Instrumental variable and variable addition based inference in predictive regressions

Breitung, Jörg; Demetrescu, Matei

doi:10.1016/j.jeconom.2013.10.018

Cited by 42 publications

(36 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is achieved through an IV method developed in Phillips and Magdalinos (2009) in the context of the cointegration literature and which we adapt to our current context (see also Breitung and Demetrescu (2014)). The key idea is to instrument x t with a slightly less persistent version of itself using its own innovations (hence the IVX terminology).…”

Section: Testingmentioning

confidence: 99%

Inferring the Predictability Induced by a Persistent Regressor in a Predictive Threshold Model

Gonzalo

Pitarakis

2017

Journal of Business & Economic Statistics

View full text Add to dashboard Cite

We develop tests for detecting possibly episodic predictability induced by a persistent predictor. Our framework is that of a predictive regression model with threshold effects and our goal is to develop operational and easily implementable inferences when one does not wish to imposeà priori restrictions on the parameters of the model other than the slopes corresponding to the persistent predictor. Differently put our tests for the null hypothesis of no predictability against threshold predictability remain valid without the need to know whether the remaining parameters of the model are characterised by threshold effects or not (e.g. shifting versus non-shifting intercepts). One interesting feature of our setting is that our test statistics remain unaffected by whether some nuisance parameters are identified or not. We subsequently apply our methodology to the predictability of aggregate stock returns with valuation ratios and document a robust countercyclicality in the ability of some valuation ratios to predict returns.

show abstract

Section: Testingmentioning

confidence: 99%

Inferring the Predictability Induced by a Persistent Regressor in a Predictive Threshold Model

Gonzalo

Pitarakis

2017

Journal of Business & Economic Statistics

View full text Add to dashboard Cite

show abstract

“…Closely related methods to IVX that use modifed variable addition (VA) regressions have most recently been introduced by Breitung and Demetrescu (2015) where lagged predictors are replaced by persistent time series using the Phillips-Magdalinos methodology of self-generated variables and instrumentation. These VA methods, like IVX, help remove non-pivotal inference problems when there are LUR predictors, and are similarly applicable when there are multiple predictors.…”

Section: Ivx Endogenous Instrumentationmentioning

confidence: 99%

Pitfalls and Possibilities in Predictive Regression

Phillips

2015

SSRN Journal

View full text Add to dashboard Cite

Financial theory and econometric methodology both struggle in formulating models that are logically sound in reconciling short run martingale behaviour for …nancial assets with predictable long run behavior, leaving much of the research to be empirically driven. The present paper overviews recent contributions to this subject, focussing on the main pitfalls in conducting predictive regression and on some of the possibilities o¤ered by modern econometric methods. The latter options include indirect inference and techniques of endogenous instrumentation that use convenient temporal transforms of persistent regressors. Some additional suggestions are made for bias elimination, quantile crossing amelioration, and control of predictive model misspeci…cation.

show abstract

“…Although nearly integrated asymptotics approximates the finite sample behavior of the t-statistic for no predictability considerably better when regressors are persistent, the exact degree of persistence of a given regressor, and thus the correct critical values for a predictability test, are unknown in practice. To overcome these difficulties, a number of alternative (robust) approaches have been proposed in the literature to test predictability without characterizing the stochastic properties of regressors (i.e., whether they are stationary or nearly integrated or unit root); see, for instance, Cavanagh et al (1995), 1 Campbell and Yogo (2006), Jansson and Moreira (2006), Phillips and Lee (2013), Cai and Wang (2014), Breitung and Demetrescu (2015), Kostakis, et al (2015), Demetrescu and Rodrigues (2016), and references therein.…”

Section: Introductionmentioning

confidence: 99%

“…see Demetrescu (2014) and Breitung and Demetrescu (2015) for more details on this model and the variable addition approach. Hence, an interesting question is whether the lagged variables are really econometrically needed in real applications, i.e., how to test the existence of a lagged predicted variable in a predictive regression, which apparently has not been formally addressed in predictive regressions when regressors may be nearly integrated.…”

Section: Introductionmentioning

confidence: 99%

Unified Tests for a Dynamic Predictive Regression

Yang

Liu

Peng

et al. 2020

Journal of Business & Economic Statistics

View full text Add to dashboard Cite

Testing for predictability of asset returns has been a long history in economics and finance. Recently, based on a simple predictive regression, Kostakis, Magdalinos and Stamatogiannis (2015, Review of Financial Studies) derived a Wald type test based on the context of the extended instrumental variable (IVX) methodology for testing predictability of stock returns and Demetrescu (2014) showed that the local power of the standard IVX-based test could be improved in some cases when a lagged predicted variable is added to the predictive regression on purpose, which poses a general important question on whether a lagged predicted variable should be included in the model or not. This paper proposes novel robust procedures for testing both the existence of a lagged predicted variable and the predictability of asset returns in a predictive regression regardless of regressors being stationary or nearly integrated or unit root and the AR model for regressors with or without intercept. A simulation study confirms the good finite sample performance of the proposed tests before applying the proposed tests to some real datasets in finance to illustrate their practical usefulness.

show abstract

Instrumental variable and variable addition based inference in predictive regressions

Cited by 42 publications

References 25 publications

Inferring the Predictability Induced by a Persistent Regressor in a Predictive Threshold Model

Inferring the Predictability Induced by a Persistent Regressor in a Predictive Threshold Model

Pitfalls and Possibilities in Predictive Regression

Unified Tests for a Dynamic Predictive Regression

Contact Info

Product

Resources

About