#Calling the packages 
library(quantmod)
## Loading required package: xts
## Loading required package: zoo
## 
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric
## Loading required package: TTR
## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo
library(ggplot2)
#Fetching the Stock prices data
quantmod::getSymbols("AMZN",from="2018-02-01",to="2023-02-01",src="yahoo")
## [1] "AMZN"
#Plotting the time sereies chart of the data
ggplot(data = AMZN, aes(x=index(AMZN), y=AMZN$AMZN.Close))+geom_line(colour="blue")+ labs(title = "Amazon stock Closing price 2018-2024", x="Date",y="Daily closing prices")
## Don't know how to automatically pick scale for object of type <xts/zoo>.
## Defaulting to continuous.

#computing daily close log returns
AMZN$log_returns<-diff(log(AMZN$AMZN.Close))
#Plotting Daily close log returns
ggplot(data = AMZN, aes(x=index(AMZN), y= log_returns))+ geom_line(color="red")+labs(title = "Amazon Stock daily log returns", x="Date", y="log returns")
## Warning: Removed 1 row containing missing values (`geom_line()`).

#commenting on the chart. As it shows in the plot, the log return of stock is not stationary. Approximately the mean is 0, but the volatility seems to be random.

#Question d i)
#presence of correlation tests
#carrying out Autocorrelation tests
acf(AMZN$AMZN.Close,lag.max = 10)

#PACF test
pacf(AMZN$AMZN.Close, lag.max = 10)

#commenting on both tests.An outcome closely around 2 means a very low level of autocorrelation. An outcome closer to 0 suggests a stronger positive autocorrelation, and an outcome closer to 4 suggests a stronger negative autocorrelation. In our case daily stock closing prices of Amazon are strongly correlated. For PACF Large spike at lag 1 that decreases on the latter lags.

#Calling required library
library(tseries)


# Question d ii) 
#Asymmetry test
#jarque.bera.test
jarque.bera.test(AMZN$AMZN.Close)
## 
##  Jarque Bera Test
## 
## data:  AMZN$AMZN.Close
## X-squared = 139.57, df = 2, p-value < 2.2e-16
#Commenting. A p-value less than the significance level (usually set at 0.05) indicates that the null hypothesis should be rejected and the data does not follow a normal distribution. In our case we got p-value < 2.2e-16. Therefore the data does not follow normal distribution. Hence the stock for Amazon between the period is asymmetric


#question d iii)
#fat tail test
#Shapiro.test failed to run so we did not include it
#plotting a histogram to show kurtosis and skewness
hist(AMZN$AMZN.Close)

#commenting on the histogram. From the diagram, it is clear that the data is not normally distributed hence data is fat tailed



#question d iv)
#Augmented dicky fuller test
adf.test(AMZN$AMZN.Close)
## 
##  Augmented Dickey-Fuller Test
## 
## data:  AMZN$AMZN.Close
## Dickey-Fuller = -1.0624, Lag order = 10, p-value = 0.9287
## alternative hypothesis: stationary
#Commenting on it.The augmented Dickey–Fuller (ADF) statistic, used in the test, is Dickey-Fuller = -1.7618 a negative number. The more negative it is, the stronger the rejection of the hypothesis that there is a unit root at some level of confidence. It has a  Lag order = 11, p-value = 0.6791 alternative hypothesis: stationary. Stationary series indicate absence of leverage effect.
Box.test(AMZN$AMZN.Close, lag=10, type = "Ljung-Box")
## 
##  Box-Ljung test
## 
## data:  AMZN$AMZN.Close
## X-squared = 12116, df = 10, p-value < 2.2e-16
#commenting on test . p-value < 2.2e-16 indicate absence of leverage effect.



#question d v)
#volatilty clustering
garch(AMZN$AMZN.Close, lags.multi= c(5,10,15))
## 
##  ***** ESTIMATION WITH ANALYTICAL GRADIENT ***** 
## 
## 
##      I     INITIAL X(I)        D(I)
## 
##      1     1.106003e+03     1.000e+00
##      2     5.000000e-02     1.000e+00
##      3     5.000000e-02     1.000e+00
## 
##     IT   NF      F         RELDF    PRELDF    RELDX   STPPAR   D*STEP   NPRELDF
##      0    1  9.351e+03
##      1    2  6.626e+03  2.91e-01  3.74e+00  4.5e-04  3.5e+04  1.0e+00  6.54e+04
##      2    4  6.616e+03  1.45e-03  1.34e-03  2.3e-05  2.0e+00  5.0e-02  2.56e+00
##      3    5  6.602e+03  2.21e-03  2.19e-03  3.6e-05  2.8e+00  1.0e-01  5.52e-03
##      4    6  6.599e+03  4.40e-04  7.93e-04  8.8e-05  1.5e+00  2.0e-01  1.00e-03
##      5    7  6.598e+03  8.34e-05  1.40e-04  6.5e-05  0.0e+00  1.7e-01  1.40e-04
##      6   10  6.598e+03  3.04e-07  3.04e-07  3.9e-08  7.7e+01  1.1e-04  1.18e-05
##      7   12  6.598e+03  6.02e-07  6.02e-07  7.9e-08  1.7e+01  2.3e-04  2.13e-05
##      8   14  6.598e+03  1.19e-07  1.19e-07  1.6e-08  3.1e+02  4.6e-05  2.07e-05
##      9   16  6.598e+03  2.37e-07  2.37e-07  3.1e-08  3.9e+01  9.2e-05  2.06e-05
##     10   19  6.598e+03  4.73e-09  4.73e-09  6.3e-10  7.6e+03  1.8e-06  2.04e-05
##     11   21  6.598e+03  9.46e-10  9.46e-10  1.3e-10  3.8e+04  3.7e-07  2.04e-05
##     12   23  6.598e+03  1.89e-09  1.89e-09  2.5e-10  4.8e+03  7.4e-07  2.04e-05
##     13   25  6.598e+03  3.78e-10  3.78e-10  5.0e-11  9.5e+04  1.5e-07  2.03e-05
##     14   27  6.598e+03  7.56e-10  7.56e-10  1.0e-10  1.2e+04  2.9e-07  2.03e-05
##     15   29  6.598e+03  1.51e-09  1.51e-09  2.0e-10  6.0e+03  5.9e-07  2.03e-05
##     16   31  6.598e+03  3.03e-10  3.03e-10  4.0e-11  1.2e+05  1.2e-07  2.03e-05
##     17   33  6.598e+03  6.05e-11  6.05e-11  8.1e-12  6.0e+05  2.4e-08  2.03e-05
##     18   35  6.598e+03  1.21e-10  1.21e-10  1.6e-11  7.4e+04  4.7e-08  2.03e-05
##     19   37  6.598e+03  2.42e-11  2.42e-11  3.2e-12  1.5e+06  9.4e-09  2.03e-05
##     20   39  6.598e+03  4.84e-12  4.84e-12  6.4e-13  7.4e+06  1.9e-09  2.03e-05
##     21   41  6.598e+03  9.68e-12  9.68e-12  1.3e-12  9.3e+05  3.8e-09  2.03e-05
##     22   43  6.598e+03  1.94e-12  1.94e-12  2.6e-13  1.9e+07  7.5e-10  2.03e-05
##     23   46  6.598e+03 -1.52e+06  3.87e-14  5.2e-15  9.3e+08  1.5e-11  2.03e-05
## 
##  ***** FALSE CONVERGENCE *****
## 
##  FUNCTION     6.598208e+03   RELDX        5.160e-15
##  FUNC. EVALS      46         GRAD. EVALS      23
##  PRELDF       3.872e-14      NPRELDF      2.035e-05
## 
##      I      FINAL X(I)        D(I)          G(I)
## 
##      1    1.106001e+03     1.000e+00     2.277e-03
##      2    9.273068e-01     1.000e+00     1.107e+01
##      3    8.728749e-12     1.000e+00     1.286e+01
## 
## Call:
## garch(x = AMZN$AMZN.Close, lags.multi = c(5, 10, 15))
## 
## Coefficient(s):
##        a0         a1         b1  
## 1.106e+03  9.273e-01  8.729e-12