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 dynamic social relations model for clustered longitudinal dyadic data with continuous or ordinal responses.

Social relations models allow the identification of cluster, actor, partner, and relationship effects when analysing clustered dyadic data on interactions between individuals or other units of analysis. We propose an extension of this model which handles longitudinal data and incorporates dynamic structure, where the response may be continuous, binary, or ordinal. This allows the disentangling of the relationship effects from temporal fluctuation and measurement error and the investigation of whether individuals respond to their partner's behaviour at the previous observation. We motivate and illustrate the model with an application to Canadian data on pairs of individuals within families observed working together on a conflict discussion task.

Clarifications on the intersectional MAIHDA approach: A conceptual guide and response to Wilkes and Karimi (2024).

Intersectional Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy (MAIHDA) has been welcomed as a new gold standard for quantitative evaluation of intersectional inequalities, and it is being rapidly adopted across the health and social sciences. In their commentary "What does the MAIHDA method explain?", Wilkes and Karimi (2024) raise methodological concerns with this approach, leading them to advocate for the continued use of conventional single-level linear regression models with fixed-effects interaction parameters for quantitative intersectional analysis. In this response, we systematically address these concerns, and ultimately find them to be unfounded, arising from a series of subtle but important misunderstandings of the MAIHDA approach and literature. Since readers new to MAIHDA may share confusion on these points, we take this opportunity to provide clarifications. Our response is organized around four important clarifications: (1) At what level are the additive main effect variables defined in intersectional MAIHDA models? (2) Do MAIHDA models have problems with collinearity? (3) Why does the Variance Partitioning Coefficient (VPC) tend to be small, and the Proportional Change in Variance (PCV) tend to be large in MAIHDA? and (4) What are the goals of MAIHDA analysis?

Extending intersectional multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA) to study individual longitudinal trajectories, with application to mental health in the UK.

The intersectional Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy (MAIHDA) approach is gaining prominence in health sciences and beyond, as a robust quantitative method for identifying intersectional inequalities in a range of individual outcomes. However, it has so far not been applied to longitudinal data, despite the availability of such data, and growing recognition that intersectional social processes and determinants are not static, unchanging phenomena. Drawing on intersectionality and life course theories, we develop a longitudinal version of the intersectional MAIHDA approach, allowing the analysis not just of intersectional inequalities in static individual differences, but also of life course trajectories. We discuss the conceptualization of intersectional groups in this context: how they are changeable over the life course, appropriate treatment of generational differences, and relevance of the age-period-cohort identification problem. We illustrate the approach with a study of mental health using United Kingdom Household Longitudinal Study data (2009-2021). The results reveal important differences in trajectories between generations and intersectional strata, and show that trajectories are partly multiplicative but mostly additive in their intersectional inequalities. This article provides an important and much needed methodological contribution, enabling rigorous quantitative, longitudinal, intersectional analyses in social epidemiology and beyond.

Local government spending and mental health: Untangling the impacts using a dynamic modelling approach.

This study investigated the impact of local government spending on mental health in England between 2013 and 2019. Guided by the "Health in All Policies" vision, which encourages the integration of health in all decision-making areas, we explored how healthcare and multiple nonmedical budgeting decisions related to population mental health. We used random curve general cross-lagged modelling to dynamically partition effects into the short-run (from t to t + 1) and long-run (from t to t + 2) impacts, account for unobserved area-level heterogeneity and reverse causality from health outcomes to financial investments, and comprehensive modelling of budget items as an interconnected system. Our findings revealed that spending in adult social care, healthcare, and law & order predicted long-term mental health gains (0.004-0.081 SDs increase for each additional 10% in expenditure). However, these sectors exhibited negative short-term impulses (0.012-0.077 SDs decrease for each additional 10% in expenditure), markedly offsetting the long-term gains. In turn, infrastructural and environmental spending related to short-run mental health gains (0.005-0.031 SDs increase for each additional 10% in expenditure), while the long-run effects were predominantly negative (0.005-0.028 SDs decrease for each additional 10% in expenditure). The frequent occurrence of short-run and long-run negative links suggested that government resources may not be effectively reaching the areas that are most in need. In the short-term, negative effects could also imply temporary disruptions to service delivery largely uncompensated by later mental health improvements. Nonetheless, some non-health spending policies, such as law & order and infrastructure, can be related to long-lasting positive mental health impacts.

Mapping socio-geographical disparities in the occurrence of teenage maternity in Colombia using multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA).

BACKGROUND: The prevalence of teenage pregnancy in Colombia is higher than the worldwide average. The identification of socio-geographical disparities might help to prioritize public health interventions. AIM: To describe variation in the probability of teenage maternity across geopolitical departments and socio-geographical intersectional strata in Colombia. METHODS: A cross-sectional study based on live birth certificates in Colombia. Teenage maternity was defined as a woman giving birth aged 19 or younger. Multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA) was applied using multilevel Poisson and logistic regression. Two different approaches were used: (1) intersectional: using strata defined by the combination of health insurance, region, area of residency, and ethnicity as the second level (2) geographical: using geopolitical departments as the second level. Null, partial, and full models were obtained. General contextual effect (GCE) based on the variance partition coefficient (VPC) was considered as the measure of disparity. Proportional change in variance (PCV) was used to identify the contribution of each variable to the between-strata variation and to identify whether this variation, if any, was due to additive or interaction effects. Residuals were used to identify strata with potential higher-order interactions. RESULTS: The prevalence of teenage mothers in Colombia was 18.30% (95% CI 18.20-18.40). The highest prevalence was observed in Vichada, 25.65% (95% CI: 23.71-27.78), and in the stratum containing mothers with Subsidized/Unaffiliated healthcare insurance, Mestizo, Rural area in the Caribbean region, 29.08% (95% CI 28.55-29.61). The VPC from the null model was 1.70% and 9.16% using the geographical and socio-geographical intersectional approaches, respectively. The higher PCV for the intersectional model was attributed to health insurance. Positive and negative interactions of effects were observed. CONCLUSION: Disparities were observed between intersectional socio-geographical strata but not between geo-political departments. Our results indicate that if resources for prevention are limited, using an intersectional socio-geographical approach would be more effective than focusing on geopolitical departments especially when focusing resources on those groups which show the highest prevalence. MAIHDA could potentially be applied to many other health outcomes where resource decisions must be made.

Profiles of vulnerability for suicide and self-harm in UK prisoners: Neurodisability, mood disturbance, substance use, and bullying.

Screening for vulnerability factors associated with historic suicidality and self-harm on entry to prison is critical to help prisons understand how to allocate extremely limited mental health resources. It has been established that having previous suicide attempts increases odds of future suicidality and self-harm in prison. We utilised administrative screening data from 665 adult male prisoners on entry to a category B prison in Wales, UK, collected using the Do-IT Profiler. This sample represents 16% of all prisoners who entered that prison during a 26-month period. 12% of prisoners reported a history of attempted suicide, 11% reported historic self-harm, and 8% reported a history of both. Historic traumatic brain injury and substance use problems were associated with a 3.3- and 1.9- times increased odds of a historic suicide attempt, respectively, but no significant increased risk of historic self-harm (95% CI: 1.51-6.60 and 1.02-3.50). However, those who were bullied at school had 2.7 times increased odds of reporting a history of self-harm (95% CI: 1.63-6.09). The most salient risk factors associated with both historic suicide and self-harm were higher levels of functional neurodisability (odds ratio 0.6 for a 1 standard deviation change in score, 95% CI: 0.35-0.75), and mood disturbance (odds ratio 2.1 for a 1 standard deviation change in score, 95% CI: 1.26-3.56). Therefore, it could be beneficial for prisons to screen for broader profiles of needs, to better understand how to provide appropriate services to prisoners vulnerable to suicide and self-harm. Multidisciplinary care pathways for prisoner mental health interventions are important, to account for complex multimorbidity. Adaptations may be needed for mental health interventions to be appropriate for, for example, a prisoner with a brain injury. Understanding this broad profile of vulnerability could also contribute to more compassionate responses to suicide and self-harm from prison staff.

Geographical and sociodemographic differences in statin dispensation after acute myocardial infarction in Sweden: a register-based prospective cohort study applying analysis of individual heterogeneity and discriminatory accuracy (AIHDA) for basic comparisons of healthcare quality.

BACKGROUND: In Sweden, as in many other countries, official monitoring of healthcare quality is mostly focused on geographical disparities in relation to a desirable benchmark. However, current evaluations could be improved by considering: (1) The intersection of other relevant axes of inequity like age, sex, income and migration status; and (2) The existence of individual heterogeneity around averages. Therefore, using an established quality indicator (ie, dispensation of statins after acute myocardial infarction, AMI), we valuate both geographical and sociodemographic inequalities and illustrate how the analysis of individual heterogeneity and discriminatory accuracy (AIHDA) enhances such evaluations. POPULATION AND METHODS: We applied AIHDA and calculated the area under the receiver operating characteristics curve (AUC) of regional and sociodemographic differences in the statin dispensations of 35 044 patients from 21 Swedish regions and 24 sociodemographic strata who were discharged from the hospital with an AMI diagnosis between January 2011 and December 2013. Following the Swedish National Board of Health and Welfare, we used a benchmark value of 90%. RESULTS: Dispensation of stains after AMI in Sweden did not reach the desired target of 90%. Regional differences were absent/very small (AUC=0.537) while sociodemographic differences were small (AUC=0.618). Women, especially those with immigrant background and older than 65 years, have the lowest proportions of statin dispensations after AMI. CONCLUSIONS: As the AUC statistics are small, interventions trying to achieve the benchmark value should be universal. However, special emphasis should nevertheless be directed towards women, especially older women with immigrant backgrounds.

Looked after children in prison as adults: life adversity and neurodisability.

PURPOSE: Looked after children (LAC) are criminalised at five times the rate of children in the general population. Children in contact with both child welfare and child justice systems have higher rates of neurodisability and substance use problems, and LAC in general have high rates of school exclusion, homelessness and unemployment. This study aims to understand whether these factors persist in LAC who are in prison as adults. DESIGN/METHODOLOGY/APPROACH: Administrative data collected by the Do-IT profiler screening tool in a prison in Wales, UK, were analysed to compare sentenced prisoners who were LAC (n = 631) to sentenced prisoners who were not LAC (n = 2,201). The sample comprised all prisoners who were screened on entry to prison in a two-year period. FINDINGS: Prisoners who were LAC scored more poorly on a functional screener for neurodisability (effect size = 0.24), and on four self-report measures capturing traits of dyslexia (0.22), attention-deficit hyperactivity disorder (0.40), autism spectrum disorders (0.34) and developmental co-ordination disorder (0.33). Prisoners who were LAC were more likely to have been to a pupil referral unit (0.24), have substance use problems (0.16), be homeless or marginally housed (0.18) and be unemployed or unable to work due to disability (0.13). ORIGINALITY/VALUE: This study uniquely contributes to our understanding of prisoners who were LAC as a target group for intervention and support with re-integration into the community upon release. LAC in prison as adults may require additional interventions to help with employment, housing and substance use. Education programmes in prison should screen for neurodisability, to develop strategies to support engagement.

Multilevel modelling for measuring interaction of effects between multiple categorical variables: An illustrative application using risk factors for preeclampsia.

BACKGROUND: Measuring multiple and higher-order interaction effects between multiple categorical variables proves challenging. OBJECTIVES: To illustrate a multilevel modelling approach to studying complex interactions. METHODS: We apply a two-level random-intercept linear regression to a binary outcome for individuals (level-1) nested within strata (level-2) defined by all observed combinations of multiple categorical exposure variables. As a pedagogic application, we analyse 36 strata defined by five risk factors of preeclampsia (parity, previous preeclampsia, chronic hypertension, multiple pregnancies, body mass index category) among 652,603 women in the Swedish Medical Birth Registry between 2002 and 2010. RESULTS: The absolute risk of preeclampsia was 4% but was predicted to vary from 1% to 44% across strata. The stratum discriminatory accuracy was 30% according to the variance partition coefficient (VPC) and 0.73 according to the area under the receiver operating characteristic curve (AUC). While the risk heterogeneity across strata was primarily due to the main effects of the categories defining the strata, 5% of the variation was attributable to their two- and higher-way interaction effects. One stratum presented a positive interaction, and two strata presented negative interaction. CONCLUSIONS: Multilevel modelling is an innovative tool for identifying and analysing higher-order interaction effects. Further work is needed to explore how this approach can best be applied to making causal inferences.

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.

The Early Social Cognition Inventory (ESCI): An examination of its psychometric properties from birth to 47 months.

Social cognition refers to a broad range of cognitive processes and skills that allow individuals to interact with and understand others, including a variety of skills from infancy through preschool and beyond, e.g., joint attention, imitation, and belief understanding. However, no measures examine socio-cognitive development from birth through preschool. Current test batteries and parent-report measures focus either on infancy, or toddlerhood through preschool (and beyond). We report six studies in which we developed and tested a new 21-item parent-report measure of social cognition targeting 0-47 months: the Early Social Cognition Inventory (ESCI). Study 1 (N = 295) revealed the ESCI has excellent internal reliability, and a two-factor structure capturing social cognition and age. Study 2 (N = 605) also showed excellent internal reliability and confirmed the two-factor structure. Study 3 (N = 84) found a medium correlation between the ESCI and a researcher-administered social cognition task battery. Study 4 (N = 46) found strong 1-month test-retest reliability. Study 5 found longitudinal stability (6 months: N = 140; 12 months: N = 39), and inter-observer reliability between parents (N = 36) was good, and children's scores increased significantly over 6 and 12 months. Study 6 showed the ESCI was internally reliable within countries (Australia, Canada, United Kingdom, United States, Trinidad and Tobago); parent ethnicity; parent education; and age groups from 4-39 months. ESCI scores positively correlated with household income (UK); children with siblings had higher scores; and Australian parents reported lower scores than American, British, and Canadian parents.

The Early Humor Survey (EHS): A reliable parent-report measure of humor development for 1- to 47-month-olds.

We created a 20-item parent-report measure of humor development from 1 to 47 months: the Early Humor Survey (EHS). We developed the EHS with Study 1 (N = 219) using exploratory factor analysis, demonstrating the EHS works with 1- to 47-month-olds with excellent reliability and a strong correlation with age, showing its developmental trajectory. We replicated the EHS with Study 2 (N = 587), revealing a one-factor structure, showing excellent reliability, and replicating a strong correlation with age. Study 3 (N = 84) found the EHS correlated with a humor experiment, however it no longer correlated once age was accounted for, suggesting low convergent validity. Subsamples of parents from Studies 2 and 3 showed excellent inter-observer reliability between both parents, and good longitudinal stability after 6 months. Combining participants from all studies, we found the EHS is reliable across countries (Australia, United Kingdom, United States), parent education levels, and children's age groups. We charted expected humor development by age (in months), and the expected proportion of children who would appreciate each humor type by age (in months). Finally, we found no demographic differences (e.g., country: Australia, Canada, United Kingdom, United States; parents' education) in humor when pooling all data. The EHS is a valuable tool that will allow researchers to understand how humor: (1) emerges; and (2) affects other aspects of life, e.g., making friends, coping with stress, and creativity. The EHS is helpful for parents, early years educators, and children's media, as it systematically charts early humor development.

Population heterogeneity in associations between hormonal contraception and antidepressant use in Sweden: a prospective cohort study applying intersectional multilevel analysis of individual heterogeneity and discriminatory accuracy (MAIHDA).

OBJECTIVES: From a reproductive justice framework, we aimed to investigate how a possible association between hormonal contraceptive (HC) and antidepressants use (as a proxy for depression) is distributed across intersectional strata in the population. We aimed to visualise how intersecting power dynamics may operate in combination with HC use to increase or decrease subsequent use of antidepressants. Our main hypothesis was that the previously observed association between HC and antidepressants use would vary between strata, being more pronounced in more oppressed intersectional contexts. For this purpose, we applied an intersectional multilevel analysis of individual heterogeneity and discriminatory accuracy approach. DESIGN: Observational prospective cohort study using record linkage of national Swedish registers. SETTING: The population of Sweden. PARTICIPANTS: All 915 954 women aged 12-30 residing in Sweden 2010, without a recent pregnancy and alive during the individual 1-year follow-up. PRIMARY OUTCOME MEASURE: Use of any antidepressant, meaning being dispensed at least one antidepressant (ATC: N06A) during follow-up. RESULTS: Previously mentally healthy HC users had an OR of 1.79 for use of antidepressants compared with non-users, whereas this number was 1.28 for women with previous mental health issues. The highest antidepressant use were uniformly found in strata with previous mental health issues, with highest usage in women aged 24-30 with no immigrant background, low income and HC use (51.4%). The largest difference in antidepressant use between HC users and non-users was found in teenagers, and in adult women of immigrant background with low income. Of the total individual variance in the latent propensity of using antidepressant 9.01% (healthy) and 8.16% (with previous mental health issues) was found at the intersectional stratum level. CONCLUSIONS: Our study suggests teenagers and women with immigrant background and low income could be more sensitive to mood effects of HC, a heterogeneity important to consider moving forward.

What makes for responsive family interactions? Disentangling individual, family-level, and socioeconomic contributions.

Families function best, and children benefit the most, when familial interactions are characterized by responsivity-an understanding and consideration of other people's thoughts and feelings. How responsive people are during interactions with others is a product of individual propensities, observed family norms, and unique relationship patterns, though these influences are often hard to disentangle. In the current study, we used a Social Relations Model (SRM) to parse out the extent to which being responsive during family interactions is attributable to individual traits or familial tendencies. Mothers, fathers, and two children each interacted with every other person in the family (N = 198 families) and each person's behavior was coded for the level of responsivity they displayed toward their interactional partner. Data were modeled using a multilevel formulation of the SRM. Between 15% and 30% of the variance in individual's responsivity was attributable to stable traits, with parents tending to be more consistent across all interactional partners than their children. On average, 14% of the variance in responsivity was shared across all members of a given family. Income explained 28% of family-level variance, while other family characteristics, including parent education, parent mental health, interparental conflict, and household chaos, explained little to no variance. Furthermore, it was found that parents contributed more to the family tone of responsivity than did their children. These results provide new insights into what makes family members responsive toward one other and suggest there are likely benefits of providing supports across individual-, family-, and financial-levels to enhance family responsivity. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Evaluating the "Dove Confident Me" Five-Session Body Image Intervention Delivered by Teachers in Schools: A Cluster Randomized Controlled Effectiveness Trial.

PURPOSE: Body dissatisfaction is common during adolescence and predicts poor psychological and physical health. Interventions have traditionally overrelied on delivery by external providers (e.g., researchers and psychologists), preventing scalability. This study evaluated the acceptability and effectiveness of a school-based body image intervention delivered by schoolteachers. METHODS: Six British schools participated in a pragmatic cluster randomized controlled trial. Girls and boys aged 11-13 years received the five-session intervention delivered by their teachers (n = 848) or lessons-as-usual control (n = 647) and were assessed at baseline, postintervention, and 2-, 6-, 12-, 24- and 36-month follow-up. The primary outcome was body image (body esteem), secondary outcomes included risk factors for body image (internalization of appearance ideals, sociocultural pressures, social comparisons, appearance-related teasing, and conversations), and tertiary outcomes included psychosocial well-being (negative affect, self-esteem, dietary restraint, and life engagement). RESULTS: Compared with the control group, intervention students demonstrated improvements in the primary outcome of body esteem at postintervention (Cohen's d = .15), 2-month (d = .26), and 6-month follow-up (d = .15). For girls, there was also a significant reduction in experienced appearance-related teasing at 6-month (d = .24) and 12-month (d = .30) follow-up. No other significant intervention effects were observed. The intervention was acceptable to students. CONCLUSIONS: These findings present the longest sustained improvements in a cognitive-affective body image outcome observed among girls and boys during a teacher-led universal body image program to date. Intervention refinement and improved teacher training may further improve outcomes. Task-shifting intervention delivery to community providers to scale up interventions is a promising strategy.

Joint Modeling of Individual Trajectories, Within-Individual Variability, and a Later Outcome: Systolic Blood Pressure Through Childhood and Left Ventricular Mass in Early Adulthood.

Within-individual variability of repeatedly measured exposures might predict later outcomes (e.g., blood pressure (BP) variability (BPV) is an independent cardiovascular risk factor above and beyond mean BP). Because 2-stage methods, known to introduce bias, are typically used to investigate such associations, we introduce a joint modeling approach, examining associations of mean BP and BPV across childhood with left ventricular mass (indexed to height; LVMI) in early adulthood with data (collected 1990-2011) from the UK Avon Longitudinal Study of Parents and Children cohort. Using multilevel models, we allowed BPV to vary between individuals (a "random effect") as well as to depend on covariates (allowing for heteroskedasticity). We further distinguished within-clinic variability ("measurement error") from visit-to-visit BPV. BPV was predicted to be greater at older ages, at higher body weights, and in female participants and was positively correlated with mean BP. BPV had a weak positive association with LVMI (10% increase in within-individual BP variance was predicted to increase LVMI by 0.21%, 95% credible interval: -0.23, 0.69), but this association became negative (-0.78%, 95% credible interval: -2.54, 0.22) once the effect of mean BP on LVMI was adjusted for. This joint modeling approach offers a flexible method of relating repeatedly measured exposures to later outcomes.

A review and evaluation of secondary school accountability in England: Statistical strengths, weaknesses and challenges for 'Progress 8' raised by COVID-19.

School performance measures are published annually in England to hold schools to account and to support parental school choice. This article reviews and evaluates the 'Progress 8' secondary school accountability system for state-funded schools. We assess the statistical strengths and weaknesses of Progress 8 relating to: choice of pupil outcome attainment measure; potential adjustments for pupil input attainment and background characteristics; decisions around which schools and pupils are excluded from the measure; presentation of Progress 8 to users, choice of statistical model, and calculation of statistical uncertainty; and issues related to the volatility of school performance over time, including scope for reporting multi-year averages. We then discuss challenges for Progress 8 raised by the COVID-19 pandemic. Six simple recommendations follow to improve Progress 8 and school accountability in England.

Cross-classified Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy (MAIHDA) to evaluate hospital performance: the case of hospital differences in patient survival after acute myocardial infarction.

OBJECTIVE: To describe a novel strategy, Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy (MAIHDA) to evaluate hospital performance, by analysing differences in 30-day mortality after a first-ever acute myocardial infarction (AMI) in Sweden. DESIGN: Cross-classified study. SETTING: 68 Swedish hospitals. PARTICIPANTS: 43 247 patients admitted between 2007 and 2009, with a first-ever AMI. PRIMARY AND SECONDARY OUTCOME MEASURES: We evaluate hospital performance by analysing differences in 30-day mortality after a first-ever AMI using a cross-classified multilevel analysis. We classified the patients into 10 categories according to a risk score (RS) for 30-day mortality and created 680 strata defined by combining hospital and RS categories. RESULTS: In the cross-classified multilevel analysis the overall RS adjusted hospital 30-day mortality in Sweden was 4.78% and the between-hospital variation was very small (variance partition coefficient (VPC)=0.70%, area under the curve (AUC)=0.54). The benchmark value was therefore achieved by all hospitals. However, as expected, there were large differences between the RS categories (VPC=34.13%, AUC=0.77) CONCLUSIONS: MAIHDA is a useful tool to evaluate hospital performance. The benefit of this novel approach to adjusting for patient RS is that it allowed one to estimate separate VPCs and AUC statistics to simultaneously evaluate the influence of RS categories and hospital differences on mortality. At the time of our analysis, all hospitals in Sweden were performing homogeneously well. That is, the benchmark target for 30-day mortality was fully achieved and there were not relevant hospital differences. Therefore, possible quality interventions should be universal and oriented to maintain the high hospital quality of care.

Precision-weighted estimates of neonatal, post-neonatal and child mortality for 640 districts in India, National Family Health Survey 2016.

BACKGROUND: The conventional indicators of infant and under-five mortality are aggregate deaths occurring in the first year and the first five years, respectively. Monitoring deaths by <1 month (neonatal), 1-11 months (post-neonatal), and 12-59 months (child) can be more informative given various etiological causes that may require different interventions across these three mutually exclusive periods. For optimal resource allocation, it is also necessary to track progress in robust estimates of child survival at a smaller geographic and administrative level. METHODS: Data on 259 627 children came from the 2015-2016 Indian National Family Health Survey. We used a random effects model to account for the complex survey design and sampling variability, and predicted district-specific probabilities of neonatal, post-neonatal, and child mortality. The resulting precision-weighted estimates are more reliable as they pool information and borrow strength from other districts that share the same state membership. The Pearson correlation and Spearman's rank correlation were assessed for the three mortality estimates, and the Moran's I measure was used to detect spatial clustering of high burden districts for each outcome. RESULTS: The majority of under-five deaths was disproportionately concentrated in the neonatal period. Across all districts, the predicted probability of neonatal, post-neonatal, and child mortality varied from 6.0 to 63.9 deaths, 3.8 to 47.6 deaths, and 1.7 to 11.8 deaths per 1000 live births, respectively. The overall correlation between district-wide probabilities of mortality for the three mutually exclusive periods was moderate (Pearson correlation = 0.47-0.58, Spearman's rank correlation = 0.58-0.64). For each outcome, a relatively strong spatial clustering was detected across districts that transcended state boundaries (Moran's I = 0.61-0.76). CONCLUSIONS: Sufficiently breaking down the under-five mortality to distinct age groups and using the precision-weighted estimations to monitor performances at smaller geographic and administrative units can inform more targeted interventions and foster accountability to improve child survival.