Statistical Arbitrage
What is arbitrage trading? What is Statistical Arbitrage?
This post describes the arbitrage concept and examines statistical arbitrage, a trading and fund management methodology that is the core of Emerging Market Intrinsic (EMI)’s Arbitrage Trader Model used in Stock Arbitrage Trader for the iPad.
Arbitrage is described as the practice of taking advantage of a price difference between two or more markets: striking a combination of matching deals that capitalize upon the imbalance, the profit being the difference between the market prices.
To give a simple and hypothetical (and also almost impossible) example, if 1.00 Euro trades at $1.50 in London, and only $1.20 in New York that provides a clear arbitrage opportunity for investors/ traders, to buy Euros in New York and sell in London and make $0.30 on each dollar. A clear, risk-free, but also very rare window of opportunity, arbitrage chances are usually caught by machines or computers continuously observing millions of data points simultaneously.
More specifically, if professionals talk about stock arbitrage, they usually mean one of the two main trading strategies. These are:
➤ Stock arbitrage in different geographic markets for the same equity. If for example Toyota’s American Depository Receipts (ADRs) / or US-equivalent shares is trading at $75 in New York and at $68 in Tokyo (a discrepancy this wide is again almost impossible), that again provides an imbalance, and a profit opportunity for the trader to buy the equity in one geographic market and sell in another.
➤ Statistical arbitrage. In conventional or deterministic arbitrage (see the basic examples above), a sure profit can be obtained from being long some securities and short others. In statistical arbitrage, there is a statistical mispricing of one or more assets based on the expected value of these assets. In other words, statistical arbitrage conjectures statistical mispricings of price relationships that are true in expectation, in the long run when repeating a trading strategy.
The Stock Arbitrage Trader App uses a complex version of statistical arbitrage strategy. Also referred in the finance world as mean reversion, statistical arbitrage observes real-time data of market and stock movements and assumes that each instrument must revert to its own mean or normal characteristic.
To measure normalcy or characteristic, the methodology examines each instrument’s volatility. Volatility of a stock is composed of market volatility (systematic risk) plus idiosyncratic (firm-specific) risk. In today’s markets, market volatility or the systematic risk dominates short-term trading patterns of most equities.
σ²(i)=β²(i)σ²(M)+σ²(ei)
σ²(i)………. Total risk or volatility
β²(i)σ²(M)… Market risk
σ²(ei)……… Firm-specific risk
Based on real-time calculations and analysis of multi-factor inputs/ variables, the arbitrage model determines a characteristic (or a price range) at which the stock is assumed to be statistically fairly valued.
If the price falls below this dynamically changing range, the model sends a “buy” signal, if the price goes above this range it says “sell”, or if the real-time price is between these intervals then it signals a “hold” call.
By using rigorous statistical methodology, the model identifies non-random patterns in the behavior of equities.
Exploiting these inefficiencies allows earning exceptional returns with little risk.
































