Heteroskedasticity and Distributional Assumptions in the Censored Regression Model
Data censoring causes ordinary least squares estimators of linear models to be biased and inconsistent. The Tobit estimator yields consistent estimators in the presence of data censoring if the errors are normally distributed. However, non-normality or heteroskedasticity results in the Tobit estimators being inconsistent. Various estimators have been proposed for circumventing the normality assumption. Some of these estimators include censored least absolute deviations (CLAD), symmetrically censored least squares (SCLS), and partially adaptive estimators. CLAD and SCLS will be consistent in the presence of heteroskedasticity; however, SCLS performs poorly in the presence of asymmetric errors. This paper extends the partially adaptive estimation approach to accommodate possible heteroskedasticity as well as non-normality. A simulation study is used to investigate the estimators’ relative efficiency in these settings. The partially adaptive censored regression estimators have little efficiency loss for censored normal errors and appear to outperform the Tobit and semiparametric estimators for non-normal error distributions and be less sensitive to the presence of heteroskedasticity. An empirical example is considered which supports these results.
|Date of creation:||Aug 2012|
|Date of revision:|
|Contact details of provider:|| Postal: 130 Faculty Office Building, P.O. Box 22363, Brigham Young University, Provo, Utah 84602|
Phone: (801) 422-2859
Fax: (801) 422-0194
Web page: https://economics.byu.edu/Pages/MacroLab/Home.aspx
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.:
- McDonald, James B. & Xu, Yexiao J., 1995.
"A generalization of the beta distribution with applications,"
Journal of Econometrics,
Elsevier, vol. 69(2), pages 427-428, October.
- McDonald, James B. & Xu, Yexiao J., 1995. "A generalization of the beta distribution with applications," Journal of Econometrics, Elsevier, vol. 66(1-2), pages 133-152.
- Steven Caudill, 2012. "A partially adaptive estimator for the censored regression model based on a mixture of normal distributions," Statistical Methods & Applications, Springer;Società Italiana di Statistica, vol. 21(2), pages 121-137, June.
- Greene, William H, 1981. "On the Asymptotic Bias of the Ordinary Least Squares Estimator of the Tobit Model," Econometrica, Econometric Society, vol. 49(2), pages 505-13, March.
- Amemiya, Takeshi, 1984. "Tobit models: A survey," Journal of Econometrics, Elsevier, vol. 24(1-2), pages 3-61.
- McDonald, James B., 1989. "Partially adaptive estimation of ARMA time series models," International Journal of Forecasting, Elsevier, vol. 5(2), pages 217-230.
- Randall A. Lewis & James B. McDonald, 2014. "Partially Adaptive Estimation of the Censored Regression Model," Econometric Reviews, Taylor & Francis Journals, vol. 33(7), pages 732-750, October.
- Hansen, Bruce E, 1994.
"Autoregressive Conditional Density Estimation,"
International Economic Review,
Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association, vol. 35(3), pages 705-30, August.
- Hansen, B.E., 1992. "Autoregressive Conditional Density Estimation," RCER Working Papers 322, University of Rochester - Center for Economic Research (RCER).
- Tom Doan, . "RATS programs to replicate Hansen's GARCH models with time-varying t-densities," Statistical Software Components RTZ00086, Boston College Department of Economics.
- McDonald, James B. & Xu, Yexiao J., 1996. "A comparison of semi-parametric and partially adaptive estimators of the censored regression model with possibly skewed and leptokurtic error distributions," Economics Letters, Elsevier, vol. 51(2), pages 153-159, May.
- Panayiotis Theodossiou, 1998. "Financial Data and the Skewed Generalized T Distribution," Management Science, INFORMS, vol. 44(12-Part-1), pages 1650-1661, December.
- Powell, James L., 1984. "Least absolute deviations estimation for the censored regression model," Journal of Econometrics, Elsevier, vol. 25(3), pages 303-325, July.
- Nawata, Kazumitsu, 1990. "Robust estimation based on grouped-adjusted data in censored regression models," Journal of Econometrics, Elsevier, vol. 43(3), pages 337-362, March.
- McDonald, James B. & Newey, Whitney K., 1988. "Partially Adaptive Estimation of Regression Models via the Generalized T Distribution," Econometric Theory, Cambridge University Press, vol. 4(03), pages 428-457, December.
- Powell, James L, 1986. "Symmetrically Trimmed Least Squares Estimation for Tobit Models," Econometrica, Econometric Society, vol. 54(6), pages 1435-60, November.
- Stephen R. Cosslett, 2004. "Efficient Semiparametric Estimation of Censored and Truncated Regressions via a Smoothed Self-Consistency Equation," Econometrica, Econometric Society, vol. 72(4), pages 1277-1293, 07.
- Newey, Whitney K., 1987. "Specification tests for distributional assumptions in the Tobit model," Journal of Econometrics, Elsevier, vol. 34(1-2), pages 125-145.
- Paarsch, Harry J., 1984. "A Monte Carlo comparison of estimators for censored regression models," Journal of Econometrics, Elsevier, vol. 24(1-2), pages 197-213.
- Amemiya, Takeshi, 1973. "Regression Analysis when the Dependent Variable is Truncated Normal," Econometrica, Econometric Society, vol. 41(6), pages 997-1016, November.
- Butler, Richard J, et al, 1990. "Robust and Partially Adaptive Estimation of Regression Models," The Review of Economics and Statistics, MIT Press, vol. 72(2), pages 321-27, May.
When requesting a correction, please mention this item's handle: RePEc:byu:byumcl:201209. 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: (Kerk Phillips)
If references are entirely missing, you can add them using this form.