2018 SIDE Summer School

2018 SIdE Summer School of Econometrics

Cathy Yi-Hsuan Chen (University of Berlin), Wolfgang Härdle (University of Berlin), Andrew Patton (Duke University), and Kevin Sheppard (Oxford University) will give lectures at the 2018 SIdE Summer School of Econometrics. SIdE is the acronym for the Italian Econometric Association.

The dates of the Summer School are: 

-    from July 16 through July 20 for Text Analysis and Sentiment Analysis (TASA) with Applications to Finance with Wolfgang Härdle and Cathy Yi-Hsuan Chen.

-    from July 23 through July 27 for Recent Developments in Financial Econometrics with Andrew Patton and Kevin Sheppard

-    2017 Students' Evaluations:
  1.             Link to first week evaluation;
  2.             Link to second week

First week
Text Analysis & Sentiment Analysis (TASA) with Applications to Finance


Dates: July 16th - July 20th, 2018

Course Contents

TASA Learning Objectives

Since information mostly exists in language data, the TASA course presents tools and concepts for text data with a strong focus on modeling the econometric effects of language or more specific sentiment.  It presents the decision analytics in a way that is understandable for non-mathematicians and practitioners who are confronted with day to day number crunching statistical textual analysis.  This course details the development of textual analysis and sentiment projection, and compare the pros and cons of them. The TASA course endows the practitioner with ready to use practical tools for these purposes and applications. All practical examples may be recalculated and modified: software and Quantlets  are in www.quantlet.de.


TASA Structure

Data are everywhere and the ubiquitous availability of huge amounts of data makes it necessary to develop smart data analytics.  Out of the plethora of tools that are available for many scientific disciplines this course offers for the common data analyst an easy access to all levels of analysis without deep computer programming knowledge. Python is becoming the lingua franca, and can be easily applied for the analysis involved textual data.  TASA provides a wide variety of exercises, with Python or R step-by-step demonstrations for web-scraping, Natural Language Processing combined with statistical learning methods. 



Franke J, Härdle WK, Hafner C (2015) Statistics of Financial Markets: an Introduction. 4th ed., Springer Verlag, Heidelberg. ISBN: 978-3-642-54538-2

Chen C YH, Härdle WK, Overbeck L (2017) Applied Quantitative Finance. 3rd extended ed., Springer Verlag, Heidelberg.

Härdle WK, Simar L (2015) Applied Multivariate Statistical Analysis. 4th ed., Springer Verlag, Heidelberg. ISBN 978-3-662-45170-0

Härdle WK, Okhrin O, Okhrin Y (2017) Basics of Computational Statistics, Springer Verlag, Heidelberg.

All examples are presented in R or Python. The Quantlets are available here: www.quantlet.de



Unit 1  

What do we see?                     

·              Basic concepts

·              Data Management

·              Structuring Data elements

Unit 2  

Data Analysis                          

·              Natural Language Processing

·              Stemming, lemmatizing

·              DTM Dynamic Topic Modeling

Unit 3  

Modern Data Analysis             

·              Python tools for text mining

·              Text mining in Quantitative Finance

·              Applications & Empirics

Unit 4                 

Modern Data Analytics           

·               Cluster Analysis and Classification

·              Support Vector Machine

·              CRIX a CRypto currency IndeX

Unit 5  

Sentiment Analysis                 

·              Unsupervised projection: lexicon-based

·              Supervised projection: sentence-based

·              News sentiment extraction

·              Crypocurrency-specific lexicon and sentiment projection

Unit 6  

Smart Data Analytics              

·              Financial Risk Meter

·              DDI Networks Topology

·              Q3 D3 LSA

Unit 7  

Very Smart Data Analytics          

·              fraud and scam detection

·              Options on cryptos

·              Adaptive weight clustering

Unit 8  

We do Smart Data Analytics      

·              Machine learning in Economics

·              Deep Learning of Forecasts

·              Complexity in Banking, Scores and Networks

Second week
Recent Developments in Financial Econometrics

Dates: July 23rd - July 27th, 2018

Course description: The course will cover the most recent developments in financial econometrics.

In particular, after setting the stage for the more standard techniques and models for volatility, more sophisticated issues will be covered, including high frequency data, and high-dimensional approaches, semivariances and semicovariances.

We will also see how to implement some of the techniques in R/Matlab/Python.


Topics covered

1.            Univariate volatility models

2.            Multivariate volatility models

3.            MV GARCH models, estimation and testing

4.            High frequency data and volatility forecasting

5.            Realized covariance and kernels, vast kernels

6.            Recent developments in forecasting volatility with high frequency data

7.            Composite likelihood and other high dimensional approaches

8.            Semivariances and semicovariances




Session 1A (Patton): Univariate volatility models

Session 1B (Sheppard): Multivariate volatility models


Session 2A (Sheppard): More sophisticated MV GARCH models, estimation options

Session 2B (Patton): High frequency data and volatility forecasting


Session 3A (Sheppard): Realized covariance and kernels, vast kernels

Session 3B: Group computer assignment session


Session 4A (Patton): Recent developments in forecasting volatility with high frequency data

Session 4B (Sheppard): Composite likelihood and other high dimensional approaches


Session 5A (Patton): Semivariances and semicovariances



Andersen, T.G., and T. Bollerslev, 1998, Answering the skeptics: yes, standard volatility models do provide accurate forecasts, International Economic Review, 39, 885–905.

Andersen, T.G., T. Bollerslev, P.F. Christoffersen, and F.X. Diebold, 2006, Volatility and correlation forecasting. In: G. Elliott, C.W.J. Granger, and A. Timmermann, (Eds.), Handbook of Economic Forecasting. North Holland Press, Amsterdam.

Andersen, T.G., T. Bollerslev, and F.X.Diebold, 2007, Roughing it up: including jump components in the measurement, modeling and forecasting of return volatility, Review of Economics and Statistics, 89, 701–720.

Andersen, T.G., T. Bollerslev, and F.X. Diebold, 2010, Parametric and nonparametric volatility measurement. In: L.P. Hansen and Y. Aït-Sahalia (Eds.), Handbook of Financial Econometrics. North-Holland Press, Amsterdam.

Bollerslev, T., A.J. Patton, and R. Quaedvlieg, 2016, Exploiting the Errors: A Simple Approach for Improved Volatility Forecasting, Journal of Econometrics, 192, 1-18.

Bollerslev, T., A.J. Patton, and R. Quaedvlieg, 2017, Realized SemiCovariances: Looking for Signs of Direction Inside the Covariance Matrix, working paper.

Bollerslev, T., A.J. Patton, and R. Quaedvlieg, 2017, Modeling and Forecasting (Un)Reliable Realized Covariances for More Reliable Financial Decisions, working paper.

Hansen, P.R., and A. Lunde, 2006, Realized variance and market microstructure noise, Journal of Business and Economic Statistics, 24, 127–161.

Patton, A.J., 2011, Volatility Forecast Comparison using Imperfect Volatility Proxies, Journal of Econometrics, 160(1), 246-256.

Patton, A.J., and K. Sheppard, 2015, Good Volatility, Bad Volatility: Signed Jumps and the Persistence of Volatility, Review of Economics and Statistics, 97(3), 683-697.

To enroll 

Please follow the link to the SIDE's website.

Organizer (on behalf of SIDE): Juri Marcucci

Venue: Bank of Italy Sadiba Center, Perugia, Italy 

Some useful links:

If you have any further questions, please send an email to "Società Italiana di Econometria - SIdE" at info@side-iea.it