Confidence intervals in regressions with estimated factors and idiosyncratic components

Fosten, Jack (2017) Confidence intervals in regressions with estimated factors and idiosyncratic components. Economics Letters, 157. 71–74. ISSN 0165-1765

[img]
Preview
PDF (Accepted manuscript) - Submitted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (602kB) | Preview

    Abstract

    This paper shows that HAC standard errors must be adjusted when constructing confidence intervals in regressions involving both the factors and idiosyncratic components estimated from a big dataset. This result is in contrast to the seminal result of Bai and Ng (2006) where the assumption that √T/N→0 is sufficient to eliminate the effect of estimation error, where T and N are the time-series and cross-sectional dimensions. Simulations show vast improvements in the coverage rates of the adjusted confidence intervals over the unadjusted ones.

    Item Type: Article
    Uncontrolled Keywords: factor model,idiosyncratic component,inference,confidence intervals
    Faculty \ School: Faculty of Social Sciences > School of Economics
    Related URLs:
    Depositing User: Pure Connector
    Date Deposited: 31 May 2017 09:31
    Last Modified: 09 Apr 2019 12:15
    URI: https://ueaeprints.uea.ac.uk/id/eprint/63621
    DOI: 10.1016/j.econlet.2017.05.034

    Actions (login required)

    View Item