https://www.um.edu.mt/library/oar/handle/123456789/1035 Fri, 05 Jun 2026 05:03:28 GMT 2026-06-05T05:03:28Z https://www.um.edu.mt/library/oar/handle/123456789/147019 Title: Analyzing ordinal categorical responses using multilevel models with an application related to dancing Authors: Camilleri, Liberato; Pellicano, Milena Abstract: Ordinal categorical outcomes frequently arise in applied research, particularly in settings where responses are recorded using rating scores rather than continuous measurements. In many practical applications, the data may be nested in higher level structures, with observations clustered within higher-level units, leading to dependence that cannot be adequately handled by standard regression models. This paper analyses ordinal categorical responses within a multilevel modelling framework, with particular emphasis on likelihood-based estimation methods for generalized mixed-effects models and their practical application to dance competition data. The study first develops the theoretical foundation of two-level models for ordinal responses assuming a multinomial distribution and a logit link function. Particular attention is given to random intercept and random coefficient structures, the interpretation of between-cluster variation, and the role of intra-class correlation in assessing dependence within hierarchical data. The paper then discusses the estimation and inferential techniques used for multilevel ordinal models and explores procedure to overcome difficulties that arise when the marginal likelihood involves integrals over random effects that do not have a closed-form solution. The study examines various numerical integration methods used in marginal likelihood estimation, with emphasis on Gaussian quadrature and Gauss-Hermite quadrature. The construction of quadrature rules and their role in approximating intractable integrals are discussed in detail, together with the use of modified Newton-Raphson procedures for maximising the approximated likelihood. In addition, Bayesian ideas are introduced in the context of predicting random effects, where empirical Bayes estimates (posterior means) are used to obtain cluster-specific predictions within the fitted models. These modelling methods are applied to a dance competition dataset. Since the dancing performance scores awarded by judges had a left skewed non-normal distribution, it was decided to categorise these scores to five ordinal response categories and analysed using multilevel logit models. The hierarchical structure is represented by individual performers (level-1 units) nested within dance types (level-2 units) allowing two-level models to be fitted. The models are implemented in Stata using the GLLAMM software, which provides flexible likelihood-based estimation for multilevel models with ordinal responses using numerical integration. The analysis demonstrates how multilevel models for ordinal responses can be used to account for clustering, estimate random-effects variability, compare alternative model structures, and interpret the effects of explanatory variables in a practically meaningful way. Overall, the paper provides a methodological and applied examination of multilevel modelling for ordinal categorical data. It shows that when ordinal responses are analysed within a hierarchical framework, likelihood-based estimation supported by quadrature methods offers a rigorous and practical approach for modelling complex dependence structures and obtaining interpretable statistical inferences. Thu, 01 Jan 2026 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/147019 2026-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/146074 Title: Improving discharge summary documentation of older adults in a rehabilitation hospital with an electronic discharge template Authors: Portelli, Christopher; Bonnici, Maria; Scerri, Claudia; Camilleri, Liberato; Ferry, Peter Abstract: Background: During past quality improvement projects at our rehabilitation hospital, inconsistencies were observed in the inclusion of essential information in discharge notes. The introduction of an electronic discharge summary template (EDST) aimed to address this by providing guidance to clinicians for comprehensive documentation. Methods: The EDST was developed through feedback from healthcare professionals using the Delphi method. 100 discharge letters were audited against the EDST criteria before and after implementation, following formal training for foundation year doctors. Results: Initial analysis revealed areas requiring improvement, particularly the Barthel score, patient weight, and cognitive assessment. Following implementation of the EDST, significant improvements were observed in these areas. Conclusion: The introduction of the EDST resulted in improved documentation and overall discharge summary completeness, supporting ongoing improvements in patient care continuity. Thu, 01 Jan 2026 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/146074 2026-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/143744 Title: Bayesian birth-death skyline model : a case study on heterochronous Maltese SARS-Cov-2 genomic data Authors: Ursino, Gianluca; Borg Inguanez, Monique; Suda, David; Borg, Joseph J.; Zahra, Graziella Abstract: When studying viral genome sequence data the Bayesian framework has the advantage that it can simultaneously construct phylogenetic trees and infer viral dynamics across time. This requires the specification of three models: (i) the transmission modelthe substitution model and the molecular clock model. In this study as transmission model we consider the Bayesian birth-death skyline (BDSKY) model and use the bModelTest method to define the substitution model. As a case study we consider 681 heterochronous genome sequences of COVID-19 sampled in Malta between 19/8/2020 and 5/1/2022. We consider both serial and multi-rho BDSKY models with two different molecular clock models: the strict and relaxed, and two settings for the number of intervals over which the reproductive number is considered constant (m=15 and m=30). In general the serial and the multi-rho BDSKY models gave considerably similar results yet some discrepancies were observed and these will be discussed. [excerpt] Wed, 01 Jan 2025 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/143744 2025-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/142999 Title: Implementing PROMEHS to foster social and emotional learning, resilience, and mental health : evidence from Croatian schools Authors: Tatalović Vorkapić, Sanja; Vujičić, Lidija; Čamber Tambolaš, Akvilina; Grazzani, Ilaria; Cavioni, Valeria; Cefai, Carmel; Camilleri, Liberato Abstract: Background/Objectives: In light of the concerning research data on students’ mental health, it is essential to provide high-quality programs that support children and young people in strengthening their psychological well-being. To address this need, the three-year Erasmus+ KA3 international project PROMEHS: Promoting Mental Health at Schools was developed. The project involved universities and education policy representatives from seven European countries, Italy (project leader), Greece, Croatia, Latvia, Malta, Portugal, and Romania. Its core activities included the development of the PROMEHS curriculum, grounded in three key components: social and emotional learning, resilience, and the prevention of behavioral problems, alongside a rigorous evaluation of its implementation. The main research aim was to test the effect of PROMEHS on students’ and teachers’ mental health. Methods: In Croatia, the curriculum was introduced following the training of teachers (N = 76). It was implemented in kindergartens, and primary and secondary schools (N = 32), involving a total of 790 children. Using a quasi-experimental design, data were collected at two measurement points in both experimental and control groups by teachers, parents, and students. Results: The findings revealed significant improvements in children’s social and emotional competencies and resilience, accompanied by reductions in behavioural difficulties. These effects were most evident in teachers’ assessments, compared to parents’ ratings and student self-reports. Furthermore, teachers reported a significantly higher level of psychological well-being following implementation. Conclusions: Bearing in mind some study limitations, it can be concluded that this study provides evidence of the positive effects of PROMEHS in Croatian educational settings. Building on these outcomes and PROMEHS as an evidence-based program, a micro-qualification education was created to ensure the sustainability and systematic integration of the PROMEHS curriculum into Croatian kindergartens and schools. Thu, 01 Jan 2026 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/142999 2026-01-01T00:00:00Z