使用mlogit在R中嵌套Logit模型时出错

问题描述

我已经成功运行了以下两个嵌套的logit模型：

summary(mlogit(Response ~ 1 | Age + Sex + Income + Educatio + HomeLoca
+ CarOwn + CarHouse + LTimePT + LTimeCar + UmwFrei1 + distPT1 + FrqInfo1Neu| Cost + Time + WalkTime,data =TM6,nests = list(convent = c("OwnCar","PT"),pooling = c("PoolPass","PoolDriv"))))

summary(mlogit(Response ~ 1 | Age + Sex + Income + Educatio + HomeLoca + CarOwn + CarHouse + LTimePT + LTimeCar + UmwFrei1 + distPT1 + FrqInfo1Neu| Cost + Time + WalkTime,nests = list(beingDriven = c("PT","PoolPass"),Drive = c("OwnCar","PoolDriv"))))

但是，接下来的三个嵌套logit模型不起作用：

summary(mlogit(Response ~ 1 | Age + Sex + Income + Educatio + HomeLoca + CarOwn + CarHouse + LTimePT + LTimeCar + UmwFrei1 + distPT1 + FrqInfo1Neu| Cost + Time + WalkTime,unscaled = TRUE,nests = list(PTT = "PT",Cars = c("OwnCar","PoolDriv","PoolPass"))))

summary(mlogit(Response ~ 1 | Age + Sex + Income + Educatio + HomeLoca + CarOwn + CarHouse + LTimePT + LTimeCar + UmwFrei1 + distPT1 + FrqInfo1Neu| Cost + Time + WalkTime,nests = list(OwnCar = "OwnCar",Else = c("PT",OwnCar = "OwnCar",Pool = c("PoolDriv","PoolPass"))))

在这里，我遇到以下错误：

Error in solve.default(crossprod(attr(x,"gradi")[,!fixed])) : 
  system is computationally singular: reciprocal condition number = 8.23452e-21

mlogit软件包（https://cran.r-project.org/web/packages/mlogit/mlogit.pdf）上有更新。该语法去年有效，但现在却提供了错误。有人知道我必须更改吗？

感谢您的帮助。谢谢！

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）

mlogit r r