Statistical Arbitrage And Tests Of Market Efficiency

Statistical arbitrage strategy has become a major force at both hedge funds and investment banks. Many researchers have studied different strategies of statistical arbitrage to provide a steady stream of returns that are unrelated to the market condition. Among different strategies, factor-based mean reverting strategies have been popular and covered by many. This thesis aims to add value by evaluating the generalized pairs trading strategy and suggest enhancements to improve out-of-sample performance. The enhanced strategy generated the daily Sharpe ratio of 6.07% in the out-of-sample period from January 2013 through October 2016 with the correlation of -.03 versus S&P 500.

  • In statistical arbitrage trading, investors calculate the historical distance between the standardized daily return paths and choose the pair with the smallest trading distance.
  • Lastly, the study also provided evidence from the LETF markets for an inverse relationship between volatility and momentum, as established in some recent studies.
  • The first one is given by the fact that the strategy focuses on the expected return.
  • The reason is that the relationships are often tenuous and fall about.
  • Simulations of simple StatArb strategies by Khandani and Lo show that the returns to such strategies have been reduced considerably from 1998 to 2007, presumably because of competition.

Now granted, there’s more to it than this, such as exchange risk, slippage, using algorithmic trading platforms, etc. But the point remains the same, buy an asset trading at a lower price in one market and sell it for a higher price in another. On a stock-specific level, there is risk of M&A activity or even default for an individual name.

Suppose you find that, in a smaller, computable universe consisting of just two securities, a portfolio comprising, say, SPY and QQQ was found to be cointegrated. Then, when extending consideration to portfolios of three securities, instead of examining every possible combination, you might instead restrict your search to only those portfolios which contain SPY and QQQ. Having fixed the first triangular arbitrage two selections, you are left with only 83 possible combinations of three securities to consider. This process is repeated as you move from portfolios comprising 3 securities to 4, 5, 6, … etc. Another application might be to construct robust portfolios of lower-correlated assets. Here for example we use the graph to identify independent vertices that have very few correlated relationships .

Accounting Data As Investment Factors

Their result shows that the systematic component of stock returns explains between 40 and 60% of the variance. Huck and Afawubo explore the performance of a pairs trading system based on various pairs-selection methods. They use the components of the S&P 500 index as an observation target. They argue that when the stock price deviates from equilibrium, the investor can enter the trade after controlling for risk and transaction costs.

statistical arbitrage

Second, we use the Ornstein Uhlenbeck process to test the statistical arbitrage trading of the synthetic asset constructed from the original Berkshire Hathaway stock and its replicating asset. Traditional pairs trading strategies are prone to failures when fundamental or economic reasons cause a structural break and the pair of assets that were expected to move together are no longer having a strong relationship. Such a break may result in asset price spread having abnormally high deviations failing to revert to its historical mean values. Under these circumstances, betting on the spread to revert to its historical mean would result in a loss. To overcome the problem of detecting whether the deviations are temporary or longer-lasting, Bock, M.

Pairs trading or statistical arbitrage is a famous strategy among institutional and individual investors since the 1990s. If the prices of assets move together historically, this tendency is likely to continue in the future. When the spread of the prices diverges from its long-term mean, one can short sell the over-priced stock, buy the under-priced one, and wait for the spread to converge to take the profit. Whilst both cointegration and correlation can measure asset prices that move together and hence establish a relationship, correlation breaks down on the long-term but is somewhat robust in identifying short-term relationships.

What Is Quantitative Trading?

All definitions embed the concept of take profit as long as it is assumed that a strategy is closed at maturity or when the expected returns are no longer positive. AOs can be closed in stop loss if the realized loss is higher than what is acceptable according to the stress measures. Hogan’s SA has the concept of stop loss if it is assumed that a strategy is closed when the constraints on the probability of a loss are no longer satisfied. AA trades are closed in stop loss only if the gain-loss ratio is lower than one.

statistical arbitrage

The positions are squared off when the assets return to their normalized value. There are also other mean reversion trading elements when exploiting an arbitrage opportunity, such as identifying how long it should take for a spread to revert to the mean. This is called the half-life of the mean, and for that, I highly recommend reading my favorite books on statistical arbitrage.

The underlying securities may or may not belong to the same asset class. In finance, statistical arbitrage is a class of short-term financial trading strategies that employ mean reversion models involving broadly diversified portfolios of securities held for short periods of time . These strategies are supported by substantial mathematical, computational, and trading platforms. It turns out to be much more challenging to find reliable stock pairs to trade than one might imagine, for reasons I am about to discuss. It is that the research effort required to build a successful statistical arbitrage strategy is beyond the capability of the great majority of investors. In our previous article, we’ve discussed a couple of trading strategies exploiting arbitrage between similar stocks using stochastic optimal control methods.

Simons’ co-president, Robert Mercer, attained political notoriety when he became the largest funder of the Trump campaign . For example, the use of a common classification system allows investigating the profitability and riskiness of SA strategies across asset classes and time. This enables mapping pricing anomalies and can provide directions on how to improve pricing models.

Many large institutional trades throughout the day have nothing to do with information and everything to do with liquidity. Investors that feel overexposed will aggressively hedge or liquidate positions, which will end up affecting the price. These liquidity demanders are often willing to pay a price to exit their positions, which can result in a profit for liquidity providers. This ability to profit on information seems to contradict the efficient market hypothesis but forms the foundation of fibonacci sequence.

Pairs Trading With Markov Regime

We want to know the “why” behind a time series, and we do this by decomposing the time series into its constituent components. Suppose you’re an algorithmic trader and plan on creating a statistical arbitrage strategy. In that case, the first step is to perform data manipulation to remove incorrect values, check for outlying data, and order the bits and bytes in a useful manner. Cross asset arbitrage is an investment strategy that bets on the price discrepancy between a financial asset and its underlying.

However, we filter out companies with less than 10 years of daily pricing data and are left with only the final 15 stocks. We take the daily closing price for these 15 stocks and split the dataframe into test and training sets. This is to ensure that our decision to select a cointegrated pair is based on the training dataset and backtesting is done using out of sample test dataset. As a first step, we will use the Pearson correlation coefficient to get the basic idea about the relationship between these stocks and then work to identify cointegrated stocks using the function coint form statsmodels.tsa.stattools .

Investors can maximize profits by shorting the overpriced and buying the underpriced. However, this method still has some problems, such as when to trade to maximize the profit of paired trading. Bertram uses the statistical arbitrage trading based on to drive the timing of pairs trading entry and exits. Cummins and Bucca followed Bertram’s method and achieved good results. Do and Faff examine the impact of trading costs on pairs trading profitability.

The best defense to these risks is always to assume the model could fail at any point in time and fully understand each arbitrage strategy’s individual risks and the overall risks in the context of your portfolios. When gold prices moved up faster than gold miners, we would sell the gold miners short and buy the gold miners; when gold’s price movements fell more quickly than gold miners, we could buy gold and sell the miners. Going back in time, we could have profited from this relationship with almost zero market risk – meaning if the market went up, down, or sideways, we still made money.

According to the other definitions instead a trade is closed only when the defining criteria are no longer met and this does not necessarily involve a stop loss. Although some definitions are compatible with various strategies’ common features, nevertheless they fail to incorporate all of them as defining elements. In the literature, there are two definitions of Statistical Arbitrage which differ significantly from each other.

The basic methodology for constructing a long/short portfolio using cointegration is covered in an earlier post. But problems arise when trying to extend the universe of underlying securities. Recently I have been working on the problem of how to construct large portfolios of cointegrated securities. My focus has been on ETFs rather that stocks, although in principle the methodology applies equally well to either, of course.

An Overview Of Pairs Trading

If the price of gold goes up, the profitability of gold miners should increase, also. If the gold price increases quickly, either the gold miner’s stock prices must follow, or the gold price must fall. An overview of research and development in algorithmic trading is provided and key issues involved in Swing trading the current effort on its improvement are discussed, which would be of great value to traders and investors. As the speed at which the time series correct themselves from this disequilibrium, we can see that this formalizes the way cointegrated variables adjust to match their long-run equilibrium.

Data Availability

Let’s keep in mind that any decision to implement a strategy should be based only after considering all the critical performance parameters including its feasibility and returns net of fee and charges. Next, we follow the steps 1 to 4 for the second stock and sum up two asset’s positions for the total portfolio value. Create a signals dataframe of our two stocks with the closing price from the testing dataset and calculate their price ratio.

Algorithmic Strategies Catalog

This dissertation examined whether it is possible to exploit these market conditions for leveraged ETF trading using statistical arbitrage strategies. The study proposed a regime switching model tailored for LETF markets to predict volatility and time-series momentum in the behavior of the underlying indexes of the LETFs. The study then used this model to test short pair trading strategies on a varied set of commodity LETFs to see if theoretical intuitions informed by these analyses were empirically supported by data. The study also introduced the concept of lag relative expected volatility based on inductive learning in a binary classification framework to model upward shocks in expected volatility on any given trading day. This outperformance was, however, found to be present in Sortino ratios only.

Build, Test, And Implement Statistical Arbitrage Trading Strategies With Matlab

Trexquant applies quantitative methods to systematically build optimized global market-neutral equity portfolios in liquid markets. Trading signals are developed from thousands of data variables and extensively tested. Strategies dynamically adjust allocations to Alphas depending on recent performance.

Author: Daniela Sabin Hathorn

Tags: No tags

Add a Comment

Your email address will not be published. Required fields are marked *