【正文】
ific, 5063.[4] Connor, G. , and R. Korajczyk, 1988, “Risk and Return in an Equilibrium APT: Application of a New Test Methodology,” Journal of Financial Economics, 21,255290.[5] Hann, T. H. and E. Steurer, 1996, “Much Ado about Nothing? Exchange Rate Forecasting: Neural Networks vs. Linear Models Using Weekly and Monthly Data,” Neuroputing, 10, 323339.[6] Lo, A. , and A. C. MacKinlay, 1990b, “DataSnooping Biases in Tests of Financial Asset Pricing Models,” Review of Financial Studies, 3, 431468[7] Lo, A. , and A. C. MacKinlay, 1996, “Maximizing Predictability in the Stock and Bond Markets,” Working Paper, LFE101996, MIT Laboratory for Financial Engineering.Statistical Arbitrage Models of the Shangzheng50HAN Guangzhe CHEN Shoudong ZHANG Binghui (Quantitative Economic Research Center, Business Sdhool of Jilin University,Changchun,130012)Abstract: In order to study the statistical arbitrage models of the Shangzheng50, this paper uses stepwise regression method to identify the appropriate subspace for pricing。Variance ratio analysis which tests the predictability shows that the detrended stock prices deviate significantly from random walk behaviour and contain predictable ponents. A model of simultaneous equations indicates that the “mispricing” of the stocks tends to trend in the shortterm and revert in the longer term. The outof sample performance of the statistical arbitrage models is profitable using a simple trading rule(build and hold), with the bined portfolio suggesting a annualised Sharpe Ratio of with costs of %. This study can help to discover the statistical arbitrage chances in the market and to improve the performance of the portfolio.Key Words: Statistical Arbitrage Models Mispricing Variance Ratio Analys