School of Business publications portal
This portal is no longer updated. Aalto University School of Business Master's Theses are now in the Aaltodoc publication archive (Aalto University institutional repository)
School of Business | Department of Finance | Finance | 2013
Thesis number: 13138
Modeling Intraday Implied Volatility: Evidence From EURO STOXX 50
Author: Tikanoja, Juuso
Title: Modeling Intraday Implied Volatility: Evidence From EURO STOXX 50
Year: 2013  Language: fin
Department: Department of Finance
Academic subject: Finance
Index terms: rahoitus; financing; pörssit; stock exchanges; osakemarkkinat; stock markets; optiot; option; kurssivaihtelut; volatility
Pages: 72
Full text:
» hse_ethesis_13138.pdf pdf  size:2 MB (1061930)
Key terms: Implied volatility; Modeling; Intraday; Patterns; Options; EURO STOXX 50; VSTOXX

PURPOSE OF THE STUDY The objective of this thesis is to study intraday implied volatility with high-frequency observations. Specifically, I study if systematic intradaily and weekly patterns exist in implied volatility of EURO STOXX 50. Furthermore, I study if the implied volatility can be modeled using the possible patterns and time series econometric methods. Additionally, I study if the modeling can provide abnormal economic profits.


The dataset includes over 110 000 observations from VSTOXX, the implied volatility index of EURO STOXX 50 from January 2012 to the end of November 2012. Additionally, I acquire similar time-series of several financial instruments. To test the hypotheses, I study patterns with means and variances of VSTOXX. In addition, I model the data with ARMA family models and with several variables. Furthermore, I try to take advantage of possible patterns in intradaily/weekly implied volatility and use dummy variables in the modeling.


The empirical results of this thesis show that both intradaily and weekly patterns exist in implied volatility. Three possible reasons for the patterns were found: systematic patterns because of the VSTOXX formula misspecification, patterns driven by stock markets and patterns driven by traders. Modeling of implied volatility is found to be possible. ARMA models perform the best with the dataset. Several economic/financial variables are significant. Also, the weekday/time dummies were significant. However, when measuring the directional accuracy of the models, it seems that only ARMA model can forecast the direction and adding external variables is not useful. Even though proper trading simulation was not conducted, it seems that abnormal profits would not be created with models
Electronic publications are subject to copyright. The publications can be read freely and printed for personal use. Use for commercial purposes is forbidden.