Abstract
We study the asymptotic distribution of the L 1 regression estimator under general conditions with matrix norming and possibly non i.i.d. errors. We then introduce an appropriate bootstrap procedure to estimate the distribution of this estimator and study its asymptotic properties. It is shown that this bootstrap is consistent under suitable conditions and in other situations the bootstrap limit is a random distribution.
Similar content being viewed by others
References
Bassett G, Koenker R. Asymptotic theory of least absolute error regression. J Amer Statist Assoc, 73: 618–622 (1978)
Bloomfield P, Steiger W L. Least Absolute Deviations: Theory, Applications and Algorithms. Boston: Birkhäuser, 1983
Bai Z D, Chen X R, Wu Y, et al. Asymptotic normality of minimum L 1 norm estimates in linear models. Sci China Ser A, 33: 449–463 (1990)
Pollard D. Asymptotics for least absolute deviation regression estimators. Econom Theory, 7: 186–199 (1991)
Smirnov N V. Limit distributions for the terms of a variational series. Amer Math Soc Transl Ser, 11: 82–143 (1952)
Jureckova J. Asymptotics behavior of M-estimators of location in nonregular cases. Statist Decisions, 1: 323–340 (1983)
Bose A, Chatterjee S. Generalised bootstrap in nonregular M estimation problems. Statist Prob Lett, 55: 319–328 (2000)
Knight K. Limit distributions for L 1 regression estimators under general conditions. Ann Statist, 26: 755–770 (1998)
Knight K. Bootstrapping sample quantiles in non-regular cases. Statist Prob Lett, 37: 259–267 (1998)
Hjort N L, Pollard D. Asymptotics for minimisers of convex processes. Preprint, Department of Statistics, Yale University, 1993
Bickel P J, Freedman D A. Some asymptotic theory for the bootstrap. Ann Statist, 9(6): 1196–1217 (1981)
Bose A, Chatterjee S. Generalised bootstrap for estimators of minimisers of convex functionals. J Statist Plan Infer, 11: 225–239 (2003)
Hu F, Kalbfleisch J D. The estimating function bootstrap (with discussion). Canad J Statist, 28: 449–499 (2000)
Liu R Y, Singh K. Efficiency and robustness in resampling. Ann Statist, 20(1): 370–384 (1992)
Bose A, Kushary D. Jackknife and weighted jackknife estimation of the variance of M-estimators in linear regressions. Technical Report No. 96-12, Department of Statistics, Purdue University, 1996
Wu C F J. On the asymptotic properties of the jackknife histogram. Ann Statist, 18: 1438–1452 (1990)
Bickel P J, Gotze F, Van Z W R. Resampling fewer than n observations: gains, losses and remedies for losses. Statistica Sinica, 7: 1–31 (1997)
Athreya K B, Fukuchi J I. Bootstrapping extremes of i.i.d. random variables. In: Proc of Conf on Extreme Value Theory and its Applications. Maryland: NIST, 1997
Athreya K B, Fukuchi J I. Confidence intervals for endpoints of a C.D.F. via bootstrap. J Statist Plan Infer, 58: 299–320 (1997)
Deheuvels P, Mason D, Shorack G. Some results on the influence of extremes on the bootstrap. Ann Inst Henri Poincare, 29: 83–103 (1993)
Athreya K B. Bootstrap of the mean in the infinite variance case. Ann Statist, 14: 724–731 (1987)
Knight K. On the bootstrap of the sample mean in the infinite variance case. Ann Statist, 17: 1168–1175 (1989)
Praestgaard J, Wellner J. Exchangeably weighted bootstrap of the general empirical process. Ann Probab, 21: 2053–2086 (1993)
Knight K. Asymptotics for L 1 estimators of regression parameters under heteroscedasticity. Canad J Statist, 27: 497–507 (1999)
Author information
Authors and Affiliations
Corresponding author
Additional information
Dedicated to Professor Zhidong Bai on the occasion of his 65th birthday
This work was supported by J.C. Bose National Fellowship, Government of India
Rights and permissions
About this article
Cite this article
Bose, A. L 1 regression estimate and its bootstrap. Sci. China Ser. A-Math. 52, 1251–1261 (2009). https://doi.org/10.1007/s11425-009-0087-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11425-009-0087-6