Permutation-based multivariate regression analysis: The case for least sum of absolute deviations regression

被引:6
|
作者
Mielke, PW
Berry, KJ
机构
[1] COLORADO STATE UNIV,DEPT STAT,FT COLLINS,CO 80523
[2] COLORADO STATE UNIV,DEPT SOCIOL,FT COLLINS,CO 80523
关键词
agreement; distribution-free; linear regression; nonlinear regression; permutation tests; statistical inference;
D O I
10.1023/A:1018926522359
中图分类号
C93 [管理学]; O22 [运筹学];
学科分类号
070105 ; 12 ; 1201 ; 1202 ; 120202 ;
摘要
Linear and nonlinear multivariate least sum of absolute deviations regression models are profiled and evaluated. A chance-corrected measure of agreement between observed and predicted values is presented, a technique for establishing empirically-derived quantile limits for predicted values is introduced, and a permutation-based inference procedure for the measure of agreement is described.
引用
收藏
页码:259 / 268
页数:10
相关论文
共 50 条