Statistik für Fortgeschrittene
Transcription
Statistik für Fortgeschrittene
Statistik für Fortgeschrittene Dr. Kateřina Schindlerová Faculty of Psychology University of Vienna Multivariate Data Analysis Wintersemester 2014-2015 K. Schindlerová Statistik für Fortgeschrittene Introduction 1 / 16 Vorlesungsverzeichnis 200088 VO - Statistik für Fortgeschrittene Studienprogrammleitung Psychologie 2 Stunde(n), 5,0 ECTS credits Kapitel: 20.01 Katerina Schindlerova DO wtl von 09.10.2014 bis 29.01.2015 08.00-09.30 Ort: Hörsaal I NIG Erdgeschoß K. Schindlerová Statistik für Fortgeschrittene Introduction 2 / 16 Tutors: contacts 1 2 Title of the lecture: Advanced Statistics Tutoring: Dr. Kateřina Schindlerová Consultation hours: Mondays 1:00-2:00 a.m. email: [email protected] 3 Student Assistant Sandra Peer Consultation hours on request: email: [email protected] 4 Languages: German and English 5 A vocabulary of relevant English statistical terms will be provided on-line before every lecture; 6 The final exam is planned to be in German with the optional choice in English K. Schindlerová Statistik für Fortgeschrittene Introduction 3 / 16 Description of the Lectures Introduction of terms, definitions and methods, problems and applications of multivariate data analysis. The lectures will be given in seven modules: 1 2 3 4 5 6 7 Introduction into classification methods: cluster analysis and discrimination analysis; Introduction into exploratory dimensional analytical methods of principal component analysis and factor analysis; Regression modeling: regression of generalized linear models and logistic regression; Analysis of variance from the perspective of generalized linear models; Structural equation modeling; Log-linear modeling; Configural frequency analysis; The last modules will be taught depending how much time allows. K. Schindlerová Statistik für Fortgeschrittene Introduction 4 / 16 Requirements on the Students Presence in lectures helps the student considerably; not everything said is in slides; Knowledge of the definitions and methods of the intermediary statistics as well as understanding their algebraic and statistical elements; Ability to select a correct method in SPSS for solution and handling an appropriate software; SPSS available in Rechenzentrum of University Vienna, www.univie.ac.at/zid/software-shop; In principle, the on-line lectures cover the required knowledge to the final exam; The expected duration of the final exam: 60 to 90 minutes The concrete form of the exam will be announced in the last lecture of the semester K. Schindlerová Statistik für Fortgeschrittene Introduction 5 / 16 Literature There is no one-volume textbook which would cover all methods discussed in this course; These two-volume book covers all methods except structural equation modeling and configural frequency analysis: Jobson, J.D. (1991). Applied multivariate data analysis. Volume I: Regression and experimental design. New York: Springer. Jobson, J.D. (1992) Applied multivariate data analysis. Volume II: Categorical and multivariate data methods. New York: Springer. K. Schindlerová Statistik für Fortgeschrittene Introduction 6 / 16 Literature The following text is for advanced, statistically interested readers: it treats modeling out of the perspective of the general linear models: Fahrmeir, L., Tutz, G. (2001). Multivariate statistical modelling based on generalized linear models, 2nd ed. New York: Springer. K. Schindlerová Statistik für Fortgeschrittene Introduction 7 / 16 Literature Both the following texts are easier to read. However, configural freuquency analysis, structural equation models and general linear models are not discussed: Bartholomew, D.J., Steele, F., Moustaki, I, Galbraith, J.I. (2002). The analysis and interpretation of multivariate data for social scientists. Boca Raton: Chapman and Hall. Raykov, T., Marcoulides, G. (2008). An introduction to applied multivariate analysis. New York, NY: Taylor and Francis. K. Schindlerová Statistik für Fortgeschrittene Introduction 8 / 16 Literature The following text is recommended for general linear models: Kutner, M.H., Nachtsheim, C.J., Neter, J. Li, W. (2005). Applied linear statistical models, 5th ed., Boston, MA. McGraw Hill. K. Schindlerová Statistik für Fortgeschrittene Introduction 9 / 16 Literature Both the following books offer an introduction into structural equation models: Kline, R.B. (2011). Principles and and practice of structural equation modeling, 3rd ed. New York: The Guilford Press. Raykov, T., Marcoulides, G.A. (2006). A first course in structural equation modeling, 2n d ed. Mahwah, NJ: Erlbaum. K. Schindlerová Statistik für Fortgeschrittene Introduction 10 / 16 Literature The following text can be applied to explain the LISREL applications more in detail: Jöreskog, K.G., Sörbom, D. (2004). LISREL 8.7 for Windows. Lincolnwood, IL: Scientific Software International. An instructive introduction into in LISREL and SEM can be downloaded for free under: http://www.ssicentral.com/ K. Schindlerová Statistik für Fortgeschrittene Introduction 11 / 16 Literature The description of structural equation models for special application can be found in: Pugesek, B., Tomer, A., von Eye, A., (Eds.)(2003). Structural equation modeling. Applications in Ecological and Evolutionary Biology. Cambridge, UK: Cambridge University Press. Von Eye, A., Clogg, C. (Eds.)(1994). Latent variables analysis Applications for developmental research. Newbury Park, CA: Sage. K. Schindlerová Statistik für Fortgeschrittene Introduction 12 / 16 Literature An introduction into cluster analysis can be found in: Everitt, B.S., Landau, S., Leese, M. (2001). Cluster analysis. 4th ed. New York: Oxford University Press. Z. Huang. Extensions to the k-means algorithm for clustering large data sets with categorical values”. Data Mining and Knowledge Discovery, 2:283304, 1998. The following is a classics in area of categorical data analysis: Agresti, A. (2013). Categorical data analysis, 3th ed. New York, Wiley. The following book gives an introduction into log-linear models: von Eye, A., Mun, E.-Y. (2013). Log -linear modeling Concepts, interpretation and applications. New York: Wiley. K. Schindlerová Statistik für Fortgeschrittene Introduction 13 / 16 Literature The following two books deal with configural freuquency analysis: von Eye, A. (2002). Configural Freuquency Analysis - Methods, Models, and Approximations, Mahwab, NJ: Lawrence Erlbaum. von Eye, A., Mair. P., Mun, E.-Y. (2010). Advances in Configural Freuquency Analysis, new York: Guilford Press. K. Schindlerová Statistik für Fortgeschrittene Introduction 14 / 16 Organisation of the Course and Grading Organisation of the Course: The course consists of lectures, in which methods of multivariate data analysis will be explained theoretically and in concrete applications and examples. Recommendation to reading as well as voluntary homework will be given. The topics as well as the order of the lectures can change. Grading: In the last meeting in semester the written final exam will take place. Its results are the basis for the grade of the course. Other dates for exams will be given in the following semester. K. Schindlerová Statistik für Fortgeschrittene Introduction 15 / 16 List of topics - Themenliste Modul I II III IV V VI VII List of topics - Themenliste Topic Literature classification methods Jobson, 1992 for discrimination analysis; Everitt et al. (2001) for cluster analysis dimensional methods Jobson, 1992 regression Jobson, 1991; Neter et al., 2005; Agresti, 2013; von Eye and Mun, 2013 ANOVA Jobson, 1991; Neter et al., 2005 SEM Kline, 2011 Log-linear models Agresti, 2013; von Eye and Mun, 2013 CFA von Eye, 2002; von Eye et al., 2010 K. Schindlerová Statistik für Fortgeschrittene Introduction 16 / 16