We propose a new hypothesis-testing method for multipredictor regressions in small samples, where the dependent variable is regressed on lagged variables that are autoregressive. The new test is based on the augmented regression method (Amihud and Hurvich, 2004), which produces reduced-bias...

Studies of predictive regressions analyze the case where yt is predicted by xt - 1 with xt being first-order autoregressive, AR(1). Under some conditions, the OLS-estimated predictive coefficient is known to be biased. We analyze a predictive model where yt is predicted by xt - 1,...

It has been shown that Akaike information criterion (AIC)-type criteria are asymptotically efficient selectors of the tuning parameter in nonconcave penalized regression methods under the assumption that the population variance is known or that a consistent estimator is available. We relax this...

We consider a general long memory time series, assumed stationary and linear, but not necessarily Gaussian or generated by a finite-parameter model. For such a process, we derive the asymptotic joint distribution of the normalized periodogram at a fixed, finite collection of Fourier frequencies....

We consider semiparametric estimation of the memory parameter in a model that includes as special cases both long-memory stochastic volatility and fractionally integrated exponential GARCH (FIEGARCH) models. Under our general model the logarithms of the squared returns can be decomposed into the...