Archived Events

28.05.2018 - 29.05.2018Workshop

Longitudinal Structural Equation Models

Kenneth A. Bollen (The University of North Carolina at Chapel Hill)
Place:
Unicom
Room: 3.0170
Mary-Somerville-Straße 3
28359 Bremen
Time:
09.00 a.m. - 4.30 p.m.
Contact Person:
Organization:
Lecture Series:
Method Lectures of the Bridge Professorship
Semester:
SoSe 2018

With the increasing availability of longitudinal data, researchers need to decide the best models for their data.

A wide variety of models have been proposed, many of which are available using Structural Equation Models (SEM).  This course will review some of the major longitudinal SEMs.  Among others this will include autoregressive/crosslag models, latent growth curve models, and Autoregressive Latent Trajectory (ALT) models.  The workshop will present each type of model and illustrate their estimation and fit with empirical data.

Some knowledge of SEMs is assumed.

Ken A. Bollen is the Henry Rudolph Immerwahr Distinguished Professor in the Department of Sociology and the Department of Psychology and Neuroscience at UNC at Chapel Hill.  He is a faculty member in the Quantitative Psychology Program in the Thurstone Psychometric Laboratory.  He also is chair of the Methods Core and a Fellow of the Carolina Population Center and a Faculty member of the Center for Developmental Science. Since 1980 he has been an instructor in the ICPSR Summer Program in Quantitative Methods of Social Research. Bollen's primary areas of statistical research are in structural equation models, longitudinal methods, and latent growth curve models.

Registration:
E-Mail to Johannes Nostadt (nostadt@uni-bremen.de)

Place:
Unicom
Room: 3.3380
Mary-Somerville-Straße 3
28359 Bremen
Time:
12.00 - 2.00 p.m.
Organization:
Cooperation:
Semester:
SoSe 2018

Data mining, especially as applied to social science data, is a rapidly changing and emerging field.
Data mining (DM) is the name given to a variety of computer-intensive techniques for discovering structure and for analyzing patterns in data. Using those patterns, DM can create predictive models, or classify things, or identify  different groups or clusters of cases within data. Data mining uses machine learning and predictive analytics that are already widely used in technical areas and business and are starting to spread into social science and other areas  of research. This talk will give an introduction to machine learning techniques, its challenges, applications, and pitfalls closely related to social sciences.

Place:
Guesthouse of the University of Bremen
Teerhof 58
28199 Bremen
Time:
Friday, 27th April: 1 - 6:45 p.m.; Saturday, 28th April 2018: 9 a.m. - 2:30 p.m.
Organization:
Partic. Organization:

05.04.2018 - 06.04.2018Workshop

Possibilities in Computational Social Science. Automated web data collection for the social sciences using R

Dr. Dominic Nyhuis (Goethe University Frankfurt)
Place:
Unicom
Room: 7.3280
Mary-Somerville-Straße 7
28359 Bremen
Time:
10:00 a.m. - 4:30 p.m.
Organization:
Cooperation:
Semester:
SoSe 2018

The vast availability of data on the web is fundamentally changing the research practices in the social sciences. By mastering the tools needed for automated web data collection, a single researcher can construct a data set that would have required tremendous efforts and expenses not too long ago. The course is intended to provide an applied overview of the skills required for automatically collecting data from the web. It will give a cursory introduction  to some of the most important skills and techniques. In particular, the workshop will provide an introduction to the basic structure of HTML to enable an understanding of the underlying architectures and mechanics of websites. XPath will be introduced as a syntax to address specific elements of websites and a tool to extract them as needed. Regular expressions are covered which allow further processing textual data gathered from the web. Finally, client-server  interactions in the HTTP protocol and the structure of URLs are discussed to understand web interactions in practice.  The applied elements of the workshop will make use of the programming language R.
*Therefore, a basic familiarity with R is a prerequisite for attending the course.*

Place:
House of Science (Haus der Wissenschaft)
Room: Olbers-Saal
Sandstraße 4/5
28195 Bremen
Time:
9 a.m. - 5 p.m.
Sc. Administration:
Contact Person:
Organization:

Place:
Cartesium
Room: Rotunde
Enrique-Schmidt-Straße 5
28359 Bremen
Time:
12:15 - 1:45 p.m.
Contact Person:
Organization:
Lecture Series:
Method Lectures of the Bridge Professorship
Semester:
WiSe 2017/18

17.01.2018Lecture

How do Environmental Norms Enter the Trade Regime? A Network-Theoretical Perspective

Prof. Dr. James Hollway (Graduate Institute of International and Development Studies)
Place:
SOCIUM Research Center on Inequality and Social Policy
Room: 3.3380
Mary-Somerville-Straße 3
28359 Bremen
Time:
12:15 - 1:45 p.m.
Organization:
Cooperation:
Lecture Series:
Jour Fixe
Semester:
WiSe 2017/18

Using the example of environmental norms appearing in trade agreements, James Hollway develops an analysis of legal innovation based on a complex adaptive systems perspective and network theory. With this he can show that legal innovation is mainly an endogenous process and that contrary to prevailing wisdom, power asymmetries are less relevant.

16.01.2018Workshop

Dynamic Network Actor Models

Prof. Dr. James Hollway (Graduate Institute of International and Development Studies)
Place:
SOCIUM Research Center on Inequality and Social Policy
Room: 3.3380
Mary-Somerville-Straße 3
28359 Bremen
Time:
12 - 4 p.m.
Organization:

The workshop on network dynamics introduce the R package "Goldfish" that was developed to analyze and model networks using dynamic network actor models (DyNAMs).

In a recently published paper, James Hollway and his colleagues write that DyNAMs are

  • network models that allow researchers to control for and explicitly test hypotheses about observational dependence,

  • actor-oriented and conceive of network ties as the expression of actors’ preferences and available opportunities,

  • model coordination between the two actors involved in the creation of a tie,

  • more precise than existing panel-based models as they allow to draw inference from more granular time-stamped data,

  • permit simultaneous tests of hypotheses about weighted, windowed, and signed processes.

DyNAMs thus offer an alternative to stochastic actor oriented models (Siena) and exponential random graph models (ERGM).

The workshop will be taught in English.

Place:
Unicom
Room: 3.3380
Mary-Somerville-Straße 3
28359 Bremen
Time:
10 - 12 a.m.
Contact Person:

08.01.2018Lecture

Opportunistische Netzwerke und Katastrophenmanagement

Prof. Dr. Anna Förster (University of Bremen)
Place:
Cartesium
Room: Rotunde
Enrique-Schmidt-Straße 5
28359 Bremen
Time:
12:15 - 1:45 p.m.
Contact Person:
Organization:
Lecture Series:
Method Lectures of the Bridge Professorship
Semester:
WiSe 2017/18