Panel Kink Threshold Regression Model with a Covariate-Dependent Threshold

2020 ◽  
Author(s):  
Lixiong Yang ◽  
Chunli Zhang ◽  
Chingnun Lee ◽  
I-Po Chen
Keyword(s):  
Monte Carlo ◽  
Panel Data ◽  
Regression Model ◽  
Threshold Effect ◽  
Test Statistics ◽  
Threshold Regression ◽  
Finite Sample ◽  
Data Framework ◽  
Threshold Estimators ◽  
Threshold Regression Model

Abstract This paper extends the kink threshold regression (KTR) model with a constant threshold in Hansen (2017) to a panel data framework with a covariate-dependent threshold, where the threshold is modeled as a function of informative covariates. We suggest an estimator based on the within-group transformation, and propose test statistics for kink threshold effect and threshold constancy. We establish the asymptotic joint normality of the slope and threshold estimators, and derive the limiting distributions of the test statistics. Our asymptotical results show that the inclusion of a covariate-dependent threshold does not affect the asymptotic joint normality of the slope and threshold estimates in the kink threshold regression model. Monte Carlo simulations show that the finite sample proprieties of the proposed estimator and test statistics are generally satisfactory.

The threshold effect of firm size on technological innovation: examination of panel data from China

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Xiaoxue Zhou ◽  
Yu Li ◽  
Yao Zhang
Keyword(s):  
Panel Data ◽  
Regression Model ◽  
Technological Innovation ◽  
Firm Size ◽  
Manufacturing Sector ◽  
Threshold Effect ◽  
Nonlinear Relationship ◽  
Threshold Regression ◽  
Content Type ◽  
Threshold Regression Model

PurposeThe purpose of this paper is to explore the threshold effect of firm size on technological innovation using panel data from 2007 to 2012 for listed enterprises in China's manufacturing sector.Design/methodology/approachConsidering the aim of research question is to examine the nonlinear relationship, this paper utilizes the threshold regression proposed by Hansen's (2000).FindingsBased on a threshold regression model using panel data from 2007 to 2012 for listed enterprises in China's manufacturing sector, we find a series of new results. This nonlinear relationship is under the restrictions and impacts of various factors, such as industry characteristics and government subsidies. The results suggest that the threshold regression model well explains the complicated nonlinear relationship and transition process, and it can also shed light on management practice and policy.Originality/valueThere are categorical arguments regarding why firm size is not as effective as before in explaining the monotonic principle of industrial innovation, especially for establishing an effective industrial policy in a particular situation. One of the important reasons is that we have begun to adopt a new perspective from the nonlinear view on the relationship between firm size and industrial innovation. In this study, we have examined the threshold effect of firm size on industrial technological innovation, which is the most representative nonlinear relationship.

An Empirical Analysis of Asymmetry and Threshold Effect of Intergovernmental Grants in India: A Panel Data Analysis

2018 ◽  
Vol 21 (2) ◽  
pp. 458-472 ◽  
Author(s):  
Asharani Samal
Keyword(s):  
Panel Data ◽  
Regression Model ◽  
State Government ◽  
Capital Expenditure ◽  
Threshold Effect ◽  
Threshold Regression ◽  
Flypaper Effect ◽  
Intergovernmental Grants ◽  
Data Set ◽  
Reform Period

The present study empirically examines the effect of intergovernmental grants on the expenditure of state government in India. Using a panel data set during 1980–1981 to 2009–2010, the flypaper effect was found in the case of total and revenue expenditure and also an evidence of an asymmetric effect to change (increase or decrease) in grant variable for entire sample period. Again, to understand the flypaper and asymmetry effect in the pre- and post-reform period, this study uses the data from 1980–1981 to 1989–1990 as a pre-reform period and 1991–1992 to 2009–2010 as a post-reform period. The results of the panel regression model and two-stage least squares (2SLS) method show that there is an absence of flypaper effect except capital expenditure in the pre-reform period, whereas there exists an evidence of flypaper effect except capital expenditure in the post-reform period. Similarly, the responses of all the expenditure accounts are found to be asymmetric except capital expenditure. Further, in order to find the non-linear effect, this study employs Hansen (1999) threshold regression model to measure the threshold effect of intergovernmental grants on total expenditure of state government. The threshold regression results indicate that lower-income state grants have a stronger flypaper effect than middle- and higher-income states.

Finite Sample Distributions of t and F Statistics in an AR(1) Model with Anexogenous Variable

1987 ◽  
Vol 3 (3) ◽  
pp. 387-408 ◽  
Author(s):  
J.C. Nankervis ◽  
N.E. Savin
Keyword(s):  
Monte Carlo ◽  
Time Trend ◽  
Stable Process ◽  
Asymptotic Approximations ◽  
Test Statistics ◽  
Finite Sample ◽  
Sampling Behavior ◽  
Exogenous Process ◽  
Exogenous Time Series ◽  
F Statistics

The distributions of the test statistics are investigated in the context of an AR(1) model where the root is unity or near unity and where the exogenous process is a stable process, a random walk or a time trend. The finite sample distributions are estimated by Monte Carlo methods assuming normal disturbances. The sensitivity of the distributions to both the values of the parameters of the AR(1) model and the process generating the exogenous time series is examined. The Monte Carlo results motivate several theorems which describe the exact sampling behavior of the test statistics. The analytical and empirical results present a mixed picture with respect to the accuracy of the relevant asymptotic approximations.

scholarly journals Variable Selection in Threshold Regression Model with Applications to HIV Drug Adherence Data

2020 ◽  
Vol 12 (3) ◽  
pp. 376-398 ◽  
Author(s):  
Takumi Saegusa ◽  
Tianzhou Ma ◽  
Gang Li ◽  
Ying Qing Chen ◽  
Mei-Ling Ting Lee
Keyword(s):  
Variable Selection ◽  
Regression Model ◽  
Drug Adherence ◽  
Threshold Regression ◽  
Adherence Data ◽  
Threshold Regression Model
Sign in / Sign up

Export Citation Format

Share Document