Research On The Application Of ETF Futures-Cash Arbitrage Method Based On Statistical Arbitrage

In fluctuate security market, earning steady excess yield is all investors want to pursue forever.With index future and financing securities opening to investors,we will say good bye to no short mechanism period, we can only profit in market when stock index rise up without short mechanism. It give us a chance to arbitrage.Statistical arbitrage strategy is widely used by foreign hedge-fund,for our country always lack short mechanism,scholars of mainland China rarely processed related research.This paper used statistical arbitrage strategy in our country's security market,to test the feasibility of this strategy in China.The main works of this paper are described as follows:(1) Through analysis of average transaction amount per day, we choose 50ETF which has the best liquidity as our research object.We design two indexes to measure the liquidity risk of 50ETF which are instant impulse cost and wait cost. Further more,we use VaR method to calculate two liquidity risk indexes of 50ETF and compare them with each other.We get the result that wait cost is obvious less than instant impulse cost,we choose wait for a moment to complish our transtaction when the volume is very large other than to complish it instantly,this transtaction can decrease transaction cost for the lack of liquidity.(2) Use cointegration to test long term equilibrium relation of 50ETF and hs300 index future,further to establish the coefficient of pairs trading.Test result shows that there exist long term equilibrium relation between them.After suited object of pairs trading have decided,we use the sample data to construct the optimized threthold as the trigger point for the arbitrage which can provide us maximal expected arbitrage profit.In order to control arbitrage risk,we use POT model of extreme value theory to decide the stop-loss boundary which can provide us a stable arbitrage strategy.After the optimized arbitrage strategy has construct,we us the data in sample period and out sample period to transact simulately with the optimized arbitrage strategy we have construct to test wether it profitable and feasible.The test result give us a affirmative answer, not only in bull but also in bear, we always get alpha larger than 10% per year,which approve the arbitrage strategy is profitable and feasible in our security market.