Jackknife, bootstrap and other resampling methods in regression analysis (Q1822432)

From MaRDI portal
scientific article
Language Label Description Also known as
English
Jackknife, bootstrap and other resampling methods in regression analysis
scientific article

    Statements

    Jackknife, bootstrap and other resampling methods in regression analysis (English)
    0 references
    1986
    0 references
    Statistical inference based on data resampling has been mostly based on the assumption of independence and identical distribution, the i.i.d. case. The author maintains that resampling methods justifiable in the i.i.d. case may not work in more complex situations. These methods are studied in the context of regression models. New methods are proposed that take into account special features of regression data. A class of weighted jackknife variance estimators for the least squares estimator, which deletes a fixed number of observations at a time, is proposed. The proposed estimator is unbiased for homoscedastic errors. The special (delete-one) jackknife is almost unbiased for heteroscedastic errors. The method is extended to cover nonlinear parameters, regression M-estimators, nonlinear regression and generalized linear models. Three bootstrap methods are considered. Two of them are biased variance estimators. A general method for resampling residuals is proposed. It gives variance estimators that are bias-robust.
    0 references
    0 references
    0 references
    0 references
    0 references
    interval estimators
    0 references
    histogram
    0 references
    bias-reducing estimators
    0 references
    weighted delete-one jackknife variance estimators
    0 references
    variable jackknife
    0 references
    simulation results
    0 references
    jackknife percentile
    0 references
    Fieller's interval
    0 references
    resampling methods
    0 references
    weighted jackknife variance estimators
    0 references
    least squares estimator
    0 references
    homoscedastic errors
    0 references
    heteroscedastic errors
    0 references
    nonlinear parameters
    0 references
    regression M-estimators
    0 references
    generalized linear models
    0 references
    bootstrap methods
    0 references
    resampling residuals
    0 references
    bias-robust
    0 references
    0 references
    0 references
    0 references