2018/07/11 by Stanislav Anatolyev, Anatolyev, Stanislav, Anna Mikusheva +1 · 1 citation
Economics, Econometrics and Finance · #Econometrics (econ.EM) #Economic Policies and Impacts #FOS: Economics and business #Monetary Policy and Economic Impact #Politics, Economics, and Education Policy
paper · pdf · doi:10.48550/arxiv.1807.04094
openalex publication_date 2018/07/11 · openalex created_date 2022/08/04 · openalex updated_date 2026/07/28
This paper re-examines the problem of estimating risk premia in linear factor\npricing models. Typically, the data used in the empirical literature are\ncharacterized by weakness of some pricing factors, strong cross-sectional\ndependence in the errors, and (moderately) high cross-sectional dimensionality.\nUsing an asymptotic framework where the number of assets/portfolios grows with\nthe time span of the data while the risk exposures of weak factors are\nlocal-to-zero, we show that the conventional two-pass estimation procedure\ndelivers inconsistent estimates of the risk premia. We propose a new estimation\nprocedure based on sample-splitting instrumental variables regression. The\nproposed estimator of risk premia is robust to weak included factors and to the\npresence of strong unaccounted cross-sectional error dependence. We derive the\nmany-asset weak factor asymptotic distribution of the proposed estimator, show\nhow to construct its standard errors, verify its performance in simulations,\nand revisit some empirical studies.\n