图如下:
- #对收益率序列进行DCC-GARCH模型的拟合,选择0-4绘制相关图示。0表示退出,其中4是最重要的,是两者之间的动态相关系数时序图。
- #本次数据有2个样本序列,两两组合,共1种
- #install.packages('rmgarch')
- library(rmgarch)
- meanSpec=list(armaOrder=c(1,1),include.mean=FALSE,archpow=1,arfima = FALSE, external.regressors = NULL, archex = FALSE)
- distSpec=c("mvnorm")
- varSpec=list(model="sGARCH",garchOrder=c(1,1))
- spec1=ugarchspec(mean.model=meanSpec,variance.model=varSpec)
- mySpec=multispec(replicate(2,spec1))
- mspec=dccspec(mySpec,VAR=F,robust = F,lag=1,lag.max=NULL,lag.criterion = c("AIC"),external.regressors = NULL,robust.control = list(gamma=0.25,delta=0.01,nc=10,ns=500),dccOrder = c(1,1),distribution = distSpec,start.pars = list(),fixed.pars = list(),model = "DCC")
- ##上述是方程参数估计准备过程
- fdcc12=dccfit(data=p1ld[,c(1,2)],mspec,out.sample = 0,solver = "solnp",solver.control = list(),fit.control = list(eval.se=TRUE,stationary=TRUE,scale=FALSE),parallel=TRUE,parallel.control=list(pkg=c("multicore"),cores=2),fit=NULL,VAR.fit=NULL,cluster = NULL)
- show(fdcc12) #dcca1 和dccb1 显著,表明存在DCC效应。(行业联动性、时变相关性)
- plot(fdcc12)


雷达卡




京公网安备 11010802022788号







