Improving Likelihood-Ratio-Based Confidence Intervals for Threshold Parameters in Finite Samples
Within the context of threshold regressions, we show that asymptotically-valid likelihood-ratio-based confidence intervals for threshold parameters perform poorly in finite samples when the threshold effect is large. A large threshold effect leads to a poor approximation of the profile likelihood in finite samples such that the conventional approach to constructing confidence intervals excludes the true threshold parameter value too often, resulting in low coverage rates. We propose a modification to the standard likelihood-ratio-based confidence interval that has coverage rates at least as high as the nominal level, while still being informative in the sense of including relatively few observations of the threshold variable.
|Date of creation:||Mar 2014|
|Date of revision:|
|Contact details of provider:|| Postal: Sydney, NSW 2006|
Phone: 61 +2 9351 5055
Fax: 61 +2 9351 4341
Web page: http://sydney.edu.au/arts/economics
More information through EDIRC
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- JesÃºs Gonzalo & Jean-Yves Pitarakis, 2013.
"Estimation and inference in threshold type regime switching models,"
in: Handbook of Research Methods and Applications in Empirical Macroeconomics, chapter 8, pages 189-205
Edward Elgar Publishing.
- Pitarakis, Jean-Yves & Gonzalo, Jesús, 2012. "Estimation and inference in threshold type regime switching models," UC3M Working papers. Economics we1204, Universidad Carlos III de Madrid. Departamento de Economía.
- Seo, Myung Hwan & Linton, Oliver, 2007.
"A smoothed least squares estimator for threshold regression models,"
Journal of Econometrics,
Elsevier, vol. 141(2), pages 704-735, December.
- Oliver Linton & Myunghwan Seo, 2005. "A smoothed least squares estimator for threshold regression models," LSE Research Online Documents on Economics 4434, London School of Economics and Political Science, LSE Library.
- Potter, Simon M, 1995.
"A Nonlinear Approach to US GNP,"
Journal of Applied Econometrics,
John Wiley & Sons, Ltd., vol. 10(2), pages 109-25, April-Jun.
- Yunjong Eo & James Morley, 2015.
"Likelihood‐ratio‐based confidence sets for the timing of structural breaks,"
Econometric Society, vol. 6(2), pages 463-497, 07.
- Eo, Yunjong & Morley, James, 2011. "Likelihood-Ratio-Based Confidence Sets for the Timing of Structural Breaks," Working Papers 2011-07, University of Sydney, School of Economics, revised Feb 2014.
- Jesús Gonzalo & Michael Wolf, 2001.
"Subsampling inference in threshold autoregressive models,"
Economics Working Papers
573, Department of Economics and Business, Universitat Pompeu Fabra.
- Gonzalo, Jesus & Wolf, Michael, 2005. "Subsampling inference in threshold autoregressive models," Journal of Econometrics, Elsevier, vol. 127(2), pages 201-224, August.
- Bruce E. Hansen, 1996.
"Sample Splitting and Threshold Estimation,"
Boston College Working Papers in Economics
319., Boston College Department of Economics, revised 12 May 1998.
- Alan J. Auerbach & Yuriy Gorodnichenko, 2012.
"Measuring the Output Responses to Fiscal Policy,"
American Economic Journal: Economic Policy,
American Economic Association, vol. 4(2), pages 1-27, May.
- Nathan S. Balke, 2000. "Credit and Economic Activity: Credit Regimes and Nonlinear Propagation of Shocks," The Review of Economics and Statistics, MIT Press, vol. 82(2), pages 344-349, May.
- Hansen, Bruce E, 1996.
"Inference When a Nuisance Parameter Is Not Identified under the Null Hypothesis,"
Econometric Society, vol. 64(2), pages 413-30, March.
- Tom Doan, . "TAR: RATS procedure to estimate a threshold autoregression, tests for threshold effect," Statistical Software Components RTS00209, Boston College Department of Economics.
- Hansen, B.E., 1991. "Inference when a Nuisance Parameter is Not Identified Under the Null Hypothesis," RCER Working Papers 296, University of Rochester - Center for Economic Research (RCER).
- Tom Doan, . "RATS programs to replicate Hansen's threshold estimation and testing results," Statistical Software Components RTZ00091, Boston College Department of Economics.
- Pesaran, H.M. & Potter, S.M., 1995.
"A Floor and Ceiling Model of U.S. Output,"
Cambridge Working Papers in Economics
9407, Faculty of Economics, University of Cambridge.
- Yu, Ping, 2012. "Likelihood estimation and inference in threshold regression," Journal of Econometrics, Elsevier, vol. 167(1), pages 274-294.
- Gary Koop & Simon M. Potter, 1998.
"Dynamic asymmetries in US unemployment,"
ESE Discussion Papers
15, Edinburgh School of Economics, University of Edinburgh.
When requesting a correction, please mention this item's handle: RePEc:syd:wpaper:2014-04. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Vanessa Holcombe)
If references are entirely missing, you can add them using this form.