scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Jump-Preserving Varying-Coefficient Models for Nonlinear Time Series

01 May 2020-Econometrics and Statistics (Elsevier)-Vol. 19, pp 58-96
TL;DR: In this paper, a varying-coefficient model is proposed for time series with heteroskedastic and serially correlated errors, where the conditional error variance is allowed to exhibit discontinuities at a finite set of points.
About: This article is published in Econometrics and Statistics.The article was published on 2020-05-01 and is currently open access. It has received 3 citations till now. The article focuses on the topics: Classification of discontinuities & Asymptotic distribution.
Citations
More filters
Journal ArticleDOI
TL;DR: In this article, a detailed analysis of the asymptotic properties of a kernel estimator for a Seemingly Unrelated Regression Equations model with time-varying coefficients (TV-SURE) under very general conditions is provided.
Abstract: This paper provides a detailed analysis of the asymptotic properties of a kernel estimator for a Seemingly Unrelated Regression Equations model with time-varying coefficients (tv-SURE) under very general conditions. Theoretical results together with a simulation study differentiates the cases for which the estimation of a tv-SURE outperforms the estimation of a Single Regression Equations model with time-varying coefficients (tv-SRE). The study shows that Zellner's results cannot be straightforwardly extended to the time-varying case. The tv-SURE is applied to the Fama and French five-factor model using data from four different international markets. Finally, we provide the estimation under cross-restriction and discuss a testing procedure.

14 citations

Posted Content
TL;DR: In this paper, a general class of nonlinear varying coefficient time series models with possible nonstationarity in both the regressors and the varying cost components are studied, and nonparametric and semiparametric estimation methods are proposed to estimate the varying coefficient functions.
Abstract: This paper studies a general class of nonlinear varying coefficient time series models with possible nonstationarity in both the regressors and the varying coffiecient components. The model accommodates a cointegrating structure and allows for endogeneity with contemporaneous correlation among the regressors, the varying coefficient drivers, and the residuals. This framework allows for a mixture of stationary and non-stationary data and is well suited to a variety of models that are commonly used in applied econometric work. Nonparametric and semiparametric estimation methods are proposed to estimate the varying coefficient functions. The analytical findings reveal some important differences, including convergence rates, that can arise in the conduct of semiparametric regression with nonstationary data. The results include some new asymptotic theory for nonlinear functionals of nonstationary and stationary time series that are of wider interest and applicability and subsume much earlier research on such systems. The finite sample properties of the proposed econometric methods are analyzed in simulations. An empirical illustration examines nonlinear dependencies in aggregate consumption function behavior in the US over the period 1960-2009.

9 citations

Journal ArticleDOI
TL;DR: In this paper, a new semiparametric time series model is introduced, the semi-parametric transition (SETR) model, which generalizes the threshold and smooth transition models by allowing the transition function to be modified.
Abstract: A new semiparametric time series model is introduced – the semiparametric transition (SETR) model – that generalizes the threshold and smooth transition models by letting the transition function to...
References
More filters
Journal ArticleDOI
TL;DR: In this article, the authors examine how recent econometric policy evaluation research on monetary policy rules can be applied in a practical policymaking environment, and the discussion centers around a hypothetical but representative policy rule much like that advocated in recent research.

8,414 citations

Journal ArticleDOI
TL;DR: In this paper, the problem of estimating the break dates and the number of breaks in a linear model with multiple structural changes has been considered and an efficient algorithm based on the principle of dynamic programming has been proposed.
Abstract: In a recent paper, Bai and Perron (1998) considered theoretical issues related to the limiting distribution of estimators and test statistics in the linear model with multiple structural changes. In this companion paper, we consider practical issues for the empirical applications of the procedures. We first address the problem of estimation of the break dates and present an efficient algorithm to obtain global minimizers of the sum of squared residuals. This algorithm is based on the principle of dynamic programming and requires at most least-squares operations of order O(T2) for any number of breaks. Our method can be applied to both pure and partial structural change models. Second, we consider the problem of forming confidence intervals for the break dates under various hypotheses about the structure of the data and the errors across segments. Third, we address the issue of testing for structural changes under very general conditions on the data and the errors. Fourth, we address the issue of estimating the number of breaks. Finally, a few empirical applications are presented to illustrate the usefulness of the procedures. All methods discussed are implemented in a GAUSS program. Copyright © 2002 John Wiley & Sons, Ltd.

4,026 citations

Posted Content
TL;DR: In this paper, the problem of estimating the number of break dates in a linear model with multiple structural changes has been studied and an efficient algorithm to obtain global minimizers of the sum of squared residuals has been proposed.
Abstract: In a recent paper, Bai and Perron (1998) considered theoretical issues related to the limiting distribution of estimators and test statistics in the linear model with multiple structural changes. In this companion paper, we consider practical issues for the empirical applications of the procedures. We first address the problem of estimation of the break dates and present an efficient algorithm to obtain global minimizers of the sum of squared residuals. This algorithm is based on the principle of dynamic programming and requires at most least-squares operations of order O(T 2) for any number of breaks. Our method can be applied to both pure and partial structural-change models. Secondly, we consider the problem of forming confidence intervals for the break dates under various hypotheses about the structure of the data and the errors across segments. Third, we address the issue of testing for structural changes under very general conditions on the data and the errors. Fourth, we address the issue of estimating the number of breaks. We present simulation results pertaining to the behavior of the estimators and tests in finite samples. Finally, a few empirical applications are presented to illustrate the usefulness of the procedures. All methods discussed are implemented in a GAUSS program available upon request for non-profit academic use.

3,836 citations

Posted Content
TL;DR: This paper studied the behavior of money, credit, and macroeconomic indicators over the long run based on a newly constructed historical dataset for 12 developed countries over the years 1870-2008, utilizing the data to study rare events associated with financial crisis episodes.
Abstract: The crisis of 2008-09 has focused attention on money and credit fluctuations, financial crises, and policy responses. In this paper we study the behavior of money, credit, and macroeconomic indicators over the long run based on a newly constructed historical dataset for 12 developed countries over the years 1870-2008, utilizing the data to study rare events associated with financial crisis episodes. We present new evidence that leverage in the financial sector has increased strongly in the second half of the twentieth century as shown by a decoupling of money and credit aggregates, and we also find a decline in safe assets on banks' balance sheets. We also show for the first time how monetary policy responses to financial crises have been more aggressive post-1945, but how despite these policies the output costs of crises have remained large. Importantly, we can also show that credit growth is a powerful predictor of financial crises, suggesting that such crises are

2,021 citations

Journal ArticleDOI
Trevor Hastie1, Robert Tibshirani
TL;DR: In this paper, a class of regression and generalized regression models in which the coefficients are allowed to vary as smooth functions of other variables is explored and general algorithms are presented for estimating the models flexibly and some examples are given.
Abstract: We explore a class of regression and generalized regression models in which the coefficients are allowed to vary as smooth functions of other variables. General algorithms are presented for estimating the models flexibly and some examples are given. This class of models ties together generalized additive models and dynamic generalized linear models into one common framework. When applied to the proportional hazards model for survival data, this approach provides a new way of modelling departures from the proportional hazards assumption

1,509 citations