Bootstrap prediction intervals in beta regressions

被引:20
|
作者
Espinheira, Patricia L. [1 ]
Ferrari, Silvia L. P. [2 ]
Cribari-Neto, Francisco [1 ]
机构
[1] Univ Fed Pernambuco, Dept Estat, BR-50740540 Recife, PE, Brazil
[2] Univ Sao Paulo, Dept Estat, BR-05508090 Sao Paulo, Brazil
基金
巴西圣保罗研究基金会;
关键词
Beta distribution; Beta regression; Bootstrap; Prediction; Prediction interval; CONFIDENCE-INTERVALS;
D O I
10.1007/s00180-014-0490-5
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
We address the issue of constructing prediction intervals for responses that assume values in the standard unit interval, . The response is modeled using the class of beta regression models and we introduce percentile and (bias-corrected and accelerated) bootstrap prediction intervals. We present Monte Carlo evidence on the finite sample behavior of such intervals. An empirical application is presented and discussed.
引用
收藏
页码:1263 / 1277
页数:15
相关论文
共 50 条