Heteroskedasticity-Robust Standard Errors for Fixed Effects Panel Data Regression


  • James H. Stock,

    1. Dept. of Economics, Harvard University, Littauer Center M-27, Cambridge, MA 02138, U.S.A., and NBER; james_stock@harvard.edu
    Search for more papers by this author
  • Mark W. Watson

    1. Dept. of Economics and Woodrow Wilson School, Princeton University, Fisher Hall, Prospect Street, Princeton, NJ 08544, U.S.A., and NBER; mwatson@princeton.edu
    Search for more papers by this author
    • We thank Alberto Abadie, Gary Chamberlain, Guido Imbens, Doug Staiger, Hal White, and the referees for helpful comments and/or discussions, Mitchell Peterson for providing the data in footnote 2, and Anna Mikusheva for research assistance. This research was supported in part by NSF Grant SBR-0617811.


The conventional heteroskedasticity-robust (HR) variance matrix estimator for cross-sectional regression (with or without a degrees-of-freedom adjustment), applied to the fixed-effects estimator for panel data with serially uncorrelated errors, is inconsistent if the number of time periods T is fixed (and greater than 2) as the number of entities n increases. We provide a bias-adjusted HR estimator that is inline image-consistent under any sequences (n, T) in which n and/or T increase to ∞. This estimator can be extended to handle serial correlation of fixed order.