MET522A Multivariate Data Analysis

• Topics

  This PhD-level course covers statistical methods essential for social science research. Participants will learn to select, execute, and interpret analyses from basic hypothesis testing to structural equation modeling. We will learn and practice several types of analyses, including those listed below.

  Hypothesis Testing:

  • Tests of mean differences (one-sample, independent, and paired t-tests, one-way and factorial ANOVA, ANCOVA with continuous covariates)
  • Tests of proportions (chi-square tests of independence and goodness-of-fit)
  • Equivalence tests
  • Basic Bayesian inference tests

  Power Analysis:

  • A priori sample size calculation
  • Minimal detectable effect size

  Regression Models:

  • OLS regression
  • Binary logistic regression
  • Mixed-effects/multilevel models

  Factor Analysis:

  • Exploratory factor analysis
  • Confirmatory factor analysis: model specification, identification, fit indices

  Advanced Analysis:

  • Mediation analysis (bootstrapping, SEM)
  • Moderation analysis (interaction effects, simple slopes, Johnson-Neyman)

  Structural Equation Modeling:

  • Latent variable models
  • Measurement model evaluation
  • Multi-group SEM and measurement invariance testing

• Learning outcome

  Upon completing the course, participants can:

  Knowledge

  • Identify assumptions, calculate effect sizes, and select appropriate statistical tests for all methods from t-tests through structural equation modeling.
  • Distinguish between analytical approaches (e.g., fixed vs random effects, EFA vs CFA) and their applications.

  Skills

  • Program analyses in R, perform tests in jamovi, and conduct power analyses in G*Power.
  • Prepare data for different types of analysis.
  • Create publication-ready tables and figures.

  General Competence

  • Detect statistical errors and questionable research practices (p-hacking, unreported tests, assumption violations) in published work.
  • Report results following APA standards with complete statistics and clear interpretations.

• Teaching

  The teaching consists of lectures, pen-and-paper quizzes, and software exercises.

• Restricted access

  • PhD candidates at NHH
  • PhD candidates at Norwegian institutions
  • PhD candidates at other institutions
  • PhD candidates from the ENGAGE.EU alliance
  • Motivated master’s students may be admitted after application, but are subject to the approval from the course responsible on a case by case basis
  • Individuals outside academia may be admitted after application, but are subject to the approval from the course responsible and the Vice Rector for Research on a case by case basis

  There is no cap on the number of students.

  NHH Research Scholars should register for the course as recommended.

• Recommended prerequisites

  Understanding of OLS regression.

• Required prerequisites

  Basic course in statistics at the undergraduate level.

• Compulsory Activity

  Score an average of 60% or higher in the four pen-and-paper quizzes.

  Compulsory activities (work requirements) are valid for one semester after the semester they were obtained.

• Assessment

  Individual term paper. Students will work on a set of datasets, conduct analyses, and write results sections. Students will have three months to submit the term paper from the last day of the course.

• Grading Scale

  Grading scale A-F.

• Literature

  The course reading list will be shared on Leganto.

• Retake

  Re-take is offered the semester after the course was offered for students with valid compulsory activities (work requirements). Additionally, the students must fulfill one of the two requirements listed below in order to be eligible for re-take:

  • Students who, at the original exam failed or got a grade below C
  • Students who were sick on the day of the exam and has provided a valid sick note ("sykemelding")

  Students will have the opportunity to submit a revised version of the replication project for the re-take assessment. If a revised version of the work is submitted, this must be clearly indicated on the front page.