Limit Theory for Moderate Deviations from a Unit Root under Weak Dependence

By Peter C. B. Phillips, Tassos Magdalinos. 2005

392 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance

View Paper: https://www.semanticscholar.org/paper/54c515e40a32ab9d36fb54de6df8121e010fec30

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Finance

Citations in the corpus

Episodes of Exuberance in Housing Markets: In Search of the Smoking Gun (2016, background): “Phillips and Magdalinos (2007a), Phillips and Magdalinos (2007b) and Phillips and Magdalinos (2012) provide a large sample asymptotic theory for this class of processes that enables econometric inference in this case, unlike for purely explosive processes.”
Inference on stochastic time-varying coefficient models (2014, background): “Phillips (1987), Chan and Wei (1987), Phillips and Magdalinos (2007), Andrews and Guggenberger (2008) extended it to AR(1) models that are local to unity.”
Predictive regression under various degrees of persistence and robust long-horizon regression (2013, methodology): “This additional level of generality is not considered in the present work but may be handled by the methods given here and in MP. space (Phillips and Magdalinos, 2007a,b; Magdalinos and Phillips, 2009a) enables a more generally applicable approach to predictive regression.”
LIMIT THEORY FOR COINTEGRATED SYSTEMS WITH MODERATELY INTEGRATED AND MODERATELY EXPLOSIVE REGRESSORS (2009, background): “In the moderately explosive case (where ci > 0) the limit theory is mixed normal with Cauchy-type tail behavior, and the rate of convergence is explosive, as in the case of a moderately explosive scalar autoregression (Phillips and Magdalinos, 2007, Journal of Econometrics 136, 115–130).”
REGRESSION ASYMPTOTICS USING MARTINGALE CONVERGENCE METHODS (2008, neutral): “2 dv 102 + Further, when there are moderate deviations from unity of the form a 1 ~c0nb! for some b ~0,1! and c 0 ~as in Giraitis and Phillips, 2006; Phillips and Magdalinos, 2007!, ~6+2! continues to hold but with Xn~r!”
Bubbles in food commodity markets: Four decades of evidence ☆ (2014, positive): “…autoregressive processes as the central limit theory does not apply (White 1958; Anderson 1959), the asymptotic behavior of mildly explosive processes is more regular and a least squares regression theory can be established to construct confidence intervals (Phillips and Magdalinos 2007a,b).”
UNIT ROOT AND COINTEGRATING LIMIT THEORY WHEN INITIALIZATION IS IN THE INFINITE PAST (2008, neutral): “…also play a dominant role in determining the form of the signal, which behaves like the square of a one-dimensional random variable whose distribution depends on the distribution of the shocks in the pure explosive case but not in the mildly explosive case (see Phillips and Magdalinos, 2007).”
Folklore Theorems, Implicit Maps, and Indirect Inference (2012, background): “A similar point applies in the case of mildly explosive asymptotics (Phillips and Magdalinos, 2007).”
ASYMPTOTIC THEORY FOR ESTIMATING DRIFT PARAMETERS IN THE FRACTIONAL VASICEK MODEL (2018, methodology): “The asymptotic law for κ̂LS is a Cauchy-type and is similar to that developed in the explosive discrete-time and continuous-time models in Phillips and Magdalinos (2007); Magdalinos (2012); Wang and Yu (2015, 2016); Arvanitis and Magdalinos (2018).”
Asymptotic properties of the efficient estimators for cointegrating regression models with serially dependent errors (2009, positive): “Therefore, ω̂Δ11 in (23) converges to 0 in probability.”
Unit root log periodogram regression (2007, methodology): “Most recently, models with mildly nonstationary or mildly explosive behavior have been analyzed by Phillips and Magdalinos (2006a, b) and Giraitis and Phillips (2006). In these models, the roots deviate from unity by the sense that the deviations are Oðk 1 n Þ where kn=n! 0 as n!1.”
Econometric Inference in the Vicinity of Unity. 1 (2009, background): “For example, suitably standardized sample moments converge to constant matrices rather than random matrices as n ! 1 (c.f., MP, and in the univariate case, Phillips and Magdalinos, 2007 ), in which case the traditional e¤ects of (…rst order) simultaneous equations bias begin to manifest in ordinary”
Predictive quantile regression with persistent covariates: IVX-QR approach (2015, background): “2 (MI) and (ME) spaces are introduced in Phillips and Magdalinos (2007).”
X-DIFFERENCING AND DYNAMIC PANEL MODEL ESTIMATION (2013, background): “Similarly, extensions to mildly explosive cases (Phillips and Magdalinos, 2007) are left to future work.”
Instrumental variable and variable addition based inference in predictive regressions (2015, background): “If αT = 1 − a/T η, xt is mildly (or moderately) integrated in the sense of Phillips and Magdalinos (2007) and Magdalinos and Phillips (2009).”