Learn SEM with Mplus in Cambridge

Get a unique learning experience.

Learn SEM with Mplus in Cambridge

Immerse yourself in the learning process.

Learn SEM with Mplus in Cambridge

Explore the beautiful town.

Learn SEM with Mplus in Cambridge

Feel the history of the place.

Welcome

 

For over 3 years I’ve been delivering courses on Structural Equation Modelling (SEM) with Mplus at the University of Cambridge, UK. I love it. In 2017 I will be teaching 2 courses, one in July and one in September, whose content is detailed below. The courses will be hosted at one of the Cambridge University colleges: Wolfson College. Having the course hosted at a College means you will also get to experience the uniqueness and charm of the Cambridge Collegiate system. And I am particularly excited about having Wolfson College as our host because it has one of the most beautiful teaching rooms, a jaw-dropper!

 

TESTIMONIALS

This MPlus course was fantastic. It not only provided me with the skills and confidence to conduct the analyses in MPlus but, also, the details of why, how, and what the analyses were about. Furthermore, I now know how to read and interpret the output files to assess and modify my models.

Dr Melissa Scarpate, University of Cambridge, UK

I attended the Structural Equation Modeling with Mplus course this autumn and found it very helpful. Gabriela explains and illustrates statistical models and Mplus programming in ways that ensures understanding, practical knowledge, and interpretation of the results. Her pedagogical ways in teaching are extraordinary and she explains difficult topics very well and ensures integrated understanding from the audience. The course, with good theoretical introductions and examples, ensures that every participant will progress in practice and understanding throughout the course.

Dr Rolf Gjestad, University of Bergen, Norway

Mplus course in Structural Equation Modelling (SEM) is truly unique. The course offers important topics about SEM and factor analysis that are all taught by a wonderfully supportive instructor who made me love statistics, even more; especially that it was not taught in a technical way. All the examples that were used made it easy to understand the statistics behind it. I wholeheartedly recommend it to anyone who is interested in statistics and looking to gain the essential skills needed for their academic careers, including graduates and researchers from different fields.

Eman El Sahan, University of Cambridge, UK

I did three courses in SEM in different UK universities last year, and this is by far the best. This course is pragmatic, it teaches you what you need without dwelling into complex mathematical explanations but at the same time, the basics are covered so you can be confident you will do your analysis rigorously.

Dr Blanca Bolea, University of Bristol, UK

The Mplus course is practical oriented. Many useful and helpful examples are provided in a cooperative atmosphere. And I really enjoyed the group atmosphere of the course.

Amelie Rogiers, Ghent University, Belgium

Attending the course turned out to be the best decision I ever made. The course has indeed provided me with the knowledge and skills necessary to analyze my data and turn them into meaningful causal models. Advanced topics such as mixture modeling, which I thought I’d never ever grasp, was made very simple. In sum, the course was awesome and enjoyable and I would highly recommend it.

Amna Al Abri, University of Conneticut, USA

Before starting on the course I didn’t know anything about SEM or MPlus. By the end of the course I felt confident enough to try these techniques on my own data. It was a very supportive and flexible course taught by a very knowledgeable tutor.

Dr Fiona Kyle, London City University, UK

The most useful course I went to. If you want to start working with Mplus, I strongly recommend taking this course. Everything is right: the pace, the reasonable size of the group, the theory kept to a bearable amount and the multiple applications and examples to get hands on the data analysis straight away. Gabriela makes sure everyone follows and is not stuck before moving on, so that we actually learn and apply the new knowledge straight away. I started using Mplus for longitudinal data analysis (latent growth curve modelling) for my own research after the course and the course material is my bible – I am referring to it all the time!

Dr Camille Lassale, UCL, UK

I really enjoyed the Mplus course. You don’t feel left behind, as it is practical and hands-on. I did not know a thing about Mplus nor SEM before I started the course and now I was already able to use some of the techniques on my own data…with success!

Mona De Smul, Ghent University, Belgium

This MPlus course with Gabriela was a great experience! It offered me a profound theoretical basis on SEM together with a lot of useful tips-and-tricks to work on my own data. Gabriela’s enthusiasm really encouraged me and she managed to explain complex ideas in a really comprehensible way. I would recommend this course to anyone interested in MPlus!

Sofie Heirweg, Ghent University, Belgium

I recently attended the structural equation modeling course run by Dr Gabriela Roman at Cambridge University. It was an instant relief to be a part of this course since I knew I would be using SEM for one of my PhD chapters but had no prior knowledge of this technique, and the course was run at a very comfortable pace, it was highly comprehensive and enjoyable. I benefitted very much, taking away with me invaluable knowledge of the basic foundations of SEM as well as insight into the intricacies of actually running these models and dealing with common and unusual problems- the latter of which I have been very grateful for recently when working with my own data! I highly recommend anyone who will be working with SEM to attend this course, it was excellent.

Ada Miltz, UCL, UK

This is a course that you should take, no matter whether you studied SEM before or not, or whether you used Mplus before or not. The scope of the topics covered in this course caters for pretty much every SEM researcher.

Ali Al Hoorie, UCL, UK

The course is very useful; the clear instruction explains how to trouble shoot difficulties in Mplus, leaving students confident at approaching future analysis.

Hanna Creese, UCL, UK

Gabriela’s course is unique in being taught by a real statistics expert who can answer any question you can imagine. The fact that she can also teach the basics with clarity makes this class highly valuable.

Peter Ward, University of Warwick, UK

Venue and Accomodation

The University of Cambridge is a “collegiate” university and is composed of Faculties, Departments and Colleges. As such, the Colleges are integral to the make-up of the University. Indeed, when students apply for a Bachelor’s degree, their application is evaluated by one or more colleges and they are admitted by a college, rather than a department. Furthermore, teaching for undergraduates contains two components: lectures and supervisions. Lectures are delivered at the department. Supervisions, which are small-group teaching sessions, are arranged and delivered by the colleges. They accompany broad-brush lectures and are regarded as one of the best teaching models in the world. Each college has its unique features and history.

Wolfson College, where our course will take place, was the first Cambridge College to admit men and women as students and Fellows on an equal basis – pretty awesome! It is also known for admitting a large number of mature applicants from a wide variety of backgrounds. Within the college, we’ll be having our sessions at the Chancellor’s Centre, where, if you like historical trivia, you will get to see the old 11th bell of the University Church of Great St Mary’s (a very important landmark in Cambridge).

Clare Hall College,  located a mere 10 minutes walk away from the course venue might be the perfect place for you to stay. Clare Hall is a graduate college and is renowned for its informal approach to college life and international diversity. The college offers a range of rooms, from single en-suite rooms (£70/night) to 1-bed flats (£110/night).

Tulip Tree House: If you prefer to go for the B&B experience, I recommend the nearby Tulip Tree House. It offers 2 rooms (one en-suite), each priced at £75/night. And it comes with continental breakfast.

A final note: If you plan to register for the course, please consider your accommodation options as soon as possible thereafter. Cambridge is very popular with tourists in the summer. So, if you’re interested in any of these rooms, do ask for details by emailing: contact[at]mpluscambridge.com.

Course

The course is aimed at complete beginners, so you don’t need to have any prior knowledge of either SEM or Mplus. You will need to bring a laptop that has the demo version of Mplus installed (you can download that free of charge from statmodel.com). Please be aware that to do your analyses, it is not likely that the demo version will suffice. If you don’t yet have Mplus, it is best to come to the course first and then buy it, as the course will help you choose the correct version for your research needs.

 

All about the research question

All about the research question

It’s not about learning a method, but learning how to answer different types of research questions.

Hands-on

Hands-on

Build models and interpret outputs in every session.

Comfort

Comfort

Includes lunch, as well as mid-morning and mid-afternoon coffee and cakes.

Materials

Materials

Get handouts and Mplus files to keep as work “companions” for your research.

Interactive

Interactive

An interactive course where you get to ask and answer questions throughout.

Unique

Unique

Get the full “Cambridge experience” in a university college.

Quiz

Quiz

Each day includes a quiz to help you grow your confidence.

Your research

Your research

Bring your own questions and ask me during the breaks.

Schedule

Day 1

Day 1

Introduction to Path Analysis and SEM

The first day provides an introduction to SEM and Mplus. The power of SEM lies in the fact that it combines factor analysis and regression analysis. Thus SEM has two main components: the measurement paths and the structural paths. These two main building blocks will be introduced on Day 1, together with details on how to specify and evaluate models in Mplus.

Schedule:

  • Session 1: Introduction to SEM and Mplus
  • Session 2: Confirmatory factor analysis
  • Session 3: SEM and mediation analysis
  • Session 4: Recap and Quiz

 

The programme is from 10am-5pm, split into 4 sessions of 1-1.5 hours each. Click on the other “bubbles” above to see the schedule for each day.

Day 2

Day 2

Multiple-group analysis

Research on differences between groups usually warrants two main research questions: ‘Are the average levels of a construct different between groups?’ and “Is the strength of the relationship between 2 (or more) constructs different between groups?”. But to answer both of these questions, the searcher must first ensure that the constructs measured function equivalently across groups. Can one truly conclude that 2 groups differ in a construct if it is revealed that the 2 groups under investigation interpreted the questionnaire differently?

Day 2 covers multiple group analysis and includes both information about measurement equivalence (i.e. invariance) and how to answer the main research questions of multiple-group studies.

Schedule:

  • Session 1: Introduction to multiple-group analysis and invariance testing
  • Session 2: Measurement invariance
  • Session 3: Structural invariance and Moderated mediation
  • Session 4: Recap and Quiz
Day 3

Day 3

Multilevel analysis

From a theoretical standpoint, multilevel analysis becomes relevant when one is interested in interactions between individual characteristics and features of an environment shared by multiple individuals. From a methodological standpoint, whenever you have a nested sample (e.g., random samples of children from different schools or classrooms), not taking the sampling into account in your analysis through multilevel analysis can lead to very biased results. But did you know you don’t always have to – and indeed in many cases you should not – use multilevel analysis even if your sample is hierarchical?

The material covered in Day 3 will explain when to use multilevel modelling and will address the analytical tools needed to understand cross-levels interactions between features of specific environments and of the people within these environments.

Schedule:

  • Session 1: Introduction to multilevel modelling and when to use it
  • Session 2: Multilevel modelling with predictors at each level
  • Session 3: Multilevel modelling with cross-level interactions
  • Session 4: Recap and Quiz
Day 4

Day 4

Path analysis and SEM with longitudinal data

Structural equation modelling with longitudinal data can be a powerful tool in understanding behaviour over time. Although often disregarded, longitudinal invariance is essential for models where one wishes to compare mean levels over time and models depicting individual trajectories over time. Indeed, if the questionnaire was not interpreted in the same way at different time-points, how can one conclude that any observed differences in scores represented true differences?

In addition to providing an introduction to modelling using Mplus and explaining longitudinal invariance, Day 4 provides insights into path analysis with longitudinal data, auto-regressive (including cross-lagged) models and longitudinal mediation analysis.

Schedule:

  • Session 1: Auto-regressive models and Longitudinal mediation
  • Session 2: Longitudinal Confirmatory Factor Analysis
  • Session 3: Longitudinal CFA with measurement invariance constraints
  • Session 4: Recap and Quiz
Day 5

Day 5

Modelling individual trajectories over time

Modelling individual trajectories over time is one of the most interesting and revealing techniques that can be applied to longitudinal data. It can provide information about the general pattern of people’s behaviour and attitudes, as well as each person’s individual trajectory over time. This can then be incorporated into structural equation models to better understand the extent to which a variety of antecendents translate into steeper increases or decreases of a behaviour over time.

Day 5 covers latent growth curve models (linear, quadratic and piecewise) and further builds on these models to show how to answer research questions that pertain to the development and mutual relationship between 2 (or multiple) psychological constructs, as well as questions about predictors and outcomes of individual trajectories.

Schedule:

  • Session 1: Introduction to latent growth curve models
  • Session 2: The trajectory shape
  • Session 3: Dual growth models and Growth models with covariates
  • Session 4: Recap and Quiz
Day 6

Day 6

Group-based trajectories

Sometimes a single average trajectory doesn’t equally well describe your entire sample. In this case, it is likely that different sub-groups exist, each sub-group having its own trajectory of behaviour / attitudes over time. This is where group-based trajectory modelling comes in.

Day 6 covers the main tenets of identifying sub-groups of people with specific developmental trajectories over time and explains the difference between several major technique variations: growth mixture models, latent class growth analysis, latent profile analysis, longitudinal latent class analysis, etc. It also explains how you can use information on each person’s “profile” (i.e. trajectory group membership) to further build models that include covariates/predictors and outcomes.

Schedule:

  • Session 1: Introduction to group-based trajectory modelling
  • Session 2: Latent Class Growth Analysis and Growth Mixture Models
  • Session 3: Group-based trajectories with covariates; Further topics
  • Session 4: Recap and Quiz

Buy

You can register for a place to the full course, or choose either the cross-sectional or longitudinal component. If you need to take only a selection of days (e.g., only the multi-level day or a set of 3 days that straddles the 2 components), please get in touch. I will be happy to offer you the pattern of days that best suits your research needs.

The fee includes tuition, course materials and lunch, but does not include accommodation. Upon check-out, you will receive a receipt. If you prefer to pay via invoice/bank transfer, please let me know (email: contact[at]mpluscambridge.com). Below you can purchase one or both course components for either July 2017 or September 2017.

The structure of the course is:

  • Cross-Sectional component: Monday, Tuesday and Wednesday.
  • Thursday is a day of independent study (no course takes place, an opportunity to relax and explore Cambridge).
  • Longitudinal component: Friday, Saturday and Sunday.

Checkout

The new Mplus book

I havRM_cover_smalle just finished reviewing the new Mplus book, titled “Regression and Mediation Analysis Using Mplus“. If you don’t already have it, you should get a copy now! You can get it from the Mplus website.

Here are my thoughts:

Importantly, the book offers a plethora of nuggets of knowledge that are near-impossible to find out there (at least it’s impossible to find them without scouring the internet and various obscure fora), like how set up loop plots or how to flexibly use the “model constraint” command for your own analyses.

A whole set of different mediation models. Whatever your research topic, you are bound to want to answer the “why” and “how” questions, which will call for the introduction of causal chains and mediators. But mediation models can vary greatly and having this book handy will really  make a difference.

Trouble-shooting problems in a detailed way. For example, what can you do if you get a standardized coefficient greater than 1?

Detailed examples of a multitude of regression models, with explanations of how to interpret the output files. If you’re a beginner and need to do a zero-regression Poisson regression because your outcome variable is a count variable (e.g., nr. of crimes or nr. of hours spend playing video games), you can find how to specify a simple model in the user guide. But interpreting the output is a whole different ball-game and this book really provides all the hand-holding you might need.

Easy explanation of the Maths behind regression models (I’ve put this first because it’s such a relief to find all this infomation in one place, instead of struggling to learn it from fragmented sources – but if this is not your cup of tea, move on to the next point).

About

Gabriela RomanMy name is Gabriela Roman and I am a Research Associate at the Institute of Criminology, University of Cambridge. Previously I was fortunate to learn a little bit about various branches of psychology and criminology: a PhD in developmental psychology (Cambridge University), an MPhil in criminological research (Cambridge University), and a BA in cognitive and social psychology (Jacobs University Bremen).

My main research interest is the development of cognitive and emotional self-regulation and the role of self-regulation for behaviour difficulties (in early childhood) and criminal behaviour (in adolescence and early adulthood). I am particularly interested in family contributions to the development of self-regulation. I have also been involved in various interesting projects as a consultant. I am currently working on a book about young people’s pathways into crime, from age 13 to age 24.

In 2013, I developed an 8-day course on Mplus together with my friend Dr Arielle Bonneville-Roussy. This was hosted by the Psychometrics Centre within the Department of Psychology at the University of Cambridge. Teaching it and interacting with so many interested (and interesting!) participants has been a truly wonderful experience! In 2016 Arielle took up a lectureship elsewhere and the Psychometrics Centre became part of Judge Business School Executive Education Ltd, a company associated with the Judge Business School at Cambridge. I thought for a while about whether the course should continue, but when I started receiving queries about future courses from people who’d seen old ads online, I realised the course must go on.

I hope you will enjoy the course at least as much as I enjoy teaching it. Best wishes and I hope to see you soon!

Gabriela.