Professional Development Seminar: Multilevel Modeling with International Datasets
Data from large-scale international studies reflects the nested structure of education systems and is, therefore, very well suited for hierarchical linear modeling (HLM). However, because this data comes from complex cluster samples, there are methodological aspects that a researcher needs to understand when doing HLM, e.g., the need for using sampling weights and multiple achievement values for parameter estimation.
This course will teach participants how to do HLM with data from these studies, including PIRLS, TIMSS, and PISA. The content of the course will include a presentation on the design of large-scale international studies and databases, and implications for HLM analysis. Participants will learn how to specify simple two- and three-level models using the HLM 7 software package, incorporating students, classes or schools, and countries as hierarchical levels. There will be hands-on demonstrations on how to prepare an international dataset (using SPSS) for analysis with HLM 7 software and how to perform various HLM analyses. Participants will get the chance to work on practice exercises, with several instructors available to mentor and answer questions. Participants should have a solid understanding of OLS regression and a basic understanding of hierarchical/multi-level models.
Prior experience using a statistical software package, such as Stata or SPSS, is helpful. Prior knowledge about large-scale international studies or prior experience using the respective databases or HLM software is not required.
April 2017 at AERA (San Antonio)
April 2015 at AERA (Chicago)
March 2016 at CIES (Vancouver)
April 2016 at AERA (Washington DC)