方差组分估计方法MIVQUE和REML的模拟比较  

Comparison of MIVQUE and REML with Monte Carlo Simulation

作　　者：张勤[1] 张沅[1] 刘增廷 

机构地区：[1]北京农业大学动物科学技术学院

出　　处：《Acta Genetica Sinica》1995年第6期424-430,共7页

摘　　要：利用ＭｏｎｔｅＣａｒｌｏ方法，对４种数据结构进行了ＭＩＶＱＵＥ和ＲＥＭＬ两种方差组分估计方法的模拟比较。方差组分估计所用的模型为奶牛育种中常用的公畜模型，它包括场年季固定效应、公牛组固定效应和公牛随机效应。４种数据结构中最大的有１２８４７个观察值，场年季效应和公牛效应水平数分别为７７８和４７，它与北京市目前可利用的奶牛头胎产奶量记录资料相当。最小的数据结构只有２００个观察值，１４８个场年季和２０头公牛。比较指标为估计值的偏差和方差（理论的或根据１０００次重复模拟所得的经验值）。结果表明，对于较大样本的数据结构，两种方法差异很小，它们间的估计值的相关接近于１，偏差小于真值的１％，方差近似相等。对于较小样本的数据结构，ＭＩＶＱＵＥ则明显优于ＲＥＭＬ。本研究还表明，对于ＲＥＭＬ来说，类似数据结构１的样本已能满足其渐近无偏性和有效性的大样本特性。A comparison of two methods for estimation of variance component,MIVQUE and KEML,was carried out on four data sets with Monte Carlo simulation. The model used was the sire model containing herd-year-season(HYS) effect(fixed),sire group effect(fixed)and sire effect(random), which is widely used in dairy cattle breeding. The largest data set consisted of 12847 records with 47 sires and 778 HYSs, which is corresponding to the milk yield data available currently in Beijing area. The smallest data set comprised 200 records with 148 HYSs and 20 sires. The criterion for the comparison were the bias and variance, either theoretical or empirical based on 1000 repeated simulations, of the estimates. The results show that for the larger data sets the two methods are little different from each other:Bias<1% of the true values,correlation≈1,and variance(MIVQUE)≈variance(REML).For the smaller data sets the MIVQUE was significantly better than REM L.It was also shown that for REML the sample size like the first data set can satisfy its large sample properties of asymptotical unbiasedness and efficiency.

关 键 词：数量遗传学 方差组分 MIVQUE REML 比较 

分 类 号：Q348[生物学—遗传学]