我试图将auto.arima函数中的arma模型的顺序输入到garchFit函数中。
我有一个df calles datatsr。
我以这种方式提取AR术语的顺序：
auto.arima(datatsr[,1])$arma[1] :
[1] 4
MA术语的顺序：
auto.arima(datatsr[,1])$arma[2] :
[1] 3
因此，我有arma(4,3)
然后我尝试在garchFit公式中输入这些值，并预测我的嵌入列表中的前一步值（59天用于预测第60天），名为mmk：
Garchfore <- function(datatsr, mmk) {
library(fGarch)
windowsL <- split(t(mmk), rep(1:nrow(mmk), each=ncol(mmk)))
names(windowsL) <- unlist(lapply(windowsL,
function(x) paste(rownames(datatsr)[range(x)], sep="", collapse=" - ")))
one<-lapply(windowsL, function(x)
predict(garchFit(formula = ~arma(auto.arima(datatsr[,1])$arma[1],auto.arima(datatsr[,1])$arma[2])
+garch(1,1), data = datatsr[rev(unlist(x)),1]),
n.ahead=1))
}
然后我调用函数
predi=Garchfore(datatsr,mmk)
我收到错误：
Error in predict(garchFit(formula = ~arma(auto.arima(datatsr[, 1])$arma[1], :
error in evaluating the argument 'object' in selecting a method for function 'predict':
Error in .garchArgsParser(formula = formula, data = data, trace = FALSE) :
Formula and data units do not match.
无论如何都知道我做错了什么？或者甚至可以在我尝试时将auto.arima传递给garchFit吗？
祝你好运！
答案 0 :(得分：4)
函数garchFit（）期望公式作为第一个参数（参见garchFit() here）。 ＆＃34;式＆＃34;参数类型无法计算表达式，因此garchFit（）无法正确解析变量，例如 auto.arima（datatsr [，1]）$ arma [2] 。从表达式中获取公式的一种方法是替换函数（参见substitute() here）。以下是使用garchFit（）的substitute（）的简化用法，用于演示：
library(fGarch)
library(doParallel)
N = 200
x.vec = as.vector(garchSim(garchSpec(rseed = 1985), n = N)[,1])
m.list <-
foreach(i=1:2) %:%
foreach(j=1:2) %do% {
garchFit(substitute(~ garch(p,q),list(p=i, q=j)),
data = x.vec, trace = FALSE)
}
在garchFit（）用法的上下文中，您可以将公式参数替换为garchFit（），如下所示：
garchFit(substitute(formula = ~arma(p,q)+garch(1,1),
list(p=auto.arima(datatsr[,1])$arma[1],
q=auto.arima(datatsr[,1])$arma[2])),
data = datatsr[rev(unlist(x)),1])
我希望这会有所帮助，虽然有点晚。
答案 1 :(得分：-1)
的 1。指定公式的方式是错误的
的 2。您应该手动输入arima订单
让我试着解释一下 使用我自己的数据
garchFit(formula= ~arma(3,2) + aparch(1,1), data=ret.fin.chn)
产量结果
Title:
GARCH Modelling
Call:
garchFit(formula = ~arma(3, 2) + aparch(1, 1), data = ret.fin.chn)
Mean and Variance Equation:
data ~ arma(3, 2) + aparch(1, 1)
<environment: 0x0df1f498>
[data = ret.fin.chn]
Conditional Distribution:
norm
Coefficient(s):
mu ar1 ar2 ar3 ma1 ma2 omega alpha1
1.4860e-04 6.3611e-01 -6.1945e-01 1.9331e-02 -6.6944e-01 6.4677e-01 1.0186e-05 3.1339e-02
gamma1 beta1 delta
3.6329e-04 9.7088e-01 1.4759e+00
Std. Errors:
based on Hessian
Error Analysis:
Estimate Std. Error t value Pr(>|t|)
mu 1.486e-04 2.893e-04 0.514 0.607512
ar1 6.361e-01 3.752e-01 1.695 0.090028 .
ar2 -6.195e-01 1.872e-01 -3.310 0.000934 ***
ar3 1.933e-02 3.307e-02 0.585 0.558851
ma1 -6.694e-01 3.754e-01 -1.783 0.074552 .
ma2 6.468e-01 2.066e-01 3.130 0.001748 **
omega 1.019e-05 3.645e-06 2.794 0.005202 **
alpha1 3.134e-02 5.490e-03 5.708 1.14e-08 ***
gamma1 3.633e-04 6.787e-02 0.005 0.995729
beta1 9.709e-01 4.663e-03 208.212 < 2e-16 ***
delta 1.476e+00 3.241e-01 4.554 5.26e-06 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Log Likelihood:
7311.694 normalized: 2.659765
Description:
Wed Oct 16 23:43:41 2013 by user: ASUS
，而
> garchFit(formula= ~arma(arima.ret.fin.chn$arma[1],arima.ret.fin.chn$arma[2]) + aparch(1,1), data=ret.fin.chn)
产量结果
[1] "arima.ret.fin.chn" "arma" "data"
[1] "data"
Error in .garchArgsParser(formula = formula, data = data, trace = FALSE) :
Formula and data units do not match.
现在让我们看看
> arima.ret.fin.chn$arma[1]
[1] 3
> arima.ret.fin.chn$arma[2]
[1] 2
> class(arima.ret.fin.chn$arma[1])
[1] "integer"
> class(3)
[1] "numeric"
，而
b<-as.numeric(3)
c<-as.numeric(2)
> garchFit(formula=~garch(b,c),data=ret.fin.chn)
[1] "b" "c" "data"
[1] "data"
了解它呢？
我的建议是你 直接写出arima订单的价值
尝试通过
检查garch适合代码> garchFit
function (formula = ~garch(1, 1), data = dem2gbp, init.rec = c("mci",
"uev"), delta = 2, skew = 1, shape = 4, cond.dist = c("norm",
"snorm", "ged", "sged", "std", "sstd", "snig", "QMLE"), include.mean = TRUE,
include.delta = NULL, include.skew = NULL, include.shape = NULL,
leverage = NULL, trace = TRUE, algorithm = c("nlminb", "lbfgsb",
"nlminb+nm", "lbfgsb+nm"), hessian = c("ropt", "rcd"),
control = list(), title = NULL, description = NULL, ...)
{
DEBUG = FALSE
init.rec = match.arg(init.rec)
cond.dist = match.arg(cond.dist)
hessian = match.arg(hessian)
algorithm = match.arg(algorithm)
CALL = match.call()
Name = capture.output(substitute(data))
if (is.character(data)) {
eval(parse(text = paste("data(", data, ")")))
data = eval(parse(text = data))
}
data <- as.data.frame(data)
if (isUnivariate(data)) {
colnames(data) <- "data"
}
else {
uniqueNames = unique(sort(colnames(data)))
if (is.null(colnames(data))) {
stop("Column names of data are missing.")
}
if (length(colnames(data)) != length(uniqueNames)) {
stop("Column names of data are not unique.")
}
}
if (length(formula) == 3 && isUnivariate(data))
formula[2] <- NULL
if (length(formula) == 2) {
if (isUnivariate(data)) {
formula = as.formula(paste("data", paste(formula,
collapse = " ")))
}
else {
stop("Multivariate data inputs require lhs for the formula.")
}
}
robust.cvar <- (cond.dist == "QMLE")
args = .garchArgsParser(formula = formula, data = data, trace = FALSE)
if (DEBUG)
print(list(formula.mean = args$formula.mean, formula.var = args$formula.var,
series = args$series, init.rec = init.rec, delta = delta,
skew = skew, shape = shape, cond.dist = cond.dist,
include.mean = include.mean, include.delta = include.delta,
include.skew = include.skew, include.shape = include.shape,
leverage = leverage, trace = trace, algorithm = algorithm,
hessian = hessian, robust.cvar = robust.cvar, control = control,
title = title, description = description))
ans = .garchFit(formula.mean = args$formula.mean, formula.var = args$formula.var,
series = args$series, init.rec, delta, skew, shape, cond.dist,
include.mean, include.delta, include.skew, include.shape,
leverage, trace, algorithm, hessian, robust.cvar, control,
title, description, ...)
ans@call = CALL
attr(formula, "data") <- paste("data = ", Name, sep = "")
ans@formula = formula
ans
}