Nonparametric estimation of individual food availability along with bootstrap confidence intervals in household budget surveys

被引:6
作者
Vasdekis, VGS
Trichopoulou, A
机构
[1] Athens Univ Econ & Business, Dept Stat, Athens 10434, Greece
[2] Natl Sch Publ Hlth, Dept Biochem & Nutr, Athens 11521, Greece
关键词
nonparametric models; least squares; bias; bootstrap confidence intervals;
D O I
10.1016/S0167-7152(99)00120-0
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
An additive nonparametric model is proposed for the analysis of household budget surveys data whose estimation reduces to least squares. Parameter estimates are biased. A first-order approximation for the bias is obtained and it is used to bias correct the residuals of the model in order to construct bootstrap confidence intervals for the model parameter estimates. The results show somewhat shorter intervals than pointwise intervals which are based on a normal approximation with less bias. (C) 2000 Published by Elsevier Science B.V. All rights reserved.
引用
收藏
页码:337 / 345
页数:9
相关论文
共 7 条
[1]  
CARTER CK, 1992, J ROY STAT SOC B MET, V54, P773
[2]   Diet revealed?: Semiparametric estimation of nutrient intake age relationships [J].
Chesher, A .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES A-STATISTICS IN SOCIETY, 1997, 160 :389-420
[3]   SMOOTHING NOISY DATA WITH SPLINE FUNCTIONS [J].
WAHBA, G .
NUMERISCHE MATHEMATIK, 1975, 24 (05) :383-393
[4]  
EFORN B, 1993, INTRO BOOTSTRAP
[5]   SEMIPARAMETRIC ESTIMATES OF THE RELATION BETWEEN WEATHER AND ELECTRICITY SALES [J].
ENGLE, RF ;
GRANGER, CWJ ;
RICE, J ;
WEISS, A .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1986, 81 (394) :310-320
[6]  
Green P. J., 1993, Nonparametric regression and generalized linear models: a roughness penalty approach
[7]   BOOTSTRAPPING IN NONPARAMETRIC REGRESSION - LOCAL ADAPTIVE SMOOTHING AND CONFIDENCE BANDS [J].
HARDLE, W ;
BOWMAN, AW .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1988, 83 (401) :102-110