Bootstrap Methods for Median Regression Models

Joel L. Horowitz ()

Econometrics from EconWPA

Abstract: The least-absolute-deviations (LAD) estimator for a median-regression model does not satisfy the standard conditions for obtaining asymptotic refinements through use of the bootstrap because the LAD objective function is not smooth. This paper overcomes this problem by smoothing the objective function so that it becomes differentiable. The smoothed estimator is asymptotically equivalent to the standard LAD estimator. With bootstrap critical values, the levels of symmetrical t and c2 tests based on the smoothed estimator are correct through O(n-g), where g < 1 but can be arbitrarily close to 1. In contrast, first-order asymptotic approximations make an error of size O(n-g). The bootstrap accounts for terms of size O(n-g) in the asymptotic expansions of the test statistics, whereas first-order approximations ignore these terms. These results also hold for symmetrical t and c2 tests for censored median regression models.

JEL-codes: C1 C5 C8 (search for similar items in EconPapers)
Date: 1996-08-30
Note: Zipped using PKZIP v2.04, encoded using UUENCODE v5.15. Zipped file includes 1 file --ui9609.wpa (TeX file 27 pages)
View list of references

Downloads: (external link)
http://129.3.20.41/eps/em/papers/9608/9608004.html (text/html)
http://129.3.20.41/eps/em/papers/9608/9608004.pdf (application/pdf)
http://129.3.20.41/eps/em/papers/9608/9608004.ps.gz (application/postscript)

Related works:
Journal Article: Bootstrap Methods for Median Regression Models (1998)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:wpa:wuwpem:9608004

Access Statistics for this paper

More papers in Econometrics from EconWPA
Series data maintained by EconWPA ().