Prospectus

nl en

Multilevel Analysis

Course 2012-2013

Admission requirements

Master’s students in Psychology with a:

  • Basic understanding of the concepts underlying multiple regression analysis
  • Basic understanding of vector and matrix algebra

Description

Multilevel analysis concerns the modeling of hierarchically structured data. These kinds of data are frequently encountered in many areas of (social) scientific research. Hierarchically structured data are characterized by so-called “nested” membership relations among the units of observation. For instance, students are nested within classes, which are nested within schools, employees are nested within departments, or repeated measurements are nested within participants. Traditional, “single level”, data analysis methods fail when data are hierarchically structured, because the nested structure causes intra-class correlation among the observations within units at the higher level. As a result, the assumption of independence is violated.

Multilevel analysis is a class of methods employing hierarchical linear regression models that explicitly take into account the hierarchical data structure. It provides researchers with a flexible and powerful set of tools with respect to both model formulation and hypothesis testing. Multilevel analysis proves to be statistically more precise. Also, it has been argued that multilevel models are conceptually uplifting.

Course objectives

This multilevel analysis course provides students with a basic understanding of the so called random coefficient model, which can be regarded as one of the key models in multilevel modeling. Additionally, students acquire basic skills in the application of the software package SPSS and R for multilevel analysis

Timetable

Multilevel Analysis (2012-2013):

Mode of instruction

  • Seven lectures
  • Supervised computer practicals.

Assessment method

Take home exam.

Blackboard

Multilevel Analysis occasionally uses of the learning environment Blackboard . (http://blackboard.leidenuniv.nl/)

Reading list

  • J.D. Singer and J.B. Willett (2003). Applied longitudinal data analysis: modeling change and event occurrence. Oxford University Press, Inc.
  • M. de Rooij (2012). Standard regression models for repeated measures data. (paper will be distributed during course).
  • J. Hox (2010). The basic two level regression model. Chapter 2 from Hox. J (2010). Multilevel Analysis. Techniques and applications (2nd edition). New York, NY: Routledge. Chapter available on the web. http://joophox.net/mlbook2/MLbook.htm

Registration

Course enrolment

Students need to enrol for the course via uSis on the master’s introduction and course enrolment day that takes place at the start of each semester. Please, consult the master’s agenda Psychology.

Contact information

Dr. M. de Rooij
Methodology and Statistics Unit, room 3B14
Tel: +31(0)71 527 4102
E-mail: rooijm@fsw.leidenuniv.nl