Does Implied Volatility Predict Future Realized Volatility?

Posted on Apr 30, 2016

Contributed by Zach Escalante. He  is currently in the NYC Data Science Academy 12 week full time Data Science Bootcamp program taking place between April 11th to July 1st, 2016. This post is based on his first class project - R  Visualization (due on the 2th week of the program).


The question of whether implied volatility (IV) is a precursor to future realized volatility (RV) of assets has been the subject of much academic research (1). My goal in doing this analysis was to see if we could visually ascertain whether data in exchange rate between the Brazilian Real  (BRL) and United States Dollar (USD) lends itself to supporting our hypothesis that IV is a forerunner to RV.

The reason I have decided to use BRL/USD as the asset on which we will conduct our analysis is that since the time of the 2008 financial crisis, much of the movement in currencies has been the result of central bank (CB) policies and decisions. This has created a binary atmosphere in currency markets where FX rates of large, highly credit-worthy countries (think Japan, Germany, the US or Britain) are ultimately predicated upon whether that country's CB decides to pursue a tighter/looser monetary policy. A contrast to this is Brazil,  where notable geo-political events (including the potential impeachment of their current president, Dilma Rousseff) outside the scope of local central bank policy have been significant factors in the movements in BRL, and have introduced an additional source of volatility.

Exploratory Data Analysis:

The data set that I used to conduct my analysis was the three month historical IV (3MIV) and three month historical RV (3MRV). This was obtained from Bloomberg L.P. and can only be accessed with a paid subscription to Bloomberg. The first charts I produced were the last years' BRL/USD FX rate, and the last years' 3MIV vs 3MRV:


We see from the graph of BRLUSD over the past year that the BRL bottomed in value against the USD around October of 2015 and then fell back that level again in January of 2016 after having briefly strengthened in between. Since January it has risen from just over 4:1 against the USD to just under 3.6:1. This is still well below the 3:1 level it touched last Spring.


Over this same time period, we see that volatility was spiking in October of 2015 and January of 2016, concurrent with the BRL touching its lowest levels. We also see that the 3MIV seems to precede 3MRV directionally on at least three occasions (circled in red).

At this point, it became clear that more historical observations would be necessary in order to see if this relationship persisted, or was a recent phenomenon specifically related to the impeachment proceedings of Dilma Rousseff. To analyze this, I obtained the past five years data of 3MIV and 3MHV and created this bar chart:


We see here that on at least seven occasion a rise in 3MRV is precede by a spike in 3MIV over the past five years. I find this to be a very interesting phenomenon which should be explored further.


My conclusion is that there does exist a relationship between implied volatility and historical volatility for the Brazilian Real should be investigated further. This can clearly be seen from the data collected and graphed in the preceding examples, and should make for some very interesting research questions in the future.

Research Questions for the Future:

These are several questions that are a natural extension of the analysis I have already conducted and would like to explore in the future:

  • Does the volatility skew corresponding with spikes in 3MIV tell us anything about which direction the FX rates moves when 3MRV rises?
  • Can we make any implications regarding the direction of the currency in relation to the ratio of puts to calls?
  • What did movements in Brazilian Equity Indices look like over this time period?
  • Do Brazilian Equity Indices experience similar volatility patterns?

Coding This Project:

To write the code for this project, I first imported a CSV file with all of my data as columns:

ImpVol <- read.csv("IV.csv") 

HistVol <- read.csv("realVol.csv")

Rates <- read.csv("1yr_swaps.csv") 

FX <- read.csv("brlFx.csv")

Then used the 'merge' function to match each of these columns against their corresponding dates:

vol <- merge(iVol, hVol)  #this merged hist imp vol and hist realized vol

One of the more interesting aspects of creating these graphs had to do with plotting time series in the R package ggplot2, which I finally solved in the following manner with the help of the "melt" function in R:

sub <- last_year[, c(1, 4, 8)]     #temporary data frame which received 
subin <- melt(sub, id = "Date")    #which was passed 3MIV & 3MRV data
Vol1516 <- ggplot(subin, aes(x=Date, y=value, colour=variable)) +geom_line() +
scale_colour_manual(values=c("blue","green")) +
ggtitle("BRL Imp Vol vs Hist Vol 2015-2016") +
ylab(" ")

Thank you for taking the time to read this blog post! If you have questions, comments or suggestions, please feel free to reach out and provide your feedback.

The complete code is included below:

 ImpVol <- read.csv("IV.csv")
 HistVol <- read.csv("realVol.csv")
 Rates <- read.csv("1yr_swaps.csv")
 FX <- read.csv("brlFx.csv")
 #Remove the first 6 rows of FX data frame
 FX <- FX[-c(1:6),]
 colnames(FX) <- c("Date", "BRL") #Change the column names
#Remove the first 5 rows of Rates data frame
 Rates <- Rates[-c(1:6),-c(3:4)] #Delete rows 1-6 and columns 3-4
 colnames(Rates) <- c("Date", "iRate")
#Remove first columns 1, 5, 8 of ImpVol
 iVol <- ImpVol[,-c(1, 5, 8)]
#Remove x bland of HistVol
 hVol <- HistVol[, -c(1, 5, 8)]
vol <- merge(iVol, hVol)
 vol <- vol[-1,]
#At this point each of the csv files has been loaded as a dataframe
 #and we now have to combine the data. We have already combined the
 #implied volatility data since those two data frames were identical
 #and this will cut down on data manipulation. Next we need to cut the
 #Date columns so that they match and we can use join/merge functions
 #in order to create one large data frame with all of our data
#Delete the leading zero for dates in the 'Date' column of 'vol' dataframe
#Convert the 'Date' column from factor -> character
 vol[,1] <- as.character(vol$Date)
#Convert the 'Date' column for Rates from factor -> character
 Rates[,1] <- as.character(Rates$Date)
 Rates[,2] <- as.numeric(as.character(Rates$iRate))
##Convert the 'Date' column for FX from factor -> character
 FX[,1] <- as.character(FX$Date)
 FX[,2] <- as.numeric(as.character(FX$BRL))
#Run a for loop to concatenate the strings with leading zeros
 #and remove leading zeros for the day value
for(i in 1:nrow(vol))
 if(substring(vol$Date[i], 1,1) == '0')
 vol$Date[i] = substr(vol$Date[i], 2, nchar(vol$Date[i]))
 } else{vol$Date[i] = vol$Date[i]}
 vol$Date[i] = sub("/0", "/", vol$Date[i])
brl_data <- merge(vol, Rates) #Finish mergin the data
 brl_data <- merge(brl_data, FX)
 brl_data$Date <- as.Date(brl_data$Date, "%m/%d/%Y") #conver the 'Date' column to 'date' format
 class(brl_data$Date) #show that the new class is 'date'
clean<-arrange(brl_data, desc(Date))
last_year <- clean[1:252,]
 last_year2 <- clean[253:500,]
#Create graphs
#2014/2015 Implied Vol vs Hist Vol.
 sub <- last_year2[, c(1, 4, 8)]
 subin <- melt(sub, id = "Date")
 Vol1415 <- ggplot(subin) + geom_line(aes(x=Date, y=value, colour=variable)) +
 scale_colour_manual(values=c("blue","green")) +
 ggtitle("BRL Imp Vol vs Hist Vol 2014-2015") +
 ylab(" ")
#FX Graph for 2014/2015
 FX1415 <- ggplot(last_year2, aes(x=Date, y=BRL)) +
 geom_line(color = "dark green") +
 ggtitle("BRLUSD 2014-2015")
#2015/2016 Implied Vol vs Hist Vol.
 sub <- last_year[, c(1, 4, 8)]
 subin <- melt(sub, id = "Date")
 Vol1516 <- ggplot(subin, aes(x=Date, y=value, colour=variable)) + geom_line() +
 scale_colour_manual(values=c("blue","green")) +
 ggtitle("BRL Imp Vol vs Hist Vol 2015-2016") +
 ylab(" ")
#FX Graph for 2015/2016
 FX1516 <- ggplot(last_year, aes(x=Date, y=BRL)) +
 geom_line(color = "dark green") +
 ggtitle("BRLUSD 2015-2016")
#2015/2016 Volatitily Bar Chart
 sub <- last_year[, c(1, 4, 8)]
 subin <- melt(sub, id = "Date")
 ggplot(subin, aes(x=Date, y = value, fill = variable)) +
 geom_bar(stat = "identity", position = "dodge") +
 scale_fill_discrete(name = "Volatility") +
 ggtitle("Hist vs Implied Volatility") +
 scale_fill_manual(values = c("blue", "green"))
#Historic Volatitily Bar Chart
 sub <- clean[, c(1, 4, 8)]
 subin <- melt(sub, id = "Date")
 HistVol <- ggplot(subin, aes(x=Date, y = value, fill = variable)) +
 geom_bar(stat = "identity", position = "dodge") +
 scale_fill_discrete(name = "Volatility") +
 ggtitle("Hist vs Implied Volatility") +
 scale_fill_manual(values = c("blue", "green"))
#Historic Vol comparison - Line Chart
 tmp <- clean[,c(1, 4, 8)]
 tmp2 <-melt(tmp, id = "Date")
 volHist <- ggplot(tmp2) + geom_line(aes(x=Date, y=value, colour=variable)) +
 scale_colour_manual(values=c("blue","green")) +
 scale_fill_discrete(name = "Volatility") +
 ggtitle("Hist Volatility Comparison") +
 ylab(" ")
#Historic FX Chart
 FXHist <- ggplot(clean, aes(x=Date, y=BRL)) +
 geom_line(color = "dark green") +
 ggtitle("Historic FX Chart")

About Author

Zachary Escalante

Zach Escalante's path to the field of Data Analysis has not been a conventional one. Born and raised in South Florida, Zach did his first bachelor's degree in Finance at Florida Atlantic University (FAU). Following the completion of...
View all posts by Zachary Escalante >

Related Articles

Leave a Comment

James March 15, 2017
Hey I am so happy I found your website, I really found you by error, while I was searching on Digg for something else, Regardless I am here now and would just like to say kudos for a incredible post and a all round thrilling blog (I also love the theme/design), I don't have time to read it all at the minute but I have saved it and also added in your RSS feeds, so when I have time I will be back to read a great deal more, Please do keep up the great job.

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 2020 Revenue 3-points agriculture air quality airbnb airline alcohol Alex Baransky algorithm alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus ames dataset ames housing dataset apartment rent API Application artist aws bank loans beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep boston safety Bundles cake recipe California Cancer Research capstone car price Career Career Day citibike classic cars classpass clustering Coding Course Demo Course Report covid 19 credit credit card crime frequency crops D3.js data data analysis Data Analyst data analytics data for tripadvisor reviews data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization database Deep Learning Demo Day Discount disney dplyr drug data e-commerce economy employee employee burnout employer networking environment feature engineering Finance Financial Data Science fitness studio Flask flight delay gbm Get Hired ggplot2 googleVis H20 Hadoop hallmark holiday movie happiness healthcare frauds higgs boson Hiring hiring partner events Hiring Partners hotels housing housing data housing predictions housing price hy-vee Income Industry Experts Injuries Instructor Blog Instructor Interview insurance italki Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter las vegas airport lasso regression Lead Data Scienctist Lead Data Scientist leaflet league linear regression Logistic Regression machine learning Maps market matplotlib Medical Research Meet the team meetup methal health miami beach movie music Napoli NBA netflix Networking neural network Neural networks New Courses NHL nlp NYC NYC Data Science nyc data science academy NYC Open Data nyc property NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time performance phoenix pollutants Portfolio Development precision measurement prediction Prework Programming public safety PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R Data Analysis R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn seafood type Selenium sentiment analysis sentiment classification Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau teachers team team performance TensorFlow Testimonial tf-idf Top Data Science Bootcamp Top manufacturing companies Transfers tweets twitter videos visualization wallstreet wallstreetbets web scraping Weekend Course What to expect whiskey whiskeyadvocate wildfire word cloud word2vec XGBoost yelp youtube trending ZORI