Bootstrap methods for median regression models

Research output: Contribution to journalArticlepeer-review

112 Scopus citations


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. The smoothed estimator is asymptotically equivalent to the standard LAD estimator. With bootstrap critical values, the rejection probabilities of symmetrical t and χ2 tests based on the smoothed estimator are correct through O(n) under the null hypothesis, where γ < 1 but can be arbitrarily close to 1. In contrast, first-order asymptotic approximations make errors of size O(n). These results also hold for symmetrical t and χ2 tests for censored median regression models.

Original languageEnglish (US)
Pages (from-to)1327-1351
Number of pages25
Issue number6
StatePublished - Nov 1998


  • Asymptotic expansion
  • L regression
  • Least absolute deviations
  • Smoothing

ASJC Scopus subject areas

  • Economics and Econometrics


Dive into the research topics of 'Bootstrap methods for median regression models'. Together they form a unique fingerprint.

Cite this