Turning Over Turnover

This paper applies the newly developed methodology of Bai and Ng (2002, 2003), providing the decomposition of large panel data into systematic and idiosyncratic components, to both returns and turnover. When combined with a GLS-based principal components approach, we demonstrate their procedure works well for both returns and turnover, despite the presence of severe heteroscedasticity and non-stationarity in turnover of individual stocks. Using this method, we provide a new test of Lo and Wang’s (2000) theoretical model’s restriction that returns and turnover should have the same number of systematic factors. We find this restriction is strongly rejected by the data, suggesting that stock price and trading volume may not be compatible under the existing multi-factor asset pricing-trading framework. We further demonstrate that several commonly used turnover measures may understate the price impact of stock trading.