Federal Dposit InsuranceCorporation• Center for Financial Researchh
Sanjiv R. Das
Darrell Duffie
Nikunj Kapadia
Risk-Based Capital Standards,
Deposit Insurance and Procyclicality
Risk-Based Capital Standards,
Deposit Insurance and Procyclicality
FDIC Center for Financial Research
Working Paper
No. 2009-09
More Powerful Unit Root Tests with Non-normal Errors
November 2009
Empirical Comparisons and Implied Recovery Rates
kkk
An Empirical
An Empirical Analysis
State-
Efraim Benmel Efraim Benmelech May, 2005
June 20
May , 2005 Asset S2005-14
September 2005
Sanjiv R. Das
Darrell Duffie
Nikunj Kapadia
Risk-Based Capital Standards,
Deposit Insurance and Procyclicality
Risk-Based Capital Standards,
Deposit Insurance and Procyclicality
FDIC Center for Financial Research
Working Paper
No. 2009-09
More Powerful Unit Root Tests with Non-normal Errors
November 2009
Empirical Comparisons and Implied Recovery Rates
kkk
An Empirical
An Empirical Analysis
State-
Efraim Benmel Efraim Benmelech May, 2005
June 20
May , 2005 Asset S2005-14
September 2005
More Powerful Unit Root Tests with Non-normal
Errors
Kyung So Im
Federal Deposit Insurance Corporation
Junsoo Lee
University of Alabama
Margie Tieslau
University of North Texas
November 8, 2009
Abstract
This paper proposes new unit root tests that are more powerful when the error
term follows a non-normal distribution. The improved power is gained by utilizing the
additional moment conditions embodied in non-normal errors. SpeciÖcally, we follow
the work of Im and Schmidt (2008), using the framework of generalized methods
of moments (GMM), and adopt a simple two-step procedure based on the "residual
augmented least squares" (RALS) methodology. Our RALS-based unit root tests make
use of non-linear moment conditions through a computationally simple procedure. Our
Monte Carlo simulation results show that the RALS-based unit root tests have good
size and power properties, and they show signiÖcant e¢ ciency gains when utilizing the
additional information contained in non-normal errorsó information that is ignored in
traditional unit root tests.
JEL ClassiÖcation: C22, C12, C13.
Key Words: Unit root test, Generalized methods of moments (GMM), Residual augmented
least squares (RALS), Non-normality.
1
Errors
Kyung So Im
Federal Deposit Insurance Corporation
Junsoo Lee
University of Alabama
Margie Tieslau
University of North Texas
November 8, 2009
Abstract
This paper proposes new unit root tests that are more powerful when the error
term follows a non-normal distribution. The improved power is gained by utilizing the
additional moment conditions embodied in non-normal errors. SpeciÖcally, we follow
the work of Im and Schmidt (2008), using the framework of generalized methods
of moments (GMM), and adopt a simple two-step procedure based on the "residual
augmented least squares" (RALS) methodology. Our RALS-based unit root tests make
use of non-linear moment conditions through a computationally simple procedure. Our
Monte Carlo simulation results show that the RALS-based unit root tests have good
size and power properties, and they show signiÖcant e¢ ciency gains when utilizing the
additional information contained in non-normal errorsó information that is ignored in
traditional unit root tests.
JEL ClassiÖcation: C22, C12, C13.
Key Words: Unit root test, Generalized methods of moments (GMM), Residual augmented
least squares (RALS), Non-normality.
1