Skip to main content

# Unit information: Multivariate Statistical Methods in Education in 2018/19

Please note: you are viewing unit and programme information for a past academic year. Please see the current academic year for up to date information.

Unit name Multivariate Statistical Methods in Education EDUCM5507 20 M/7 Teaching Block 2 (weeks 13 - 24) Professor. Leckie Not open Familiarity with basic descriptive and inferential statistics and the SPSS software to the level covered in EDUCM5504 Statistics in Education / EDUCM0003 Introduction to Quantitative Methods in the Social Sciences. Students should therefore be confident producing and interpreting standard summary statistics, data tabulations, graphs, 95% confidence intervals around sample means, t-tests and correlation coefficients. None School of Education Faculty of Social Sciences and Law

## Description

The unit will introduce students to a range of multivariate statistical methods widely applied in quantitative educational research. The philosophy of this course is that students will learn more by applying these methods using the SPSS software and to real education and social science datasets than by focusing solely on their underlying statistical theory. Methods covered include: analysis of variance, factor analysis, linear regression, and multilevel modelling.

The unit aims to:

• provide students with an understanding of when multivariate statistical methods are appropriate and how these methods can contribute to a more robust/powerful evidence base in educational research;
• provide students with the knowledge and skills to apply a range of multivariate statistical methods to secondary datasets using the SPSS computer package and to interpret their statistical output in relation to specific research questions.

## Intended learning outcomes

Upon successful completion of this unit students will be able to demonstrate that they:

1. Understand which multivariate statistical methods (ANOVA, factor analysis, linear regression, multilevel modelling) are appropriate in different data situations and for addressing different research questions.
2. Have a working knowledge of these methods and are able to apply them to data in SPSS and are able to interpret the resulting statistics appropriately.
3. Are able to select relevant information from SPSS statistical output and present the results in a format appropriate for publication.
4. Understand the key statistical issues associated with analysing clustered (i.e., hierarchical or multilevel) data and how multilevel modelling can be used to address these issues.

## Teaching details

Lectures, computer practicals using SPSS software, critical reading and discussion of published quantitative articles.

## Assessment Details

Formative assessment:

Weekly SPSS worksheets will be provided in which students attempt to apply the taught methods to data and to interpret the results. Annotated answers will then be provided, allowing students to check their progress.

Students will also have the opportunity to start the summative assignment in the final computer practical allowing them to receive feedback on general questions about the assignment and related unit material and SPSS.

Summative assessment:

The summative assessment consists of a structured assignment with several sections. In each section, students will be required to identify the appropriate method for the given research question and SPSS dataset. They will then have to apply the method and associated descriptive statistics in SPSS, present the results in the format of an academic report, and give a critical interpretation of the findings, reflect on the strengths and weaknesses of their analyses, and suggest potential improvements. (4,000 words equivalent). ILOs 1-4.

## Reading and References

Field A. (2013) Discovering Statistics Using SPSS (4th Edition). London, Sage

Miles, J. & Shevlin, M. (2001). Applying Regression & Correlation: A Guide for Students and Researchers. Sage Publications Ltd.

Modules 1 to 5 of the LEMMA on-line multilevel modelling on-line course: http://www.bristol.ac.uk/cmm/learning/online-course/course-topics.html

Taylor, Alan (2004). A Brief Introduction to Factor Analysis. http://www.psy.mq.edu.au/psystat/other/FactorAnalysis.PDF