Understanding COVID-19 infection among people with intellectual and developmental disabilities using machine learning.

BACKGROUND: People with intellectual and developmental disabilities (IDD) were disproportionately affected by the COVID-19 pandemic. Predicting COVID-19 infection has been difficult. OBJECTIVE: We sought to address two research questions in this study: 1) to assess the overall utility of a machine learning model to predict COVID-19 diagnosis for people with IDD, and 2) to determine the primary predictors of COVID-19 diagnosis in a random sample of Home and Community Based Services users in one state. METHODS: We merged three major IDD-specific datasets (National Core Indicators, Supports Intensity Scale, Medicaid HCBS expenditures) from one state to create one combined dataset for analyses that included more than 700 variables. We then built a random forest machine learning algorithm to predict COVID-19 diagnosis and to explore the top predictors of such a diagnosis, when present. RESULTS: Our algorithm predicted COVID-19 diagnosis in a random sample of HCBS users with IDD with 62.5% accuracy. The top predictors of having a documented case of COVID-19 among our sample were higher age, having high overall, medical, or behavioral support needs, living in a lower-income neighborhood, total Medicaid expenditure, and higher body mass index. CONCLUSIONS: Results largely followed trends in the general population, and were largely suggestive that increased contact with other people may have exposed a person with IDD to greater COVID-19 risk.

A case study of pragmatic measure development of the Treatment Integrity for Elementary Settings self-report measure for teachers.

Introduction: Due to usability, feasibility, and acceptability concerns, observational treatment fidelity measures are often challenging to deploy in schools. Teacher self-report fidelity measures with specific design features might address some of these barriers. This case study outlines a community-engaged, iterative process to adapt the observational Treatment Integrity for Elementary Settings (TIES-O) to a teacher self-report version designed to assess the use of practices to support children's social-emotional competencies in elementary classrooms. Method: Cognitive walkthrough interviews were conducted with teachers to improve the usability of the teacher self-report measure, called the Treatment Integrity for Elementary Schools-Teacher Report (TIES-T). Qualitative content analysis was used to extract themes from the interviews and inform changes to the measure. Results: Increasing clarity and interactive elements in the measure training were the dominant themes, but suggestions for the measure format and jargon were also suggested. Conclusion: The suggested changes resulted in a brief measure, training, and feedback system designed to support the teacher's use of practices to support children's social-emotional competencies in elementary classrooms. Future research with the TIES-T will examine the score reliability and validity of the measure.

Collecting observational data in schools is challenging, so developing teacher self-report measures and involving teachers in the design process is important to help make them easier to use. This paper reports on the development of a teacher self-report measure designed to collect information about the instructional practices teachers deliver to promote positive student behavior.

Exploring control-value motivational profiles of mathematics anxiety, self-concept, and interest in adolescents.

In this study, we identified multidimensional profiles in students' math anxiety, math self-concept, and math interest using data from a large generalizable sample of 16,547 9th grade students in the United States who participated in the National Study of Learning Mindsets. We also analyzed the extent that students' profile memberships are associated with related measures such as prior mathematics achievement, academic stress, and challenge-seeking behavior. Five multidimensional profiles were identified: two profiles which demonstrated relatively high levels of interest and self-concept, along with low math anxiety, in line with the tenets of the control-value theory of academic emotions (C-VTAE); two profiles which demonstrated relatively low levels of interest and self-concept, and high levels of math anxiety (again in accordance with C-VTAE); and one profile, comprising more than 37% of the total sample, which demonstrated medium levels of interest, high levels of self-concept, and medium levels of anxiety. All five profiles varied significantly from one another in their association with the distal variables of challenge seeking behavior, prior mathematics achievement, and academic stress. This study contributes to the literature on math anxiety, self-concept, and interest by identifying and validating student profiles that mainly align with the control-value theory of academic emotions in a large, generalizable sample.

Variable- and person-centered approaches to examining construct-relevant multidimensionality in writing self-efficacy.

Self-efficacy is an essential component of students' motivation and success in writing. There have been great advancements in our theoretical understanding of writing self-efficacy over the past 40 years; however, there is a gap in how we empirically model the multidimensionality of writing self-efficacy. The purpose of the present study was to examine the multidimensionality of writing self-efficacy, and present validity evidence for the adapted Self-Efficacy for Writing Scale (SEWS) through a series of measurement model comparisons and person-centered approaches. Using a sample of 1,466 8th-10th graders, results showed that a bifactor exploratory structural equation model best represented the data, demonstrating that the SEWS exhibits both construct-relevant multidimensionality and the presence of a global theme. Using factor scores derived from this model, we conducted latent profile analysis to further establish validity of the measurement model and examine how students disaggregate into groups based on their response trends of the SEWS. Three profiles emerged, differentiated by global writing self-efficacy, with substantively varying factor differences among the profiles. Concurrent, divergent, and discriminant validity evidence was established through a series of analyses that assessed predictors and outcomes of the profiles (e.g., demographics, standardized writing assessments, and grades). Theoretical and practical implications and avenues for future research are discussed.

An Examination of Support Needs, Supports, and Outcomes for People With Intellectual and Developmental Disabilities.

Researchers used a merged dataset to examine if more resources were expended on those with greater support needs and if support needs impacted personal outcomes when controlling for relevant personal and contextual factors. Results indicated that the amount of support a person receives had a direct relationship to their needs. However, we also found that people with the greatest needs had weaker personal outcomes suggesting that distribution of resources based on need may not result in equivalent outcomes. The authors suggest strategies at an individual and systems level to address the outcomes gap for people with the greatest support needs.

Using social network analysis in applied psychological research: A tutorial.

Social network analysis (SNA) is a highly flexible research method that allows for novel exploration of a wide variety of research phenomena. Evidence from fields as disparate as public health, education, informatics, sociology, and medicine has demonstrated the importance of recognizing the complexity inherent in individuals' connections with others. In this article, we provide a brief conceptual overview of social network theory and methodology, and then demonstrate how to apply SNA to an applied psychological research context studying students embedded in classrooms. We also provide numerous supporting materials on our OSF page, including R code for all analyses, a dataset containing social network data, and a glossary of key terms in social network analysis. We conclude with a set of recommendations for researchers interested in applying SNA to their own contexts and content areas. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Comparing employment, employment services, and employment goals in propensity-matched samples of people with intellectual and developmental disabilities with and without autism.

Background: People with intellectual and developmental disabilities (IDD) tend to have poor employment outcomes relative to the general population, as do people with autism. Research is unclear, however, about how people with IDD with and without autism compare on a variety of employment-related indicators, including desire to work, having work as a goal in their service plans, and being employed. Objectives: To understand how people with IDD with and without autism compare on important employment related outcomes, based on a matched random sample. Methods: Using merged administrative datasets, we used propensity score matching to construct statistically proximate samples of Medicaid waiver users in a single state with IDD both with and without autism, and then tested differences between the two groups on important employment-related indicators. Results: People with IDD and autism were less likely than people with IDD alone to have a goal for employment in their individualized service plans and to hold employment in group community settings. There was no statistical difference between the two groups in terms of desire to have a job or employment in individual community settings. Conclusions: Results reinforce the importance of planning for employment if holding employment is a person's aim, regardless of the presence of autism.

The Effects of Prime Supporters within a College Student's Support Network.

College students face academic and emotional challenges within and outside of the classroom. There is not a unique way to deal with all of these challenges, however obtaining support from other individuals in their network can be an important factor in their success in dealing with these challenges. Exploratory social support network data from 38 undergraduate students were collected and analyzed to find common network structures and examine the relationship between these structures and student characteristics, GPA, perceived social support, and use of other help resources. We found half of the students had what we defined to be a novel network characteristic, prime supporters, which are individuals who provided academic and emotional support to students for both routine and intense academic and emotional problems. We found students with a prime supporter in their social network tended to have higher GPAs and perceived social support than those without a prime supporter. Students with prime supporters also had differences in academic help-seeking behavior. These findings suggest the need for further research on the social networks of college students, particularly the presence of individuals who are providers of multiple sources of support.

Measuring Four Personal Opportunities for Adults With Intellectual and Developmental Disabilities.

This study tests an empirically derived model for measuring personal opportunities for people with intellectual and developmental disabilities (IDD) using National Core Indicators In-Person Survey (NCI-IPS) state and national datasets. The four personal opportunities measured, (a) privacy rights, (b) everyday choice, (c) community participation, and (d) expanded friendships, were informed by existing conceptualizations of service as well as NCI-IPS measures. Analyses confirmed the fit of a four-factor model and demonstrated that factors were significantly and positively correlated. To demonstrate the relationships between personal opportunities and personal and environmental characteristics, we estimated a structural equation model that regressed personal opportunities on age, gender, place of residence, and level of intellectual disability. Implications for using personal opportunities for evaluating service quality of IDD systems are discussed.

Language skills and friendships in kindergarten classrooms: A social network analysis.

The purpose of this study was to determine the extent that language skills contribute to kindergarten children's classroom-based friendship networks. We assessed language skills and collected friendship data via individual interviews of 419 children from 21 kindergarten classrooms. Using social network analysis, we found that language skills were significantly associated with friendship centrality and reciprocity after controlling for classroom and child-level factors. Children classified as at risk for specific language impairment (SLI) were significantly less central to friendship networks, and the odds of a reciprocal friendship tie were more than 50% lower compared to children who were not classified as at risk. Of children at risk, girls were significantly more central than boys. We couch our results within limitations of our study and provide recommendations for future research. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Children With Intellectual Disability and Victimization: A Logistic Regression Analysis.

It is a common assumption that children with disabilities are more likely to experience victimization than their peers without disabilities. However, there is a paucity of robust research supporting this assumption in the current literature. In response to this need, we conducted a logistic regression analysis using a national dataset of responses from 26,572 parents/caregivers to children with and without disabilities across all 50 states, plus the District of Columbia. The purpose of our study was to acquire a greater understanding of the odds of victimization among children with and without intellectual disability (ID), while controlling for several child and parent/adult demographic correlates. Most notably, our study revealed that children with ID have 2.84 times greater odds of experiencing victimization than children without disabilities, after adjusting for the other predictors in the model. Implications for future research and practice are discussed.

Using Machine Learning to Predict Patterns of Employment and Day Program Participation.

In this article, we demonstrate the potential of machine learning approaches as inductive analytic tools for expanding our current evidence base for policy making and practice that affects people with intellectual and developmental disabilities (IDD). Using data from the National Core Indicators In-Person Survey (NCI-IPS), a nationally validated annual survey of more than 20,000 nationally representative people with IDD, we fit a series of classification tree and random forest models to predict individuals' employment status and day activity participation as a function of their responses to all other items on the 2017-2018 NCI-IPS. The most accurate model, a random forest classifier, predicted employment outcomes of adults with IDD with an accuracy of 89 percent on the testing sample, and 80 percent on the holdout sample. The most important variable in this prediction was whether or not community employment was a goal in this person's service plan. These results suggest the potential machine learning tools to examine other valued outcomes used in evidence-based policy making to support people with IDD.

Measuring and Tracking Personal Opportunity Outcome Measures Over 3 Years to Guide Policy and Services That Promote Inclusive Community Living.

National policy and litigation have been a catalyst in many states for expanding personal outcomes for people with intellectual and developmental disabilities (IDD) and have served as an impetus for change in state IDD systems. Although several metrics are used to examine personal outcomes, the National Core Indicators (NCI) In-Person Survey (IPS) is one tool that provides an annual depiction of the lives of people who receive Medicaid Home and Community Based IDD waiver services (HCBS). This article examines whether a validated, three-factor (Privacy Rights, Everyday Choice, and Community Participation) measure of Personal Opportunity, derived from NCI items, functions as predicted across non-equivalent, NCI cohorts (N=2400) from Virginia in 2017, 2018, and 2019. Multiple-groups confirmatory factor analysis (CFA) was employed to examine the invariance and generalizability of the Personal Opportunity constructs. Results indicated that Privacy Rights, Everyday Choice, and Community Participation measured the same concepts even when time and group varied. Significant improvements in Privacy Rights and Community Participation were observed when comparing latent factor means across years. Findings provide stakeholders with a tool for interpreting personal outcomes in the contexts of policy and practice intended to improve inclusion and quality of life for adults with IDD.