嗯，可以。。。

在使用library( systemfit )包建立非线性联立方程组时
程序如下：
library( systemfit )
rd<-read.csv("5.csv")
LEAF.formula<- LEAF~ 1/( 1+ r1*DBH^r2*H^r3*CW^r4)* CWB
BRANCH.formula<-BRANCH~1/( 1+(1/ r1*DBH^-r2*H^-r3*CW^-r4))* CWB
labels <- list("LEAF.formula", "BRANCH.formula")
inst <- ~ DBH+H+CW+LEAF+BRANCH
start.values<-c(r1=0.4,r2=0.9, r3=-0.2,r4=-1.0)
model<-list(LEAF.formula, BRANCH.formula)
model.ols <- nlsystemfit( "OLS", model, start.values, data=rd, eqnlabels=labels )
我用权重后精度怎么降低了
相关系数成负数了，请问怎么回事

library( systemfit )
rd<-read.csv("4444.csv")
LEAF.formula<- LEAF*1/DBH^0.23~ 1/( 1+ r1*DBH^r2*H^r3*CW^r4)* CWB*1/DBH^0.23
BRANCH.formula<-BRANCH*1/DBH^0.96~1/( 1+(1/ r1*DBH^-r2*H^-r3*CW^-r4))* CWB*1/DBH^0.96
labels <- list("LEAF.formula", "BRANCH.formula")
inst <- ~ DBH+H+CW+LEAF+BRANCH
start.values<-c(r1=0.4,r2=0.9, r3=-0.2,r4=-1.0)
model<-list(LEAF.formula, BRANCH.formula)
model.ols <- nlsystemfit( "OLS", model, start.values, data=rd, eqnlabels=labels )

https://bbs.pinggu.org/thread-2177875-1-1.html
指点一下这个问题可以吗？