Linear mixed effects models in SPSS 3201-LST-OC-RM5-OG

We will learn how to organize data in the long format so it is suitable
for mixed models

2. We will learn what multi-level data is.
3. We will learn the difference between fixed effects and random
effects
4. We will learn how to conduct mixed models using different types of
dependent variables.
5. We will discuss different modelling techniques (and how to steer
clear of p hacking).
6. We will discuss model assumptions, e.g., eBLUPS (Empirical Best
Linear Unbiased Predictions) and Pearson-residual plots.
7. We will visualize the predicted results.

Type of course

general courses

Mode

Classroom

Prerequisites (description)

Expectations of the participants (skills, applications, equipment): 1. English proficiency at B2 (upper-intermediate) or higher 2. Software IBM SPSS statistics installed and ready to use (the license is available for staff and students at the University of Warsaw), and practical knowledge of it's functions 3. Knowledge of the following statistical concepts will be assumed: - The meaning of p values, standard errors, confidence intervals - The importance of effects sizes and how to obtain them. - The assumptions of parametric tests: how to check the assumptions and potentially solve problems when the assumptions are not met. - Test assumptions using residuals, where appropriate (e.g., normality, homogeneity of variance, linearity, collinearity). - Different types of variable transformations (e.g., log, square root) - T-tests (independent and dependent), ANOVAs (including interactions; between-subject and repeated measures). - Linear regression analysis (simple and multiple regression) and their assumptions. - How to normalise, re-scale (standardize), and center continuous predictors. - Using model predicted values to generate graphs to visualise results Note that some of these topics will be reviewed but only briefly. If necessary, the participant is advised to review these topics in more detail at their own time. A working knowledge of these topics will be assumed during the course.

Course coordinators

Breno Barreto Silva

Learning outcomes

After completing the course, a participant will:
 Have basic knowledge of linear mixed-effects models: theory
 Be able to run simple mixed-effects models
 Be able to diagnose the models
 Be able to visualize results

Assessment criteria

Work methods (underline the relevant points, or suggest others):
 individual work,
 pairwork,
 teamwork,
 audiovisual material,
 work on case studies,
 presentations,
 brainstorming,
 conceptual exercises,
 group discussions,

 other (specify) ……………..

Additional information

Information on level of this course, year of study and semester when the course unit is delivered, types and amount of class hours - can be found in course structure diagrams of apropriate study programmes. This course is related to the following study programmes:

Additional information (registration calendar, class conductors, localization and schedules of classes), might be available in the USOSweb system:

Description of 3201-LST-OC-RM5-OG in USOSweb