PSY028_E Data Analysis

Faculty of Social Studies
Autumn 2018
Extent and Intensity
0/0/0. 10 credit(s) (from 5 credits increase by 5). Type of Completion: z (credit).
Teacher(s)
Mgr. Hynek Cígler, Ph.D. (lecturer)
Mgr. Michal Jabůrek, Ph.D. (lecturer)
doc. Mgr. Stanislav Ježek, Ph.D. (lecturer)
Bc. Adam Růžička (lecturer)
Mgr. Adam Ťápal, M.A. (lecturer)
Guaranteed by
doc. Mgr. Stanislav Ježek, Ph.D.
Department of Psychology – Faculty of Social Studies
Contact Person: doc. Mgr. Stanislav Ježek, Ph.D.
Supplier department: Department of Psychology – Faculty of Social Studies
Timetable of Seminar Groups
PSY028_E/Rustove_modely: No timetable has been entered into IS. S. Ježek, A. Ťápal
PSY028_E/SEM: No timetable has been entered into IS. S. Ježek, A. Ťápal
Prerequisites
--- Growth curves ---
Basic knowledge of multilevel (mixed) models, basics of structural equations modeling and beginner-to-intermediate proficiency with R.

--- Structural equation modeling ---
Good knowledge of (multiple) linear regression, basics of R, knowledge of latent variable models is an advantage.
Course Enrolment Limitations
The course is only offered to the students of the study fields the course is directly associated with.
fields of study / plans the course is directly associated with
there are 12 fields of study the course is directly associated with, display
Course objectives
--- Growth curves ---
Modeling growth with growth-curve models is the basic element of modeling development of psychological variables. Ii is useful not only in projects analysing explicitly developmental data but also in projects analysing repeated measurements without focusing on development. By the end of the course the students should be able to specify, estimate and interpret growth curve models (linear and non-linear) of both manifest and latent variables, assess longitudinal measure ment invariance and present the results of these analyses.

--- Structural equation modeling ---
Structural equation models constitute a wide family of models allowing to investigate relationships between manifest (measured, observed) variables and latent variables (factors). Structural models are commonly utilized in the correlational research tradition, while their general formulation allows for many uses in cases where one needs to work with latent variables above and beyond factor analysis (such as use them as predictors or predicted variables). After the course, the student will be able to formulate a structural model, estimate it using the lavaan package, interpret estimated parameters and evaluate model fit.
Learning outcomes
--- Growth curves ---
By the end of the course the students should be able to specify, estimate and interpret growth curve models (linear and non-linear) of both manifest and latent variables, assess longitudinal measurement invariance and present the results of these analyses.

--- Structural equation modeling ---
After the course, the student will be able to formulate a structural model, estimate it using the lavaan package, interpret estimated parameters and evaluate model fit.
Syllabus
  • --- Growth curves ---
  • 1. Repeated-measurement data - visualisation, description and transformation between wide and long format.
  • 2. Growth curve model based on multilevel (mixed) linear modelu. Unconditional model of linear and non-linear growth and its extension with covariates (conditional model).
  • 3. Latent curve/growth model based on the general SEM model.
  • 4. Higher-order growth curves. Curves of Factors and Factors of Curves with covariates. Longitudinal invariance.
  • 5. Growth mixture models (optional module)
  • --- Structural equation modeling ---
  • 1. Structural models / Analysis of covariance structures - an overview. Linear regression in a nutshell.
  • 2. Path analysis - from simpler relationships to the complicated.
  • 3. Exploratory (Unrestricted) factor analysis - an introduction to latent variables. Principal components analysis (optional).
  • 4. Confirmatory (Restricted) factor analysis.
  • 5. Factor analysis and latent regression.
  • 6. Structural models with means. Group models.
Literature
  • Bates, D. M. (2010). lme4: Mixed-effects modeling with R. Springer
  • WICKRAMA, K. A. S., Tae Kyoung LEE, Catherine Walker O'NEAL and Frederick O. LORENZ. Higher-order growth curves and mixture modeling with Mplus : a practical guide. First published. New York: Routledge, Taylor & Francis Group, 2016, xviii, 326. ISBN 9781138925151. info
  • BEAUJEAN, A. Alexander. Latent variable modeling using R : a step-by-step guide. First published. New York: Routledge, Taylor & Francis Group, 2014, xii, 205. ISBN 9781848726987. info
  • MCARDLE, John J. and John R. NESSELROADE. Longitudinal data analysis using structural equation models. Washington, DC: American Psychological Association, 2014, xi, 426. ISBN 9781433817151. info
  • SINGER, Judith D. and John B. WILLETT. Applied longitudinal data analysis : modeling change and event occurrence. Oxford: Oxford University Press, 2003, xx, 644. ISBN 0195152964. URL info
Teaching methods
Workshop, lecture.
Assessment methods
---- Growth curves ----
In order to finish the course, a student needs to attend at least 80% of the classes (thus, approximately 1 to 1.5 classes can be skipped). The course is graded on the basis of individual consultation/discussion between the lecturer and the student. For the consultation/discussion, the knowledge of the topic and class material is expected, as well as materials chosen based on individual preference.

---- Structural equation modeling ----
In order to finish the course, a student needs to attend at least 80% of the classes (thus, approximately 1 to 1.5 classes can be skipped). The course is graded on the basis of individual consultation/discussion between the lecturer and the student. For the consultation/discussion, the knowledge of the topic and class material is expected, as well as materials chosen based on individual preference.
Language of instruction
Czech
Further Comments
Study Materials
The course can also be completed outside the examination period.
The course is taught annually.
The course is also listed under the following terms Spring 2018.
  • Enrolment Statistics (recent)
  • Permalink: https://is.muni.cz/course/fss/autumn2018/PSY028_E