[Forside] [Hovedområder] [Perioder] [Udannelser] [Alle kurser på en side]
LEARNING OBJECTIVES:
After successful completing the course, the participants can
COURSE DESCRIPTION:
The creation of knowledge is pivotal to research and science. A central element of the knowledge process is methods and tools to create knowledge. Methods and tools are important skills and apabilities of master students and junior researcher for two reasons. First, a methodological apability would help their projects and development. Second, methodological insights are necessary o understand and discuss the findings of other researchers.
This course addresses the quantitative methodological aspect of social science. With off-set in research articles and methodologies, the course aims at developing students capabilities in data analysis and evaluation of the quality of this output. Students are expected to gain qualifications in how to create knowledge with a variety of quantitative methodologies. The choice of methods in this
course reflects the applications in empirical papers found in leading journals. The methods are derived to obtain an intimate relationship with the methods and to make it possible to derive own methods.
The course focuses on structural models with latent variables playing a key role. In the social sciences, variables determining observed behavior are often not directly observable, that is, they are patent variables (factors). From e.g. surveys, a variety of variables may be observed that measures aspects of the latent variables. It is the purpose of the course to estimate models that uncovers the structure among latent variables such that this structure can be given a causal interpretation. These
models include factor models, path analysis and structural equation models. The application of these models depends on the type of data. For instance, is the data quantitative or ordinal, or a combination of the two, and is the data a cross-section or longitudinal. Each of these data structures gives rise to different versions of the aforementioned models. Furthermore, new emerging methodologies in social
science like agent-based simulations are address.
COURSE SUBJECT AREAS:
PREREQUISITES:
Students attending the course are expected to have methodological and analytical competences in statistics and business research methods equivalent to Master studies of social science at the Faculty of social science, University of Aarhus.
LECTURER: Kristina Risom Jespersen and Allan Würtz
TEACHING METHOD: 4 lectures weekly for 10 weeks. There will be homework to practice the various inference methods including computer exercises. A short term paper is due at the end of the semester.
TEACHING LANGUAGE: English.
LITERATURE:
Main texts:
Johnson and Wichern (2007): Applied Multivariate Statistical Analysis. Pearson Education, Inc. Sixth edition. Chapters 8 - 11.
Kaplan (2008): Structural Equation Modeling. Sage Publications, Inc; Second Edition. Chapters 1 - 9.
Chaturvedi, A., S. Mehta, et al. (2004). "Agent-based simulation for computational experimeentation: Developing an artificial labor market." European Journal of Operational Research(In press).
Garcia, R. (2005). "Uses of agent-based modeling in innovation/new product development research." Journal of Product Innovation Management 22: 380-398.
Srbljinovic, A. and O. Skunca (2003). "An introduction to agent based modelling and simulation of social processes." Interdisciplinary Description of Complex Systems 1(1-2): 1-8.
Davis & Bingham (2007) Developing theory through simulation methods. Academy of Management review.
Chen (2004) Computational intelligence in economics and finance: Carrying on the legacy of Herbert Simon. Information Sciences.
Manuals for the statistical programming language.
(some of the main texts may be replaced with other texts covering the same material)
Supplementary readings:
Anderson, T. W. (2003): An Introduction to Multivariate Statistical Analysis. Wiley Series in probability and statistics.
Bloomberg, Boris (2009), "Business Research Methods", McGraw-Hill, 9 th edition.
Hair, Black, Babin, Anderson and Tatham (2006): Multivariate Data Analysis. Pearson Education, New Jersey.
Bollen (1989): Structural equations with latent variables. Wiley, New York.
Muthen (1983): "Latent variable structural equation modelling with categorical data." Journal of Econometrics 22, 43-65.
Joreskog and Moustaki (2001): "Factor analysis of ordinal variables: A comparison of three approaches." Multivariate Behavioral Research, 36 (3), 347-387.
Dijkstra (1983): "Some comments on maximum likelihood and partial least squares methods." Journal of Econometrics 22, 67-90.
Bentler (1990): "Comparative fit indexes in structural models." Psychological Bulletin 107, 238-246.
Muliak, James, Alstine, Bennett, Lind and Stilwell (1989): "Evaluation of goodness-of-fit indices for structural equation models." Psychological Bulletin 105, 430-445.
A selection of articles with a relevant methodological application to social sciences.
FORM OF ASSESSMENT: The assessment is based on points collected from home-work assignments, the evaluation of a short term paper (10 pages) by the student and the grade on a take-home exam.
EXAMINATION AIDS ALLOWED: All - except any means of electronic communication including calculators, mobile phones and PCs.
