|
|
Vorlesungsverzeichnis >> Fakultät Sozial- und Wirtschaftswissenschaften >> Bachelor-/Masterstudiengang Soziologie >> Master Soziologie >>
|
Methoden der empirischen Sozialforschung inkl. Studienschwerpunkt
Lehrveranstaltungen der Modulgruppe B] Methoden der empirischen Sozialforschung und des Kernbereichs der Modulgruppe C3] Empirische Sozialforschung
Zur aktuellen Zusammensetzung der Module
| |
Fortgeschrittene Verfahren der Längsschnittanalyse: Ereignisanalyse II Diskrete Modelle (Übung) -
- Dozent/in:
- Gwendolin Bloßfeld
- Angaben:
- Übung, 2 SWS, Übung und Vorlesung gehören zusammen! Eine Anmeldung, über FlexNow, für die Vorlesung ist erforderlich!
- Termine:
- Einzeltermin am 5.11.2020, Einzeltermin am 12.11.2020, Einzeltermin am 19.11.2020, Einzeltermin am 11.2.2021, Einzeltermin am 18.2.2021, Einzeltermin am 25.2.2021, 8:00 - 12:00, RZ/00.07
|
| |
Fortgeschrittene Verfahren der Längsschnittanalyse: Ereignisanalyse II Diskrete Modelle (Vorlesung) -
- Dozent/in:
- Gwendolin Bloßfeld
- Angaben:
- Vorlesung, 2 SWS, Zur Vorlesung gehört die Übung! Eine Anmeldung, über FlexNow, ist erforderlich! Bitte melden Sie sich bis zum 28.10.2020 über FlexNow zu der Veranstaltung an. Personen, die in FlexNow angemeldet sind, werden in den VC eingetragen. Personen, die in den VC eingetragen sind, erhalten hierüber alle Informationen zur Lehrveranstaltung.
- Termine:
- Einzeltermin am 5.11.2020, Einzeltermin am 12.11.2020, Einzeltermin am 19.11.2020, Einzeltermin am 11.2.2021, Einzeltermin am 18.2.2021, Einzeltermin am 25.2.2021, 8:00 - 12:00, RZ/00.07
- Inhalt:
- Description
Over the last two decades, social scientists have been collecting and analyzing event history data with increasing frequency. Illustrative examples of this type of substantive process can be given for a wide variety of social research fields: in labor market studies, workers move between unemployment and employment, full-time and part-time work, or among various kinds of jobs; in social inequality studies, people become a home-owner over the life course; in demographic analyses, men and women enter into consensual unions, marriages, or into father/motherhood, or are getting a divorce; in sociological mobility studies, employees shift through different occupations, social classes, or industries; in studies of organizational ecology, firms, unions, or organizations are founded or closed down; in political science research, governments break down, voluntary organizations are founded, or countries go through a transition from one political regime to another; in migration studies, people move between different regions or countries; in marketing applications, consumers switch from one brand to another or purchase the same brand again; in criminological studies, prisoners are released and commit another criminal act after some time; in communication analysis, interaction processes such as inter- personal and small group processes are studied; in educational studies, students drop out of school before completing their degrees, enter into a specific educational track, or later in the life course, start a program of further education; in analyses of ethnic conflict, incidences of racial and ethnic confrontation, protest, riot, and attack are studied; etc.
Depending on theoretical considerations about the process time axis and the degree of measurement accuracy of event times, the literature often distinguishes between discrete-time and continuous-time event history models. Discrete-time event history methods (1) either theoretically presuppose a discrete process time axis, i.e. that the events can only occur at fixed time intervals; (2) or they assume a continuous process time axis, i.e. that events can happen at any point in time, but that the measurement of these event times could only be achieved in a sequence of quite crude time intervals. For example, in some national panel studies events such as job shifts are only recorded as happening in yearly intervals. Various publications on discrete-time models are available in the literature. In the seminar, we will use a new book manuscript by Blossfeld, G.J. (forthcoming) and refer to Yamaguchi (1991), Singer and Willett (1993), Blossfeld and Blossfeld (2015a, 2015b)), and Blossfeld, Rohwer and Schneider (2019).
|
| |
Fortgeschrittene Verfahren der Längsschnittanalyse: Applied Panel Data Analysis -
- Dozentinnen/Dozenten:
- Michael Gebel, Chen-Hao Hsu
- Angaben:
- Seminar, 4 SWS
- Termine:
- Mo, 8:00 - 12:00, RZ/00.07
- Voraussetzungen / Organisatorisches:
- Requirements:
Students have to be familiar with the contents of the compulsory lecture "Research design" and multiple linear and binary logistic regression analysis.
Moreover, students are required to be familiar with the statistics package Stata. These skills could either be acquired or refreshed in self-studies or by attending an online tutorial course. Link to Stata Tutorial [https://univis.uni-bamberg.de/form?dsc=anew/lecture_view&lvs=sowi/sozwiss/metho/einfhr_1&anonymous=1&ref=tlecture&sem=2020w&tdir=sowi/sozwiss/haupts/method]
Registration:
Please register in the VC of the event until 28.10.2021. Only the persons who are registered in the VC will receive all information about the course.
Type of instruction:
Live online teaching via Zoom (Mo, 8h-12h) is planned. There will be no video recording. Changes are possible depending on the guidelines of the university.
Language of instruction:
English
Module exam:
Portfolio in German or English (time: 3 months)
- Inhalt:
- Learning targets:
The central aim of this course is to empower participants to critically discuss basic concepts and assumptions of linear and logistic fixed effect and random effect panel data analyses, to conduct theory-driven empirical research, to choose and specify the appropriate regression models according to the ideas of modern causal analysis, to independently carry out linear and logistic fixed effect and random effect panel data analyses using the statistics package Stata and data of the Socio-Economic Panel (SOEP), to correctly interpret the results and clearly present the results of regression analyses in tables and graphs.
Course contents:
Pooled OLS, fixed effect, first difference, random effect models as well as hybrid models for linear dependent variables are presented and the basic assumptions are critically discussed. Following the principles of theory-driven empirical research participants learn to choose and specify the appropriate panel regression models according to the ideas of modern causal analysis. Advanced topics of the fixed effect estimator in terms of modelling the impact function and anticipation effects as well as the fixed effects individual-slopes (FEIS) model are introduced. The general idea and challenges of dynamic panel data models are discussed. Panel data models for categorical dependent variables (binary, ordinal and multinomial) are presented. The general idea of mixed-coefficients/mixed effects panel models are introduced and their equivalence to other panel data estimators is highlighted. Finally, the topic of missing data in panel regressions is addressed. Next to theoretical introductions of the models the logic of the different panel data estimators is illustrated based on play data. In lab sessions participants will learn how to practically implement panel data analyses using the statistics package Stata. The lab sessions and the seminar theses will draw exclusively on topical sociological questions of life course research (consequences of life course events) and data of the Socio-Economic Panel (SOEP). Specifically, the course offers an applied introduction and hands-on experience in the complex preparation of panel data for the statistical analyses during the lab sessions.
|
| |
Research Design: Research Design (Übung) -
- Dozentinnen/Dozenten:
- Jonas Voßemer, Daniel Zeddel
- Angaben:
- Übung, 2 SWS
- Termine:
- Mi, 14:00 - 16:00, Online-Meeting
- Voraussetzungen / Organisatorisches:
- Registration:
Please register for the course via the VC until October 28, 2020. All students who are registered will receive information about this course via the VC.
The course Research Design is composed of a lecture and a complimentary exercise course. The lecture takes place every week; the exercise course consists of e-learning exercises and occasional online classroom sessions (dates will be announced in first lecture/exercise). It is recommended to take this course at the beginning of the Master's studies.
It is not necessary to register for the course (lecture and exercise course) in advance (e.g., via FlexNow, via email, etc.). More information about the course and the registration guidelines will only be provided during the first lecture.
Language of instruction: English.
Module-related examination: Exam (time: 60 min).
- Inhalt:
- Learning targets:
After successfully attending the lecture and the exercise course, participants will be able to
- postulate research questions,
- deduct and formulate hypotheses following the principles of theory-driven empirical research,
- explain and critically discuss advanced topics of causality and causal inference in experimental and non-experimental cross-sectional and longitudinal research designs.
Course contents:
Participants will learn to formulate research hypotheses and to distinguish between different kinds of causal hypotheses. They will reflect on how to deduct hypotheses from theory according to the principles of theory-driven empirical social research. Rubin's notation of potential outcomes, which has become the backbone of modern causal analysis in the social sciences, will be introduced. Moreover, directed acyclic graphs (DAGs) will be introduced, because they offer an illustrative graphical approach to the problem of causal inference. Advanced topics of common-cause confounding, overcontrol bias, and endogenous selection bias will be discussed in the framework of DAGs. Advanced issues of validity, especially drawing causal inferences, will be addressed in experimental and non-experimental cross-sectional and longitudinal research designs. Throughout the course practical examples from empirical sociological research will be critically discussed.
|
| |
Research Design: Research Design (Vorlesung) -
- Dozent/in:
- Peter Valet
- Angaben:
- Vorlesung, 2 SWS
- Termine:
- Di, 10:00 - 12:00, Online-Webinar
- Voraussetzungen / Organisatorisches:
- Registration:
Please register for the course via the VC until October 28, 2020. All students who are registered will receive information about this course via the VC.
The course Research Design is composed of a lecture and a complimentary exercise course. The lecture takes place every week; the exercise course consists of e-learning exercises and occasional online classroom sessions (dates will be announced in first lecture/exercise). It is recommended to take this course at the beginning of the Master's studies.
It is not necessary to register for the course (lecture and exercise course) in advance (e.g., via FlexNow, via email, etc.). More information about the course and the registration guidelines will only be provided during the first lecture.
Language of instruction: English.
Module-related examination: Exam (time: 60 min).
- Inhalt:
- Learning targets:
After successfully attending the lecture and the exercise course, participants will be able to
- postulate research questions,
- deduct and formulate hypotheses following the principles of theory-driven empirical research,
- explain and critically discuss advanced topics of causality and causal inference in experimental and non-experimental cross-sectional and longitudinal research designs.
Course contents:
Participants will learn to formulate research hypotheses and to distinguish between different kinds of causal hypotheses. They will reflect on how to deduct hypotheses from theory according to the principles of theory-driven empirical social research. Rubin's notation of potential outcomes, which has become the backbone of modern causal analysis in the social sciences, will be introduced. Moreover, directed acyclic graphs (DAGs) will be introduced, because they offer an illustrative graphical approach to the problem of causal inference. Advanced topics of common-cause confounding, overcontrol bias, and endogenous selection bias will be discussed in the framework of DAGs. Advanced issues of validity, especially drawing causal inferences, will be addressed in experimental and non-experimental cross-sectional and longitudinal research designs. Throughout the course practical examples from empirical sociological research will be critically discussed.
|
|
 |
|
|
UnivIS ist ein Produkt der Config eG, Buckenhof |
|
|