Job market paper
Bootstrapping
out-of-sample predictability tests
with real-time data
with Silvia Goncavles
&
Michael McCracken
In this paper, we develop a block bootstrap approach to out-of-sample inference when real-time data is used to produce forecasts. In particular, we establish its first-order validity for West-type (1996) tests of predictive ability in the presence of regular data revisions. This allows the user to conduct asymptotically valid inference without having to estimate the asymptotic variances derived in Clark and McCracken's (2009) extension of West (1996) when data is subject to revision. Monte Carlo experiments indicate that the bootstrap provides a reasonable finite sample size and power irrespective of whether the revisions consist of news or noise.
Work in progress
Impacts of macroeconomic releases
and future revisions
on exchange-traded funds
In this paper, we investigate both the direct impacts of macroeconomic releases and the effects of future revisions on the financial market with daily and high-frequency minute returns.
with Fan Yang
Evaluating
non-linear forecasting models
with vintage data
a block bootstrap approach
In this paper, we extend our bootstrap method to a more general M-estimation framework. By adjusting our bootstrap method to the M-estimation framework, the new bootstrap method is not only limited to OLS estimation but also compatible with non-linear least squares and maximum likelihood estimations
with Silvia Goncavles
&
Michael McCracken