Applied Statistics for Educational Researchers (DUH165)

Content

This week-long seminar consists of a series of workshops designed to introduce participants to basic and advanced statistical techniques, including confirmatory factor analysis (CFA), structural equation models (SEM), multilevel SEM, and growth curve modeling. Participants will gain hands-on experience using Mplus and R software for their analyses.

Learning outcome

By the end of this course, PhD candidates will have acquired the following knowledge:

Knowledge

• An understanding of basic measurement theory.

• A solid grasp of multiple regression and factor analysis within the structural equation modeling (SEM) framework.

• A clear comprehension of hierarchical structures in data and methods to analyze them effectively.

• A good understanding of SEM and latent growth curve (LGC) models in the context of complex survey data.

Skills

• Conducting preliminary analyses to assess the validity and reliability of data.

• Performing SEM and LGC analyses using Mplus or R.

• Preparing the results of these analyses for publication.

General Competencies:

• Ability to choose and apply the appropriate analyses for the given design and data.

• Development of advanced strategies for future quantitative research.

Required prerequisite knowledge

Recommended prerequisites

The students are expected to have the software package Mplus or R installed on their personal computers. It is beneficial to have some familiarity with the data structure of one's own projects and the potential research questions. It is advantage to get acquainted with Mplus or R before the course in order to master preparation of the data for import (for Mplus syntax, please see chapters 1 + 2 in Muthén & Muthén).

Exam

Coursework requirements

80 % attendance

At least 80 % attendance in lectures and seminars.

Course teacher(s)

Course coordinator:

Course teacher:

Course teacher:

Course teacher:

Study Program Director:

Course teacher:

Method of work

In this week-long seminar, we will introduce confirmatory factor analysis (CFA) structural equation modeling (SEM), and multilevel modeling work within the SEM framework. The seminar also demonstrates how Latent Growth Curve Modelling can be understood as an extension of SEM with intercepts and/or slopes being modeled as latent variables, first as an unconditional latent curve model. We will then look at conditional Latent Growth Curve models (including mediation models, and a comparison of (latent) groups with different approaches to testing measurement invariance. The latter will also be replicated and shown in R.

The working format is a blending of lectures, group discussions, and hands-on analyses in Mplus/R.

Open for

International and local students enrolled in a doctoral program. Max. 25 participants.

Course assessment

Literature