Causal Modelling and Evaluation: A Practical Hands-on Workshop
Date: 1st July 2019 – 5th July 2019
Venue: Seminar Rooms 1 & 2, Main Building. Institute of Psychiatry, Psychology & Neurosciences (IoPPN), King's College London. View Map.
Much of applied health and social research is aimed at estimating causal effects of risk factors or interventions (treatments, programmes, policies etc.). This includes analyses and assessments carried out by research organisations to inform their strategies and help with their management and funding decisions (policy and programme evaluation). However, it is not always clear whether the quantity targeted in a particular analysis/assessment has a causal interpretation and even if that is the case, whether it can be estimated without bias from the study data. For example, findings from observational studies are frequently criticised for lacking confounding control.
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.
The module will assume that participants are familiar with common research designs and have a good knowledge of regression analysis as can be gained from the BHI Introduction to Statistical Modelling course run in January and additional for those who want advanced regression knowledge in the BHI Multilevel and longitudinal Modelling run in February. Some experience of STATA or any other syntax-based statistical software such as R or SAS would be helpful (such as can be obtained from the BHI Introduction to Programming course running in October or the BHI Introduction to STATA course running in January).
Participants will need to bring their own laptop computer with STATA installed.
Subject specific: Knowledge, Understanding and Skills
On successful completion of this course the participant should be able to
- will have acquired a thorough understanding of core concepts of causal inference such as potential outcomes, marginal and local causal effects, self-selection and confounding, non-compliance, effectiveness and efficacy, mediation;
- will have knowledge of population summaries which have a causal meaning and will be aware of research designs which allow estimating causal effects. This will help participants identify and articulate causal effects of interest in new research contexts and help them in planning empirical studies to assess them.
- will have obtained an overview of study designs and principled analysis methods (including Propensity Scoring, Structural Equation Modelling and Instrumental Variables methods) that can be used to provide valid estimates of causal effects.
- will have acquired the skill to implement popular causal analysis approaches using the STATA general purpose statistics software;
- will be able to apply this understanding in the interpretation of evaluation studies and the critical appraisal of research papers.
- will have practised the specification of causal research hypotheses and the running of relevant statistical analyses on a number of datasets from different contexts and so acquired practical experience as a causal analyst.
General: Knowledge, Understanding and Skills
On successful completion of this module the participant should be able to
- will be equipped with a range of statistical skills, including problem-solving, team work and presentation, which enable them to take prominent roles in a wide spectrum of employment and research;
- will be able to effectively communicate how causal modelling techniques can be applied to evaluate health treatments and risk factors to non-specialist audiences;
- will be able to critically assess their own work using discussion groups;
- will be able to show initiative and the ability to work autonomously and independently with minimal guidance from others;
- will be able to show confidence in the use of general purpose statistical software to implement causal modelling for real-life applications.
Cost and Booking
Booking / Application
- External Early bird: £855 (till 31/05/19, price thereafter £950)
- KCL Staff Early bird: £641.25 (till 31/05/19, price thereafter £712.5)
- KCL Student Early bird: £427.5 (till 31/05/19, price thereafter £475)
- Other student Early bird: £641.25 (till 31/05/19, price thereafter £712.5)
- King's Health Partners Early bird: £641.25 (till 31/05/19, price thereafter £712.5)
That is, 50% discount to King's College London PhD students, 25% discount to other students and staff at King's College London and King's Health Partners.
Booking for this course has now closed.
To apply please email firstname.lastname@example.org with the following details:
Subject: Application for Causal Modelling and Evaluation: A Practical Hands-on Workshop 2019
Contact Phone Number:
- Are you affiliated with KCL and/or King's Health Partners?
- If Yes, indicate how you are affiliated with KCL and/or King's Health Partners
- Indicate your education/employee status: KCL PhD, KCL student, KCL staff, King's Health Partners affiliate, External Student or External
- In 100 words, state why you wish to enrol/participate in this course:
In 100 words, state which skills you hope to acquire:
Once your application has been approved, you will be sent a link to payment and a discount code if one is to be applied.
Professor Sabine Landau (Academic Lead)
Sabine is a Professor of Biostatistics and Lead of the Causal Modelling Group. She joined the Institute of Psychiatry as Lecturer in 1997 after early work in agricultural research (Rothamsted Research Harpenden) and obtaining a PhD in Applied Statistics from the University of Nottingham.
Her interest is in developing and applying statistical methods for behavioural research. Past methodological work has been on a variety of topics, including Cluster Analysis and the Analysis of Spatial Cell Patterns. Her current focus is on Causal Inference, in particular the development of methods and their application to learn more from clinical trials and to fully exploit information provided by observational data sources.
Causal modelling has an important role to play in advancing behavioural research methodology and can lead to new substantive insights. For example relevant techniques can be used to address questions about treatment mechanisms in trials. (How and for whom do treatments work?). A causal mediation analysis of a parenting programme led to a better understanding of the parenting components changed by the programme and translated into an improvement in child conduct. Another route of enquiry is the specification of conditions under which psychological therapies work. Sabine is involved in projects that develop methods for assessing treatment effect modification by post-randomisation variables (therapeutic alliance, compliance, contamination) to address such questions.
Sabine has extensive experience and expertise in Biostatistics and Trials. She currently serves as the senior trial statistician for a number of trials, in particular for the evaluation of complex interventions (psychological therapies). Most of her trials work is NIHR funded and affiliated to the King’s Clinical Trials Unit. She also supports the NIHR by serving on their funding panels. She is currently the statistics editor for the Journal of Child Psychiatry and Psychology.
Sabine is also active in education, supervising MSc and PhD students, co-leading the Research Methods and Statistics module for the MSc in Forensic Mental Health, running a number of advanced statistics courses for IoPPN staff and postgraduate students (including multilevel modelling, missing data) as well as leading a summer school in Causal Modelling and Evaluation.
Sabine is the departmental representative of the Diversity & Inclusion Self Assessment Team (D&I SAT) and a member of several IoPPN committees. She also acts as the department’s postgraduate research (PGR) lead.
See Sabine's research profile here.
Your place will not be confirmed until payment has been made. Failure to cancel without sufficient notice will forfeit your course fee and access to future courses. If you would like to pay by internal transfer, please contact email@example.com