Data frequency and the number of factors in stock returns

Abstract

Determining the number of factors that explain stock returns plays an important role in empirical tests of the Arbitrage Pricing Theory. This paper examines the sensitivity of the number of factors to different data frequencies using daily, weekly, and monthly returns. The empirical results are consistent with the null hypothesis that the number of factors is the same for different data frequencies once daily returns are adjusted for nonsynchronous trading. The evidence also identifies only one or two factors.