribute much less. A double-sorted investment strategy based on both return continuation and reversal yields to portfolio gains which are significantly higher than that of the corresponding trend-following strategy.     

Technical trading rules for nonlinear dynamics of stock returns: evidence from the G-7 stock markets

This paper explores a possible link between an asymmetric dynamic process of stock returns and profitable technical trading rules. Using the G-7 stock market indexes, we show that the dynamic process of daily index returns is better characterized by nonlinearity arising from an asymmetric reverting property. The asymmetric reverting property of stock returns is exploitable in generating profitable buy and sells signals for technical trading strategies. The bootstrap analysis shows that not all nonlinearities generate profitable buy and sell signals, but rather only the nonlinearities generating a consistent asymmetrical pattern of return dynamics can be exploitable for the profitability of the trading rules. The significant positive (negative) returns from buy (sell) signals are a consequence of trading rules that exploit the asymmetric nonlinear dynamics of the stock returns that revolve around positive (negative) unconditional mean returns under prior positive (negative) return patterns. Our results corroborate the arguments for the usefulness of technical trading strategies in stock market investments.     

Estimation of the effective bid-ask spread on high frequency Danish bond data

In this paper the effective bid-ask spread is estimated using 12 high frequency Danish bond samples. A clear-cut MA(1)-model for the mean of the return series, and a GARCH(1,1)-model for the variance, are found. Basically, Roll's model is used, but three different methods of calculating the first-order autocovariance are suggested. Each of these in turn produces three possible ways of estimating the effective bid-ask spread. First, Roll's original autocovariance estimate is used. Second, the autocovariance is calculating using the parameters of an estimated MA(1) model. Third, the autocovariance is obtained from the parameters of a joint MA(1)-GARCH(1,1) model. By means of bootstrapping the standard error of the bid-ask spread estimates are found. It is shown that the gain in efficiency, measured by the relative difference in the standard error of the estimates, is 29% when going from method one to method two, but only 1% when going from method two to method three. These results indicate that the extra gain in efficiency obtained by taking account of the MA(1) structure of the data is noteworthy, but the gain when incorporating the GARCH-effects is negligible.     

The predictability of security returns with simple technical trading rules

Technical traders base their analysis on the premise that the patterns in market prices are assumed to recur in the future, and thus, these patterns can be used for predictive purposes. This paper uses the daily Dow Jones Industrial Average Index from 1897 to 1988 to examine the linear and nonlinear predictability of stock market returns with simple technical trading rules. The nonlinear specification of returns are modelled by single layer feedforward networks. The results indicate strong evidence of nonlinear predictability in the stock market returns by using the past buy and sell signals of the moving average rules.     

Lottery stocks and stop-loss rules

We show that stop-loss rules increase the returns to investment in stocks with lottery features. These stocks typically have sporadic big gains and frequent small losses. However, stop-loss rules can reduce losses and allow investors to receive the gains from large price increases. We also highlight that sell signals of popular technical rules resemble stop-loss rules and are effective at increasing risk-adjusted returns for lottery stock. These rules could have helped investors avoid losses from major historical drawdowns, are particularly beneficial in declining markets, and are robust to the inclusion of transaction costs.     

Predictability of nonlinear trading rules in the U.S. stock market

Most of the existing technical trading rules are linear in nature. This paper investigates the predictability of nonlinear time series model based trading strategies in the U.S. stock market. The performance of the nonlinear trading rule is compared with that of the linear model based rules. It is found that the self-exciting threshold autoregressive (SETAR) model based trading rules perform slightly better than the AR rules for the Dow Jones and Standard and Poor 500, while the AR rules perform slightly better in the NASDAQ market. Both the SETAR and the AR rules outperform the VMA rules. The results are confirmed by bootstrap simulations.     

Investment portfolio balancing: application of a generic self-organizing fuzzy neural network (GenSoFNN)

In contrast to short-term stock trading, portfolio managers are interested in the medium- to long-term peaks and troughs of the stock price cycles as signals to balance their stock portfolios – the predicted trough is the signal to buy the stock and the predicted peak is the signal to sell the stock. As statistical models are generally inadequate or incapable of providing such portfolio balancing signals, we propose using the generic self-organizing fuzzy neural network (GenSoFNN)—a fuzzy neural system – as a tool for portfolio balancing. The network adopts the supervised learning approach to detect inflection points in the stock price cycles, and a modified locally weighted regression algorithm is employed to smooth the stock cycles. The GenSoFNN-based portfolio balancing system was evaluated with experiments conducted using 23 stocks from the New York Stock Exchange and NASDAQ, and the results showed an average profit return of 65.66%. The contributions of the proposed GenSoFNN intelligent portfolio balancing system are twofold: it can be used as an efficient trading solution and it can provide decision support in trading via its generated rules. Copyright © 2009 John Wiley & Sons, Ltd.     

Simple Technical Trading Rules and the Stochastic Properties of Stock Returns

This paper tests two of the simplest and most popular trading rules—moving average and trading range break—by utilizing the Dow Jones Index from 1897 to 1986. Standard statistical analysis is extended through the use of bootstrap techniques. Overall, our results provide strong support for the technical strategies. The returns obtained from these strategies are not consistent with four popular null models: the random walk, the AR(1), the GARCH-M, and the Exponential GARCH. Buy signals consistently generate higher returns than sell signals, and further, the returns following buy signals are less volatile than returns following sell signals, and further, the returns following buy signals are less volatile than returns following sell signals. Moreover, returns following sell signals are negative, which is not easily explained by any of the currently existing equilibrium models.     

The Use of Management Accounting Techniques by Small and Medium‐Sized Enterprises: A Field Study of Canadian and Australian Practice

Small and medium‐sized enterprises (SMEs) represent a large and important part of developed economies. However, little is known about the extent to which SMEs use contemporary management accounting (MA) techniques such as costing systems, budgets, responsibility center reporting, and analysis for decision making. To address this gap in the literature, we conducted in‐depth field interviews at 22 SMEs to: (1) determine the extent to which common MA techniques and tools are being used by SMEs; and (2) explore the underlying reasons why specific MA techniques are not being used. We find that of the 19 common MA techniques covered in our interviews, a very small number are moderately or highly used by our respondent companies. Moreover, we find that manufacturing companies in our study are more likely to use a broader set of techniques such as costing systems, operating budgets, and variance analysis and that smaller, early‐stage SMEs are the lightest users of MA tools overall. We identify three main factors affecting the adoption and use of MA techniques: (1) the perceived decision‐usefulness of the technique; (2) the complexity of the SMEs’ operating environment; and (3) the age of the SME. We discuss the contributions of our study and its potential implications for MA educators, developers of professional education programs, designers of SME control systems, and textbook authors.     

A quarterly time-series classifier based on a reduced-dimension generated rules method for identifying financial distress

Predicting financial distress has been and will remain an important and challenging issue. Many methods have been proposed to predict bankruptcies and detect financial crises, including conventional approaches and techniques involving artificial intelligence (AI). Financial distress information influences investor decisions, and investors depend on analysts’ opinions and subjective judgements in assessing such information, which sometimes results in investors making mistakes. In the light of the foregoing, this paper proposes a novel quarterly time series classifier, which reduces the sheer volume of high-dimensional data to be analysed and provides decision-makers with rules that can be used as a reference in assessing the financial situation of a company. This study employs the following six attribute selection methods to reduce the high-dimensional data: (1) the chi-square test, (2) information gain, (3) discriminant analysis, (4) logistic regression (LR) analysis, (5) support vector machine (SVM) and (6) the proposed Join method. After selecting attributes, this study utilises the rough set classifier to generate the rules of financial distress. To verify the proposed method, an empirically collected financial distress data-set is employed as the experimental sample and is compared with the decision tree, multilayer perceptron and SVM under Type I error, Type II error and accuracy criteria. Because financial distress data are quarterly time series data, this study conducts non-time series and time series (moving windows) experiments. The experimental results indicate that the LR and chi-square attribute selection combined with the rough set classifier outperform the listing methods under Type I, Type II error and accuracy criteria.     

Intraday technical analysis of individual stocks on the Tokyo Stock Exchange

This paper conducts an intraday technical analysis of individual stocks listed on the Nikkei 225. In addition to the price-based technical rules popularly examined in the literature, we uniquely propose and statistically investigate technical rules that utilize information regarding (1) the order-flow imbalance and (2) the order-book imbalance. Technical analysis using the imbalance-based trading rules is motivated by the evidence presented first in this paper that short-term returns can be predicted from the information regarding the order-flow and order-book imbalances for more than half of Nikkei 225-listed stocks. However, we demonstrate that no strategies, including limit order trading where trading signals are derived from the order-book imbalance, beat the buy-and-hold strategy within our sample. The results imply that past prices and demand/supply imbalances do not contribute to profiting in intraday trading and that non-execution and picking-off risks are too large for limit order trading to be profitable in our sample.