Sparse spatially clustered coefficient model via adaptive regularization.

Large spatial datasets with many spatial covariates have become ubiquitous in many fields in recent years. A question of interest is to identify which covariates are likely to influence a spatial response, and whether and how the effects of these covariates vary across space, including potential abrupt changes from region to region. To solve this question, a new efficient regularized spatially clustered coefficient (RSCC) regression approach is proposed, which could achieve variable selection and identify latent spatially heterogeneous covariate effects with clustered patterns simultaneously. By carefully designing the regularization term of RSCC as a chain graph guided fusion penalty plus a group lasso penalty, the RSCC model is computationally efficient for large spatial datasets while still achieving the theoretical guarantees for estimation. RSCC also adopts the idea of adaptive learning to allow for adaptive weights and adaptive graphs in its regularization terms and further improves the estimation performance. RSCC is applied to study the acceptance of COVID-19 vaccines using county-level data in the United States and discover the determinants of vaccination acceptance with varying effects across counties, revealing important within-state and across-state spatially clustered patterns of covariates effects.

A Two-Step Algorithm to Estimate Variable Importance for Multi-State Data: An Application to COVID-19

Survival data with a multi-state structure are frequently observed in follow-up studies. An analytic approach based on a multi-state model (MSM) should be used in longitudinal health studies in which a patient experiences a sequence of clinical progression events. One main objective in the MSM framework is variable selection, where attempts are made to identify the risk factors associated with the transition hazard rates or probabilities of disease progression. The usual variable selection methods, including stepwise and penalized methods, do not provide information about the importance of variables. In this context, we present a two-step algorithm to evaluate the importance of variables for multi-state data. Three different machine learning approaches (random forest, gradient boosting, and neural network) as the most widely used methods are considered to estimate the variable importance in order to identify the factors affecting disease progression and rank these factors according to their importance. The performance of our proposed methods is validated by simulation and applied to the COVID-19 data set. The results revealed that the proposed two-stage method has promising performance for estimating variable importance. © 2023 Tech Science Press. All rights reserved.

Survival Analysis of Thai Micro and Small Enterprises during the Covid-19 Pandemic

Micro and small enterprises (MSEs) are important to the local economy and are the most crucial source of employment in Thailand. Using the three-round survey data, we assess the impact of COVID-19 on the survival probability of MSEs in the tourism and manufacturing sectors. Enter-prise characteristics such as owner characteristics, employment and business strategies are examined as potential factors to mitigate or stimulate business failures. The Cox proportional hazards model and Kaplan-Meier estimator are employed. Our findings reveal that the survival probability paths from the three rounds of survey show a gradual decrease of survival probability from the first week of interview and approximately 50% of MSEs could not survive longer than 52 weeks during the COVID-19 pandemic. We also find that the survival of MSEs mainly depends on location, number of employees, and business model adjustment, namely operation with social distancing and online marketing. Particularly, retaining employees and not reducing the working hours are one of the key factors increasing the survivability of MSEs. However, the longer length of the crisis reduces the contribution of these key factors. The longer the period of the COVID-19 pandemic, the lower the chance of MSEs survivability.

An Overview of Healthcare Data Analytics With Applications to the COVID-19 Pandemic

In the era of big data, standard analysis tools may be inadequate for making inference and there is a growing need for more efficient and innovative ways to collect, process, analyze and interpret the massive and complex data. We provide an overview of challenges in big data problems and describe how innovative analytical methods, machine learning tools and metaheuristics can tackle general healthcare problems with a focus on the current pandemic. In particular, we give applications of modern digital technology, statistical methods,data platforms and data integration systems to improve diagnosis and treatment of diseases in clinical research and novel epidemiologic tools to tackle infection source problems, such as finding Patient Zero in the spread of epidemics. We make the case that analyzing and interpreting big data is a very challenging task that requires a multi-disciplinary effort to continuously create more effective methodologies and powerful tools to transfer data information into knowledge that enables informed decision making.

Prediction of COVID-19 Infections for Municipalities in the Netherlands: Algorithm Development and Interpretation.

BACKGROUND: COVID-19 was first identified in December 2019 in the city of Wuhan, China. The virus quickly spread and was declared a pandemic on March 11, 2020. After infection, symptoms such as fever, a (dry) cough, nasal congestion, and fatigue can develop. In some cases, the virus causes severe complications such as pneumonia and dyspnea and could result in death. The virus also spread rapidly in the Netherlands, a small and densely populated country with an aging population. Health care in the Netherlands is of a high standard, but there were nevertheless problems with hospital capacity, such as the number of available beds and staff. There were also regions and municipalities that were hit harder than others. In the Netherlands, there are important data sources available for daily COVID-19 numbers and information about municipalities. OBJECTIVE: We aimed to predict the cumulative number of confirmed COVID-19 infections per 10,000 inhabitants per municipality in the Netherlands, using a data set with the properties of 355 municipalities in the Netherlands and advanced modeling techniques. METHODS: We collected relevant static data per municipality from data sources that were available in the Dutch public domain and merged these data with the dynamic daily number of infections from January 1, 2020, to May 9, 2021, resulting in a data set with 355 municipalities in the Netherlands and variables grouped into 20 topics. The modeling techniques random forest and multiple fractional polynomials were used to construct a prediction model for predicting the cumulative number of confirmed COVID-19 infections per 10,000 inhabitants per municipality in the Netherlands. RESULTS: The final prediction model had an R² of 0.63. Important properties for predicting the cumulative number of confirmed COVID-19 infections per 10,000 inhabitants in a municipality in the Netherlands were exposure to particulate matter with diameters <10 µm (PM10) in the air, the percentage of Labour party voters, and the number of children in a household. CONCLUSIONS: Data about municipality properties in relation to the cumulative number of confirmed infections in a municipality in the Netherlands can give insight into the most important properties of a municipality for predicting the cumulative number of confirmed COVID-19 infections per 10,000 inhabitants in a municipality. This insight can provide policy makers with tools to cope with COVID-19 and may also be of value in the event of a future pandemic, so that municipalities are better prepared.

Forecasting Crude Oil Prices with Major S&P 500 Stock Prices: Deep Learning, Gaussian Process, and Vine Copula

This paper introduces methodologies in forecasting oil prices (Brent and WTI) with multivariate time series of major S&P 500 stock prices using Gaussian process modeling, deep learning, and vine copula regression. We also apply Bayesian variable selection and nonlinear principal component analysis (NLPCA) for data dimension reduction. With a reduced number of important covariates, we also forecast oil prices (Brent and WTI) with multivariate time series of major S&P 500 stock prices using Gaussian process modeling, deep learning, and vine copula regression. To apply real data to the proposed methods, we select monthly log returns of 2 oil prices and 74 large-cap, major S&P 500 stock prices across the period of February 2001–October 2019. We conclude that vine copula regression with NLPCA is superior overall to other proposed methods in terms of the measures of prediction errors.

Association between short-term exposure to air pollution and COVID-19 mortality in all German districts: the importance of confounders.

Background: The focus of many studies is to estimate the effect of risk factors on outcomes, yet results may be dependent on the choice of other risk factors or potential confounders to include in a statistical model. For complex and unexplored systems, such as the COVID-19 spreading process, where a priori knowledge of potential confounders is lacking, data-driven empirical variable selection methods may be primarily utilized. Published studies often lack a sensitivity analysis as to how results depend on the choice of confounders in the model. This study showed variability in associations of short-term air pollution with COVID-19 mortality in Germany under multiple approaches accounting for confounders in statistical models. Methods: Associations between air pollution variables PM2.5, PM10, CO, NO, NO2, and O3 and cumulative COVID-19 deaths in 400 German districts were assessed via negative binomial models for two time periods, March 2020-February 2021 and March 2021-February 2022. Prevalent methods for adjustment of confounders were identified after a literature search, including change-in-estimate and information criteria approaches. The methods were compared to assess the impact on the association estimates of air pollution and COVID-19 mortality considering 37 potential confounders. Results: Univariate analyses showed significant negative associations with COVID-19 mortality for CO, NO, and NO2, and positive associations, at least for the first time period, for O3 and PM2.5. However, these associations became non-significant when other risk factors were accounted for in the model, in particular after adjustment for mobility, political orientation, and age. Model estimates from most selection methods were similar to models including all risk factors. Conclusion: Results highlight the importance of adequately accounting for high-impact confounders when analyzing associations of air pollution with COVID-19 and show that it can be of help to compare multiple selection approaches. This study showed how model selection processes can be performed using different methods in the context of high-dimensional and correlated covariates, when important confounders are not known a priori. Apparent associations between air pollution and COVID-19 mortality failed to reach significance when leading selection methods were used. Supplementary Information: The online version contains supplementary material available at 10.1186/s12302-022-00657-5.

Backcasting world trade growth using data reduction methods

This paper compares backcasting performance of models based on variable selection to dynamic factor model for backcasting the world trade growth rate with two months ahead. The variable selection models are specified by applying penalised regressions and an automatic general-to-specific procedure, using a large data set. A recursive forecast study is carried out to assess the backcasting performance by distinguishing crisis and non-crisis periods. The results show that, some selection-based models exhibit a good backcasting performance during both periods. The more accurate backcasts seem to be SCAD, adaptive Elastic-Net and adaptive SCAD during the global financial crisis (GFC) and COVID-19 crisis, whereas it seems rather Lasso, Elastic-Net, adaptive Lasso and DFM during the non-crisis period. Amongst the predictors for backcasting world trade growth, it appears that the index of global economic conditions proposed by Baumeister et al. (The Review of Economics and Statistics, 2020), the PMI indicator on new export orders in manufacturing sector and the MSCI world index are relevant. © 2022 The Authors. The World Economy published by John Wiley & Sons Ltd.

Nowcasting world GDP growth with high-frequency data

Although the Covid-19 crisis has shown how high-frequency data can help track the economy in real time, we investigate whether it can improve the nowcasting accuracy of world GDP growth. To this end, we build a large dataset of 718 monthly and 255 weekly series. Our approach builds on a Factor-Augmented MIxed DAta Sampling (FA-MIDAS), which we extend with a preselection of variables. We find that this preselection markedly enhances performances. This approach also outperforms a LASSO-MIDAS-another technique for dimension reduction in a mixed-frequency setting. Though we find that a FA-MIDAS with weekly data outperform other models relying on monthly or quarterly data, we also point to asymmetries. Models with weekly data have indeed performances similar to other models during "normal" times but can strongly outperform them during "crisis" episodes, above all the Covid-19 period. Finally, we build a nowcasting model for world GDP annual growth incorporating weekly data that give timely (one per week) and accurate forecasts (close to IMF and OECD projections but with 1- to 3-month lead). Policy-wise, this can provide an alternative benchmark for world GDP growth during crisis episodes when sudden swings in the economy make usual benchmark projections (IMF's or OECD's) quickly outdated.

Mental well-being and quality of working life in UK social workers before and during the COVID-19 pandemic: A propensity score matching study

Social work, like many other health and social care services has been overwhelmed by the COVID-19 pandemic. This article compares the differences of mental well-being and work-related quality of life (WRQoL) for UK social workers before and during the pandemic. Mental well-being and WRQoL were better during the COVID-19 pandemic in 2020 than prior to the pandemic in 2018. The findings of this study suggest that during the highpoint of the pandemic other factors such as increased support to changes in working practices may be responsible for this improvement. During the COVID-19 pandemic interest into its potential impact on mental well-being has intensified. Within the social care sector, the pandemic has increased job demands and prolonged stress taking a disproportionate toll on the workforce, particularly social workers. This article compares the mental well-being and quality of working life of social workers in the United Kingdom (UK) before and during the pandemic. Data were collected in 2018 (N = 1,195) and 2020 (N = 1,024) using two cross-sectional surveys. To account for the differences between the datasets, propensity score matching was employed prior to effect estimation, utilising demographic and work-related variables common to both datasets. The differences between the two time-points were estimated using multiple regressions. Both mental well-being and quality of working life were significantly higher during the COVID-19 pandemic in 2020 compared to 2018. This suggests that during the highpoint of the pandemic in the UK, increased support, and changes to working practices, such as reprioritisation of work and other initiatives, may be responsible for increased mental well-being and quality of working life. While acknowledging the known pressures on UK social workers during the COVID-19 pandemic this evidence suggests a mixed picture of the pandemic with lessons for managers and employers.

Carbon prices forecasting in quantiles

This paper proposes two new methods (the Quantile Group LASSO and the Quantile Group SCAD models) to evaluate the predictability of a large group of factors on carbon futures returns. The most powerful predictors are selected through the dimension-reduction mechanism of the two models, while potential differences of the statistically significant predictors for different quantiles of carbon returns are carefully considered. First, we find that the proposed models outperform a series of competing ones with respect to prediction accuracy. Second, impacts of the selected predictors over the carbon price distribution are estimated through a quantile approach, which outperforms the mean shrinkage model in our case with data featured by a non-normal distribution. Specifically, the Brent spot price, the crude oil closing stock in the UK, and the growth of natural gas production in the UK are found to impact carbon futures returns only in extreme conditions with a strong asymmetric feature. Importantly, our estimators remain robust against the extreme event caused by the Covid-19. Our findings reveal that the identification of appropriate carbon return predictors and their impacts hinge on the carbon market conditions, and should be of interest to various stakeholders.

On the relationship between COVID-19 reported fatalities early in the pandemic and national socio-economic status predating the pandemic.

This study investigates the relationship between socio-economic determinants pre-dating the pandemic and the reported number of cases, deaths, and the ratio of deaths/cases in 199 countries/regions during the first months of the COVID-19 pandemic. The analysis is performed by means of machine learning methods. It involves a portfolio/ensemble of 32 interpretable models and considers the case in which the outcome variables (number of cases, deaths, and their ratio) are independent and the case in which their dependence is weighted based on geographical proximity. We build two measures of variable importance, the Absolute Importance Index (AII) and the Signed Importance Index (SII) whose roles are to identify the most contributing socio-economic factors to the variability of the COVID-19 pandemic. Our results suggest that, together with the established influence on cases and deaths of the level of mobility, the specific features of the health care system (smart/poor allocation of resources), the economy of a country (equity/non-equity), and the society (religious/not religious or community-based vs not) might contribute to the number of COVID-19 cases and deaths heterogeneously across countries.