DCC GARCH估计相关性

时间:2018-06-19 09:06:04

标签: correlation

我在计算相关性的DCC GARCH矩阵时遇到了一些麻烦。似乎数据的维度与dimnames相矛盾(diccfit函数以错误结束)。

library(rugarch)
library(rmgarch)
library(xts)

D <- read.csv(file.choose(), header=T)
D$Date <- as.POSIXct(D$Date,"%d/%m/%Y",tz = "")

D <- as.xts(D[,-1], order.by = D$Date)

uspec = ugarchspec(mean.model = list(armaOrder = c(0,0)), variance.model = list(garchOrder = c(1,1), model = "eGARCH"), distribution.model = "std")
spec1 = dccspec(uspec = multispec(replicate(4, uspec)), dccOrder = c(1,1),  distribution = "mvt")

fit = dccfit(data = D, spec = spec1, out.sample = 10, solver = "solnp",
      fit.control = list(scale = TRUE, eval.se = TRUE))

我将非常感谢您的建议! 感谢,滨海

0 个答案:

没有答案