Bayesian quantile inference

被引:74
作者
Tsionas, EG [1 ]
机构
[1] Athens Univ Econ & Business, Dept Econ, Athens 10434, Greece
关键词
Laplace distribution; quantile regression; Bayesian analysis; Gibbs sampling; kuznets curve;
D O I
10.1080/0094965031000064463
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The paper proposes a Bayesian interpretation of quantile regression that is shown to be equivalent to scale mixtures of normals leading to a skewed Laplace distribution. This representation of the model facilitates Bayesian analysis by means of Gibbs sampling with data augmentation, and nests regression in the L-1 norm as a special case. The new methods are applied to an analysis of the patents - R&D relationship for U.S. firms and unit root inference for the dollar-deutschemark exchange rate.
引用
收藏
页码:659 / 674
页数:16
相关论文
共 27 条
[1]  
Abramowitz M., 1970, HDB MATH FUNCTIONS
[2]  
AKAHIRA M, 1993, STAT SCI DATA ANAL, P375
[3]  
Andrews D.F., 1972, ROBUST ESTIMATES LOC
[4]  
[Anonymous], 1992, Stata Technical Bulletin
[5]   ASYMPTOTIC THEORY OF LEAST ABSOLUTE ERROR REGRESSION [J].
BASSETT, G ;
KOENKER, R .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1978, 73 (363) :618-622
[6]  
BASSETT G, 1982, J AM STAT ASSOC, V77, P407
[8]  
Cohen W.M., 1989, Handbook of Industrial Organization, V2, P1059, DOI DOI 10.1016/S1573-448X(89)02006-6
[9]  
DAMSLETH E, 1989, J ROY STAT SOC B MET, V51, P61