Abstract
Bayesian inference provides a flexible way of combining data with prior information from our knowledge. However, Bayesian estimation is very sensitive to the likelihood. We need to evaluate the likelihood density, which is difficult to evaluate, in order to use MCMC. Thus, this study considers using the Bayesian empirical likelihood(BEL) approach to kink regression. By taking the empirical likelihood into a Bayesian framework, the simulation results show an acceptable bias and MSE values when compared with LS, MLE, and Bayesian when the errors are generated from both normal and non-normal distributions. In addition, BEL can outperform the competing methods with quite small sample sizes under various error distributions. Then, we apply our approach to address a question: Has the accumulation of foreign reserves effectively protected the Thai economy from the financial crisis? The results demonstrate that foreign reserves provide both positive and negative effects on economic growth for high and low growth regimes of foreign reserve, respectively. We also find that foreign reserves seem to have played a role in offsetting the effect of the crisis when the growth rate of foreign reserves is less than 2.48%.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Button, K.S., Ioannidis, J.P., Mokrysz, C., Nosek, B.A., Flint, J., Robinson, E.S., Munaf, M.R.: Power failure: why small sample size undermines the reliability of neuroscience. Nat. Rev. Neurosci. 14(5), 365–376 (2013)
Chang, I.H., Mukerjee, R.: Bayesian and frequentist confidence intervals arising from empirical type likelihoods. Biometrika 95, 139–147 (2008)
Chib, S., Shin, M., Simoni, A.: Bayesian empirical likelihood estimation and comparison of moment condition models. arXiv preprint arXiv:1606.02931 (2016)
Fang, K.T., Mukerjee, R.: Empirical-type likelihoods allowing posterior credible sets with frequentist validity: higher-order asymptotics. Biometrika 93, 723–733 (2006)
Hansen, B.E.: Regression kink with an unknown threshold. J. Bus. Econ. Stat. 35(2), 228–240 (2017)
Hastings, W.K.: Monte Carlo sampling methods using Markov chains and their applications. Biometrika 57, 97–109 (1970)
Howrey, E.P.: The role of time series analysis in econometric model evaluation. In: Evaluation of Econometric Models, pp. 275–307. Academic Press (1980)
Kwon, Y.: Bayesian analysis of threshold autoregressive models (2003)
Kass, R.E., Raftery, A.E.: Bayes factors. J. Am. Stat. Assoc. 90(430), 773–795 (1995)
Lee, S.Y., Song, X.Y.: Evaluation of the Bayesian and maximum likelihood approaches in analyzing structural equation models with small sample sizes. Multivar. Behav. Res. 39(4), 653–686 (2004)
Lourens, S., Zhang, Y., Long, J.D., Paulsen, J.S.: Bias in estimation of a mixture of normal distributions. J. Biometrics Biostatistics 4 (2013)
Mykland, P.A.: Bartlett identities and large deviations in likelihood theory. Ann. Stat. 1105–1117 (1999)
Owen, A.B.: Empirical Likelihood. Wiley, New York (1998)
Peto, R., Pike, M.C., Armitage, P., Breslow, N.E., Cox, D.R., Howard, S.V., Smith, P.G.: Design and analysis of randomized clinical trials requiring prolonged observation of each patient. II. analysis and examples. Br. J. Cancer 35(1), 1 (1977)
Sriboochitta, S., Yamaka, W., Maneejuk, P., Pastpipatkul, P.: A generalized information theoretical approach to non-linear time series model. In: Robustness in Econometrics, pp. 333–348. Springer International Publishing (2017)
Van de Schoot, R., Broere, J.J., Perryck, K.H., Zondervan-Zwijnenburg, M., Van Loey, N.E.: Analyzing small data sets using Bayesian estimation: the case of posttraumatic stress symptoms following mechanical ventilation in burn survivors. Eur. J. Psychotraumatology 6(1), 25216 (2015)
Yamaka, W., Pastpipatkul, P., Sriboonchitta, S.: Has the accumulation of foreign reserves protect the thai economy from financial crisis?: An approach of empirical likelihood. Int. J. Econ. Res. 14(6), 275–285 (2017)
Stein, C.: Inadmissibility of the usual estimator for the mean of multivariate normal distribution. In: Proceedings of the Third Berkeley Symposium on Mathematical Statistics and Probability, vol. 1, pp. 197–206 (1955)
Variyath, A.M., Chen, J., Abraham, B.: Empirical likelihood based variable selection. J. Stat. Plann. Infer. 140(4), 971–981 (2010)
Yang, Y., He, X.: Bayesian empirical likelihood for quantile regression. Ann. Stat. 40(2), 1102–1131 (2012)
Zhang, Y.Q., Tang, N.S.: Bayesian empirical likelihood estimation of quantile structural equation models. J. Syst. Sci. Complex. 30(1), 122–138 (2017)
Acknowledgements
The authors are grateful to Puay Ungphakorn Centre of Excellence in Econometrics, Faculty of Economics, Chiang Mai University for the financial support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Yamaka, W., Pastpipatkul, P., Sriboonchitta, S. (2018). Bayesian Empirical Likelihood Estimation for Kink Regression with Unknown Threshold. In: Kreinovich, V., Sriboonchitta, S., Chakpitak, N. (eds) Predictive Econometrics and Big Data. TES 2018. Studies in Computational Intelligence, vol 753. Springer, Cham. https://doi.org/10.1007/978-3-319-70942-0_54
Download citation
DOI: https://doi.org/10.1007/978-3-319-70942-0_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70941-3
Online ISBN: 978-3-319-70942-0
eBook Packages: EngineeringEngineering (R0)