Category Archives: Quantitative Methods

Multivariate Analysis Methods

Institution: Fakultät für Betriebswirtschaft, Universität Hamburg

Lecturer: Tammo Bijmolt (University of Groningen, Faculty of Economics and Business)

Dates: 21st November 2016, 12th December 2016, 16th January 2017, 6th February 2017 (all sessions scheduled on Mondays)

Course Value: 3 SWS or 6 LP

Course Overview:
The PhD course deals with a variety of multivariate analysis methods. The main focus of the course is rather applied: students who have successfully finished the course should be able to apply multivariate analysis methods at an advanced level in scientific research in marketing (or more general, in business). A full-day lecture will be used to explain a particular method and to learn about conducting the analyses. There will be four topics, each with a lecture and an assignment (see below).
The course is open for students from outside Hamburg, from other departments within the Business School, and junior faculty members (max. 15-20 participants). In principle, participants could sign up for all sessions / the entire course, or cherry-pick the topic(-s) that they like.

Objectives:
After attending the course, students should have acquired:
a) State-of-the-art knowledge of potential application of these multivariate analysis methods
b) Understanding of the methodological underpinnings of the methods
c) Practical skills to perform the analyses

Assessment and Credits:
After the session, participants will have to work on an assignment (if the participant requires formal credits), using real data, and write a short report (about 10 pages; to be graded as pass/fail) about this. Participants who attend all sessions and pass the four assignments can attain 6 LP.

Potential topics:
Topics of the PhD course will be selected based on preferences of participants. Therefore, please indicate your preferred topic(s) out of the following methods when registering for the course. Four out of seven topics will be taught in the course.

# Topic

  1. Latent class analysis / mixture modelling
  2. Hierarchical models
  3. Hidden Markov models {assuming knowledge of 1}
  4. Moderation & mediation
  5. Meta-analysis
  6. Factor analysis & principal component analysis
  7. Duration models

Assessment and Credits: After the session, participants will have to work on an assignment (if the participant requires formal credits), using real data, and write a short report (about 10 pages; to be graded as pass/fail) about this. Participants who attend all sessions and pass the four assignments can attain 6 LP.

Registration: To register for this seminar please contact Marius Johnen (marius.johnen@uni-hamburg.de). Registration is open till 16th October 2016 and is on a first come, first serve basis.

Tammo H.A. Bijmolt is Professor of Marketing Research at the Department of Marketing. From March 2009 till November 2015, he has been Director of the research school SOM, Faculty of Economics and Business Administration, University of Groningen, The Netherlands. His research interests include conceptual and methodological issues such as consumer decision making, e-commerce, advertising, retailing, loyalty programs, and meta-analysis. His publications have appeared in international, prestigious journals, among others: Journal of Marketing Research, Journal of Marketing, Journal of Consumer Research, Marketing Science, International Journal of Research in Marketing, Psychometrika, and the Journal of the Royal Statistical Society (A). His articles have won best paper awards from International Journal of Research in Marketing (2007), Journal of Interactive Marketing (2011), and European Journal of Marketing (2015). He is member of the editorial board of International Journal of Research in Marketing and International Journal of Electronic Commerce. Tammo Bijmolt is vice-president of EIASM and lectures in the EDEN programs. He has lectured in a broad range of programs at the Bachelor, Master, PhD and executive MBA level. He has been involved in several research-based consultancy projects for a variety of companies including MetrixLab, GfK, Wehkamp, and Unilever. Finally, he served as expert in several legal cases involving market research projects.

 

 

Reminder/Update HSU-Doktorandenkurs: Combining Rigor and Relevance with Necessary Condition Analysis (NCA)

Institution: Helmut-Schmidt-University Hamburg

Lecturer: Jan Dul, Rotterdam School of Management, Erasmus University

Date: 20.10.2016 – 10 a.m. to 15 p.m.

Place: Helmut-Schmidt-Universität, Holstenhofweg 85, 22043 Hamburg

Room: Seminarraum 0105

Language of instruction: English

Registration: Please notify Dr. Sven Hauff via email (hauffs@hsu-hh.de)

Contents:
Necessary Condition Analysis (NCA) is a novel methodology, recently published in Organizational Research Methods (Dul, 2016). Reactions of editors and reviewers of papers that use NCA are very promising. For example, an editor of a 4-star journal said:
“From my perspective, [this NCA paper] is the most interesting paper I have handled at this journal, insofar as it really represents a new way to think about data analyses”.

How does NCA work?
NCA understands cause-effect relations in terms of “necessary but not sufficient”. It means that without the right level of the condition a certain effect cannot occur. This is independent of other causes, thus the necessary condition can be a bottleneck, critical factor, constraint, disqualifier, etc. In practice, the right level of necessary condition must be put and kept in place to avoid guaranteed failure. Other causes cannot compensate for this factor.

Whom is NCA for?
NCA is applicable to any discipline, and can provide strong results even when other analyses such as regression analysis show no or weak effects. By adding a different logic and data analysis approach, NCA adds both rigor and relevance to your theory, data analysis, and publications. NCA is a user-friendly method that requires no advanced statistical or methodological knowledge beforehand. It can be used in both quantitative research as well as in qualitative research. You can become one of the first users of NCA in your field, which makes your publication(s) extra attractive.

What will be discussed in the seminar?
The seminar consists of two parts:

  1. The first part (one hour) is open to anyone who is interested in NCA and its potential value. We will discuss the method and its applications in different management fields.
  2. Immediately afterwards, in the second part (1-3 hours depending on the number of participants) we will discuss the method in more detail. In particular we will focus on the participants’ research areas and datasets. If you are interested in a demonstration of the method on your dataset, please bring your dataset (scores of the variables) on a USB drive (e.g., excel.csv file). Normally, an NCA analysis takes less than 5 minutes to get the main results.

More information:

  • www.erim.nl/nca
  • Dul, J. (2016) Necessary Condition Analysis (NCA): Logic and methodology of “necessary but not sufficient” causality, Organizational Research Methods, 19(1), 10-52.

JMP Intro & DOE / Kriging Workshop using JMP and R

Institution: Helmut-Schmidt-University Hamburg, hosted by Univ.-Prof. Dr. Sven Knoth, WiSo (sven.knoth@hsu-hh.de)

Presenter: Volker Kraft, JMP Academic Ambassador

Time: 25th November 2016, 10am – 5pm

Location: Helmut-Schmidt-Universität, Holstenhofweg 85, 22043, Hamburg,  WiSo Hörsaal 3 (or PC-Pool)

Registration: Please click here an fill out the form to register for the workshop.

Number of attendees: 25 max. (hands-on only)

Agenda:
10-12: Introduction to JMP, Design of Experiments and Predictive Modeling (live demo & discussion)
12-13: Lunch break – pizza session by JMP
13-17: Kriging Workshop – attendees should have JMP 13 pre-installed (see www.jmp.com/trial for 30 days trial license)

Target Group:
Morning: Anybody interested to see JMP 13, or to get ready for the afternoon hands-on workshop.
Afternoon: Anybody with applications that require to work with functions, often of many variables, that are costly to evaluate.
Knowledge of linear regression, statistical modeling, and stochastic processes is helpful but is not required for the workshop. Similarly, basic knowledge of R and/or JMP will be helpful for the hands-on lab component, but is not mandatory.

Content:
JMP is an easy-to-use, standalone statistics and graphics software from SAS Institute. It includes comprehensive capabilities for every academic field, and its interactive point-and-click interface and linked analyses and graphics make it ideal for research and for use in statistics courses, from the introductory to the advanced levels. JMP runs on Windows and Macintosh operating systems and also functions as an easy, point-and-click interface to SAS®, R, MATLAB and Excel.

The JMP INTRO SESSION introduces the interactive user interface of JMP. Sample applications will focus on Experimental Design and Data Modeling. Get to know about JMP academic resources and where to find help.

KRIGING (or Gaussian process regression) has proven to be of great interest when trying to approximate a costly to evaluate function in a closed form. The principle aim of the workshop is to show how to build useful surrogate models using this approach, and to make clear the assumptions that such models rely on. Furthermore, once it exists, we will show how a surrogate model can be used for optimization.

Lab sessions will use both R and JMP. The main aim of the lab is to quickly find optimal settings of a catapult numerical simulator that can fire the longest shot.

Workshop content and installation instructions for R (packages) and JMP will be shared mid of November.

 

Introduction to Regression Analysis

Institution: Fakultät für Betriebswirtschaft, Universität Hamburg

Course Instructor: Dr. Alexa Burmester (Universität Hamburg)

Dates, location: October 10. and 11. 2016; 09:15 – 13:45 h (block course), R. 4030/4031

Course Value: 1 SWS or 2 LP

Course Overview:
This course will give an introduction to regression analysis with Stata.
Course Contents: This course will focus on basic regression analysis. Topics include (1) Data preparation, (2) Summary statistics, (3) Model free evidence, (4) Regression analysis, (5) Check of model assumptions, (6) Nonlinear models & interaction effects, and (7) Panel data.
Individual (or two-person team, with permission) research assignments will be re-quired. Please schedule some time at Monday afternoon for the assignment. Own re-search questions and data are very welcome to be discussed in the course.

Software: Please bring a laptop with Stata 13 or newer. If applicable, you can bring your own data set of your research project.

Prerequisites:
Please also study the following text:
Backhaus, K., B. Erichson, W. Plinke und R. Weiber (2016): Multivariate Analysemethoden, 14. Auflage, Heidelberg (Kapitel 1: Regressionsanalyse)

Assessment: Assessment will be based on active participation and performance on assignments. Grading for students of University of Hamburg will be pass/fail.

Registration: Please e-mail Alexa Burmester: Alexa.Burmester@uni-hamburg.de until 06. October 2016. (Please remember that places will be allocated in order of received registrations.)

SYLLABUS
Day 1:

  • Data preparation
  • Summary statistics
  • Model free evidence
  • Regression analysis
  • Check of model assumptions

Day 2:

  • Presentation of assignment
  • Nonlinear models & interaction effects
  • Panel data
  • Summary

5th Bamberg Statistics Conference 2016 on “Income Inequality and Poverty in Germany: Measurement, Findings and Political Interventions”, 21st to 22nd July 2016, Bamberg, Germany

Institution: Bayerisches Landesamt für Statistik/Otto-Friedrich-Universität Bamberg

Date: 21.-22. Juli 2016

Place: Aula der Universität Bamberg, Dominikanerstraße 2a, 96049 Bamberg

Registration: www.statistik.bayern.de/statistiktage2016

Contents:
Researchers, practitioners and the interested public are invited to join the 5th Bamberg Statistics Conference, this year dealing with income inequality and poverty in Germany. It is organized by the University of Bamberg, the Institute for Employment Research of the German  Federal Employment Agency and the Bavarian State Office for Statistics. Please check the event website for more details.

Die Otto-Friedrich-Universität Bamberg und das Bayerische Landesamt für Statistik organisieren in Kooperation mit dem Institut für Arbeitsmarkt- und Berufsforschung am 21. und 22. Juli 2016 die StatistikTage Bamberg|Fürth. Ziel der Veranstaltungsreihe ist eine Stärkung des Austauschs zwischen amtlicher Statistik und Wissenschaft sowie weiteren Nutzergruppen amtlicher Daten. Das Thema im Jahr 2016 lautet “Einkommensungleichheit und Armut in Deutschland: Messung, Befunde und Maßnahmen”. Weitere Informationen zur Tagung finden Sie auf der Tagungswebsite sowie im Programmflyer.

Qualitative Methoden und Mixed Methods in der Managementforschung

Institution: Technische Universität Hamburg-Harburg

Zeit: 13. – 16. September 2016

Ort: Am Schwarzenberg-Campus 1 (Gebäude A), 21073 Hamburg

Anmeldung:
Ab sofort per Email unter doktorandenprogramm@vhbonline.org. Die Themenzuordnung zu den Teilnehmern, die sich bis 26. Februar 2016 angemeldet haben, erfolgt auf der Basis einer Prioritätenliste. Nachfolgende Anmeldungen werden durch die Referenten zugeordnet. Letzter möglicher Anmeldetag ist der 03. Juni 2016.

Teilnahmegebühr: 600 Euro pro Teilnehmer

Kursbeschreibung:
Grundlegendes Ziel dieses Kurses ist es, den Teilnehmern Kenntnisse über den Prozess und die Methoden qualitativer Forschungsdesigns zu vermitteln und die Eignung solcher Designs für konkrete Problemstellungen der Teilnehmer zu diskutieren (Werkstatt-Prinzip).

  • Grundlagen und spezifische Merkmale qualitativer Forschung
  • die Indikation qualitativer Forschung und die Rolle der Wissenschaftstheorie
  • der qualitative Forschungsprozess und der Einfluss von Theorien
  • die Erhebung qualitativer Daten
  • die Auswertung qualitativer Daten
  • Grounded Theory, Qualitative Inhaltsanalyse
  • Gütekriterien und Geltungsbegründung qualitativer Befunde
  • Methodenintegrative Designs (Mixed Methods)

Referenten:
Prof. Dr. Thomas Wrona
(Institut für Strategisches & Internationales Management, Technische Universität Hamburg-Harburg; www.tu-harburg.de/isim)

Prof. Dr. Philipp Mayring
(Institut für Psychologie der Alpen-Adria-Universität Klagenfurt; wwwu.uni-klu.ac.at/pmayring/)

Weitere Informationen und ein Syllabus zur Veranstaltung finden sich hier bzw. hier.

 

 

R-Kurs an der Helmut-Schmidt-Universität

Institution: Helmut-Schmidt-University Hamburg

Lecturer: Prof. Dr. Torben Kuhlenkasper

Date: 03.-07.08.2015

Place: Helmut-Schmidt-Universität, Holstenhofweg 85, 22043 Hamburg

Language of instruction: German

Registration: Please mail to Vera Jahn

Contents:
In der Woche vom 03. bis 07.08.2015 wird Herr Prof. Dr. Torben Kuhlenkasper, Professor für quantitative Methoden an der Hochschule Pforzheim, bei uns einen Blockkurs zur Einführung in die Statistik-Software R geben. Dabei handelt es sich um eine von Statistikern, aber zunehmend auch von Volkswirten verwendete Statistiksoftware, die kostenlos verwendet werden kann und extrem leistungsfähig ist.

Wir freuen uns daher sehr, dass wir mit Torben Kuhlenkasper für diesen Kurs einen sehr kompetenten Dozenten gewinnen konnten, der in die Geheimnisse von R einführen wird. Er hat den Kurs in den letzten Jahren bereits mit großem Erfolg an unserer Fakultät gehalten.

Der Kurs wird ganztägig im Seminarraum 0206 stattfinden. Teilnehmer werden gebeten, ihren eigenen Laptop mitzubringen. Das Kursprogramm inklusive Zeitplan ist beigefügt.

Weitere Informationen zum Kurs finden sich hier.

Interessenten werden gebeten, sich bis zum 30.07.2015 per Mail bei Vera Jahn anzumelden.

Data Analysis with Stata

Institution: see Organisers & Supporters

Programme of study: International Research Workshop

Lecturer: Tobias Gramlich (GESIS – Leibniz Institute of Social Sciences)

Date: Monday, 28/09/15 (09:00 – 18:00) – Tuesday, 29/09/15 (09:00 – 12:00)

Max. number of participants: 20

Credit Points: 5 CP for participating in the whole IRWS

Language of instruction: English

Contents:

Stata is a statistical program package widely used (not only) in the social and economical sciences; it is used for data management, statistical graphics and analysis of quantitative data. Statistical concepts will not be part of the course, so participants should have some very basic knowledge of statistics. The course should enable participants to prepare their data for analysis, perform adequate analysis using a statistical computer program and to document these tasks to keep them reproducible.

For Beginners with no or very little Stata knowledge!

Course topics cover:

  • “What You Type is What You Get”: Basic stata Command syntax
  • Getting (and Understanding) Help within stata: stata Bulit-in Help System
  • Basic Data Management: Load and Save stata Datasets, Generate and Manipulate Variables, Describe and Label Data and Variables, Perform Basic uni- and bivariate Analyses, Change the Structure of your Data
  • Basic stata Graphics: Scatterplot, Histogram, Bar Chart
  • Working with “Do-” and “Log-” Files

You have to register for the 9th International Research Workshop to participate in this course.

Structural Equation Modeling (SEM) with R

Institution: see Organisers & Supporters

Programme of study: International Research Workshop

Lecturer: Dr. Holger Steinmetz (University of Paderborn)

Date: Tuesday, 29/09/15 (14:30 – 18:00) – Wednesday, 30/09/15 (09:00 – 18:00)

Max. number of participants: 25

Credit Points: 5 CP for participating in the whole IRWS

Language of instruction: English

Contents:

Structural equation models (SEMs) have become a powerful tool in the behavioral sciences to test hypotheses about relationships between variables and implications of causal structures. This workshop offers an introduction to the background, principles, opportunities, and limitations of SEMs. These issues are illustrated using the lavaan package (latent variable analysis) that is run within the free software platform R. Lavaan has recently become a serious competitor to commercial software packages and is delivers almost everything a user needs to perform SEM. Participation to the course requires some basic knowledge of regression analysis, variances, covariances of variables, and inferential statistics. Knowledge of R is not necessary.

Course topics cover:

  • A short treatment of causality (the counter factual approach) and introduction to causal models and their illustration with path diagrams / causal graphs.
  • The principle behind estimating parameters and basis for evaluation the adequacy of the model (e.g., chi-square test) including Wright’s path tracing rules and Pearls d-separation.
  • Treatment and modeling of latent variables and the connection to theoretical constructs.
  • Explanation of the lavaan syntax and exercises (modeling own data / models of the participants is appreciated).
  • Reasons for misfitting models, evaluation, diagnostics, and re-specification.
  • The problem of endogeneity and the valuable role of instrumental variables in SEMs.

Required packages to be installed:

  • psych
  • car
  • Hmisc
  • MASS
  • QuantPsyc
  • Boot
  • Mnormt
  • Pbivnorm
  • quadprog
  • simsem
  • lavaan

Prerequisites for attending:

  • Basic knowledge of statistics (variance, co-variance) and regression analysis.

You have to register for the 9th International Research Workshop to participate in this course.

Data Analysis with R

Institution: see Organisers & Supporters

Programme of study: International Research Workshop

Lecturer: Dr. Michael Großbach (Hanover University of Music, Drama and Media)

Date: Monday, 28/09/15 (09:00 – 18:00) – Tuesday, 29/09/15 (09:00  – 12:00)

Max. number of participants: 20

Credit Points: 5 CP for participating in the whole IRWS

Language of instruction: English

Contents:

Data analysis is one of the key skills for quantitative researchers. But data analysis is more than just your Stats 101 course in grad school. And it’s not only more I argue, it’s different. Data are not normal, there are outliers and missing values. Data often do not comply with our hypotheses. And yet we can learn from data, given the appropriate tools.

This course introduces the interactive and programmable statistical and graphics software environment R (http://www.r-project.org/), and the Integrated Development Environment RStudio (http://www.rstudio.com/) that provide a polished interface to R. The main topics will be reading data into R, exploratory data analysis – i.e. graphically scrutinising data -, data munging and, finally statistical analysis. Participants will build an ever-expanding knowledge of R as we go along.

Intermittently, participants will be given (anonymous) tests to allow for an evaluation of and give them feedback on their learning progress.

Prerequisites for attending:

  • A basic understanding of descriptive and (classic) inferential statistics would definitely be helpful
  • A laptop equipped with a wireless adaptor and a recent web browser

You have to register for the 9th International Research Workshop to participate in this course.