EM AND BEYOND

被引:62
作者
RUBIN, DB
机构
[1] Department of Statistics, Harvard University, Cambridge, 02138, MA, One Oxford Street
关键词
DATA AUGMENTATION; GIBBS SAMPLER; MISSING DATA; MONTE-CARLO METHODS; MULTIPLE IMPUTATION; SAMPLING IMPORTANCE RESAMPLING; SIMULATION TECHNIQUES; STOCHASTIC RELAXATION;
D O I
10.1007/BF02294461
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
The basic theme of the EM algorithm, to repeatedly use complete-data methods to solve incomplete data problems, is also a theme of several more recent statistical techniques. These techniques-multiple imputation, data augmentation, stochastic relaxation, and sampling importance resampling-combine simulation techniques with complete-data methods to attack problems that are difficult or impossible for EM.
引用
收藏
页码:241 / 254
页数:14
相关论文
共 45 条