Sydney School of Education and Social Work events – 2014 Archive

This page is no longer updated. Page archived on Monday, 17 November 2014.

Designing quantitative research

MULTILEVEL MODELLING: WHAT IS IT? WHEN SHOULD YOU USE IT?
WHAT ARE ITS YIELDS?

17 November 2014

How much variation in achievement, motivation and engagement is there from student-to-student, class-to-class, and school-to-school? How much variation in income or unemployment is there from house-to-house, suburb-to-suburb, and council-to-council? Answers to these questions hold significant implications for policy and practice. Multilevel (or hierarchical linear) modelling is used to explore the extent to which variance in a particular phenomenon resides at the individual or group level. Education, for example, is a classic domain in which there exists hierarchically structured data, with the most obvious structure being students nested within classes that are nested within schools. Under hierarchical structures, it is hypothesised that individuals, and the group to which they belong, influence – and are influenced by – each other.

As Goldstein [2003, p2] notes: “to ignore this relationship risks overlooking the importance of group effects, and may also render invalid many of the traditional statistical analysis techniques used for studying data relationships”. In the 1980s, researchers began modelling approaches to hierarchically structured data. However, it was not until the 1990s that efficient software was developed to account for the hierarchical structure of data and research following from these software developments demonstrated the importance of treating data in this way. Today, multilevel modelling is routinely used in educational and social research. Using recent educational research examples, this presentation describes multilevel modelling, provides guidance on when it should be used, and outlines the benefits of using this analytic approach.

Event details

  • When: 1–2.30pm

  • Where: Room 638, Education Building A35, Manning Rd, University of Sydney
    Education Building A35
    Click image for interactive map.

  • Cost: Free

  • RSVP: RSVP by emailing Camilla Pilgrim.

  • Contact:

    Camilla Pilgrim
    Research Support Officer, Sydney School of Education and Social Work
    T: +61 2 9351 8945 | E: camilla.pilgrim@sydney.edu.au

  • More info: http://sydney.edu.au/education_social_work/doctoral_studies/research_training_support/research_training_modules/quantitative-research.shtml

  • Speaker: Professor Andrew J Martin is Professorial Research Fellow and ARC Future Fellow at the University of Sydney specialising in motivation, engagement, achievement and quantitative-research methods. He is also Honorary Senior Research Fellow in the Department of Education, University of Oxford and President Elect, International Association of Applied Psychology – Division 5 Educational, Instructional and School Psychology.

    Professor Martin is a registered psychologist recognised for psychological and educational research in achievement motivation and for the quantitative methods he brings to the study of applied phenomena. Although the bulk of his research focuses on motivation, engagement and achievement, Professor Martin is also published in important cognate areas such as boys' education, gifted and talented, academic resilience and academic buoyancy, personal bests, pedagogy, parenting, teacher-student relationships and Aboriginal education.


Designing quantitative research: multilevel modelling

Where Room 638, Education Building A35, Manning Rd, University of Sydney
Education Building A35
Click image for interactive map.

When

17 November 2014


Outlook / iCal Yahoo! Windows Live! Google