Construction of a Market-Neutral ETF Portfolio: A Relative-Value Based Approach

The study describes how cointegration-based techniques can be employed in order to construct profitable trading strategies that exploit mispricing events between similar securities. Particularly, the Johansen Maximum Likelihood Estimation and the Kalman filter approaches are applied to the universe of 200 most liquid ETF stocks traded on NYSE and NASDAQ. The results show that the strategies are quite sensitive to transaction costs, but are still able to maintain profitability even after accounting for a conservative level of transaction costs. While the Kalman filter produces better results on daily data, the 15-minute timeframe is dominated by portfolios constructed by the Johansen cointegration test. Both strategies achieve significantly higher risk-adjusted returns on the intraday timeframe. The study also reveals a performance decline of both strategies in the period of 2013-2015 and outlines possible interpretation of such event.