library(quantmod)
## Warning: package 'quantmod' was built under R version 3.5.3
## Loading required package: xts
## Loading required package: zoo
## Warning: package 'zoo' was built under R version 3.5.3
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
## Loading required package: TTR
## Version 0.4-0 included new data defaults. See ?getSymbols.
library(stargazer)
##
## Please cite as:
## Hlavac, Marek (2018). stargazer: Well-Formatted Regression and Summary Statistics Tables.
## R package version 5.2.2. https://CRAN.R-project.org/package=stargazer
library(MASS)
## Warning: package 'MASS' was built under R version 3.5.3
library(fPortfolio)
## Warning: package 'fPortfolio' was built under R version 3.5.3
## Loading required package: timeDate
## Loading required package: timeSeries
##
## Attaching package: 'timeSeries'
## The following object is masked from 'package:zoo':
##
## time<-
## Loading required package: fBasics
## Warning: package 'fBasics' was built under R version 3.5.3
##
## Attaching package: 'fBasics'
## The following object is masked from 'package:TTR':
##
## volatility
## Loading required package: fAssets
library(forecast)
## Warning: package 'forecast' was built under R version 3.5.3
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 3.5.3
startDate = as.Date("2001-01-01") #Specify period of time we are interested in
endDate = as.Date("2019-06-20")
getSymbols('GDX',src='yahoo',from = startDate, to = endDate)
## 'getSymbols' currently uses auto.assign=TRUE by default, but will
## use auto.assign=FALSE in 0.5-0. You will still be able to use
## 'loadSymbols' to automatically load data. getOption("getSymbols.env")
## and getOption("getSymbols.auto.assign") will still be checked for
## alternate defaults.
##
## This message is shown once per session and may be disabled by setting
## options("getSymbols.warning4.0"=FALSE). See ?getSymbols for details.
## [1] "GDX"
#quantmod default chart.
chartSeries(GDX)
GDXreturns<-dailyReturn(GDX,type='log')
# PLOTS
# Plot 1: Histogram
#h <- hist(GDXreturns,
# prob = TRUE, # Flipside of "freq = FALSE"
# main = "GDX Returns Histogram")
x = GDXreturns
tmp <- density(x)
truehist(GDXreturns, prob = TRUE, ylim = c(0, max(tmp$y)),main = "GDX Returns Histogram")
# Plot 2: Normal curve (if prob = TRUE)
curve(dnorm(x, mean = mean(GDXreturns), sd = sd(GDXreturns)),
col = "red",
lwd = 3,
add = TRUE)
curve( dt(x, df=15), add=TRUE, col='blue' )
lines(density(GDXreturns, adjust = 2), lwd = 2, col = "Blue")
#creates a frequency table from GDX data
factorx <- factor(cut(GDXreturns, breaks=nclass.Sturges(GDXreturns)))
#TGDXulate and turn into data.frame
xoutGDX <- as.data.frame(table(factorx))
#Add cumFreq and proportions
xoutGDX <- transform(xoutGDX, cumFreq = cumsum(Freq), relative = prop.table(Freq))
# regression library which outputs nice simple rounded row summary data alernative to summarry command
library(stargazer)
summary(GDXreturns)
## Index daily.returns
## Min. :2006-05-22 Min. :-1.688e-01
## 1st Qu.:2009-08-26 1st Qu.:-1.413e-02
## Median :2012-12-03 Median :-8.223e-05
## Mean :2012-12-03 Mean :-1.275e-04
## 3rd Qu.:2016-03-11 3rd Qu.: 1.394e-02
## Max. :2019-06-19 Max. : 2.354e-01
stargazer(GDXreturns,type = "text",summary = TRUE)
##
## ===================================================================
## Statistic N Mean St. Dev. Min Pctl(25) Pctl(75) Max
## -------------------------------------------------------------------
## daily.returns 3,292 -0.0001 0.026 -0.169 -0.014 0.014 0.235
## -------------------------------------------------------------------
library(fPortfolio)
#write.csv(GDXreturns, file = "181223GDXreturns.csv")
#fportfolio Cvar calc
cv = cvarRisk(GDXreturns,1,alpha = .01)
cv
## CVaR.1%
## -0.09506055
#write.csv(xoutGDX,file = "GDX_freq231218.csv")
#last GDX data
endGDX = last(GDX)
endGDX
## GDX.Open GDX.High GDX.Low GDX.Close GDX.Volume GDX.Adjusted
## 2019-06-19 23.52 24.03 23.45 24 46225800 24
#Cvar drawdown estimate
Potential_Avalanche = endGDX[,6]*cv
Potential_Avalanche
## GDX.Adjusted
## 2019-06-19 -2.281453
#worst Cvar drawdown outcome estimate
Possible_Worst_case = endGDX[,6]+Potential_Avalanche
Possible_Worst_case
## GDX.Adjusted
## 2019-06-19 21.71855
library(pracma)
## Warning: package 'pracma' was built under R version 3.5.3
##
## Attaching package: 'pracma'
## The following objects are masked from 'package:fBasics':
##
## akimaInterp, inv, kron, pascal
hurstexp(GDXreturns)
## Simple R/S Hurst estimation: 0.5020807
## Corrected R over S Hurst exponent: 0.5124296
## Empirical Hurst exponent: 0.5001093
## Corrected empirical Hurst exponent: 0.4689422
## Theoretical Hurst exponent: 0.5311854
lastRtn <- last(GDXreturns)
lastRtn
## daily.returns
## 2019-06-19 0.01384541
#GDX_opt = getOptionChain("GDX","2019-02-15")
#view(puts)
#puts
#GDX_opt$puts
head(GDX)
## GDX.Open GDX.High GDX.Low GDX.Close GDX.Volume GDX.Adjusted
## 2006-05-22 36.52 37.29 35.87 37.23 197100 34.28022
## 2006-05-23 37.75 39.22 37.75 37.96 620900 34.95239
## 2006-05-24 37.13 37.57 35.87 36.52 638600 33.62648
## 2006-05-25 37.18 38.32 36.98 38.32 367000 35.28387
## 2006-05-26 38.74 38.74 37.77 38.55 269400 35.49564
## 2006-05-30 39.50 39.72 38.11 38.17 559100 35.14574
Adj<-GDX$GDX.Adjusted
head(Adj)
## GDX.Adjusted
## 2006-05-22 34.28022
## 2006-05-23 34.95239
## 2006-05-24 33.62648
## 2006-05-25 35.28387
## 2006-05-26 35.49564
## 2006-05-30 35.14574
fit<-auto.arima(Adj)
fcstfit=forecast(fit,h=20)
autoplot(fcstfit)
summary(fcstfit)
##
## Forecast method: ARIMA(0,1,0)
##
## Model Information:
## Series: Adj
## ARIMA(0,1,0)
##
## sigma^2 estimated as 0.6956: log likelihood=-4072.43
## AIC=8146.85 AICc=8146.85 BIC=8152.95
##
## Error measures:
## ME RMSE MAE MPE MAPE
## Training set -0.003112377 0.8338959 0.5994007 -0.04531639 1.891871
## MASE ACF1
## Training set 0.9997136 -0.007755313
##
## Forecasts:
## Point Forecast Lo 80 Hi 80 Lo 95 Hi 95
## 3293 24 22.93116 25.06884 22.36535 25.63465
## 3294 24 22.48843 25.51157 21.68825 26.31175
## 3295 24 22.14871 25.85129 21.16870 26.83130
## 3296 24 21.86231 26.13769 20.73069 27.26931
## 3297 24 21.60999 26.39001 20.34480 27.65520
## 3298 24 21.38188 26.61812 19.99593 28.00407
## 3299 24 21.17211 26.82789 19.67511 28.32489
## 3300 24 20.97686 27.02314 19.37650 28.62350
## 3301 24 20.79347 27.20653 19.09604 28.90396
## 3302 24 20.62002 27.37998 18.83077 29.16923
## 3303 24 20.45505 27.54495 18.57847 29.42153
## 3304 24 20.29742 27.70258 18.33739 29.66261
## 3305 24 20.14623 27.85377 18.10617 29.89383
## 3306 24 20.00076 27.99924 17.88368 30.11632
## 3307 24 19.86039 28.13961 17.66901 30.33099
## 3308 24 19.72463 28.27537 17.46138 30.53862
## 3309 24 19.59305 28.40695 17.26015 30.73985
## 3310 24 19.46528 28.53472 17.06475 30.93525
## 3311 24 19.34102 28.65898 16.87471 31.12529
## 3312 24 19.21999 28.78001 16.68960 31.31040
res=residuals(fcstfit)
hist(res)
autoplot(res)
GDXacf = acf(res)
autoplot(GDXacf)
rwf(Adj)
## Point Forecast Lo 80 Hi 80 Lo 95 Hi 95
## 3293 24 22.93116 25.06884 22.36535 25.63465
## 3294 24 22.48843 25.51157 21.68825 26.31175
## 3295 24 22.14871 25.85129 21.16870 26.83130
## 3296 24 21.86231 26.13769 20.73069 27.26931
## 3297 24 21.61000 26.39000 20.34480 27.65520
## 3298 24 21.38188 26.61812 19.99593 28.00407
## 3299 24 21.17211 26.82789 19.67511 28.32489
## 3300 24 20.97686 27.02314 19.37650 28.62350
## 3301 24 20.79347 27.20653 19.09604 28.90396
## 3302 24 20.62002 27.37998 18.83077 29.16923
drifted = rwf(Adj,drift = TRUE)
autoplot(drifted)
yearlag1 <- GDXreturns["2018-6/2019-6-19"]
x = yearlag1
tmp <- density(x)
truehist(GDXreturns, prob = TRUE, ylim = c(0, max(tmp$y)),main = "GDX Returns Histogram")
# Plot 2: Normal curve (if prob = TRUE)
curve(dnorm(x, mean = mean(yearlag1), sd = sd(yearlag1)),
col = "red",
lwd = 3,
add = TRUE)
curve( dt(x, df=15), add=TRUE, col='blue' )
lines(density(yearlag1, adjust = 2), lwd = 2, col = "Blue")
cv1yr = cvarRisk(yearlag1,1,alpha = .01)
cv1yr
## CVaR.1%
## -0.05501061
last<- last(GDX[,6])
drawdown <- last*cv1yr
last
## GDX.Adjusted
## 2019-06-19 24
crash <-last+drawdown
crash
## GDX.Adjusted
## 2019-06-19 22.67975