PSY9165 ¨C Quantitative Methods

Course content

This PhD-level course provides a thorough introduction to key quantitative methods for psychological research. Across three weeks, each containing 2-3 days of seminars, students will learn how to apply, interpret, and critically evaluate a range of important statistical techniques commonly used in empirical research. The course covers multiple regression with continuous and categorical variables, logistic and ordinal regression, and introduces generalized linear models. Beyond regression, students will engage with topics such as factor analysis, causal inference, power analysis, and experimental design. The course also provides a foundation in data visualization and offers a brief overview of advanced methods such as structural equation modeling, mixed-effects models, survival analysis, network analysis, and machine learning. Teaching will emphasize both conceptual understanding and hands-on data analysis using R.

Learning outcome

By the end of the course, you will be able to:

• Explain and apply fundamental concepts in quantitative research, including population vs. sample, standard error, confounding, mediation, and causal inference.
• Fit, interpret, and evaluate multiple regression models with continuous, categorical, and discrete outcomes.
• Conduct and interpret exploratory factor analysis to uncover latent structures.
• Design studies and perform power calculations.
• Use R for data analysis and visualization, including the use of ggplot2 for presenting results.
• Critically assess the strengths and limitations of different quantitative methods and their suitability for psychological and social science research questions.
• Demonstrate an awareness of more advanced techniques (e.g., SEM, mixed models, survival analysis, network analysis, machine learning) as potential tools for future learning and research.

Admission to the course

This is an elective course in the PhD program in Psychology.?PhD candidates from the Department of Psychology will have first priority, followed by PhD candidates from other institutions, and then other applicants. PhD candidates from the Department of Psychology (PSI) can register for the course via StudentWeb.

Contact the administration if you experience any issues with registration.

PhD candidates enrolled in programs outside the Department of Psychology can submit an online web form to request a place in the course.?Find the link to the online registration form here.

The registration period for the course is found on the online registration form, and you will receive an email shortly after the application deadline if you are accepted into the course. All participants must be registered before the first day of teaching.

Formal prerequisite knowledge

Admission to a PhD program.

Recommended previous knowledge

PSY9510 Intro to Statistics with R or equivalent knowledge.

Overlapping courses

• 3 credits overlap with PSY9170 ¨C Quantitative Analysis I.
• 2 credits overlap with PSY9175 ¨C Quantitative analysis II.

Teaching

Attendance at all teaching sessions is mandatory. Maximum absence allowed is 20%. Each day will consist of a combination of lectures and guided practical work with assignments. The goal is for students to be able to apply the methods to their own doctoral projects. The course will span a total of seven days, divided into three weeks. The structure is outlined below.

Week 1

• Day 1 (5 hours): Review of important concepts, including population and sample, standard deviation and standard error, experimental and observational data. Concepts will be illustrated with simple examples using, e.g., regression analysis.
• Day 2 (5 hours): Multiple regression with continuous explanatory variables. Topics include: fitting linear regression models in R, interpretation of regression coefficients, model diagnostics, and underlying assumptions.
• Day 3 (5 hours): Multiple regression with categorical and continuous explanatory variables. Topics covered will include dummy coding, F tests, and the connection between ANOVA and regression with categorical predictors.

Week 2

• Day 4 (5 hours): Regression with discrete outcome variables. We will cover logistic regression, regression with ordinal outcomes, and the concept of generalized linear models.
• Day 5 (5 hours): Discussion of important concepts, exemplified with regression methods covered on Days 2-4. Confounding, mediation, directed acyclic graphs, causality, statistical power, power simulation, and experimental design.

Week 3

• Day 6 (5 hours): Introduction to factor analysis, focusing on exploratory factor analysis. Keywords: dimensionality reduction, rotation, scales, discovering latent structures.
• Day 7 (2.5 hours): Presentation of results and data visualization using ggplot2.
• Day 7 (2.5 hours): Brief introduction to important topics: structural equation modeling, mixed effects models, survival analysis, network analysis, machine learning.

Examination

Students will have to submit a mandatory assignment given at the end of Week 1, and a final assignment (take-home exam) given at the end of Week 3. In the assignments, students will use the methods learned in the course to analyze a dataset and present the results.

Exams are submitted via Inspera.

Examination support material

All aids allowed. If using AI, you must explain and be transparent about its use; read more about guidelines for AI and exams on Artificial intelligence (AI) at UiO - University of Oslo

Language of examination

The exam can be submitted in either Norwegian or English.

Grading scale

Grades are awarded on a pass/fail scale. Read more about?the grading system.

More about examinations at UiO

• Use of sources and citations
• How to use AI as a student
• Special exam arrangements due to individual needs
• Withdrawal from an exam
• Illness at exams / postponed exams
• Explanation of grades and appeals
• Resitting an exam
• Cheating/attempted cheating

You will find further guides and resources at the web page on examinations at UiO.