State-Dependent Threshold Smooth Transition Autoregressive Models

被引：19

作者：

Dueker, Michael J. ^{[1
]}

Psaradakis, Zacharias ^{[2
]}

Sola, Martin ^{[2
,3
]}

Spagnolo, Fabio ^{[4
]}

机构：

[1] Russell Investments, New York, NY USA

[2] Univ London, Dept Econ Math & Stat, London, England

[3] Univ Torcuato Tella, Dept Econ, Buenos Aires, DF, Argentina

[4] Brunel Univ, Dept Econ & Finance, Uxbridge UB8 3PH, Middx, England

来源：

OXFORD BULLETIN OF ECONOMICS AND STATISTICS | 2013年 / 75卷 / 06期

关键词：

C22; E43; INTEREST-RATES;

D O I：

10.1111/j.1468-0084.2012.00719.x

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

In this article, we consider extensions of smooth transition autoregressive (STAR) models to situations where the threshold is a function of variables that affect the separation of regimes of the time series under consideration. Our specification is motivated by the observation that unusually high/low values for an economic variable may sometimes be best thought of in relative terms. State-dependent contemporaneous-threshold STAR and logistic STAR models are introduced and discussed. These models are also used to investigate the dynamics of US short-term interest rates, where the threshold is allowed to be a function of past output growth and inflation.

引用

页码：835 / 854

页数：20

共 18 条

[1]

Andrews D.W.K., 1993, ECONOMET REV, V12, P183

[2] Approximately normal tests for equal predictive accuracy in nested models [J].