Nonlinear IV Unit Root Tests in Panels with Cross-Sectional Dependency

By Yoosoon Chang. 2002

422 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/d4db2b933b7b2a7d8ca1113530cd1414c394f659

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

Citations in the corpus

Unit Root Testing in Heteroscedastic Panels Using the Cauchy Estimator (2012, methodology): “Following Chang (2002), we shall include one lagged difference to account for the fact that the true lag order is not known in practice.”
Testing for PPP: Should we use panel methods? (2005, background): “selection would include inter alia Frankel and Rose (1995), Jorion and Sweeney (1996), Oh (1996), Rogoff (1996), O’Connell (1998), and more recently, Bayoumi and MacDonald (1999), Pedroni (1999), Papell and Theodoridis (2001), Papell (2002), and Chang (2002) .”
TESTING FOR UNIT ROOTS IN PANELS WITH A FACTOR STRUCTURE (2007, methodology): “As shown by Chang (2004) the augmented Dickey-Fuller test, where lagged differences are included in the regression, is invalid in a panel data setup.”
Panel cointegration with global stochastic trends (2008, background): “5For example, Chang (2002,2004), Choi (2006), Moon and Perron (2004), Breitung and Das (2005), Gengenbach et al. (2005a), and Westerlund and Edgerton (2006).”
PANEL UNIT ROOT TESTS WITH CROSS-SECTION DEPENDENCE: A FURTHER INVESTIGATION (2009, background): “See Chang (2002), Chang and Song (2002), and Pesaran (2007), among others.”
Testing For A Unit Root In Panels With Dynamic Factors (2004, background): “In order to implement the t-statistics in (9) and (10) , we also need consistent estimators, say λ̂ n e , ω̂ 2 e, and φ̂ 4 e, for λ n e , ω 2 e, and φ 4 e, respectively, satisfying √ n 3 λ̂ n e − λe ́ = op (1) , (12) ω̂(2)e − ω(2)e = op (1) , (13) and φ̂ 4 e − φ(4)e = op (1) .”
Unemployment, Hysteresis and Transition (2004, positive): “…, 1 , 1 , 1 ( ) i i t c y i t i t F y y e - - - - = (5) Where c i is proportional to the sample standard error of the first difference of y it : 1/ 2 ( ) i i i t c KT s y - = D , ( 6 ) where K is a constant fixed at 5 as recommended in Chang (2002) for time dimensions larger than 25 observations.”
A Simple Panel-CADF Test for Unit Roots (2013, positive): “13 The resulting symmetric positive definite matrix Σ11 is such that most of the simulated correlations are positive, as we probably would expect in many empirical macro panel settings, and the average correlation is larger than the one simulated using the method proposed by Chang (2002) and Chang a”
Combining Significance of Correlated Statistics with Application to Panel Data (2006, positive): “The covariance matrices are drawn following the recipe used by Chang (2002) for her simulation studies.”
Testing for Unit Roots in Small Panels with Short-run and Long-run Cross-sectional Dependencies (2009, methodology): “The idea of using this type of IV estimation was explored earlier by Chang (2002) to deal with the crosssectional dependency of unknown form.”
On the Panel Unit Root Tests Using Nonlinear Instrumental Variables (2003, methodology): “However, the simulation results reported in Chang (2002) which are based on the modified instrumental variables, G(yi,t−1) exhibit little size distortions.”