Experience sampling: Opening the black box of daily life

Introduction

Key terms: quantitative research, experience sampling methodology (ESM), designing intensive longitudinal studies, analysis of intensive longitudinal data (with R), introductory course, relevant for students in any PhD phase.

ECTS: 2
Number of sessions: 3
Hours per session: 3

Are you looking for a statistical method to trace psychological and behavioural processes as they unfold in daily life? Experience sampling methods (ESM) can help you do just that.

ESM allows researchers to collect real-time data via smartphones, enabling the study of phenomena in their natural context. However, using ESM also raises methodological questions. What sampling schemes are appropriate? How can we optimise participant compliance? And how do we analyse this type of data?

The course begins with a lecture on the relevance and potential of ESM, followed by two hands-on modules. Module A focuses on the design of ESM studies, covering sampling schemes, monitoring protocols, participant engagement, and measurement development. Module B covers basic data analysis in R, including multilevel modelling and reliability.

Working methods include lectures, guided discussions and brainstorms, and practical assignments. Participants are encouraged to bring their own research ideas or data to the sessions.

The course does not cover in-depth analytical strategies for intensive longitudinal methods.

Entry level and relevance

This course is relevant for PhD students from any discipline who work with quantitative data and are interested in applying experience sampling methods. 

Module A (design) requires no prior knowledge of ESM. Module B (analysis) assumes basic knowledge of R, such as data importing. Participants unsure of their R proficiency are advised to contact the instructor in advance.

The course is useful for PhD students at any stage of their research trajectory, particularly those planning their own intensive longitudinal study.
 

Relations with other courses

Session 3 of this course offers a brief introduction in nested data and relevant multilevel analytical techniques, which will be addressed more comprehensively in the EGSH course Multilevel modelling. 

Further, the EGSH course Data analysis with R offers an extensive introduction to the program R. While taking that course may serve as useful preparation for this course on ESM, it is not a prerequisite. 

Sessions and preparations

Session 1: Introduction to Experience Sampling
A lecture on the principles, relevance, and applications of ESM in social science research. No preparation required.

Session 2: Designing an ESM Study (Module A)
Covers developing sampling schemes, compliance protocols, and item selection. Participants will discuss their own study ideas. Preparation: short reading and reflection on personal research question (provided in syllabus).

Session 3: Analysing ESM Data in R (Module B)
Participants will learn how to compute intra-class correlations, test scale reliability, and run multilevel models in R. Preparation: install required R packages and bring a cleaned dataset (optional).