library(ggplot2)
library(tidyverse)
library(readxl)
library(rugarch)
library(VineCopula)
library(goftest)
library(readxl)
library(readxl)
data <- read_excel("~/2121001544_Ngoen/E/DATA.xlsx",
col_types = c("date", "numeric", "numeric",
"numeric", "numeric"))
data <- na.omit(data)autoarfima(data$TSVN,ar.max = 2, ma.max = 2,criterion = "AIC", method = "full")## $fit
##
## *----------------------------------*
## * ARFIMA Model Fit *
## *----------------------------------*
## Mean Model : ARFIMA(2,0,2)
## Distribution : norm
##
## Optimal Parameters
## ------------------------------------
## Estimate Std. Error t value Pr(>|t|)
## ar1 0.000000 NA NA NA
## ar2 0.389644 0.035621 10.939 0
## ma1 -0.264015 0.023403 -11.281 0
## ma2 -0.640934 0.027486 -23.318 0
## sigma 0.059514 0.001142 52.096 0
##
## Robust Standard Errors:
## Estimate Std. Error t value Pr(>|t|)
## ar1 0.000000 NA NA NA
## ar2 0.389644 0.054377 7.1656 0
## ma1 -0.264015 0.031669 -8.3367 0
## ma2 -0.640934 0.034141 -18.7731 0
## sigma 0.059514 0.002328 25.5645 0
##
## LogLikelihood : 1903.342
##
## Information Criteria
## ------------------------------------
##
## Akaike -2.7993
## Bayes -2.7840
## Shibata -2.7993
## Hannan-Quinn -2.7936
##
## Weighted Ljung-Box Test on Standardized Residuals
## ------------------------------------
## statistic p-value
## Lag[1] 0.009706 0.921520
## Lag[2*(p+q)+(p+q)-1][11] 12.983259 0.000000
## Lag[4*(p+q)+(p+q)-1][19] 18.865011 0.001139
##
## H0 : No serial correlation
##
## Weighted Ljung-Box Test on Standardized Squared Residuals
## ------------------------------------
## statistic p-value
## Lag[1] 14.39 1.486e-04
## Lag[2*(p+q)+(p+q)-1][2] 26.39 9.350e-08
## Lag[4*(p+q)+(p+q)-1][5] 35.43 9.205e-10
##
##
## ARCH LM Tests
## ------------------------------------
## Statistic DoF P-Value
## ARCH Lag[2] 34.87 2 2.681e-08
## ARCH Lag[5] 38.69 5 2.743e-07
## ARCH Lag[10] 53.24 10 6.714e-08
##
## Nyblom stability test
## ------------------------------------
## Joint Statistic: 2.9799
## Individual Statistics:
## ar2 0.1309
## ma1 0.2417
## ma2 0.2695
## sigma 0.7662
##
## Asymptotic Critical Values (10% 5% 1%)
## Joint Statistic: 1.07 1.24 1.6
## Individual Statistic: 0.35 0.47 0.75
##
##
## Elapsed time : 0.1357851
##
##
## $rank.matrix
## ar1 ar2 ma1 ma2 im arf AIC converged
## 1 0 1 1 1 0 0 -2.799324 1
## 2 1 1 1 1 0 0 -2.797877 1
## 3 0 1 1 1 1 0 -2.797864 1
## 4 1 1 0 1 0 0 -2.797544 1
## 5 1 0 1 1 0 0 -2.796635 1
## 6 1 1 1 1 1 0 -2.796417 1
## 7 1 1 1 0 0 0 -2.796178 1
## 8 1 1 0 1 1 0 -2.796085 1
## 9 1 0 1 0 0 0 -2.795563 1
## 10 1 0 1 1 1 0 -2.795163 1
## 11 1 1 1 0 1 0 -2.794730 1
## 12 1 0 1 0 1 0 -2.794091 1
## 13 0 0 1 1 0 0 -2.725380 1
## 14 0 0 1 1 1 0 -2.723907 1
## 15 1 0 0 1 0 0 -2.715285 1
## 16 1 0 0 1 1 0 -2.713812 1
## 17 0 1 1 0 0 0 -2.707612 1
## 18 0 1 1 0 1 0 -2.706139 1
## 19 1 1 0 0 0 0 -2.705019 1
## 20 1 1 0 0 1 0 -2.703546 1
## 21 0 1 0 1 0 0 -2.690361 1
## 22 0 1 0 1 1 0 -2.688887 1
## 23 0 0 0 1 0 0 -2.685072 1
## 24 0 0 1 0 0 0 -2.683755 1
## 25 0 0 0 1 1 0 -2.683599 1
## 26 0 0 1 0 1 0 -2.682281 1
## 27 0 1 0 0 0 0 -2.681442 1
## 28 0 1 0 0 1 0 -2.679968 1
## 29 1 0 0 0 0 0 -2.674534 1
## 30 1 0 0 0 1 0 -2.673061 1
## 31 0 0 0 0 1 0 -2.656880 1autoarfima(data$TSX, ar.max = 2, ma.max = 2, criterion = "AIC", method = "full")## $fit
##
## *----------------------------------*
## * ARFIMA Model Fit *
## *----------------------------------*
## Mean Model : ARFIMA(2,0,2)
## Distribution : norm
##
## Optimal Parameters
## ------------------------------------
## Estimate Std. Error t value Pr(>|t|)
## ar1 1.805416 0.012940 139.526 0
## ar2 -0.879916 0.012948 -67.956 0
## ma1 -1.891028 0.000005 -345238.116 0
## ma2 0.917323 0.000024 37634.324 0
## sigma 0.060364 0.001157 52.155 0
##
## Robust Standard Errors:
## Estimate Std. Error t value Pr(>|t|)
## ar1 1.805416 0.010399 173.617 0
## ar2 -0.879916 0.008276 -106.327 0
## ma1 -1.891028 0.000002 -858459.194 0
## ma2 0.917323 0.000027 33774.792 0
## sigma 0.060364 0.002554 23.635 0
##
## LogLikelihood : 1884.091
##
## Information Criteria
## ------------------------------------
##
## Akaike -2.7695
## Bayes -2.7503
## Shibata -2.7695
## Hannan-Quinn -2.7623
##
## Weighted Ljung-Box Test on Standardized Residuals
## ------------------------------------
## statistic p-value
## Lag[1] 4.727 0.02969
## Lag[2*(p+q)+(p+q)-1][11] 23.144 0.00000
## Lag[4*(p+q)+(p+q)-1][19] 60.396 0.00000
##
## H0 : No serial correlation
##
## Weighted Ljung-Box Test on Standardized Squared Residuals
## ------------------------------------
## statistic p-value
## Lag[1] 2.285 0.13061
## Lag[2*(p+q)+(p+q)-1][2] 3.521 0.10147
## Lag[4*(p+q)+(p+q)-1][5] 6.471 0.06955
##
##
## ARCH LM Tests
## ------------------------------------
## Statistic DoF P-Value
## ARCH Lag[2] 4.948 2 8.423e-02
## ARCH Lag[5] 11.815 5 3.742e-02
## ARCH Lag[10] 48.425 10 5.190e-07
##
## Nyblom stability test
## ------------------------------------
## Joint Statistic: 5.8486
## Individual Statistics:
## ar1 0.05215
## ar2 0.06194
## ma1 0.09364
## ma2 0.07360
## sigma 1.59544
##
## Asymptotic Critical Values (10% 5% 1%)
## Joint Statistic: 1.28 1.47 1.88
## Individual Statistic: 0.35 0.47 0.75
##
##
## Elapsed time : 0.06224179
##
##
## $rank.matrix
## ar1 ar2 ma1 ma2 im arf AIC converged
## 1 1 1 1 1 0 0 -2.769479 1
## 2 1 1 1 1 1 0 -2.768007 1
## 3 1 1 1 0 0 0 -2.709054 1
## 4 1 0 1 1 0 0 -2.707904 1
## 5 1 1 1 0 1 0 -2.707842 1
## 6 1 0 1 1 1 0 -2.706704 1
## 7 0 1 0 1 0 0 -2.641478 1
## 8 1 1 0 1 0 0 -2.640023 1
## 9 0 1 0 1 1 0 -2.640006 1
## 10 1 1 0 1 1 0 -2.638551 1
## 11 0 0 0 1 0 0 -2.638400 1
## 12 0 1 0 0 0 0 -2.638356 1
## 13 0 0 1 0 0 0 -2.638001 1
## 14 1 0 0 0 0 0 -2.637993 1
## 15 0 0 0 0 1 0 -2.637942 1
## 16 0 0 1 1 0 0 -2.637006 1
## 17 1 0 0 1 0 0 -2.636993 1
## 18 0 1 1 0 0 0 -2.636951 1
## 19 1 1 0 0 0 0 -2.636942 1
## 20 0 0 0 1 1 0 -2.636928 1
## 21 0 1 0 0 1 0 -2.636884 1
## 22 0 0 1 0 1 0 -2.636529 1
## 23 1 0 1 0 0 0 -2.636524 1
## 24 1 0 0 0 1 0 -2.636521 1
## 25 0 0 1 1 1 0 -2.635534 1
## 26 0 1 1 0 1 0 -2.635479 1
## 27 1 1 0 0 1 0 -2.635471 1
## 28 1 0 0 1 1 0 -2.635187 1
## 29 1 0 1 0 1 0 -2.635052 1
## 30 0 1 1 1 1 0 98.500995 1
## 31 0 1 1 1 0 0 101.886440 1# PHÂN PHỐI CHUẨN
sgx11n.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(1,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'norm')
sgx11n <- ugarchfit(spec = sgx11n.spec, data$TSX)
# PHÂN PHỐI STUDENT
sgx11std.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(1,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'std')
sgx11std <- ugarchfit(sgx11std.spec, data$TSX)
# PHÂN PHỐI ĐỐI XỨNG
sgx11sstd.spec <- ugarchspec(variance.model = list( model = 'gjrGARCH', garchOrder = c(1,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sstd')
sgx11sstd <- ugarchfit(sgx11sstd.spec, data$TSX)
# PHÂN PHỐI PHÂN PHỐI Generalized Error Distribution
sgx11ged.spec <- ugarchspec(variance.model = list(model = "gjrGARCH", garchOrder = c(1, 1)), mean.model = list(armaOrder = c(2, 2), include.mean = TRUE), distribution.model = "ged")
sgx11ged <- ugarchfit(sgx11ged.spec, data$TSX)
# PHÂN PHỐI Generalized Error Distribution đối xứng (sged)
sgx11sged.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(1,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sged')
sgx11sged <- ugarchfit(sgx11sged.spec, data$TSX)# PHÂN PHỐI CHUẨN
sgx12n.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(1,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'norm')
sgx12n <- ugarchfit(spec = sgx12n.spec, data$TSX)
# PHÂN PHỐI STUDENT
sgx12std.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(1,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'std')
sgx12std <- ugarchfit(sgx12std.spec, data$TSX)
# PHÂN PHỐI ĐỐI XỨNG
sgx12sstd.spec <- ugarchspec(variance.model = list( model = 'gjrGARCH', garchOrder = c(1,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sstd')
sgx12sstd <- ugarchfit(sgx12sstd.spec, data$TSX)
# PHÂN PHỐI PHÂN PHỐI Generalized Error Distribution
sgx12ged.spec <- ugarchspec(variance.model = list(model = "gjrGARCH", garchOrder = c(1,2)), mean.model = list(armaOrder = c(2, 2), include.mean = TRUE), distribution.model = "ged")
sgx12ged <- ugarchfit(sgx12ged.spec, data$TSX)
# PHÂN PHỐI Generalized Error Distribution đối xứng (sged)
sgx12sged.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(1,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sged')
sgx12sged <- ugarchfit(sgx12sged.spec, data$TSX)# PHÂN PHỐI CHUẨN
sgx21n.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(2,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'norm')
sgx21n <- ugarchfit(spec = sgx21n.spec, data$TSX)
# PHÂN PHỐI STUDENT
sgx21std.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(2,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'std')
sgx21std <- ugarchfit(sgx21std.spec, data$TSX)
# PHÂN PHỐI ĐỐI XỨNG
sgx21sstd.spec <- ugarchspec(variance.model = list( model = 'gjrGARCH', garchOrder = c(2,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sstd')
sgx21sstd <- ugarchfit(sgx21sstd.spec, data$TSX)
# PHÂN PHỐI PHÂN PHỐI Generalized Error Distribution
sgx21ged.spec <- ugarchspec(variance.model = list(model = "gjrGARCH", garchOrder = c(2,1)), mean.model = list(armaOrder = c(2, 2), include.mean = TRUE), distribution.model = "ged")
sgx21ged <- ugarchfit(sgx21ged.spec, data$TSX)
# PHÂN PHỐI Generalized Error Distribution đối xứng (sged)
sgx21sged.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(2,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sged')
sgx21sged <- ugarchfit(sgx21sged.spec, data$TSX)# PHÂN PHỐI CHUẨN
sgx22n.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(2,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'norm')
sgx22n <- ugarchfit(spec = sgx22n.spec, data$TSX)
# PHÂN PHỐI STUDENT
sgx22std.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(2,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'std')
sgx22std <- ugarchfit(sgx22std.spec, data$TSX)
# PHÂN PHỐI ĐỐI XỨNG
sgx22sstd.spec <- ugarchspec(variance.model = list( model = 'gjrGARCH', garchOrder = c(2,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sstd')
sgx22sstd <- ugarchfit(sgx22sstd.spec, data$TSX)
# PHÂN PHỐI PHÂN PHỐI Generalized Error Distribution
sgx22ged.spec <- ugarchspec(variance.model = list(model = "gjrGARCH", garchOrder = c(2,2)), mean.model = list(armaOrder = c(2, 2), include.mean = TRUE), distribution.model = "ged")
sgx22ged <- ugarchfit(sgx22ged.spec, data$TSX)
# PHÂN PHỐI Generalized Error Distribution đối xứng (sged)
sgx22sged.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(2,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sged')
sgx22sged <- ugarchfit(sgx22sged.spec, data$TSX)# PHÂN PHỐI CHUẨN
vni11n.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(1,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'norm')
vni11n <- ugarchfit(spec = vni11n.spec, data$TSVN)
# PHÂN PHỐI STUDENT
vni11std.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(1,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'std')
vni11std <- ugarchfit(vni11std.spec, data$TSVN)
# PHÂN PHỐI ĐỐI XỨNG
vni11sstd.spec <- ugarchspec(variance.model = list( model = 'gjrGARCH', garchOrder = c(1,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sstd')
vni11sstd <- ugarchfit(vni11sstd.spec, data$TSVN)
# PHÂN PHỐI PHÂN PHỐI Generalized Error Distribution
vni11ged.spec <- ugarchspec(variance.model = list(model = "gjrGARCH", garchOrder = c(1, 1)), mean.model = list(armaOrder = c(2, 2), include.mean = TRUE), distribution.model = "ged")
vni11ged <- ugarchfit(vni11ged.spec, data$TSVN)
# PHÂN PHỐI Generalized Error Distribution đối xứng (sged)
vni11sged.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(1,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sged')
vni11sged <- ugarchfit(vni11sged.spec, data$TSVN)# PHÂN PHỐI CHUẨN
vni12n.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(1,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'norm')
vni12n <- ugarchfit(spec = vni12n.spec, data$TSVN)
# PHÂN PHỐI STUDENT
vni12std.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(1,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'std')
vni12std <- ugarchfit(vni12std.spec, data$TSVN)
# PHÂN PHỐI ĐỐI XỨNG
vni12sstd.spec <- ugarchspec(variance.model = list( model = 'gjrGARCH', garchOrder = c(1,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sstd')
vni12sstd <- ugarchfit(vni12sstd.spec, data$TSVN)
# PHÂN PHỐI PHÂN PHỐI Generalized Error Distribution
vni12ged.spec <- ugarchspec(variance.model = list(model = "gjrGARCH", garchOrder = c(1,2)), mean.model = list(armaOrder = c(2, 2), include.mean = TRUE), distribution.model = "ged")
vni12ged <- ugarchfit(vni12ged.spec, data$TSVN)
# PHÂN PHỐI Generalized Error Distribution đối xứng (sged)
vni12sged.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(1,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sged')
vni12sged <- ugarchfit(vni12sged.spec, data$TSVN)# PHÂN PHỐI CHUẨN
vni21n.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(2,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'norm')
vni21n <- ugarchfit(spec = vni21n.spec, data$TSVN)
# PHÂN PHỐI STUDENT
vni21std.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(2,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'std')
vni21std <- ugarchfit(vni21std.spec, data$TSVN)
# PHÂN PHỐI ĐỐI XỨNG
vni21sstd.spec <- ugarchspec(variance.model = list( model = 'gjrGARCH', garchOrder = c(2,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sstd')
vni21sstd <- ugarchfit(vni21sstd.spec, data$TSVN)
# PHÂN PHỐI PHÂN PHỐI Generalized Error Distribution
vni21ged.spec <- ugarchspec(variance.model = list(model = "gjrGARCH", garchOrder = c(2,1)), mean.model = list(armaOrder = c(2, 2), include.mean = TRUE), distribution.model = "ged")
vni21ged <- ugarchfit(vni21ged.spec, data$TSVN)
# PHÂN PHỐI Generalized Error Distribution đối xứng (sged)
vni21sged.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(2,1)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sged')
vni21sged <- ugarchfit(vni21sged.spec, data$TSVN)# PHÂN PHỐI CHUẨN
vni22n.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(2,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'norm')
vni22n <- ugarchfit(spec = vni22n.spec, data$TSVN)
# PHÂN PHỐI STUDENT
vni22std.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(2,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'std')
vni22std <- ugarchfit(vni22std.spec, data$TSVN)
# PHÂN PHỐI ĐỐI XỨNG
vni22sstd.spec <- ugarchspec(variance.model = list( model = 'gjrGARCH', garchOrder = c(2,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sstd')
vni22sstd <- ugarchfit(vni22sstd.spec, data$TSVN)
# PHÂN PHỐI PHÂN PHỐI Generalized Error Distribution
vni22ged.spec <- ugarchspec(variance.model = list(model = "gjrGARCH", garchOrder = c(2,2)), mean.model = list(armaOrder = c(2, 2), include.mean = TRUE), distribution.model = "ged")
vni22ged <- ugarchfit(vni22ged.spec, data$TSVN)
# PHÂN PHỐI Generalized Error Distribution đối xứng (sged)
vni22sged.spec <- ugarchspec(variance.model = list(model = 'gjrGARCH', garchOrder = c(2,2)), mean.model = list(armaOrder = c(2,2), include.mean = TRUE), distribution.model = 'sged')
vni22sged <- ugarchfit(vni22sged.spec, data$TSVN)sgx.model.list <- list(garch11n = sgx11n,
garch11std = sgx11std,
garch11sstd = sgx11sstd,
garch11ged = sgx11ged,
garch11sged = sgx11sged,
garch12n = sgx12n,
garch12ged = sgx12ged,
garch21n = sgx21n,
garch21std = sgx21std,
garch21sged = sgx21sged,
garch22n = sgx22n)
sgx.info.mat <- sapply(sgx.model.list, infocriteria)
rownames(sgx.info.mat) <- rownames(infocriteria(sgx11n))
sgx.info.mat## garch11n garch11std garch11sstd garch11ged garch11sged garch12n
## Akaike -2.844147 -4.130698 -4.143537 -4.197696 -4.113922 -2.842674
## Bayes -2.809573 -4.092282 -4.101280 -4.159280 -4.071665 -2.804258
## Shibata -2.844235 -4.130806 -4.143667 -4.197804 -4.114052 -2.842781
## Hannan-Quinn -2.831203 -4.116315 -4.127716 -4.183313 -4.098101 -2.828290
## garch12ged garch21n garch21std garch21sged garch22n
## Akaike -4.115692 -2.853725 -4.127735 -4.095916 -2.873255
## Bayes -4.073435 -2.811468 -4.081636 -4.045975 -2.827156
## Shibata -4.115822 -2.853855 -4.127889 -4.096097 -2.873410
## Hannan-Quinn -4.099871 -2.837904 -4.110475 -4.077218 -2.855995sgx.inds <- which(sgx.info.mat == min(sgx.info.mat), arr.ind = TRUE)
model.sgx <- colnames(sgx.info.mat)[sgx.inds[,2]]
model.sgx## [1] "garch11ged"garch11ged = sgx11gedvni.model.list <- list(garch11n = vni11n,
garch11std = vni11std,
garch11sstd = vni11sstd,
garch11ged = vni11ged,
garch12std = vni12std,
garch12sstd = vni12sstd,
garch12ged = vni12ged,
garch21n = vni21n,
garch21std = vni21std,
garch21sstd = vni21sstd,
garch22std = vni22std,
garch22sstd = vni22sstd,
garch22ged = vni22ged,
garch22sged = vni22sged)
vni.info.mat <- sapply(vni.model.list, infocriteria)
rownames(vni.info.mat) <- rownames(infocriteria(vni11n))
vni.info.mat## garch11n garch11std garch11sstd garch11ged garch12std garch12sstd
## Akaike -2.922947 -3.670058 -3.674386 -3.682093 -3.668584 -3.672912
## Bayes -2.888373 -3.631642 -3.632128 -3.643677 -3.626327 -3.626813
## Shibata -2.923034 -3.670165 -3.674516 -3.682200 -3.668714 -3.673066
## Hannan-Quinn -2.910002 -3.655675 -3.658564 -3.667710 -3.652763 -3.655652
## garch12ged garch21n garch21std garch21sstd garch22std garch22sstd
## Akaike -3.686118 -2.992916 -3.672295 -3.676397 -3.670850 -3.674932
## Bayes -3.643861 -2.950659 -3.626196 -3.626457 -3.620909 -3.621149
## Shibata -3.686249 -2.993046 -3.672449 -3.676578 -3.671031 -3.675142
## Hannan-Quinn -3.670297 -2.977095 -3.655035 -3.657699 -3.652152 -3.654795
## garch22ged garch22sged
## Akaike -3.658456 -3.681944
## Bayes -3.608516 -3.628162
## Shibata -3.658637 -3.682154
## Hannan-Quinn -3.639758 -3.661808vni.inds <- which(vni.info.mat == min(vni.info.mat), arr.ind = TRUE)
model.vni <- colnames(vni.info.mat)[vni.inds[,2]]
model.vni## [1] "garch12ged"garch12ged = vni12gedsgx.res <- residuals(sgx11ged)/sigma(sgx11ged)
fitdist(distribution = 'ged' , sgx.res, control = list())$pars## mu sigma shape
## 4.995720e-06 9.965050e-01 3.814635e-01s <- pdist(distribution = 'norm' , q = sgx.res, mu = 4.995720e-06 , sigma = 9.965050e-01, shape = 3.814635e-01)vni.res <- residuals(vni12ged)/sigma(vni12ged)
fitdist(distribution = 'ged' , vni.res, control = list())$pars## mu sigma shape
## -0.01409621 1.06039972 0.43231559v <- pdist(distribution = 'sged' , q = vni.res, mu = -0.01409621 , sigma = 1.06039972, shape = 0.43231559)# Kiểm định Anderson-Darling
ad.test(s, 'punif')##
## Anderson-Darling test of goodness-of-fit
## Null hypothesis: uniform distribution
## Parameters assumed to be fixed
##
## data: s
## An = 163.8, p-value = 4.422e-07ad.test(v, 'punif')##
## Anderson-Darling test of goodness-of-fit
## Null hypothesis: uniform distribution
## Parameters assumed to be fixed
##
## data: v
## An = 2.5271, p-value = 0.04795# Kiểm định Cramer-von Mises
cvm.test(s, 'punif')##
## Cramer-von Mises test of goodness-of-fit
## Null hypothesis: uniform distribution
## Parameters assumed to be fixed
##
## data: s
## omega2 = 31.769, p-value < 2.2e-16cvm.test(v, 'punif')##
## Cramer-von Mises test of goodness-of-fit
## Null hypothesis: uniform distribution
## Parameters assumed to be fixed
##
## data: v
## omega2 = 0.33573, p-value = 0.1075# Kiểm định ks-test
ks.test(s, 'punif')##
## Asymptotic one-sample Kolmogorov-Smirnov test
##
## data: s
## D = 0.98305, p-value < 2.2e-16
## alternative hypothesis: two-sidedks.test(v, 'punif')##
## Asymptotic one-sample Kolmogorov-Smirnov test
##
## data: v
## D = 0.033695, p-value = 0.09179
## alternative hypothesis: two-sidedBiCopSelect(s, v, familyset = 1:9, selectioncrit = 'AIC', indeptest = FALSE, level = 0.05)## Bivariate copula: t (par = 0.01, par2 = 15.67, tau = 0)Stu <- BiCopEst(s, v, family = 2, method = 'mle', se = T, max.df = 10)
summary(Stu)## Family
## ------
## No: 2
## Name: t
##
## Parameter(s)
## ------------
## par: 0 (SE = 0.04)
## par2: 10 (SE = NA)
## Dependence measures
## -------------------
## Kendall's tau: 0 (empirical = -0.01, p value = 0.41)
## Upper TD: 0.01
## Lower TD: 0.01
##
## Fit statistics
## --------------
## logLik: 23.37
## AIC: -42.73
## BIC: -32.31