r - 数据必须是矢量类型，是 'NULL' R

Question

我收到此错误消息:

Error in array(x, c(length(x), 1L), if (!is.null(names(x))) list(names(x),  : 
 'data' must be of a vector type, was 'NULL'

当我尝试运行此行时出现错误消息:

dcc.fit = dccfit(spec1, data = r_t1, fit.control=list(scale=TRUE))

但是，当我运行下面的行时它工作正常:

dcc.fit1 = dccfit(spec2, data = r_t1, fit.control=list(scale=TRUE), solver = "nlminb")

如果向量 r_t1 有问题，上面的代码行也不应该工作，所以这很奇怪。有谁知道如何解决这个问题？Multivariate3 是我导入到 R 中的 excel 文件。

Multivariate3 excel file attached here

  > head(spec2)
Error in x[seq_len(n)] : object of type 'S4' is not subsettable

我的全部代码在这里:

install.packages('rmgarch', dependencies = TRUE)
library("rmgarch")
library("parallel")
library("quantmod")

Dat<-data.frame(Multivariate3$Bitcoin,Multivariate3$SP500,Multivariate3$DAX,Multivariate3$KS11,Multivariate3$VGLT,Multivariate3$Euro,Multivariate3$Franc,Multivariate3$Yen,Multivariate3$Oil,Multivariate3$Gold)

#Returns
retBTC<-diff(log(Multivariate3$Bitcoin))
retSP<-diff(log(Multivariate3$SP500))
retDAX<-diff(log(Multivariate3$DAX))
retKS11<-diff(log(Multivariate3$KS11))
retVGLT<-diff(log(Multivariate3$VGLT))
retEUR<-diff(log(Multivariate3$Euro))
retCFH<-diff(log(Multivariate3$Franc))
retYEN<-diff(log(Multivariate3$Yen))
retOil<-diff(log(Multivariate3$Oil))
retGLD<-diff(log(Multivariate3$Gold))

# univariate normal GARCH(1,1) for each series
####UNRESTRICTED MODEL#####
xspec = ugarchspec(mean.model = list(armaOrder = c(1, 1)), variance.model = list(garchOrder = c(1,1), model = 'sGARCH'), distribution.model = 'std')
####RESTRICTED MODEL#####
xspec1 = ugarchspec(mean.model = list(armaOrder = c(1, 1)), variance.model = list(garchOrder = c(1,1), model = 'sGARCH'), distribution.model = 'std',fixed.pars=list(alpha1 = 0, beta1 = 0))

#################################
uspec = multispec(replicate(10, xspec))
uspecx = multispec(replicate(10, xspec1))
spec1 = dccspec(uspec = uspec, dccOrder = c(1, 1), distribution = 'mvnorm')
spec2 = dccspec(uspec = uspecx, dccOrder = c(1, 1), distribution = 'mvnorm')

#return vector
r_t1=cbind(retBTC,retSP,retDAX,retKS11,retVGLT,retEUR,retCFH,retYEN,retOil,retGLD)
####URESTRICTED MODEL#####
dcc.fit = dccfit(spec1, data = r_t1, fit.control=list(scale=TRUE))
####RESTRICTED MODEL#####
dcc.fit1 = dccfit(spec2, data = r_t1, fit.control=list(scale=TRUE), solver = "nlminb")

Answer 1

我在使用 cgarchfit 时碰巧遇到了同样的错误，我不得不通过 fit.control = list(eval.se = FALSE) 来摆脱'data' 必须是向量类型，是 'NULL' 错误。