BÀI THỰC HÀNH GIỮA KỲ
Nguyễn Đặng Thành Nhân - 030139230257
2026-06-09
BÀI THỰC HÀNH KIỂM TRA GIỮA KỲ MÔN QUẢN TRỊ RỦI RO TÀI CHÍNH
- Đọc dữ liệu từ link google sheet
library(googlesheets4)
gs4_deauth()
df <- read_sheet("https://docs.google.com/spreadsheets/d/10nZIVWn3i5djs0tRZbI--8nntNbfbGoNvYKX8yI7Eeo/edit?gid=1109581498#gid=1109581498", sheet = "hose3")- Lấy dữ liệu mã cổ phiếu THG
df# A tibble: 3,335 × 241
Date AAA AAM ABT ACB ACC ACL ADP AGR ANV
<dttm> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 2012-04-11 00:00:00 4582 9448 10913 3583 2760 5507 422 7418 1115
2 2012-04-12 00:00:00 4560 9557 10972 3681 2851 5446 461 7418 1115
3 2012-04-13 00:00:00 4476 9557 10972 3681 2851 5446 505 7339 1094
4 2012-04-16 00:00:00 4624 9557 11300 3681 2967 5538 477 7655 1115
5 2012-04-17 00:00:00 4624 9703 11420 3667 2993 5660 521 7971 1126
6 2012-04-18 00:00:00 4560 9849 11330 3611 3110 5568 532 8208 1115
7 2012-04-19 00:00:00 4348 9849 11390 3555 3226 5844 581 7813 1061
8 2012-04-20 00:00:00 4370 9885 11420 3569 3071 6119 581 7497 1105
9 2012-04-23 00:00:00 4370 9885 11420 3611 3006 6241 581 7339 1159
10 2012-04-24 00:00:00 4433 9995 11539 3611 3110 6241 526 7418 1207
# ℹ 3,325 more rows
# ℹ 231 more variables: APG <dbl>, ASM <dbl>, ASP <dbl>, BCE <dbl>, BIC <dbl>,
# BMC <dbl>, BMI <dbl>, BMP <dbl>, BRC <dbl>, BSI <dbl>, BTP <dbl>,
# BTT <dbl>, BVH <dbl>, C32 <dbl>, C47 <dbl>, CCI <dbl>, CCL <dbl>,
# CDC <dbl>, CHP <dbl>, CIG <dbl>, CII <dbl>, CLC <dbl>, CLW <dbl>,
# CMG <dbl>, CMV <dbl>, CMX <dbl>, CNG <dbl>, COM <dbl>, CSM <dbl>,
# CTD <dbl>, CTG <dbl>, CTI <dbl>, CTS <dbl>, CVT <dbl>, D2D <dbl>, …thg <- df[, c("Date", "THG")]- Kiểm tra dữ liệu
str(thg)tibble [3,335 × 2] (S3: tbl_df/tbl/data.frame)
$ Date: POSIXct[1:3335], format: "2012-04-11" "2012-04-12" ...
$ THG : num [1:3335] 810 850 882 907 866 826 794 794 826 786 ...head(thg)# A tibble: 6 × 2
Date THG
<dttm> <dbl>
1 2012-04-11 00:00:00 810
2 2012-04-12 00:00:00 850
3 2012-04-13 00:00:00 882
4 2012-04-16 00:00:00 907
5 2012-04-17 00:00:00 866
6 2012-04-18 00:00:00 826tail(thg)# A tibble: 6 × 2
Date THG
<dttm> <dbl>
1 2026-05-15 00:00:00 43300
2 2026-05-18 00:00:00 43300
3 2026-05-19 00:00:00 43100
4 2026-05-20 00:00:00 42650
5 2026-05-21 00:00:00 43000
6 2026-05-22 00:00:00 42900summary(thg) Date THG
Min. :2012-04-11 00:00:00 Min. : 529
1st Qu.:2015-09-16 12:00:00 1st Qu.: 2956
Median :2019-04-23 00:00:00 Median :11073
Mean :2019-05-03 01:14:16 Mean :16522
3rd Qu.:2022-12-27 12:00:00 3rd Qu.:26971
Max. :2026-05-22 00:00:00 Max. :55983 4.1. Thống kê mô tả dữ liệu giá chứng khoán
library(fBasics)
basicStats(thg$THG) X..thg.THG
nobs 3.335000e+03
NAs 0.000000e+00
Minimum 5.290000e+02
Maximum 5.598300e+04
1. Quartile 2.956000e+03
3. Quartile 2.697100e+04
Mean 1.652163e+04
Median 1.107300e+04
Sum 5.509965e+07
SE Mean 2.520508e+02
LCL Mean 1.602744e+04
UCL Mean 1.701582e+04
Variance 2.118712e+08
Stdev 1.455580e+04
Skewness 7.832710e-01
Kurtosis -4.388960e-01summary(thg$THG) Min. 1st Qu. Median Mean 3rd Qu. Max.
529 2956 11073 16522 26971 55983 4.2. Thống kê mô tả dữ liệu return của giá chứng khoán
thg_return <- diff(log(thg$THG))
head(thg_return)[1] 0.04820210 0.03695571 0.02795039 -0.04625754 -0.04729014 -0.03951131tail(thg_return)[1] 0.005790404 0.000000000 -0.004629638 -0.010495723 0.008172842
[6] -0.002328290basicStats(thg_return) thg_return
nobs 3334.000000
NAs 0.000000
Minimum -0.072453
Maximum 0.162045
1. Quartile -0.007538
3. Quartile 0.010291
Mean 0.001191
Median 0.000000
Sum 3.969593
SE Mean 0.000402
LCL Mean 0.000403
UCL Mean 0.001978
Variance 0.000538
Stdev 0.023187
Skewness 0.077569
Kurtosis 2.9045745.1. Vẽ đồ thị và hàm mật độ của giá chứng khoán
ts.plot(thg$THG)
plot(thg, type = "l")
hist(thg$THG)
d1 = density(thg$THG)
plot(d1, type = "l")
5.2 Vẽ đồ thị và hàm mật độ của giá chứng khoán
plot(thg_return, type = "l")
hist(thg_return)
d2 <- density(thg_return)
plot(d2, type = "l")
- Kiểm tra tính dừng, kiểm tra phân phối chuẩn
library(tseries)
adf.test(thg$THG)
Augmented Dickey-Fuller Test
data: thg$THG
Dickey-Fuller = -2.4302, Lag order = 14, p-value = 0.3962
alternative hypothesis: stationaryadf.test(thg_return)
Augmented Dickey-Fuller Test
data: thg_return
Dickey-Fuller = -16.115, Lag order = 14, p-value = 0.01
alternative hypothesis: stationarykpss.test(thg_return) #Ho: stationary
KPSS Test for Level Stationarity
data: thg_return
KPSS Level = 0.20872, Truncation lag parameter = 9, p-value = 0.1normalTest(thg$THG, method = c("jb")) #Ho:normal distribution
Title:
Jarque-Bera Normality Test
Test Results:
STATISTIC:
X-squared: 367.8988
P VALUE:
Asymptotic p Value: < 2.2e-16 normalTest(thg_return, method = c("jb")) #Ho:normal distribution
Title:
Jarque-Bera Normality Test
Test Results:
STATISTIC:
X-squared: 1178.185
P VALUE:
Asymptotic p Value: < 2.2e-16 - Kiểm tra tự tương quan bằng đồ thị và bằng kiểm định
acf(thg_return)
pacf(thg_return)
Box.test(thg_return, lag = 10) # H0: no autocorrelation
Box-Pierce test
data: thg_return
X-squared = 12.152, df = 10, p-value = 0.275Box.test(thg_return, lag = 10, type = c("Ljung-Box")) # H0: no autocorrelation
Box-Ljung test
data: thg_return
X-squared = 12.184, df = 10, p-value = 0.2729- Ước lượng mô hình ARIMA
# 8.1. Xây dựng mô hình AR
pacf(thg_return)
m1 <- ar(thg_return, type = c("mle"))
m1
Call:
ar(x = thg_return, type = c("mle"))
Order selected 0 sigma^2 estimated as 0.0005376names(m1) [1] "order" "ar" "var.pred" "x.mean" "aic"
[6] "n.used" "n.obs" "order.max" "partialacf" "resid"
[11] "method" "series" "frequency" "call" m1$aic 0 1 2 3 4 5 6 7
0.000000 1.957739 3.933965 5.429070 1.538159 3.448909 5.448518 7.415318
8 9 10 11 12 13 14 15
9.370438 10.767022 7.887608 8.128206 10.112239 9.110773 10.347335 10.953062
16 17 18 19 20 21 22 23
10.438664 8.176167 10.145611 11.350266 13.117708 15.052095 14.626021 15.087983
24 25 26 27 28 29 30 31
16.526684 18.453771 20.320350 21.807865 23.798609 24.632229 26.162760 27.959515
32 33 34 35
29.716350 30.720615 31.955061 33.810210 # Ước lượng AR(p)
m21 <- arima(thg_return, order = c(0, 0, 0))
m21
Call:
arima(x = thg_return, order = c(0, 0, 0))
Coefficients:
intercept
0.0012
s.e. 0.0004
sigma^2 estimated as 0.0005375: log likelihood = 7819.49, aic = -15634.97# Hàm tính p value
coeftest <- function(model){
coef <- model$coef
se <- sqrt(diag(model$var.coef))
t <- coef / se
p <- 2 * (1 - pnorm(abs(t)))
data.frame(coef, se, t, p)
}
coeftest(m21) coef se t p
intercept 0.00119064 0.0004018828 2.962654 0.003049992# Kiểm định phần dư
plot(m21$residuals, type = "l")
qqplot(m21$residuals, thg_return)
Box.test(m21$residuals, lag = 10)
Box-Pierce test
data: m21$residuals
X-squared = 12.152, df = 10, p-value = 0.2759.1. Kiểm định hiệu ứng ARCH (ARCH-LM test)
library(fGarch)
m4 <- garchFit(~ arma(0,0) + garch(1,0), data = thg_return, trace = FALSE)
summary(m4)
Title:
GARCH Modelling
Call:
garchFit(formula = ~arma(0, 0) + garch(1, 0), data = thg_return,
trace = FALSE)
Mean and Variance Equation:
data ~ arma(0, 0) + garch(1, 0)
<environment: 0x0000026d11c97cb8>
[data = thg_return]
Conditional Distribution:
norm
Coefficient(s):
mu omega alpha1
0.00075296 0.00040365 0.25296629
Std. Errors:
based on Hessian
Error Analysis:
Estimate Std. Error t value Pr(>|t|)
mu 7.530e-04 3.736e-04 2.015 0.0439 *
omega 4.037e-04 1.214e-05 33.259 <2e-16 ***
alpha1 2.530e-01 2.528e-02 10.007 <2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Log Likelihood:
7942.494 normalized: 2.382272
Description:
Tue Jun 9 22:07:39 2026 by user: Admin
Standardised Residuals Tests:
Statistic p-Value
Jarque-Bera Test R Chi^2 2434.6275306 0.0000000
Shapiro-Wilk Test R W 0.9334399 0.0000000
Ljung-Box Test R Q(10) 9.5681993 0.4791569
Ljung-Box Test R Q(15) 14.5663211 0.4830827
Ljung-Box Test R Q(20) 22.0398927 0.3383499
Ljung-Box Test R^2 Q(10) 164.7189049 0.0000000
Ljung-Box Test R^2 Q(15) 214.7518202 0.0000000
Ljung-Box Test R^2 Q(20) 249.8555175 0.0000000
LM Arch Test R TR^2 121.2976047 0.0000000
Information Criterion Statistics:
AIC BIC SIC HQIC
-4.762744 -4.757244 -4.762746 -4.760776 9.2. Ước lương ARIMA + GARCH (chọn bậc p, q hợp lý)
m5 <-garchFit(~ arma(0,0) + garch(1,1), data = thg_return, trace = FALSE)
summary(m5)
Title:
GARCH Modelling
Call:
garchFit(formula = ~arma(0, 0) + garch(1, 1), data = thg_return,
trace = FALSE)
Mean and Variance Equation:
data ~ arma(0, 0) + garch(1, 1)
<environment: 0x0000026d13a86a90>
[data = thg_return]
Conditional Distribution:
norm
Coefficient(s):
mu omega alpha1 beta1
8.7747e-04 2.5689e-05 1.2517e-01 8.2955e-01
Std. Errors:
based on Hessian
Error Analysis:
Estimate Std. Error t value Pr(>|t|)
mu 8.775e-04 3.279e-04 2.676 0.00745 **
omega 2.569e-05 4.401e-06 5.837 5.33e-09 ***
alpha1 1.252e-01 1.579e-02 7.925 2.22e-15 ***
beta1 8.295e-01 2.062e-02 40.239 < 2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Log Likelihood:
8159.368 normalized: 2.447321
Description:
Tue Jun 9 22:07:39 2026 by user: Admin
Standardised Residuals Tests:
Statistic p-Value
Jarque-Bera Test R Chi^2 5274.8924502 0.0000000
Shapiro-Wilk Test R W 0.9367452 0.0000000
Ljung-Box Test R Q(10) 5.0046653 0.8908662
Ljung-Box Test R Q(15) 8.1095034 0.9193175
Ljung-Box Test R Q(20) 16.8429706 0.6631454
Ljung-Box Test R^2 Q(10) 5.5530543 0.8513132
Ljung-Box Test R^2 Q(15) 10.1099259 0.8127689
Ljung-Box Test R^2 Q(20) 13.7457721 0.8431484
LM Arch Test R TR^2 9.3595705 0.6719501
Information Criterion Statistics:
AIC BIC SIC HQIC
-4.892242 -4.884910 -4.892245 -4.889619 predict(m5, 5) meanForecast meanError standardDeviation
1 0.0008774678 0.01353233 0.01353233
2 0.0008774678 0.01416053 0.01416053
3 0.0008774678 0.01473531 0.01473531
4 0.0008774678 0.01526389 0.01526389
5 0.0008774678 0.01575198 0.01575198- Tính và dự báo VaR
# Chạy hàm Loss để tính VaR
nreturn_thg <- - thg_return
# 10.1. Ước tính VaR theo Risk Metrics
# Cách 1: Tính thủ công
library(rugarch)
spec1 <- ugarchspec(mean.model = list(armaOrder=c(0,0)),
variance.model = list(model="iGARCH", garchOrder=c(1,1)))
m6 <- ugarchfit(spec=spec1,data = nreturn_thg)
Box.test(residuals(m6, standardize=TRUE), lag=10, type="Ljung")
Box-Ljung test
data: residuals(m6, standardize = TRUE)
X-squared = 5.4724, df = 10, p-value = 0.8575# H0: no autocorrelation
# Dự báo mean và variance (1 ngày):
ugarchforecast(m6, n.ahead = 1)
*------------------------------------*
* GARCH Model Forecast *
*------------------------------------*
Model: iGARCH
Horizon: 1
Roll Steps: 0
Out of Sample: 0
0-roll forecast [T0=1979-02-17]:
Series Sigma
T+1 -0.000836 0.01234# Tính VaR (Phương pháp của JP Morgan xem mean = 0):
VaR1 <- 0 + qnorm(0.95) * 0.01234
# Cách 2: tính từ RMeasure.R
setwd("D:\\meeee\\Đại học\\HK2 năm 3\\QTRR TÀI CHÍNH")
source("RMeasure.R")
VaR2 <- RMeasure(0, 0.01234)
Risk Measures for selected probabilities:
prob VaR ES
[1,] 0.950 0.02029749 0.02545388
[2,] 0.990 0.02870713 0.03288874
[3,] 0.999 0.03813347 0.04154989# 10.2. Ước tính VaR theo ECONOMICTRICS
m7 <- garchFit(~ arma(0,0) + garch(1,1), data = nreturn_thg, trace=F)
summary(m7)
Title:
GARCH Modelling
Call:
garchFit(formula = ~arma(0, 0) + garch(1, 1), data = nreturn_thg,
trace = F)
Mean and Variance Equation:
data ~ arma(0, 0) + garch(1, 1)
<environment: 0x0000026cd9d15d98>
[data = nreturn_thg]
Conditional Distribution:
norm
Coefficient(s):
mu omega alpha1 beta1
-8.7747e-04 2.5689e-05 1.2517e-01 8.2955e-01
Std. Errors:
based on Hessian
Error Analysis:
Estimate Std. Error t value Pr(>|t|)
mu -8.775e-04 3.279e-04 -2.676 0.00745 **
omega 2.569e-05 4.401e-06 5.837 5.33e-09 ***
alpha1 1.252e-01 1.579e-02 7.925 2.22e-15 ***
beta1 8.295e-01 2.062e-02 40.239 < 2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Log Likelihood:
8159.368 normalized: 2.447321
Description:
Tue Jun 9 22:07:40 2026 by user: Admin
Standardised Residuals Tests:
Statistic p-Value
Jarque-Bera Test R Chi^2 5274.8923886 0.0000000
Shapiro-Wilk Test R W 0.9367452 0.0000000
Ljung-Box Test R Q(10) 5.0046653 0.8908662
Ljung-Box Test R Q(15) 8.1095034 0.9193175
Ljung-Box Test R Q(20) 16.8429707 0.6631454
Ljung-Box Test R^2 Q(10) 5.5530543 0.8513132
Ljung-Box Test R^2 Q(15) 10.1099258 0.8127689
Ljung-Box Test R^2 Q(20) 13.7457722 0.8431484
LM Arch Test R TR^2 9.3595705 0.6719501
Information Criterion Statistics:
AIC BIC SIC HQIC
-4.892242 -4.884910 -4.892245 -4.889619 predict(m7, 1) meanForecast meanError standardDeviation
1 -0.0008774678 0.01353233 0.01353233#Tính VaR
VaR3 <- -0.0008774678 + qnorm(0.95)*0.01353233
# 10.3. Ước lượng QUANTILE ESTIMATION
VaR4 <- quantile(nreturn_thg, 0.95)
# 10.4. Ước lượng MONTE CARLO SIMULATION
mean_thg <- mean(nreturn_thg)
sd_thg <- sd(nreturn_thg)
# Tiến hành mô phỏng Monte Carlo
set.seed(42)
sim1 <- rnorm(10000, mean = mean_thg, sd = sd_thg)
ts.plot(sim1)
VaR5 <- quantile(sim1, 0.95)- VaR theo số tiền
VaR1_100 = VaR1*100000
VaR1_100[1] 2029.749VaR3_100 = VaR3*100000
VaR3_100[1] 2138.123VaR4_100 = VaR4*100000
VaR4_100 95%
4190.881 VaR5_100 = VaR5*100000
VaR5_100 95%
3699.63