چکیده:
The present study aims at investigating the relationship between firm specific risk and stock return using cross-sectional quantile regression. In order to study the power of firm specific risk in explaining cross-sectional return, a combination of Fama-Macbeth (1973) model and quantile regression is used. To this aim, a sample of 270 firms listed in Tehran Stock Exchange during 1999-2010 was investigated. The results revealed that the relationship between firm specific risk and stock return is significantly affected by the quantile so that the direction of changes in low quantiles is negative, and in high quantiles, is positive. Also, using the specific risk measure based on return’s standard deviation, the interactive effects of industry and the fourth moment lead to removal of this relationship. Thus, one can attribute this relation to the mutual effect of industry and kurtosis. However, using measures based factor models, industry and kurtosis cannot eliminate the explanatory power of specific risk.
خلاصه ماشینی:
com Abstract The present study aims at investigating the relationship betweenfirm specific risk and stock return using cross-sectional quantile regression.
In order to study the power of firm specific risk in explaining cross-sectional return, a combination of Fama-Macbeth (1973) model and quantile regression is used.
Therefore, the main goal of this study is to investigate FSR and cross-sectional return in Tehran Stock Market using a combination of quantile regression and Fama-Macbeth model (1973).
In this first step, the cross-sectional quantile regression is run in every quarterly time points ending in April, July, October and January using the data of the given quarter in different qunatiles of as following: ri,t (τ) = γ0,t (τ) + γ1,t (τ)σi,t + ∑K γk,t (τ)Xi,k,t + vi,t (τ), i = 1, … , Nt (9) Where, ri,t is the return of ith stock in period t, σi,t is FSR and Xi,k,t is the control variables consisting of size, beta, ratio of market value to book value, momentum, liquidity, stock turnover, institutional ownership, kurtosis and industry.
In order to test the relationship of FSR and stock return, equation (10) is estimated within the framework of cross-sectional quantile regression and the results are presented in Table (3).
As it can be seen in Table (4), if different measures and minimum trading limits are used, a specific model can be obtained in the behavior of FSR coefficient for different quantiles of return distribution, so as regardless of statistical significance, the relationship of FSR and return is negative in lower quantiles and positive in higher ones.