A tutorial for conducting intersectional multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA)

Intersectional multilevel analysis of individual heterogeneity and discriminatory accuracy (I-MAIHDA) is an innovative approach for investigating inequalities, including intersectional inequalities in health, disease, psychosocial, socioeconomic, and other outcomes. I-MAIHDA and related MAIHDA approaches have conceptual and methodological advantages over conventional single-level regression analysis. By enabling the study of inequalities produced by numerous interlocking systems of marginalization and oppression, and by addressing many of the limitations of studying interactions in conventional analyses, intersectional MAIHDA provides a valuable analytical tool in social epidemiology, health psychology, precision medicine and public health, environmental justice, and beyond. The approach allows for estimation of average differences between intersectional strata (stratum inequalities), in-depth exploration of interaction effects, as well as decomposition of the total individual variation (heterogeneity) in individual outcomes within and between strata. Specific advice for conducting and interpreting MAIHDA models has been scattered across a burgeoning literature. We consolidate this knowledge into an accessible conceptual and applied tutorial for studying both continuous and binary individual outcomes. We emphasize I-MAIHDA in our illustration, however this tutorial is also informative for understanding related approaches, such as multicategorical MAIHDA, which has been proposed for use in clinical research and beyond. The tutorial will support readers who wish to perform their own analyses and those interested in expanding their understanding of the approach. To demonstrate the methodology, we provide step-by-step analytical advice and present an illustrative health application using simulated data. We provide the data and syntax to replicate all our analyses.

A quantitative approach to the intersectional study of mental health inequalities during the COVID-19 pandemic in UK young adults

PURPOSE

Mental health inequalities across social identities/positions during the COVID-19 pandemic have been mostly reported independently from each other or in a limited way (e.g., at the intersection between age and sex or gender). We aim to provide an inclusive socio-demographic mapping of different mental health measures in the population using quantitative methods that are consistent with an intersectional perspective.

METHODS

Data included 8,588 participants from two British cohorts (born in 1990 and 2000-2002, respectively), collected in February/March 2021 (during the third UK nationwide lockdown). Measures of anxiety and depressive symptomatology, loneliness, and life satisfaction were analysed using Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy (MAIHDA) models.

RESULTS

We found evidence of large mental health inequalities across intersectional strata. Large proportions of those inequalities were accounted for by the additive effects of the variables used to define the intersections, with some of the largest gaps associated with sexual orientation (with sexual minority groups showing substantially worse outcomes). Additional inequalities were found by cohort/generation, birth sex, racial/ethnic groups, and socioeconomic position. Intersectional effects were observed mostly in intersections defined by combinations of privileged and marginalised social identities/positions (e.g., lower-than-expected life satisfaction in South Asian men in their thirties from a sexual minority and a disadvantaged childhood social class).

CONCLUSION

We found substantial inequalities largely cutting across intersectional strata defined by multiple co-constituting social identities/positions. The large gaps found by sexual orientation extend the existing evidence that sexual minority groups were disproportionately affected by the pandemic. Study implications and limitations are discussed.

What does the MAIHDA method explain?

Multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA) is a new approach to quantitative intersectional modelling. Along with an outcome of interest, MAIHDA entails the use of two sets of independent variables. These include group demographics such as race, gender, and poverty status as well as strata which are constructs such as Black female poor, Black female wealthy, and White female poor. These constructs represent the combination of the demographic variables. To operationalize the approach, an initial random intercepts model with strata as a level 2 context is specified. Then, another model is specified that includes the strata as well as the demographic variables as level 1 fixed effects. As such, it is argued that MAIHDA uniquely identifies the additive and intersectional effects for any given outcome. In this paper we show that MAIHDA falls short of this promise: the strata are an individual-level composite variable not a level 2 context. Rather than being analogous to neighborhoods as contexts, strata are analogous to socio-economic status which is a combination of individual-level demographic variables, albeit often presented as a group-level characteristic. The result is that the demographic variables are inserted in both level 2 and 1. This duplication across the levels in MAIHDA means that there is a built-in collinearity across the levels and that the models are mis-specified and, therefore, redundant. We conclude that single-level models with the demographic variables and interactions or with the strata as fixed effects are still the more accurate models for quantitative intersectional analyses.

Intersecting gender identity and racial/ethnic inequities in eating disorder risk factors, symptoms, and diagnosis among U.S. college students: An intersectional multilevel analysis of individual heterogeneity and discriminatory accuracy

INTRODUCTION

There are documented inequities in eating disorders (EDs) by gender and race/ethnicity, yet, little is known about population-level prevalence of ED risk factors, symptoms, and diagnosis at the intersection of diverse gender and racial/ethnic identities.

METHODS

Data from the Healthy Minds Study 2015-2019 (N = 251,310 U.S. university students) were used in a multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA). Participants were nested in 35 intersectional strata given by all combinations of 5 gender and 7 racial/ethnic categories. Multilevel logistic models with participants at level 1 and intersectional strata at level 2 were used to estimate stratum-specific predicted prevalence estimates for self-reported thin-ideal internalization, ED symptoms, and ED diagnosis. The variance partition coefficient (VPC) was calculated to quantify the contextual effect of the strata.

RESULTS

There was considerable heterogeneity in the predicted prevalence of our ED outcomes across the strata (e.g., .3%-18.3% for ED diagnoses). There were large disparities in all three outcomes, with transgender participants of color having a higher predicted prevalence than expected based on the additive effects of gender and race/ethnicity. Moderation by race/ethnicity was also apparent, such that racial/ethnic disparities were wider within the cisgender groups relative to the transgender groups. VPCs indicated that ~10% of the total variance in ED outcomes was due to intersectionality between gender and race/ethnicity, over and above variance due to individual-level differences.

CONCLUSION

Findings suggest that gender and racial/ethnic disparities in EDs are interrelated, underscoring the need to develop preventive interventions centering health equity.

PUBLIC SIGNIFICANCE

Despite evidence that sexism, racism, and cissexism (i.e., anti-transgender prejudice) can impact EDs risk, little research examines the social patterning of EDs at the intersection of diverse gender and racial/ethnic identities. Using data from a sample of 250,000 U.S. university students, this study found that gender and racial/ethnic disparities in eating disorder risk are interrelated, highlighting the need to develop health equity centered preventive interventions.

Socioeconomic conditions and children's mental health and quality of life during the COVID-19 pandemic: An intersectional analysis

BACKGROUND

Children and adolescents are highly vulnerable to the impact of sustained stressors during developmentally sensitive times. We investigated how demographic characteristics intersect with socioeconomic dimensions to shape the social patterning of quality of life and mental health in children and adolescents, two years into the COVID-19 pandemic.

METHODS

We used data from the prospective SEROCoV-KIDS cohort study of children and adolescents living in Geneva (Switzerland, 2022). We conducted an intersectional Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy by nesting participants within 48 social strata defined by intersecting sex, age, immigrant background, parental education and financial hardship in Bayesian multilevel logistic models for poor health-related quality of life (HRQoL, measured with PedsQL) and mental health difficulties (measured with the Strengths and Difficulties Questionnaire).

RESULTS

Among participants aged 2-17 years, 240/2096 (11.5%, 95%CI 10.1-12.9) had poor HRQoL and 105/2135 (4.9%, 95%CI 4.0-5.9) had mental health difficulties. The predicted proportion of poor HRQoL ranged from 3.4% for 6-11 years old Swiss girls with highly educated parents and no financial hardship to 34.6% for 12-17 years old non-Swiss girls with highly educated parents and financial hardship. Intersectional strata involving adolescents and financial hardship showed substantially worse HRQoL than their counterparts. Between-stratum variations in the predicted frequency of mental health difficulties were limited (range 4.4%-6.5%).

CONCLUSIONS

We found considerable differences in adverse outcomes across social strata. Our results suggest that, post-pandemic, interventions to address social inequities in HRQoL should focus on specific intersectional strata involving adolescents and families experiencing financial hardship, while those aiming to improve mental health should target all children and adolescents.

The application of intersectional multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA) to examine birthweight inequities in New York City

Exploring the intersection of dimensions of social identity is critical for understanding drivers of health inequities. We used multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA) to examine the intersection of age, race/ethnicity, education, and nativity status on infant birthweight among singleton births in New York City from 2012 to 2018 (N = 725,875). We found evidence of intersectional effects of various systems of oppression on birthweight inequities and identified U.S.-born Black women as having infants of lower-than-expected birthweights. The MAIHDA approach should be used to identify intersectional causes of health inequities and individuals affected most to develop policies and interventions redressing inequities.

college students: An intersectional Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy (MAIHDA)

We investigated how gender identity, sexual orientation, and race/ethnicity intersect to shape the social epidemiology of HPV vaccination initiation among U.S. college students. Cross-sectional survey data were from the National College Health Assessment (Fall, 2019-Spring, 2020; N = 65,047). We conducted an intersectional Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy by nesting participants within 36 social strata defined using gender identity, sexual orientation, and race/ethnicity. Bayesian multilevel logistic regression models with random intercepts for social strata were fit for HPV vaccination initiation. Intersectional models adjusted for the additive main effects to isolate intersectional interactions, controlling for age and geographic region. Social strata that included cisgender men, transgender women, and non-binary assigned-male-at-birth individuals and strata that included racial/ethnic minorities had a significantly lower likelihood of HPV vaccination initiation relative to strata including cisgender women and non-Hispanic White individuals, respectively, while strata including lesbian/gay and bisexual/pansexual/queer individuals had a significantly higher likelihood of HPV vaccination initiation relative to strata including heterosexual individuals. We also observed substantial between-stratum inequities in the predicted prevalence of HPV vaccination initiation, with estimates ranging from 59.2% for heterosexual, racial/ethnic minority, cisgender men to 87.1% for bisexual/pansexual/queer, racial/ethnic minority, non-binary assigned-female-at-birth individuals. That being said, the majority of the observed between-stratum variance was driven by additive rather than intersectional interaction effects and the discriminatory accuracy of intersectional stratification with respect to predicting HPV vaccination initiation was low. Collectively, our findings point to a need for more universal guidelines and clinician recommendations that promote HPV vaccine uptake for all adolescents, regardless of race/ethnicity, gender identity, sex-assigned-at-birth, or sexual orientation; however, utilizing an intersectional lens will ensure that resulting public health interventions address inequities and center the needs and experiences of multiply marginalized adolescents.

Eating-related pathology at the intersection of gender identity and expression, sexual orientation, and weight status: An intersectional Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy (MAIHDA) of the Growing Up Today Study cohorts

The objective of this study was to investigate how gender identity, the overwhelmingly prioritized dimension of social identity/position in eating-related pathology research, intersects with gender expression, sexual orientation, and weight status to structure the social patterning of eating disorders and disordered eating behaviors among young people in the U.S. Data were drawn from the 2010/2011 Growing Up Today Study (GUTS; N = 11,090-13,307). We conducted an intersectional Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy (MAIHDA) by nesting participants within social strata defined by intersecting gender identity, gender expression, sexual orientation, and weight status categories in a series of multilevel logistic models for four outcomes (past-year purging, overeating, and binge eating; lifetime eating disorder diagnosis). To illustrate the advantages of intersectional MAIHDA, we compared the results to those from unitary and conventional intersectional analyses. The intersectional MAIHDA revealed a complex social patterning of eating-related pathology characterized by heterogeneity and outcome-specificity. Several multiply marginalized strata (e.g., those including gender nonconforming, sexual minority, and/or larger-bodied girls/women) had disproportionately elevated prevalence, although all estimates were driven by additive effects. Notably, these patterns were obscured within the unitary and conventional intersectional analyses. Future epidemiologic research on eating-related pathology should continue to adopt an intersectional approach through the use of appropriate methodologies.

Antidepressant use in Sweden: an intersectional multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA)

INTRODUCTION

Antidepressants are among the most commonly prescribed drugs in Sweden. However, we lack detailed knowledge on the socioeconomic and demographic distribution of antidepressant use in the population. To fill this gap, we performed an intersectional multilevel analysis of individual heterogeneity and discriminatory accuracy.

METHODS

Analysing all Swedish residents older than 10 years (n=8,190,990), we measured the absolute risk of antidepressant use across 144 intersectional strata defined by combinations of age, gender, income, country of birth and psychiatric diagnosis. We calculated the strata-specific absolute risk of antidepressant use in a series of multilevel logistic regression models. By means of the variance partitioning coefficient and the area under the receiver operating characteristic curve, we quantified the discriminatory accuracy of the intersectional contexts (i.e. strata) for discerning those who use antidepressants from those who do not.

RESULTS

The absolute risk of antidepressant use ranged between 0.93% and 24.78% among those without a psychiatric diagnosis, and between 21.41% and 77.56% among those with a psychiatric diagnosis. Both the variance partitioning coefficient of 41.88% and the area under the receiver operating characteristic curve of 0.81 were considerable.

CONCLUSIONS

Besides overt psychiatric diagnoses, our study shows that antidepressant use is mainly conditioned by age, which might express the embodiment of socioeconomic conditions across the individual life course. Our analysis provides a detailed and highly discriminatory mapping of the heterogeneous distribution of antidepressant use in the Swedish population, which may be useful in public health management.

Intersectionality and Adolescent Mental Well-being: A Cross-Nationally Comparative Analysis of the Interplay Between Immigration Background, Socioeconomic Status and Gender

PURPOSE

Intersectionality theory highlights the importance of the interplay of multiple social group memberships in shaping individual mental well-being. This article investigates elements of adolescent mental well-being (life dissatisfaction and psychosomatic complaints) from an intersectional perspective. It tests mental well-being consequences of membership in combinations of multiple social groups and examines to what extent such intersectional effects depend on the national context (immigration and integration policies, national-level income, and gender equality).

METHODS

Using Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy, we assessed the role of the national context in shaping the interplay between immigration background, socioeconomic status, and gender, using data from 33 countries from the 2017/2018 Health Behaviour in School-aged Children survey.

RESULTS

We found no uniform intersectionality effects across all countries. However, when allowing the interplay to vary by national context, results did point toward some intersectional effects. Some aggravated negative effects were found for members of multiple disadvantaged social groups in countries with low levels of income equality and restrictive migration policies, whereas enhanced positive effects were found for members of multiple advantaged groups in these countries. Similarly, mitigated negative effects of membership in multiple disadvantaged groups were shown in countries with higher levels of income equality and more inclusive migration policies, whereas mitigated positive effects were found for multiply advantaged individuals. Although for national-level gender equality results pointed in a similar direction, girls' scores were counterintuitive. High national-level gender equality disproportionately benefitted groups of disadvantaged boys, whereas advantaged girls were doing worse than expected, and reversed effects were found for countries with low gender equality.

CONCLUSIONS

To fully understand social inequalities in adolescent mental well-being, the interplay between individual-level and national-level indicators must be explored.