Training & resources


CLOSER Learning Hub

The Learning Hub is an online teaching resource has been produced by CLOSER to introduce longitudinal studies to non-experts in both academic and policy settings. The Learning Hub has information and resources to help you explore longitudinal studies and get started using the data. As you progress through the different sections of the site, you can test their knowledge using interactive quizzes.

Topics covered include:

  • Introduction to longitudinal research: types of longitudinal studies and using longitudinal data for research
  • Study design: sampling, data collection instruments, methods of data collection and sweep implementation
  • Analysis: getting started and exploring the data, general linear regression, logistic regression and multinomial logistic regression

An overview of how longitudinal research can be used by researchers, policymakers and practitioners to increase our understanding of mental health and wellbeing is also available in the ‘explore by topic’ section. Case studies of longitudinal research are also provided, covering the research questions asked, what data were used, key findings and implications for policy.


UK Data Service Data Skills Modules
UK Data Service 

These introductory level interactive modules are designed for users who want to get to grips with key aspects of survey, longitudinal and aggregate data. The three modules can be conducted in your own time and you are able to dip in and out when needed. The modules give an introduction to key aspects of the data using short instructional videos, interactive quizzes and activities using open access software where possible.

Longitudinal data module units include:

  • Unit 1: What are longitudinal data?
  • Unit 2: Use cases
  • Unit 3: Downloading data & getting started
  • Unit 4: Preparing to work with the data
  • Unit 5: Analysing the data


ESS EduNet
European Social Survey

To facilitate and enrich access to and usage of survey data, the ESS-project was granted seed funding to create an Internet-based analysis-training programme, ESS EduNet. Typically, modules contains some theoretical background on an important social science problem, with this illustrated by results found by analysing the ESS data. Each topic contains exercises to be solved using ESS data either online or after data has been downloaded.

Modules include:

  • Regression
  • Measurement errors
  • Multilevel modelling
  • Weighting in the ESS
  • Latent variable modelling
  • Wellbeing
  • Family, gender and work
  • Social and political trust


NCRM Online Learning Resources
National Centre for Research Methods

NCRM has many online resources that cover a wide range of research methodologies and are intended to help people interested in social science research methods. They follow a standard format and each includes purposely-created video tutorials and supporting materials such as presentation slides and video transcripts along with related datasets, recommended readings and links to related research publications and resources.

Topics covered include:

  • Survey data quality and total survey error
  • Multilevel models: random coefficient and intercept models
  • Structural Equation Modelling (SEM): what it is and what it isn't
  • Biosocial research framework


LEMMA Online Multilevel Modelling Course
University of Bristol Centre for Multilevel Modelling

The LEMMA (Learning Environment for Multilevel Methodology and Applications) online multilevel modelling course contains a set of graduated modules starting from an introduction to quantitative research progressing to multilevel modelling of continuous and binary data. All modules have a concept component, and most modules have practical lessons - instructions on how to carry out analyses in MLwiN, R and Stata. Interactive quiz questions are included throughout the modules to self-test your understanding.

Course modules include:

  • Multiple regression
  • Multilevel structures & classifications
  • Introduction to multilevel modelling
  • Application 1: The use of performance indicators in education
  • Regression models for binary responses
  • Multilevel models for binary responses
  • Multilevel modelling in practice: Research questions, data preparation and analysis
  • Single-level and multilevel models for ordinal responses
  • Single-level and Multilevel Models for Nominal Responses
  • Three-level multilevel models
  • Cross-classified multilevel models
  • Multiple membership multilevel models
  • Missing data
  • Multilevel Modelling of Repeated Measures Data


Introduction to Growth Curve Modeling
Curran-Bauer Analytics

Growth curve models go by a variety of names (multilevel models, mixed effects models, latent curve models) but share a common focus on individual change over time. In this series of videos, Patrick Bauer introduces growth curve modeling and provides an overview of many options for analyzing repeated measures data

Materials from an introductory workshop "Introduction to Growth Curve Modeling: An Overview and Recommendations for Practice" are also available. These materials include slides from the workshop and the data on Patrick describes in the videos, as well as scripts for fitting linear growth models to this data in SAS, SPSS, Stata, and Mplus.

Video episodes include:

  • What is growth curve modeling?
  • The coding of time
  • A multilevel modeling framework
  • A structural equation modeling framework
  • Nonlinear trajectories
  • Time-invariant covariates
  • Time-varying covariates
  • Multivariate growth
  • Choosing between multilevel and structural equation approaches 


Mplus Short Course Online Resources

Mplus has made presentation videos and slides available from a range of short courses on different topics. 

Topics covered include:

  • Advanced factor analysis and structural equation modeling with continuous outcomes
  • Advanced regression analysis, IRT, factor analysis and structural equation modeling with categorical, censored, and count outcomes
  • Introductory and intermediate growth modeling
  • Advanced growth modeling, missing data analysis, and survival analysis
  • Categorical latent variable modeling with cross-sectional and longitudinal data
  • Multilevel modeling of cross-sectional and longitudinal data
  • Bayesian analysis using Mplus
  • Regression and mediation analysis
  • Introductory, intermediate and advanced dynamic structural equation modeling 


Introduction to Longitudinal Data Analysis
University of Manchester
Duration: 1 day 

The course covers basic concepts in longitudinal design and analysis. The morning session focuses on the strengths and methodological difficulties of the longitudinal approach such as defining longitudinal populations and target samples; levels and dimensions of change; age, period and cohort effects. After lunch, we start with an overview session on the sources and causes of missing data (attrition, etc), and how to adjust for missingness. 

By the end of the course, students should have gained:

  • An understanding of the different ways of measuring and explaining change using longitudinal data
  • An appreciation of the particular problems posed by missing data in longitudinal research
  • A basic understanding of ways of adjusting for missing data
  • Confidence to address questions about longitudinal design and missing data

Students should have some background in empirical social science and a basic grounding in statistical modelling, at least in linear regression.


Longitudinal Data Analysis
University College London
Duration: 2 days 

This course aims to provide a good understanding of a range of techniques for longitudinal data analysis and hands on experience of the analysis of longitudinal studies. It includes a mixture of theoretical sessions and practical sessions (using STATA) to illustrate concepts. Practical sessions will use data from longitudinal studies of health research, such as the English Longitudinal Study of Ageing (ELSA).

The course will cover:

  • Random effects models for continuous outcomes
  • Growth curve models
  • Random effects models for binary data
  • Event history analysis

This course is intended for those with experience in:

  • Using STATA or similar package
  • Linear and logistic regression
  • Data analysis


Longitudinal Data Analysis
University of Manchester

The course covers two of the most useful ways of analysing longitudinal data. In the morning we cover growth curve analysis within a multilevel modelling framework. The theoretical ideas are embellished with practical work using data from the National Child Development Study. After lunch, basic concepts in survival analysis and event history analysis are introduced followed by practical work with a simple (pencil and paper) example.

By the end of the course, students should have gained

  • An understanding of how growth curve models can be used to analyse repeated measures data
  • An appreciation of the ways in which duration and transition data can be analysed using techniques initially developed in medicine and industry
  • Confidence to carry out practical work with some kinds of longitudinal data.

Students should have a strong background in empirical social science and a good understanding of the basics of statistical modelling, at least up to multiple linear regression. Some experience with STATA would be useful but not essential.


SLLS – Summer School on Longitudinal and Life Course Research
Summer School on Longitudinal and Life Course Research
Duration: 4 days

The Summer School on Longitudinal and Life Course Research brings together scholars from diverse backgrounds and introduces them to the main theories and methods in longitudinal and life course research. Themes covered include:

  • Sociology and Demography of the Life Course
  • Life Course Epidemiology
  • Life Course and Genetics
  • Event History Techniques
  • Multilevel Models for Life Course Processes
  • Structural Equation Models (SEM) for longitudinal data
  • Sequence Analysis Approaches

Intended for post-doctoral fellows and postgraduate research students who are interested in exploring the potential of longitudinal and life course research or who want to further develop their existing skills.


Multilevel and Longitudinal Modelling
King’s College London, Institute of Psychology, Psychiatry and Neuroscience
Duration: 4 days

As health care data becomes more complex and multimodal, the structure of the data becomes increasingly complicated. There could be an increasing number of repeated measurements on the same individuals over time, longer duration of follow-up for time-to-event outcomes or nested hierarchies leading to non-independence of individuals. The use of simpler statistical approaches to analyse these data is invalid because the key assumptions of those approaches do not hold. In this module, we introduce the concept of multilevel and longitudinal modelling, including time-to-event or survival analysis.

The aim is for the student to understand the challenges of longitudinal and clustered data, and the concept and implementation of multilevel models. Students will also become familiar with the most common models for time-to-event data (including Cox proportional hazard models, additive hazard models), and finally link all these concepts together through joint modelling of survival and longitudinal data.

This workshop will assume that participants have a good knowledge of basic regression and statistical modelling and any syntax based statistical software, such as STATA.


Analysing Longitudinal Data: Using Latent Variable Models to Assess Change
Ulster University
Duration: 2 days

The analysis of change is central to much psychological and social research. Latent Growth Models (LGM) are an important class of models for the assessment of change. In essence these describe individuals’ behaviour in terms of an initial starting point and their subsequent developmental trajectories. The technique also allows for the introduction of predictors of change. Growth mixture models (GMMs) will also be introduced. These models enable the researcher to explore longitudinal data for the presence of unobserved or latent subgroups and estimate latent growth parameters for each of the subgroups.

It is expected that participants will have some knowledge and understanding of Structural Equation Modelling. This workshop will use the Mplus programme.


Longitudinal and Missing Data
Royal Statistical Society
Duration: 2 days

When analysing hierarchical and longitudinal data, one is often confronted with missing observations, i.e. scheduled measurements have not been made, due to a variety of (known or unknown) reasons. It will be shown that, if no appropriate measures are taken, missing data can seriously jeopardize results and interpretation difficulties are bound to occur. Methods to properly analyse incomplete data, under flexible assumptions, will be presented.

The course begins with a brief presentation of linear mixed models for continuous hierarchical data. Emphasis will be on model formulation, parameter estimation and hypothesis testing, as well as the distinction between the random-effects (hierarchical) model and the implied marginal model. Models for non-Gaussian data will be discussed, with a strong emphasis on generalized estimating equations (GEE) and the generalized linear mixed model (GLMM). A brief review of the classical generalized linear modelling framework will be presented. Similarities and differences to the continuous case will be discussed. The differences between marginal models (such as GEE) and random-effects models (such as the GLMM) will be explained in detail. Focus will be primarily on binary outcomes, however, GEE and GLMM model formulations will also be covered.

Throughout the course, it will be assumed that the participants are familiar with basic statistical modelling, including linear models (regression and analysis of variance), as well as generalized linear models (logistic and Poisson regression). Pre-requisite knowledge should also include general estimation and testing theory (maximum likelihood, likelihood ratio).


Analysis of Repeated Measures
University of Bristol
Duration: 3 days

This course provides an introduction to methods for analysing longitudinal/repeated continuous data, with a focus on methods for analysing individual trajectories over time. Multilevel modelling and structural equation modelling (SEM) approaches will be described and compared. Throughout the course there will be an emphasis on what kinds of research question different types of method can be used to explore, and the interpretation of results.

The course is intended for researchers who are, or will be, involved in analysing longitudinal data. Participants should be familiar with the algebra of standard regression models for continuous outcomes.


Integrating and analysing multiple datasets
National Centre for Research Methods, UK Data Service & University of Manchester
Duration: 2 days + optional Introduction to R webinar

This workshop will provide participants with conceptual and technical skills to understand the processes of using data from different sources. This course will introduce participants to the complexities of analysing data from multiple sources and cover issues of data quality, cleaning, derivation and linkage. The workshop will be comprised of presentations and practical exercises using data from the UK Data Service and open data sources.

This workshop will enable participants to:

  • Produce data descriptions and summaries to understand the data.
  • Use statistical tools to clean and manipulate data
  • Integrate relational data
  • Identify and handle missing data
  • Visualise data and explore patterns
  • Improve their interdisciplinary team working skills


Figure It Out 1-Day Quantitative Methods Training Courses
Figure It Out
Duration: 1 day

Figure It Out runs occasional one-day training courses, held in Sheffield, London or Berlin, and taught by Dr Chris Stride, assisted by Dr Charlotte McClelland or Dr Sarah Gardner. These hands-on small-group sessions offer the opportunity to be taught by a professional statistician with many years experience of both applying statistical methodology and data management skills using a variety of software packages, and of teaching non-statisticians from social science and management backgrounds.

Full details of the content of each course and the level at which it is aimed can be found here. Upcoming training courses include:

  • Structural Equation Modeling using Mplus
  • Testing for Mediation & Moderation using Mplus or SPSS
  • Multilevel Modelling using Mplus or SPSS
  • Latent Growth Curve Modeling using Mplus
  • Data Management using SPSS Syntax


Mplus: A beginner's course in longitudinal data analysis
CambridgeSEM, Selwyn College, Cambridge
Duration: 3 days

This 3-day course is a beginner's course in SEM with Mplus. It is hosted by Selwyn College, University of Cambridge. The first day provides an introduction to longitudinal data analysis and includes auto-regressive models and longitudinal factor analysis with invariance constraints. The second day is focused on individual trajectories over time and includes linear, quadratic and piecewise growth models. The third day is focused on group-based trajectory models and includes latent class growth models, growth mixture models and longitudinal latent class analysis.

The only prerequisites needed for this course are to be familiar with the general structure of the input and output files of Mplus, have knowledge about confirmatory factor analysis, and (optional) knowledge about measurement invariance.


Causal Modelling and Evaluation: A Practical Hands-on Workshop
King’s College London, Institute of Psychology, Psychiatry and Neuroscience
Duration: 4 days

This course will review statistical designs and analyses that enable valid causal effect estimation, including Propensity Scoring and Mendelian Randomisation in observational studies, methods for dealing with non-compliance in trials, Mediation Analysis and some Quasi-experimental designs. We will focus on methods that are easily accessible to the applied researcher. Throughout methods will be motivated and demonstrated with real data examples from health research. The course will use STATA, although analyses are easily translatable to other general-purpose statistical software packages.

Participants are expected to be familiar with common research designs and have a good knowledge of regression analysis. Some experience of STATA or any other syntax-based statistical software such as R or SAS would be helpful.


Causal Inference in Epidemiology: Concepts and Methods
University of Bristol
Duration: 3 days 

This course will introduce participants to concepts of and methods for, causal inference in epidemiological research, with a focus on their application. Topics covered include:

  • Potential (counterfactual) outcomes
  • Causal diagrams (DAGs)
  • Confounding
  • Control of confounding using stratification, standardization, regression models, propensity scores and inverse probability weighting
  • Selection and information biases
  • Instrumental variable estimation, including analysis of Mendelian randomization studies
  • Time-varying confounding and marginal structural models

This course is aimed at epidemiologists, statisticians and other quantitative researchers.


Causal Inference in Epidemiology: Recent Methodological Developments
London School of Hygiene and Tropical Medicine
Duration: 4 days 

This course will discuss the current state of the art with respect to these issues, while retaining a practical focus. The potential outcomes framework, causal diagrams, standardization, propensity scores, inverse probability weighting, instrumental variables, marginal structural models, causal mediation analysis and examples of sensitivity analysis will be discussed. Participants will acquire awareness of the common threads across these new methods and competence in applying them in simple settings.

Participants will be expected to be numerate epidemiologists, or applied statisticians with an interest in epidemiology and clinical trials.


NO! That's fine
This website is using anonymised Google analytics to help us work out how to make it better! More details