Sample Splitting and Threshold Estimation
Threshold models have a wide variety of applications in economics. Direct applications include models of separating and multiple equilibria. Other applications include empirical sample splitting when the sample split is based on a continuously-distributed variable such as firm size. In addition, threshold models may be used as a parsimonious strategy for non-parametric function estimation. For example, the threshold autoregressive model (TAR) is popular in the non-linear time series literature. Threshold models also emerge as special cases of more complex statistical frameworks, such as mixture models, switching models, Markov switching models, and smooth transition threshold models. It may be important to understand the statistical properties of threshold models as a preliminary step in the development of statistical tools to handle these more complicated structures. Despite the large number of potential applications, the statistical theory of threshold estimation is undeveloped. The previous literature has demonstrated that threshold estimates are super-consistent, but a distribution theory useful for testing and inference has yet to be provided. This paper develops a statistical theory for threshold estimation in the regression context. We allow for either cross-section or time series observations. Least squares estimation of the regression parameters is considered. An asymptotic distribution theory for the regression estimates (the threshold and the regression slopes) is developed. It is found that the distribution of the threshold estimate is non- standard. Methods to construct asymptotic confidence intervals are introduced, using both a t-statistic and LR-statistic approach. Monte Carlo simulations are presented to assess the accuracy of the asymptotic approximations. The empirical relevance of the theory is illustrated through an application to the multiple equilibria growth model of Durlauf and Johnson (1995).
|Date of creation:||01 Jan 1996|
|Date of revision:||12 May 1998|
|Contact details of provider:|| Postal: Boston College, 140 Commonwealth Avenue, Chestnut Hill MA 02467 USA|
Web page: http://fmwww.bc.edu/EC/
More information through EDIRC
References listed on IDEAS
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.:
- 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.
- Hansen, Bruce E, 1992.
"Tests for Parameter Instability in Regressions with I(1) Processes,"
Journal of Business & Economic Statistics,
American Statistical Association, vol. 10(3), pages 321-35, July.
- Hansen, Bruce E, 2002. "Tests for Parameter Instability in Regressions with I(1) Processes," Journal of Business & Economic Statistics, American Statistical Association, vol. 20(1), pages 45-59, January.
- Hansen, Bruce E., 1991. "Strong Laws for Dependent Heterogeneous Processes," Econometric Theory, Cambridge University Press, vol. 7(02), pages 213-221, June.
- Davidson, James, 1994. "Stochastic Limit Theory: An Introduction for Econometricians," OUP Catalogue, Oxford University Press, number 9780198774037, June.
- Härdle, W.K., 1992.
"Applied Nonparametric Methods,"
1992-6, Tilburg University, Center for Economic Research.
- Hardle, W., 1992. "Applied Nonparametric Methods," Papers 9204, Catholique de Louvain - Institut de statistique.
- Wolfgang Hardle & Oliver Linton, 1994. "Applied Nonparametric Methods," Cowles Foundation Discussion Papers 1069, Cowles Foundation for Research in Economics, Yale University.
- HÄRDLE, Wolfgang, 1992. "Applied nonparametric methods," CORE Discussion Papers 1992003, Université catholique de Louvain, Center for Operations Research and Econometrics (CORE).
- Hardle, W., 1992. "Applied Nonparametric Methods," Papers 9206, Tilburg - Center for Economic Research.
- 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).
- Hansen, Bruce E, 1996. "Inference When a Nuisance Parameter Is Not Identified under the Null Hypothesis," Econometrica, Econometric Society, vol. 64(2), pages 413-30, March.
- Oliver LINTON, .
"Applied nonparametric methods,"
Statistic und Oekonometrie
9312, Humboldt Universitaet Berlin.
- Pham, Tuan D. & Tran, Lanh T., 1985. "Some mixing properties of time series models," Stochastic Processes and their Applications, Elsevier, vol. 19(2), pages 297-303, April.
- Jushan Bai, 1997. "Estimation Of A Change Point In Multiple Regression Models," The Review of Economics and Statistics, MIT Press, vol. 79(4), pages 551-563, November.
- repec:cup:etheor:v:7:y:1991:i:2:p:213-21 is not listed on IDEAS
- Hansen, Bruce E., 2000.
"Testing for structural change in conditional models,"
Journal of Econometrics,
Elsevier, vol. 97(1), pages 93-115, July.
- Tom Doan, . "REGHBREAK: RATS procedure to perform structural break test with bootstrapped p-values," Statistical Software Components RTS00176, Boston College Department of Economics.
- Bruce E. Hansen, 1998. "Testing for Structural Change in Conditional Models," Boston College Working Papers in Economics 310., Boston College Department of Economics.
- Tom Doan, . "RATS programs to replicate structural break test with Hansen's fixed regressor bootstrap," Statistical Software Components RTZ00089, Boston College Department of Economics.
- Durlauf, Steven N & Johnson, Paul A, 1995.
"Multiple Regimes and Cross-Country Growth Behaviour,"
Journal of Applied Econometrics,
John Wiley & Sons, Ltd., vol. 10(4), pages 365-84, Oct.-Dec..
- Durlauf, S.M. & Johnson, P.A., 1995. "Multiple Regimes and Cross-Country Growth Behavior," Working papers 9419r, Wisconsin Madison - Social Systems.
- Durlauf, S.N. & Johnson, P.A., 1994. "Multiple Regimes and Cross-Country Growth Behavior," Working papers 9419, Wisconsin Madison - Social Systems.
- Chu, Chia-Shang James & White, Halbert, 1992. "A Direct Test for Changing Trend," Journal of Business & Economic Statistics, American Statistical Association, vol. 10(3), pages 289-99, July.
When requesting a correction, please mention this item's handle: RePEc:boc:bocoec:319. 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: (Christopher F Baum)
If references are entirely missing, you can add them using this form.