M-estimation in linear models under nonstandard conditions
β Scribed by Faouzi El Bantli
- Publisher
- Elsevier Science
- Year
- 2004
- Tongue
- English
- Weight
- 291 KB
- Volume
- 121
- Category
- Article
- ISSN
- 0378-3758
No coin nor oath required. For personal study only.
β¦ Synopsis
The limiting distribution of M-estimators of the regression parameter in linear models is derived under nonstandard conditions, allowing, e.g., for discontinuities in density functions. Unlike usual regularity assumptions, our conditions are satisΓΏed, for instance, in the case of regression quantiles, hence also in the context of L1 estimation; our results thus extend those of Knight (Ann. Statist. 26 (1998) 755). The resulting asymptotic distributions, in general, are not Gaussian. Therefore, the limiting bootstrap distributions of these estimators are also investigated. It is shown that bootstrap approximations are correct to the ΓΏrst order only when limiting distributions are Gaussian, or along speciΓΏc sequences mn of bootstrap sample sizes. Numerical examples are given to illustrate these asymptotic results.
π SIMILAR VOLUMES
## Abstract The varianceβcovariance matrices of restricted regression and mixed regression estimators are compared and the consequences of introducing variability in the restrictions are examined.
Order n algorithms are developed for computing the estimated mean vector, regression coefficients, standard errors and smoothing parameter selection criteria for Speckman smoothing spline estimators in partially linear models. A difference type variance estimator is proposed and shown to be x/-~-con