1 TESTING FOR ONGOING EFFICIENCY IN THE RUSSIAN STOCK MARKET 1 Stephen Hall Imperial College, 53 Princes Gate London SW7 2PG (UK) Tel. UK +/44/(0)20/7594 9120, Fax UK +/44/(0)20/7823 7685 e-mail: s.g.hall@ic.ac.uk Giovanni Urga Faculty of Finance City University Business School Frobisher Crescent, Barbican Centre London EC2Y 8HB (U.K.) Tel. +/44/(0)20/7040 8698, Fax. +/44/(0)20/7040 8881 e-mail: g.urga@city.ac.uk This version: 14 May 2002 ABSTRACT: In this paper we discuss a test of changing market efficiency based on a time varying parameter model with generalised autoregressive conditional heteroscedasticity in mean (GARCH-M) structure of the residuals. We apply this procedure to the returns from the two main indexes of the Russian stock market, running from September 1995 to the end of March 2000. When we consider the Russian Trading System (RTS) index of the most liquid stocks, the market is initially inefficient and that it takes around two and a half years to become efficient. The story from the Skate Press Agency General Index (ASPGEN), comprising a wider number of stocks, is that the overall performance of the market had remained predictable for most of the time and only in the last period there is sign of ongoing efficiency. We then apply the technique to a sample of individual liquid shares and find mixed evidence over the period but with a tendency however towards becoming efficient. Keywords: Kalman Filter, Stock Markets Efficiency, Transition Economies. JEL Classification: C22, G14,G15. 1 We acknowledge J. Hatgioannides, S. Lazarova, M. Nuti, and P. Temple for valuable comments and discussions. Special thanks go to Lorenzo Campori for extracting the data set from REUTERS and BLOOMBERG terminals, and Helen Kozlova of Skate Agency in Moscow in providing us with general information concerning the markets and shares investigated in this study. Nevertheless, the usual disclaimer applies. Financial support from PHARE-ACE Project N. T97-8118-R is gratefully acknowledged.