Robust autoregressive modeling and its diagnostic analytics with a COVID-19 related application

Autoregressive models in time series are useful in various areas. In this article, we propose a skew-t autoregressive model. We estimate its parameters using the expectation-maximization (EM) method and develop the influence methodology based on local perturbations for its validation. We obtain the normal curvatures for four perturbation strategies to identify influential observations, and then to assess their performance through Monte Carlo simulations. An example of financial data analysis is presented to study daily log-returns for Brent crude futures and investigate possible impact by the COVID-19 pandemic. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

A new ridge estimator for linear regression model with some challenging behavior of error term

Ridge regression is a variant of linear regression that aims to circumvent the issue of collinearity among predictors. The ridge parameter (Formula presented.) has an important role in the bias-variance tradeoff. In this article, we introduce a new approach to select the ridge parameter to deal with the multicollinearity problem with different behavior of the error term. The proposed ridge estimator is a function of the number of predictors and the standard error of the regression model. An extensive simulation study is conducted to assess the performance of the estimators for the linear regression model with different error terms, which include normally distributed, non-normal and heteroscedastic or autocorrelated errors. Based upon the criterion of mean square error (MSE), it is found that the new proposed estimator outperforms OLS, commonly used and closely related estimators. Further, the application of the proposed estimator is provided on the COVID-19 data of India. © 2023 Taylor & Francis Group, LLC.

A Bayesian approach for the estimation of weight matrices in spatial autoregressive models

We develop a Bayesian approach to estimate weight matrices in spatial autoregressive (or spatial lag) models. Datasets in regional economic literature are typically characterized by a limited number of time periods relative to spatial units . When the spatial weight matrix is subject to estimation severe problems of over-parametrization are likely. To make estimation feasible, our approach focusses on spatial weight matrices which are binary prior to row-standardization. We discuss the use of hierarchical priors which impose sparsity in the spatial weight matrix. Monte Carlo simulations show that these priors perform very well where the number of unknown parameters is large relative to the observations. The virtues of our approach are demonstrated using global data from the early phase of the COVID-19 pandemic.

Plausible explanation for the third COVID-19 wave in India and its implications.

Recently some of us used a random-walk Monte Carlo simulation approach to study the spread of COVID-19. The calculations were reasonably successful in describing secondary and tertiary waves of infection, in countries such as the USA, India, South Africa and Serbia. However, they failed to predict the observed third wave for India. In this work we present a more complete set of simulations for India, that take into consideration two aspects that were not incorporated previously. These include the stochastic movement of an erstwhile protected fraction of the population, and the reinfection of some recovered individuals because of their exposure to a new variant of the SARS-CoV-2 virus. The extended simulations now show the third COVID-19 wave for India that was missing in the earlier calculations. They also suggest an additional fourth wave, which was indeed observed during approximately the same time period as the model prediction.

Development of a Positive Voice Onset Time Pattern by Brazilian Speakers of English as a Second Language: a Longitudinal Study During the COVID-19 Pandemic

This study investigates additional language development in five plurilingual speakers of English as a second language (L2) during the COVID-19 pandemic and the consequent social distancing. From the perspective of language as a Complex Dynamic System (DE BOT;LOWIE;VERSPOOR, 2007;LARSEN-FREEMAN;CAMERON, 2008;VERSPOOR;DE BOT;LOWIE, 2011), this longitudinal study analyzes the development of a positive Voice Onset Time pattern among participants throughout 12 weeks, including a six-session intervention of explicit instruction of English phonetic-phonological aspects. From Monte Carlo Simulations (VAN DIJK;VERSPOOR;LOWIE, 2011), our quantitative analysis showed positive peaks of performance, indicating the role of variability in learning and developing new language patterns. The qualitative results regarding the online intervention likewise contributed to both language teaching and remote empirical-experimental research studies. © 2022, Universidade Federal de Minas Gerais, Faculdade de Letras. All rights reserved.

A Bayesian approach for the estimation of weight matrices in spatial autoregressive models

We develop a Bayesian approach to estimate weight matrices in spatial autoregressive (or spatial lag) models. Datasets in regional economic literature are typically characterized by a limited number of time periods (Formula presented.) relative to spatial units (Formula presented.). When the spatial weight matrix is subject to estimation severe problems of over-parametrization are likely. To make estimation feasible, our approach focusses on spatial weight matrices which are binary prior to row-standardization. We discuss the use of hierarchical priors which impose sparsity in the spatial weight matrix. Monte Carlo simulations show that these priors perform very well where the number of unknown parameters is large relative to the observations. The virtues of our approach are demonstrated using global data from the early phase of the COVID-19 pandemic. © 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

A Simulation Study of the Delayed Effect of Covid-19 Pandemic on Pensions and Welfare of the Elderly: Evidence from Poland

Changes in the demographic structure of the population have imposed alterations in the pension systems. In many countries, including Poland, the amount of retirement benefits is highly dependent on life expectancy, which in the case of increases in longevity leads to a decrease in accrued benefits. A dynamic Monte Carlo simulation model was developed to investigate the financial implications of the aging problem in connection with the previously unexpected demographic changes caused by the Covid-19 pandemic on future pension payments. The model uses data from Polish statistical databases. The study distinguishes different life cycle profiles, i.e. women and men with average and minimum wage earnings. Simulation experiments are conducted in two variants. The first variant takes into account the currently registered shortening of life expectancy, while the second variant assumes that life expectancy is continuously lengthening, as it was observed until the outbreak of the Covid-19 epidemic. The simulation results show that the Covid-19 pandemic has a beneficial effect for future retirees, which is reflected in the expected higher replacement rates at retirement. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

The Sustainability of Mexican Municipal Public Debt

This paper examines the sustainability of subnational governments in Mexico, focusing on its top 110 most indebted municipalities. We employ dynamic panel data techniques to assess whether municipal debt remained sustainable during 2007–2017. Our study finds that the subnational fiscal position of Mexican municipalities remains sustainable despite the rapid growth of public debt following the 2008 global financial crisis. However, using Monte Carlo simulations, we show that random disturbances can significantly impact municipal governments’ debt, deteriorating governments’ finances after the shocks materialize.

Impaired Pharmacokinetics of Amiodarone under Veno-Venous Extracorporeal Membrane Oxygenation: From Bench to Bedside.

BACKGROUND: Adjusting drug therapy under veno-venous extracorporeal membrane oxygenation (VV ECMO) is challenging. Although impaired pharmacokinetics (PK) under VV ECMO have been reported for sedative drugs and antibiotics, data about amiodarone are lacking. We evaluated the pharmacokinetics of amiodarone under VV ECMO both in vitro and in vivo. METHODS: In vitro: Amiodarone concentration decays were compared between closed-loop ECMO and control stirring containers over a 24 h period. In vivo: Potassium-induced cardiac arrest in 10 pigs with ARDS, assigned to either control or VV ECMO groups, was treated with 300 mg amiodarone injection under continuous cardiopulmonary resuscitation. Pharmacokinetic parameters Cmax, Tmax AUC and F were determined from both direct amiodarone plasma concentrations observation and non-linear mixed effects modeling estimation. RESULTS: An in vitro study revealed a rapid and significant decrease in amiodarone concentrations in the closed-loop ECMO circuitry whereas it remained stable in control experiment. In vivo study revealed a 32% decrease in the AUC and a significant 42% drop of Cmax in the VV ECMO group as compared to controls. No difference in Tmax was observed. VV ECMO significantly modified both central distribution volume and amiodarone clearance. Monte Carlo simulations predicted that a 600 mg bolus of amiodarone under VV ECMO would achieve the amiodarone bioavailability observed in the control group. CONCLUSIONS: This is the first study to report decreased amiodarone bioavailability under VV ECMO. Higher doses of amiodarone should be considered for effective amiodarone exposure under VV ECMO.

A random walk Monte Carlo simulation study of COVID-19-like infection spread.

Recent analysis of early COVID-19 data from China showed that the number of confirmed cases followed a subexponential power-law increase, with a growth exponent of around 2.2 (Maier and Brockmann, 2020). The power-law behavior was attributed to a combination of effective containment and mitigation measures employed as well as behavioral changes by the population. In this work, we report a random walk Monte Carlo simulation study of proximity-based infection spread. Control interventions such as lockdown measures and mobility restrictions are incorporated in the simulations through a single parameter, the size of each step in the random walk process. The step size l is taken to be a multiple of 〈 r 〉 , which is the average separation between individuals. Three temporal growth regimes (quadratic, intermediate power-law and exponential) are shown to emerge naturally from our simulations. For l = 〈 r 〉 , we get intermediate power-law growth exponents that are in general agreement with available data from China. On the other hand, we obtain a quadratic growth for smaller step sizes l ≲ 〈 r 〉 ∕ 2 , while for large l the growth is found to be exponential. We further performed a comparative case study of early fatality data (under varying levels of lockdown conditions) from three other countries, India, Brazil and South Africa. We show that reasonable agreement with these data can be obtained by incorporating small-world-like connections in our simulations.

Modelling Excess Mortality in Covid-19-Like Epidemics.

We develop an agent-based model to assess the cumulative number of deaths during hypothetical Covid-19-like epidemics for various non-pharmaceutical intervention strategies. The model simulates three interrelated stochastic processes: epidemic spreading, availability of respiratory ventilators and changes in death statistics. We consider local and non-local modes of disease transmission. The first simulates transmission through social contacts in the vicinity of the place of residence while the second through social contacts in public places: schools, hospitals, airports, etc., where many people meet, who live in remote geographic locations. Epidemic spreading is modelled as a discrete-time stochastic process on random geometric networks. We use the Monte-Carlo method in the simulations. The following assumptions are made. The basic reproduction number is R0=2.5 and the infectious period lasts approximately ten days. Infections lead to severe acute respiratory syndrome in about one percent of cases, which are likely to lead to respiratory default and death, unless the patient receives an appropriate medical treatment. The healthcare system capacity is simulated by the availability of respiratory ventilators or intensive care beds. Some parameters of the model, like mortality rates or the number of respiratory ventilators per 100,000 inhabitants, are chosen to simulate the real values for the USA and Poland. In the simulations we compare 'do-nothing' strategy with mitigation strategies based on social distancing and reducing social mixing. We study epidemics in the pre-vacine era, where immunity is obtained only by infection. The model applies only to epidemics for which reinfections are rare and can be neglected. The results of the simulations show that strategies that slow the development of an epidemic too much in the early stages do not significantly reduce the overall number of deaths in the long term, but increase the duration of the epidemic. In particular, a hybrid strategy where lockdown is held for some time and is then completely released, is inefficient.

A comprehensive risk assessment of toxic elements in international brands of face foundation powders.

Despite the COVID-19 pandemic and wearing masks in many countries, women are keen on elegance, beauty and the use of face foundations. Assessment of health risks associated with the regular use of face foundation by females is dynamic due to the emerging products. The most common international 14 brands of face foundation powders were collected and the concentrations of different elements (Ag, Al, As, B, Ba, Be, Ca, Cd, Co, Cr, Cu, Fe, Hg, K, Li, Mg, Mn, Mo, Na, P, Pb, Sb, Se, Sn, V and Zn) in each sample were determined. A combined approach merging the conventional and computational tools was used for investigating the risk of exposure to toxic elements. Monte Carlo simulations were applied to calculate risks associated with twenty elements. We attempted different probability distribution functions for concentrations because the actual distribution functions are not known, and the only data available are the mean value and standard deviation of concentrations obtained from experiment. Our results indicate that the total non-carcinogenic health risk through exposure to different elements (Hazardous Index, HI) does not strongly depend on the choice of the probability distribution function for the concentrations. We also show that taking into account probability distributions of other variables and parameters such as body weight, exposed skin area, skin adhesion, etc. does not significantly change the main result rather just slightly broadening the final Hazardous Index distribution function. We found that calculated HI is well below unity for all considered samples, i.e., the dermal exposure to toxic elements in the considered facial powders is negligible and the considered face foundation powders are quite safe to use.

Spreading of infections on random graphs: A percolation-type model for COVID-19.

We introduce an epidemic spreading model on a network using concepts from percolation theory. The model is motivated by discussing the standard SIR model, with extensions to describe effects of lockdowns within a population. The underlying ideas and behaviour of the lattice model, implemented using the same lockdown scheme as for the SIR scheme, are discussed in detail and illustrated with extensive simulations. A comparison between both models is presented for the case of COVID-19 data from the USA. Both fits to the empirical data are very good, but some differences emerge between the two approaches which indicate the usefulness of having an alternative approach to the widespread SIR model.