Upcoming events

Intersectionality and MAIHDA Conference

Friday, 10th July 2026, Lecture Theatre 3, The Wave, The University of Sheffield

Registration from 9.30am, Conference starts at 10am and finishes at 4.45pm

With a pre-conference course on MAIHDA – Thursday 9th July 2026; 9.30am registration, 10am course start and finishes at 4.45pm

This conference will focus on the use of MAIHDA – Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy – as a method for uncovering and understanding intersectional inequalities . MAIHDA has become widely used, both in social epidemiology where it was first proposed, and in other disciplines across the social sciences, and has been described as a gold-standard approach for quantitative evaluation of inequalities. The approach has been extended to consider causal effects, longitudinal data, spatial data, and more. There have also been a number of critiques of the method, considering both its statistical properties and its relationship with intersectional theory.

This conference will explore those issues, showcasing methodological advances and extensions of MAIHDA, advanced applications, and consideration and critique of MAIHDA and its goals. The conference will bring together academics from a range of substantive disciplines to think more deeply about the method and what it does and does not achieve. It will be of interest to researchers interested in quantitative approaches to intersectionality and multiplicative social inequalities. There will be poster presentations for those who wish to present their own MAIHDA (or MAIHDA-related) work.

The keynote speaker for the conference will be Dr Clare Evans at the University of Oregon, who first conceived of MAIHDA in her 2015 doctoral dissertation, and has been central to its development and application since then.

FULL PROGRAMME

Three 75-min sessions. Each session has three 25 min talks (including time for questions)

9.30 – 10.00 : Registration

10:00 – 11:00 Keynote: 

  • Clare Evans – A 10-Year Retrospective Review and Future Directions for Intersectional MAIHDA (tbc)

11:00 – 11:15 Break

11.15 – 12.30: Extensions of MAIHDA

  • Ansuman Swain: Extending MAIHDA for counterfactual risk prediction: Quantifying lifestyle-driven reductions in Type 2 Diabetes risk across sociodemographic intersections
  • Dario Moreno Agostino: Acknowledging intersectional complexity in both measurement and outcomes in youth mental health: evidence from the Millennium Cohort Study
  • Aaron Koay: Developing an intersectional cascade of care: A methodological case study of inequities in hypertension in Malaysia

Lunch + posters

13.30 – 14.45: Testing MAIHDA

  • Yiyang Gao: When does shrinkage improve intersectional estimation? A scenario-based simulation comparison of MAIHDA and Random Forest
  • Ruri Protopopescu: Comparing logit, poisson and linear probability MAIHDA models for discrete, rare outcomes 
  • George Leckie: Extending MAIHDA to explore intersectional differences in the variability of individual outcomes

Break

15.15 – 16.30: Critiques and reflections

Sophie Bright: A systematic review of MAIHDA applications

Joseph Lam: Studying ethnicity and intersectional effects – are more disaggregated ethnicity categories always better?

Natalie Bennett: Interpreting inequalities and causal considerations – reflections on the application of descriptive intersectional MAIHDA

To book this free conference please follow this link

Intersectionality and MAIHDA Training Course

10.00am, 9th July, The Wave, The University of Sheffield, (9.30am registration)
Course ends at 4.45pm

Multilevel models allow researchers to use data that has a clustered structure – such as pupils nested within schools, or individuals within neighbourhoods. Recently, a version of multilevel models has been developed for the study of intersectional inequalities in individual outcomes. With the Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy (MAIHDA), individuals are nested within their intersectional strata – that is their combination of various sociodemographic identity categories –for instance gender, age, ethnicity and social class.

This method has great potential for uncovering and understanding intersectional inequalities, where a combination of social identities combine in complex ways to produce societal (dis)advantage.

This training course will provide a short introduction to the intersectional MAIHDA approach. We will briefly cover multilevel models more generally, before focusing on MAIHDA. We will then consider extensions of MAIHDA, for instance when considering varying slopes, or when using longitudinal data. Throughout, we will show how to use  the MAIHDA approach, some key statistics that can be produced from that approach, give advice on how to visualize the results that are produced, and how to interpret the results robustly.

The course will include interactive lecture sessions, and computer practical exercises that can be undertaken in either Stata or R.

Prerequisites: we will assume that attendees have a good understanding of regression models and multilevel models, including random intercept and random slopes models. For those who would like a refresher in this, we recommend completing module 5 of the Centre for Multilevel Modelling LEMMA online course (this is free, but you have to register), or attending the CMM “Introduction to Multilevel Modelling” course (booking available here) that is running a few weeks prior. Attendees should also be familiar with fitting statistical models in either R or Stata.

To book this training course please follow the link