用R写的SVAR程序和eviews结果完全不一样

这是设定A,B矩阵
resA <- matrix(NA, nrow = 5, ncol = 5)
resA[2,4]=resA[2,5]=resA[3,4]=resA[3,5]=resA[4,2]=resA[4,3]=resA[4,5]=0
resA[5,2]=resA[5,3]=resA[5,4]=0
resA[1,1]=resA[2,2]=resA[3,3]=resA[4,4]=resA[5,5]=1
resA
resB <- matrix(rep(0, 25), nrow = 5, ncol = 5)
resB[1,1]=resB[2,2]=resB[3,3]=resB[4,4]=resB[5,5]=1
resB
这是模型
model=VAR(vardata, p=2, type="trend")
summary(model)
stt=matrix(0.1, nrow = 1, ncol = 10)
model1=SVAR(model, Amat=resA, Bmat=resB, estmethod="scoring", start=stt, conv.crit=0.0001, max.iter=500)
这一行如果用scoring的话, 就会报错Error in `[<-`(`*tmp*`, pos, i, value = 1) : subscript out of bounds, 如果用direct的话就没问题.  但是得到的A矩阵和eviews得到的连符号都有的不一样, 这是为什么呀?