Applied Statistics for Educational Researchers (DUH165)
This course is organized in several workshops in one week and will provide an introduction to structural equations models (SEM), latent interactions, multilevel SEM, and latent growth curve modeling. We will use the software package Mplus, and the software R will be introduced towards the end of the course.
Course description for study year 2024-2025
Course code
DUH165
Version
1
Credits (ECTS)
5
Semester tution start
Spring
Number of semesters
1
Exam semester
Spring
Language of instruction
English
Content
Learning outcome
By completion of this course, the PhD candidate will have gained the following:
Knowledge:
- of measurement theory
- a good understanding of multiple regression and factor analysis in SEM
- a good understanding of hierarchical structures in data, and how to address them in analysis a good
- a good understanding of SEM and LGC in complex survey data
Skills:
- running SEM and LGC analyses in Mplus
- preparing results of such analyses for publication
General competencies:
- being able to choose and apply the right analyses for the given design and data
- developing advanced strategies for further research
Required prerequisite knowledge
Recommended prerequisites
Exam
Form of assessment | Weight | Duration | Marks | Aid |
---|---|---|---|---|
Paper | 1/1 | Passed / Not Passed |
Evaluation will be based on active participation and analyses performed in an individual paper (Max. 4000 words). Coursework requirements: Active participation in lectures and seminars at the workshop. Self-study. The student’s workload will be approximately 150 hours of work
Coursework requirements
Course teacher(s)
Course teacher:
Simona Carla Silvia CaravitaCourse teacher:
Njål FoldnesCourse teacher:
Thormod IdsøeCourse coordinator:
Lene VestadStudy Program Director:
Hein BerdinesenCourse teacher:
Ulrich DettweilerCourse teacher:
Knud KnudsenMethod of work
In the seminar, we will introduce CFA and SEM and see how latent interaction effects and multilevel modeling work in the SEM framework. Moreover, the course demonstrates how Latent Growth Curve modeling (LGCM) 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 LGCM. The analyses will be demonstrated primarily in Mplus. The LGCM will also be replicated and shown together with an introduction to R.
The working format blends lectures, group discussions, and hands-on analyses in Mplus/ and in R.
Overlapping courses
Course | Reduction (SP) |
---|---|
Advanced Statistics for Educational Researchers: Analyzing Structural Equation Models and Latent Growth Curves w/ MPlus (DSP165_1) | 5 |