Archives

A Connected World: Data Analysis for Real-World Network Data

Over the past decade, there has been a growing public fascination with the complex “connectedness” of networks. This connectedness is found in ubiquitous situations: in the rapid growth of the Internet, in the ease with which global communication now takes place, and in the ability of news and misinformation as well as financial and political crises to spread around the globe. 

To adequately capture and understand such phenomena, network analysis has proven to be extremely useful. In this context, methodological research on network analytical models picked up a lot of traction in recent years, due to the growing need for ways to handle network data.

This workshop intends to provide interested scholars with an overview of different research strains in the field of network data analysis.

In particular, we will work with data relating to international political interactions, such as the international trade of weapons, migration, and conflicts but also with classical social network data.

Participants will be introduced to the analysis of network data from both a substantive and statistical perspective. In a hands-on session, you will learn to analyze a real-world network dataset through the use of existing, readily available software packages. Basic R Skills are required.

“A Connected World: Data Analysis for Real-World Network Data” will take place July 19, 2023 at the Leibniz Supercomputing Centre in Garching (Munich).

Program
10:00 – 11:30 Introduction to Network Data Analysis
11:30 – 12:00 Coffee Break
12:00 – 13:30 Exponential Random Graph Models
13:30 – 14:30 Lunch Break
14:30 – 16:00 Latent Space Models
16:00 – 16:30 Coffee Break
16:30 – 18:00 R Lab

About the Instructors

While Giacomo De Nicola is a research assistant and doctoral student at the Institute of Statistics at LMU Munich, Cornelius Fritz is a postdoctoral fellow at Penn State, focusing mainly on developing novel data analysis techniques by combining statistical and machine learning with solid theoretical foundations. Göran Kauermann has been a full professor of Statistics at LMU Munich since 2011 and heads the chair for Statistics in Economics, Business, and Social Sciences there. Additionally, he serves as the chairman of the German Data Science Society (GDS).

Data Science with R

You want to learn R for Data Science, but don’t find the time to visit synchronous courses regularly?

Register for this free self-paced course and learn all you need to start with R on your own schedule!

Introductory Tutorials

  • The True Basics of R
  • Data Manipulation in R
  • Data Visualization in R

Advanced Data Manipulation in R

  • Data Management
  • Subsets & Aggregation
  • Advanced Programming
  • Testing in R

Advanced Data Visualization in R

  • The Concept of Visualization & Advanced base R Graphs
  • Introduction to ggplot2
  • Advanced ggplot2

About the Instructor

Leonie Gehrmann is a doctoral student at the University of Mannheim in the field of Marketing. Her research interests primarily focus on machine learning applications in marketing, economics of data, and consumer psychology.

Machine Learning Bootcamp in R (€)

Der Machine Learning Bootcamp in R vermittelt in einzeln buchbaren Modulen elementare Methoden und Konzepte zur Anpassung und Optimierung von Vorhersagemodellen aus dem Bereich Predictive Modeling und Supervised Machine Learning (Modul 1), zum Auffinden von Strukturen in den Daten aus dem Bereich des Unsupervised Machine Learning (Modul 2), sowie praktisches Wissen zum interpretierbaren maschinellen Lernen (Modul 3). Beschreibung der Module:

Modul 1: Supervised Machine Learning in R(06.03. – 08.03.2023)

Modul 2: Unsupervised Learning in R(09.03.2023)

Modul 3: Interpretable Machine Learning in R(10.03.2023)

Data Literacy Essentials: Processing Data (R)

In this session we will introduce you to R, a programming language that allows you to edit, visualize and analyze data. We will give you an introduction to the programming environment RStudio, teach you the basics of syntax and show you examples of the possibilities that open up with the use of R. No previous knowledge is assumed.

Data Analysis Bootcamp in R (€)

Der Data Analysis Bootcamp in R vermittelt in einzeln buchbaren Modulen Grundkenntnisse in R (Modul 1), praktisches Wissen zur deskriptiven Datenanalyse, der statisischen Inferenz und Modellierung in R (Modul 2), sowie fortgeschrittene Kenntnisse zur effizienten Nutzung von R (Modul 3). Beschreibung der Module:

Modul 1: R Crashkurs (27.02.2023)

Modul 2: Praktische Datenanalyse in R (28.02. – 01.03.2023)

Modul 3: Effiziente Datenverarbeitung und Programmierung in R (02.03. – 03.03.2023)

A Connected World: Data Analysis for Real-World Network Data

Over the past decade, there has been a growing public fascination with the complex “connectedness” of networks. This connectedness is found in ubiquitous situations: in the rapid growth of the Internet, in the ease with which global communication now takes place, and in the ability of news and misinformation as well as financial and political crises to spread around the globe. 

To adequately capture and understand such phenomena, network analysis has proven to be extremely useful. In this context, methodological research on network analytical models picked up a lot of traction in recent years, due to the growing need for ways to handle network data.

This workshop intends to provide interested scholars with an overview of different research strains in the field of network data analysis.

In particular, we will work with data relating to international political interactions, such as the international trade of weapons, migration, and conflicts but also with classical social network data.

Participants will be introduced to the analysis of network data from both a substantive and statistical perspective. In a hands-on session, you will learn to analyze a real-world network dataset through the use of existing, readily available software packages.

About the Instructors

While Giacomo De Nicola is a research assistant and doctoral student at the Institute of Statistics at LMU Munich, Cornelius Fritz is a postdoctoral fellow at Penn State, focusing mainly on developing novel data analysis techniques by combining statistical and machine learning with solid theoretical foundations. Göran Kauermann has been a full professor of Statistics at LMU Munich since 2011 and heads the chair for Statistics in Economics, Business, and Social Sciences there. Additionally, he serves as the chairman of the German Data Science Society (GDS).

How to Make Use of Machine Learning & Microsimulation in Official Statistics

How can we make use of new data sources and data science methods to enhance public statistics?

This course gives an overview of advanced topics in official statistics such as Big Data, machine learning, and microsimulations. The benefits and downsides of using Big Data as a data source for official statistics production are discussed and examples of its use are given, including machine learning applications.

In addition, the course provides insights into microsimulation and gives an overview of the past, the present, and the future state-of-the-art of microsimulation methods and applications within official statistics.

This online course uses a flipped classroom design, which means that you can watch the weekly hour of video lectures according to your own schedule. In the weekly one-hour online meetings you have the chance to discuss the material and hands-on applications with the instructors from destatis and Statistics Netherlands. 

Basic R knowledge is required. Having some familiarity with the official statistics system as taught in Walter Radermacher’s BERD Academy workshop series  “Statistics for the Public Good” can be helpful.

About the Instructors

While Hanna Brenzel, who leads the department at the Federal Statistical Office, holds a doctorate in economics, Hariolf Merkle, who has a Master’s degree in survey statistics, is a Data Scientist at the Deutsche Bundesbank. Dr. Marco Puts, on the other hand, is a Methodologist and Lead Data Scientist at the Central Statistics Office in Heerlen and a Guest Researcher at Radboud University in Nijmegen. Piet Daas is a Methodologist and Professor of Big Data in Official Statistics at Eindhoven University of Technology, specializing as a Data Scientist.