Thema Surveymethodologie und Data-Science

SOEPcampus@DIW Berlin 2023

Am 9. und 10. März 2023 organisieren wir einen zweitägigen Workshop zum Sozio-oekonomischen Panel (SOEP) am DIW Berlin. Neben Vorträgen zu Aufbau, Datenstruktur, Ziehungsdesign und Gewichtungsstrategie bieten Hands-On Sessions eine praxisorientierte Annäherung an die Daten und ihre Potentiale. Der Workshop richtet sich an Wissenschaftlerinnen und Wissenschaftler auf allen Qualifikationsstufen,...

SOEPcampus@European University Viadrina

This 1/2 day workshop offers a first and practically oriented introduction into the sophisticated data source of the SOEP. Participants will be introduced to the content of the study, its data-structure, sample selection and weighting strategy and they will be provided with an overview over the study documentation. Additionally we will discuss the specific potentials for longitudinal data analyses...

SOEPcampus@Europa-Universität Viadrina Frankfurt (Oder)

Der halbtägige Workshop bietet eine erste, aber praxisorientierte Einführung in das Arbeiten mit dem umfangreichen Datenangebot des Sozio-oekonomischen Panels (SOEP). Aufbau, Datenstruktur, Ziehungsdesign und Gewichtungsstrategie des SOEP sowie sich daraus ergebende Analysepotentiale werden vorgestellt. Die Workshopsprache ist Englisch und die Anmeldung erfolgt über die Workshopleitung Sandra...

Learn to use the SOEP over Lunch

The German Socio-Economic Panel Study is a representative panel study for the German population, collecting data on a broad variety of topics of everyday life, including general wellbeing, household composition, educational aspirations and educational status, income and occupational biographies, leisure time activities, housing, health, political orientation and more. With its long running panel...

How Communication Makes the Difference between a Cartel and Tacit Collusion: A Machine Learning Approach

This paper sheds new light on the role of communication for cartel formation. Using machine learning to evaluate free-form chat communication among firms in a laboratory experiment, we identify typical communication patterns for both explicit cartel formation and indirect attempts to collude tacitly. We document that firms are less likely to communicate explicitly about price fixing and more likely ...

Decommissioning of Nuclear Power Plants: Regulation, Financing, and Production

The Hidden Homeownership Welfare State: An International Long-term Perspective on the Tax Treatment of Homeowners

Welfare is traditionally understood as social security decommodifying labour markets or as social investment policies. In the domain of housing, however, welfare for homeowners is largely hidden in the tax codes’ fiscal exemptions. Based on a content analysis of legislation, this article introduces a novel yearly database of 37 countries between 1901 and 2020 to uncover the “hidden welfare state” of ...

Foreign Exchange Intervention: A New Database

We construct a novel database of monthly foreign exchange interventions for 49 countries over up to 22 years. We build on a text classification approach that extracts information about interventions from news articles and calibrate our procedure to data about actual interventions. This new dataset allows us to document stylized facts about the use of foreign exchange interventions for countries that ...

Corona Monitoring Nationwide (RKI-SOEP-2): Seroepidemiological Study on the Spread of SARS-CoV-2 Across Germany

SARS-CoV-2, the coronavirus, spread across Germany within just a short period of time. Seroepidemiological studies are able to estimate the proportion of the population with antibodies against SARS-CoV-2 infection (seroprevalence) as well as the level of undetected infections, which are not captured in official figures. In the seroepidemiological study Corona Monitoring Nationwide (RKI-SOEP-2), biospecimens ...

Multiple Imputation of Ordinal Missing Not at Random Data

We introduce a selection model-based imputation approach to be used within the Fully Conditional Specification (FCS) framework for the Multiple Imputation (MI) of incomplete ordinal variables that are supposed to be Missing Not at Random (MNAR). Thereby, we generalise previous work on this topic which involved binary single-level and multilevel data to ordinal variables. We apply an ordered probit ...