although there is a ‘trade-off’ as the covariance matrices among random effects proportional to identity matrices generate fewer links between random effects levels
原文全段如下
CU=R (14)
Whilst the part of the coeffcient matrix C arising from the covariances among random effects is sparser than in the corresponding MME for (1), it has to be borne in mind that Z *and W* can be considerably denser than matrices Z and W, although there is a ‘trade-off’ as the covariance matrices among random effects proportional to identity matrices generate fewer links between random effects levels. Hence computational savings in manipulating the MME arise mainly from the reduction in the number of equations when mA< kA or mR< kR.
although there is a ‘trade-off’ as the covariance matrices among random effects proportional to identity matrices generate fewer links between random effects levels
Whilst the part of the coeffcient matrix C arising from the covariances among random effects is sparser than in the corresponding MME for (1), it has to be borne in mind that Z *and W* can be considerably denser than matrices Z and W, although there is a ‘trade-off’ as the covariance matrices among random effects proportional to identity matrices generate fewer links between random effects levels. Hence computational savings in manipulating the MME arise mainly from the reduction in the number of equations when mA kA or mR kR.
即使隨機(jī)效應(yīng)間的協(xié)方差矩陣與單位矩陣成比例（ as the covariance matrices among random effects proportional to identity matrices ），存在一個(gè)這樣的“轉(zhuǎn)換”（there is a ‘trade-off’），這個(gè)轉(zhuǎn)換能夠使隨機(jī)效應(yīng)各水平之間的聯(lián)系變小（a ‘trade-off’generate fewer links between random effects levels），即使如此（although ），系數(shù)矩陣C中來自隨機(jī)效應(yīng)間的協(xié)方差矩陣的那一部分（the part of the coeffcient matrix C arising from the covariances among random effects ），比式（1）的MME中的相應(yīng)部分要更加稀疏（is sparser than in the corresponding MME for (1) ），必須牢記，Z*和W*可能遠(yuǎn)比Z和W要密（it has to be borne in mind that Z *and W* can be considerably denser than matrices Z and W）。所以，在mAkA或mRkR時(shí)，計(jì)算MME的過程中節(jié)約的計(jì)算量主要來源于方程個(gè)數(shù)的減少（Hence computational savings in manipulating the MME arise mainly from the reduction in the number of equations when mA >kA or mR >kR）.
although there is a ‘trade-off’ as the covariance matrices among random effects proportional to identity matrices generate fewer links between random effects levels. 
謝謝了
although there is a ‘trade-off’ as the covariance matrices among random effects proportional to identity matrices generate fewer links between random effects levels.
although there is a ‘trade-off’ as the covariance matrices among random effects proportional to identity matrices generate fewer links between random effects levels.
你的第三點(diǎn)分析，我也不太同意，同理，因?yàn)檫@個(gè)generate是動(dòng)詞原形，它又有主語和賓語，顯然as后面有完整的主謂賓結(jié)構(gòu)，這樣可以判斷，as后面是一個(gè)從句，所以，as應(yīng)該是作為從屬連詞，引導(dǎo)表原因的狀語從句．所以，＂although A as B＂這個(gè)結(jié)構(gòu)站不穩(wěn)腳．
樓主可否提供這篇文獻(xiàn)的題目和出處？作者: cheng_zhang 時(shí)間: 2009-12-24 13:24
毫無疑問，generate 的主語是 covariance matrices. as是作為“因?yàn)椤眮斫忉尩?。這句話的難度在于首先是生統(tǒng)方面的內(nèi)容大家不熟悉，然后是第一個(gè)單詞whilst（同時(shí)，說明上面還有很重要的內(nèi)容）以及后面一層套一層的句法結(jié)構(gòu)。簡化一下句子結(jié)構(gòu)，就成了：
whilst the part of coffecient matric C is sparser than in the correstponding MME for (1), it has to b borne in mind that....., althout there is a "trade-off" as the covariance matrices generate few links. Hence, ......
Whilst the part of the coeffcient matrix C arising from the covariances among random effects is sparser than in the corresponding MME for (1), it has to be borne in mind that Z *and W* can be considerably denser than matrices Z and W, although there is a ‘trade-off’ as the covariance matrices among random effects proportional to identity matrices generate fewer links between random effects levels. Hence computational savings in manipulating the MME arise mainly from the reduction in the number of equations when mA< kA or mR< kR.
根據(jù)大家的回復(fù)，我整理一下
同時(shí)，系數(shù)矩陣C中與隨機(jī)效應(yīng)間的協(xié)方差對應(yīng)的那一部分，要比公式（1）的MME中相應(yīng)的這一部分稀疏，必需牢記矩陣Z*和W*比矩陣Z和W要稠密得多，雖然，由于隨機(jī)效應(yīng)間的協(xié)方差矩陣與單位矩陣成比例并且隨機(jī)效應(yīng)水平間的聯(lián)系更少，但是仍然存在（信息的）交換。所以，在計(jì)算MME時(shí)節(jié)約的計(jì)算量主要原因是mA<KA或mR<kR時(shí)方程個(gè)數(shù)的減少。
