Bootstrap Simultaneous Error Bars for Nonparametric Regression
Hardle, W. ; Marron, J. S.
Ann. Statist., Tome 19 (1991) no. 1, p. 778-796 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
Simultaneous error bars are constructed for nonparametric kernel estimates of regression functions. The method is based on the bootstrap, where resampling is done from a suitably estimated residual distribution. The error bars are seen to give asymptotically correct coverage probabilities uniformly over any number of gridpoints. Applications to an economic problem are given and comparison to both pointwise and Bonferroni-type bars is presented through a simulation study.
Publié le : 1991-06-14
Classification:  Bootstrap,  error bars,  kernel smoothing,  nonparametric regression,  variability bound,  62G05,  62G99 
@article{1176348120,
     author = {Hardle, W. and Marron, J. S.},
     title = {Bootstrap Simultaneous Error Bars for Nonparametric Regression},
     journal = {Ann. Statist.},
     volume = {19},
     number = {1},
     year = {1991},
     pages = { 778-796},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176348120}
}

Hardle, W.; Marron, J. S. Bootstrap Simultaneous Error Bars for Nonparametric Regression. Ann. Statist., Tome 19 (1991) no. 1, pp.  778-796. http://gdmltest.u-ga.fr/item/1176348120/