PAN-cODE: COVID-19 forecasting using conditional latent ODEs.

The coronavirus disease 2019 (COVID-19) pandemic has caused millions of deaths around the world and revealed the need for data-driven models of pandemic spread. Accurate pandemic caseload forecasting allows informed policy decisions on the adoption of non-pharmaceutical interventions (NPIs) to reduce disease transmission. Using COVID-19 as an example, we present Pandemic conditional Ordinary Differential Equation (PAN-cODE), a deep learning method to forecast daily increases in pandemic infections and deaths. By using a deep conditional latent variable model, PAN-cODE can generate alternative caseload trajectories based on alternate adoptions of NPIs, allowing stakeholders to make policy decisions in an informed manner. PAN-cODE also allows caseload estimation for regions that are unseen during model training. We demonstrate that, despite using less detailed data and having fully automated training, PAN-cODE's performance is comparable to state-of-the-art methods on 4-week-ahead and 6-week-ahead forecasting. Finally, we highlight the ability of PAN-cODE to generate realistic alternative outcome trajectories on select US regions.

Multilevel IRT models for the analysis of satisfaction for distance learning during the Covid-19 pandemic.

The Covid-19 pandemic played a relevant role in the diffusion of distance learning alternatives to "traditional" learning based on classroom activities, to allow university students to continue attending lessons during the most severe phases of the pandemic. In such a context, investigating the students' perspective on distance learning provides useful information to stakeholders to improve effective educational strategies, which could be useful also after the end of the emergency to favor the digital transformation in the higher educational setting. Here we focus on the satisfaction in distance learning for Italian university students. We rely on data comprising students enrolled in various Italian universities, which were inquired about several aspects related to learning distance. We explicitly take into account the hierarchical nature of data (i.e., students nested in universities) and the latent nature of the variable of interest (i.e., students' learning satisfaction) through a multilevel Item Response Theory model with students' and universities' covariates. As the main results of our study, we find out that distance learning satisfaction of students: (i) depends on the University where they study; (ii) is affected by some students' socio-demographic characteristics, among which psychological factors related to Covid-19; (iii) is affected by some observable university characteristics.

Bayesian adaptive selection of basis functions for functional data representation

Considering the context of functional data analysis, we developed and applied a new Bayesian approach via the Gibbs sampler to select basis functions for a finite representation of functional data. The proposed methodology uses Bernoulli latent variables to assign zero to some of the basis function coefficients with a positive probability. This procedure allows for an adaptive basis selection since it can determine the number of bases and which ones should be selected to represent functional data. Moreover, the proposed procedure measures the uncertainty of the selection process and can be applied to multiple curves simultaneously. The methodology developed can deal with observed curves that may differ due to experimental error and random individual differences between subjects, which one can observe in a real dataset application involving daily numbers of COVID-19 cases in Brazil. Simulation studies show the main properties of the proposed method, such as its accuracy in estimating the coefficients and the strength of the procedure to find the true set of basis functions. Despite having been developed in the context of functional data analysis, we also compared the proposed model via simulation with the well-established LASSO and Bayesian LASSO, which are methods developed for non-functional data. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

Were Employee Welfare and Work Commitment Impacted by the High Performance Work System?

The High Performance Work System (HPWS) serves as a decisive tool that enables organizations to prioritize quality work. Despite this, instructors in both public and private higher education do not have a strong enough collective voice to influence its policies at the state and federal levels. This study focuses in particular on the instructors of Higher Education Institutions in Pakistan, to investigate the influence of the HPWS on Employee Welfare and Work Commitment in the context of COVID-19. Nineteen items on a 5.0-point Likert scale, with "1” denoting "Strongly Disagree" and "5” indicating "Strongly Agree" was included in a survey for this study that covers its three latent variables, i.e., HPWS, Work Commitment, and Employee's Welfare. 204 teaching professionals/instructors from higher educational institutions, both public and private, made up the study's participant pool. SmartPLS was used in the measurement and structural model analyzes with Confirmatory Factor Analysis and inter-construct correlation of this study. The study concluded that the HPWS has an implicit and substantial impact on Employee Welfare and determined that Work Commitment significantly mediates the association between HPWS and Employee Welfare. This study includes earlier research on HPWS with effective collaboration and opposing viewpoints. This study contributed to the existing literature novel by concentrating on the complexity of Employees' performance and their workplace environment. This study significantly implicates the HR strategists and managers that to enhance employee engagement with their jobs and duties and to improve employee welfare, academic and corporate institutions should have efficient HPWS implemented within their organizations. © 2022 Authors. All rights reserved.

The Influence of Present Health Status (Post Covid-19) on Retirement Planning in Malaysia

Purpose: To investigate whether present health status influence retirement planning in the new economic challenge post Covid 19. The relationship between present health status and retirement planning should be better explored and investigated for strengthening the retirement planning among Malaysian women. Design/methodology/approach: This study is developed based on a quantitative approach where primary data was acquired through online surveys to 433 workers in various locations in Malaysia. The target population of this study are people who work full time in Malaysia's government and private sectors whose ages range from 25 to 55 years old. Findings: The significant result from this study has shown that there is a health status effect on the employees' retirement planning. The result identified that the health status is an important factor for retirement planning during the post-COVID-19 among the working population in Malaysia. Research limitations/implications: Even though the COVID-19 pandemic has caused many monetary, economic and social challenges, it has also opened up a new door opportunity for constructive change. Government, policymakers and the general public need more transparent and resourceful in making difficult choices and trade-offs between short-term and long-term concerns. Nevertheless, the real challenges exposed in the COVID-19 pandemic are the lack of progressive long-term thinking on retirement planning. This paper has its limitations, that since COVID-19 is still ongoing, this study only focuses on the current present health status of Malaysian employees. Originality/value: Studying the employee's behaviour during the times of distress is important to understand how do they manage their finances. This is a valuable knowledge that could be applied in future. Many employees were caught unaware and faced challenges in the recent past. This could be avoided if prior knowledge and the savings are available.

Can Resilience Buffer the Effects of Loneliness on Mental Distress Among Working-Age Adults in the United States During the COVID-19 Pandemic? A Latent Moderated Structural Modeling Analysis.

BACKGROUND: The profound health consequences of loneliness are well-established. However, less is known about the protective factors which may alleviate the effects of loneliness on mental health especially among working-age adults amidst the COVID-19 pandemic. We draw on the social ecology of resilience and examine whether resilience factors can buffer the effects of loneliness on mental distress. METHODS: Data came from the National Well-being Survey-a national study of a demographically representative sample of U.S. working-age adults (N = 4014). We used (a) structural equation models with latent variables to examine the main effects of loneliness, psychological resilience, and perceived social support on mental distress, and (b) latent moderated structural equations to estimate the latent interaction effects. RESULTS: Results revealed that (a) loneliness was positively associated with mental distress and psychological resilience was negatively related to mental distress, and (b) psychological resilience and perceived social support moderated the strength of the relationship between loneliness and mental distress. CONCLUSIONS: Our study highlights the importance of psychological resilience and perceived social support as two protective factors in the relationship between loneliness and mental distress. Given that loneliness significantly predicts worse mental and physical health and higher mortality, identifying protective factors that might disrupt these connections is vital. As such, public health efforts to strengthen and expand familial and community social support networks and foster psychological resilience are urgently needed to support mental health among working-age adults during additional waves of the pandemic or future similar stressors.

Consumers' preference for urban last-mile delivery: effects of value perception and long-term COVID-initiated contextual shifts

The economic and environmental challenges associated with Last Mile Delivery (LMD) give rise to the self-collection concept, yet the practical adoption is often below expectations. In this consumer-centric segment, adequate understandings of consumers are vital but are often lacking. To address this gap, this study examines consumers' LMD preference with the Integrated Choice and Latent Variable framework. A stated choice experiment was commissioned in Singapore during the transition of COVID pandemic toward endemic. Our results showed that consumers accept unattended delivery methods and are no longer concerned with the delivery time window, a traditionally critical delivery attribute. Regarding latent perceptions, this study confirmed the significant effects of value perception on self-collection preferences. Nonetheless, individuals' environmental consciousness was found to be insignificant. The relative effects of specific value statements were quantified using the marginal rate of substitution and the mediation roles of value perception on the sociodemographic-preferences relationships were validated.

Effects of a bike sharing system and COVID-19 on low-carbon traffic modal shift and emission reduction

The rise of dockless bike sharing and the development of bike-only roads have facilitated a low-carbon transition in transportation. In this direction, Beijing opened the first bike-only road in 2019. Shortly after opening this bike road, the city encountered the COVID-19 pandemic. In this study, we evaluate the impacts of the first bike-only road and COVID-19 on the travel modal shift of the public and quantify the corresponding changes in carbon emissions. Using proposed integrated choice and latent variable models, we find that respondents who were previously low-carbon travelers were more likely to choose low-carbon traffic options and more sensitive to perceived instrumental usefulness of the bike sharing system than were high-carbon respondents. The bike lanes significantly increased the probability for all respondents to switch their travel mode to bike sharing. The COVID-19 pandemic significantly inhibited the high-carbon group from switching to bike sharing for both long- and short-distance trips, while the pandemic significantly promoted the low-carbon group to choose bike sharing for short-distance trips. However, there was no significant effect on this group by the pandemic for long-distance trips. Furthermore, we find that bike sharing can reduce carbon emissions by 41.55% and 33.43% for short- and long-distance trips, respectively. The overall emission reduction effect of bike sharing increased from 28.29% to 47.21% when the bike lane was introduced;whereas the COVID-19 pandemic decreased bike sharing emission reduction from 43.74% before to 29.87% during the pandemic. Our research reveals that the bike sharing system plays both an alternative role to other traffic modes for short-distance traffic and a complementary role to public transport for long-distance traffic. © 2022 Elsevier Ltd

EvoVGM: A Deep Variational Generative Model for Evolutionary Parameter Estimation

Most evolutionary-oriented deep generative models do not explicitly consider the underlying evolutionary dynamics of biological sequences as it is performed within the Bayesian phylogenetic inference framework. In this study, we propose a method for a deep variational Bayesian generative model (EvoVGM) that jointly approximates the true posterior of local evolutionary parameters and generates sequence alignments. Moreover, it is instantiated and tuned for continuous-Time Markov chain substitution models such as JC69, K80 and GTR. We train the model via a low-variance stochastic estimator and a gradient ascent algorithm. Here, we analyze the consistency and effectiveness of EvoVGM on synthetic sequence alignments simulated with several evolutionary scenarios and different sizes. Finally, we highlight the robustness of a fine-Tuned EvoVGM model using a sequence alignment of gene S of coronaviruses. © 2022 Owner/Author.

Autoregressive mixture models for clustering time series

Clustering time series into similar groups can improve models by combining information across like time series. While there is a well developed body of literature for clustering of time series, these approaches tend to generate clusters independently of model training, which can lead to poor model fit. We propose a novel distributed approach that simultaneously clusters and fits autoregression models for groups of similar individuals. We apply a Wishart mixture model so as to cluster individuals while modelling the corresponding autocovariance matrices at the same time. The fitted Wishart scale matrices map to cluster-level autoregressive coefficients through the Yule-Walker equations, fitting robust parsimonious autoregressive mixture models. This approach is able to discern differences in underlying autocorrelation variation of time series in settings with large heterogeneous datasets. We prove consistency of our cluster membership estimator, asymptotic distributions of coefficients and compare our approach against competing methods through simulation as well as by fitting a COVID-19 forecast model.

Discrete Latent Variables Discovery and Structure Learning in Mixed Bayesian Networks

Latent variables pose a challenge for accurate modelling, experimental design, and inference, since they may cause non-adjustable bias in the estimation of effects. While most of the research regarding latent variables revolves around accounting for their presence and learning how they interact with other variables in the experiment, their bare existence is assumed to be deduced based on domain expertise. In this work we focus on the discovery of such latent variables, utilizing statistical hypothesis testing methods and Bayesian Networks learning. Specifically, we present a novel method for detecting discrete latent factors which affect continuous observed outcomes, in mixed discrete/continuous observed data, and device a structure learning algorithm that adds the detected latent factors to a fully observed Bayesian Network. Finally, we demonstrate the utility of our method with a set of experiments, in both controlled and real-life settings, one of which is a prediction for the outcome of COVID-19 test results. © 2021 IEEE.

Assessing Change in Intervention Research: The Benefits of Composite Outcomes

Intervention research is often time- and resource-intensive, with numerous participants involved over extended periods of time. To maximize the value of intervention studies, multiple outcome measures are often included, either to ensure a diverse set of outcomes is being assessed or to refine assessments of specific outcomes. Here, we advocate for combining assessments, rather than relying on individual measures assessed separately, to better evaluate the effectiveness of interventions. Specifically, we argue that by pooling information from individual measures into a single outcome, composite scores can provide finer estimates of the underlying theoretical construct of interest while retaining important properties more sophisticated methods often forgo, such as transparency and interpretability. We describe different methods to compute, evaluate, and use composites depending on the goals, design, and data. To promote usability, we also provide a preregistration template that includes examples in the context of psychological interventions with supporting R code. Finally, we make a number of recommendations to help ensure that intervention studies are designed in a way that maximizes discoveries. A Shiny app and detailed R code accompany this article and are available at .

Modelling the complexity of pandemic-related lifestyle quality change and mental health: an analysis of a nationally representative UK general population sample.

PURPOSE: The COVID-19 pandemic has affected the way many individuals go about their daily lives. This study attempted to model the complexity of change in lifestyle quality as a result of the COVID-19 pandemic and its context within the UK adult population. METHODS: Data from the COVID-19 Psychological Research Consortium Study (Wave 3, July 2020; N = 1166) were utilised. A measure of COVID-19-related lifestyle change captured how individuals' lifestyle quality had been altered as a consequence of the pandemic. Exploratory factor analysis and latent profile analysis were used to identify distinct lifestyle quality change subgroups, while multinomial logistic regression analysis was employed to describe class membership. RESULTS: Five lifestyle dimensions, reflecting partner relationships, health, family and friend relations, personal and social activities, and work life, were identified by the EFA, and seven classes characterised by distinct patterns of change across these dimensions emerged from the LPA: (1) better overall (3.3%), (2) worse except partner relations (6.0%), (3) worse overall (2.5%), (4) better relationships (9.5%), (5) better except partner relations (4.3%), (6) no different (67.9%), and (7) worse partner relations only (6.5%). Predictor variables differentiated membership of classes. Notably, classes 3 and 7 were associated with poorer mental health (COVID-19 related PTSD and suicidal ideation). CONCLUSIONS: Four months into the pandemic, most individuals' lifestyle quality remained largely unaffected by the crisis. Concerningly however, a substantial minority (15%) experienced worsened lifestyles compared to before the pandemic. In particular, a pronounced deterioration in partner relations seemed to constitute the more severe pandemic-related lifestyle change.

Hierarchical Modelling of COVID-19 Death Risk in India in the Early Phase of the Pandemic.

We improve upon the modelling of India's pandemic vulnerability. Our model is multidisciplinary and recognises the nested levels of the epidemic. We create a model of the risk of severe COVID-19 and death, instead of a model of transmission. Our model allows for socio-demographic-group differentials in risk, obesity and underweight people, morbidity status and other conditioning regional and lifestyle factors. We build a hierarchical multilevel model of severe COVID-19 cases, using three different data sources: the National Family Health Survey for 2015/16, Census data for 2011 and data for COVID-19 deaths obtained cumulatively until June 2020. We provide results for 11 states of India, enabling best-yet targeting of policy actions. COVID-19 deaths in north and central India were higher in areas with older and overweight populations, and were more common among people with pre-existing health conditions, or who smoke, or who live in urban areas. Policy experts may both want to 'follow World Health Organisation advice' and yet also use disaggregated and spatially specific data to improve wellbeing outcomes during the pandemic. The future uses of our innovative data-combining model are numerous.

Dans le contexte du développement international, on peut améliorer la modélisation de la vulnérabilité à une pandémie en combinant différentes disciplines, en combinant des données et en reconnaissant les nombreux niveaux imbriqués de l'épidémie. Des modèles de transmission ont été élaborés à l'échelle nationale ou pour plusieurs pays. A l'inverse, nous construisons un modèle permettant de prendre en compte les différents niveaux de risque selon les groupes sociaux, ainsi que le conditionnement des facteurs régionaux et des facteurs liés au mode de vie. La forme grave de la COVID-19 est notre résultat clé innovant. Nous utilisons trois sources de données simultanément: l'enquête nationale sur la santé des familles en Inde, le recensement de la population indienne de 2011 et les décès liés à l'épidémie de COVID-19. Nous fournissons des résultats pour 11 États en Inde, ce qui permet un meilleur ciblage des actions politiques. Les utilisations futures de ces modèles sont nombreuses. Dans le nord et le centre de l'Inde, les décès liés à la COVID-19 étaient plus nombreux dans les régions avec populations âgées et populations en surpoids. Ces décès étaient plus fréquents chez les personnes ayant déjà des problèmes de santé, ou chez celles qui fument ou qui vivent dans les zones urbaines. Les experts en politiques publiques pourront souhaiter à la fois « suivre les conseils de l'Organisation mondiale de la santé ¼ tout en utilisant des données désagrégées et spatiales pour améliorer les résultats en matière de bien-être pendant la pandémie.