Search

The devastating impact of COVID-19 on the United States has been profound since its onset in January 2020. Predicting the trajectory of epidemics accurately and devising strategies to curb their progression are currently formidable challenges. In response to this crisis, we propose COVINet, which combines the architecture of Long Short-Term Memory and Gated Recurrent Unit, incorporating actionable covariates to offer high-accuracy prediction and explainable response. First, we train COVINet models for confirmed cases and total deaths with five input features, and compare Mean Absolute Errors (MAEs) and Mean Relative Errors (MREs) of COVINet against ten competing models from the United States CDC in the last four weeks before April 26, 2021. The results show COVINet outperforms all competing models for MAEs and MREs when predicting total deaths. Then, we focus on prediction for the most severe county in each of the top 10 hot-spot states using COVINet. The MREs are small for all predictions made in the last 7 or 30 days before March 23, 2023. Beyond predictive accuracy, COVINet offers high interpretability, enhancing the understanding of pandemic dynamics. This dual capability positions COVINet as a powerful tool for informing effective strategies in pandemic prevention and governmental decision-making. [ABSTRACT FROM AUTHOR]

This paper introduces a new statistical methodology for estimating Duncan dissimilarity indexes of occupational segregation by sex in administrative areas and time periods. Given that direct estimators of the proportion of men (or women) in the group of employed people for each occupational sector are not accurate enough in the considered estimation domains, we fit to them a three-fold Fay–Herriot model with random effects at three hierarchical levels. Based on the fitted area-level model, empirical best predictors of the cited proportions and Duncan segregation indexes are derived. A parametric bootstrap algorithm is implemented to estimate the mean squared error. Some simulation studies are included to show how the proposed predictors have a good balance between bias and mean squared error. Data from the Spanish Labour Force Survey are used to illustrate the performance of the new statistical methodology and to give some light about the current state of sex occupational segregation by province in Spain. Research claims that there is a sex gap that persists despite advances in the inclusion of women in the labour market in recent years and that is related to the unequal sharing of family responsabilities and the stigmas still present in modern societies. [ABSTRACT FROM AUTHOR]

Scientific cooperation is gaining importance as worldwide trends in co-authorship indicate. While clustering is an established method in this field and several have studied scientific-cooperation dynamics within a single discipline, little literature exists on its interdisciplinary facet. This paper analyses the evolution of co-authorship amongst social scientists in Slovenia over the three decades between 1991 and 2020 using bibliographic databases. The identification of groups (clusters) of authors based on patterns in their co-authorship ties both within and across decades is carried out using network-analytical method called stochastic blockmodeling (SBM). Meanwhile, previous research used generalised blockmodeling accounting only for within-period ties. Additionally, a topic model is developed to tentatively assess whether co-authorship is driven by research interests, organisational or disciplinary affiliation. Notably, while focusing on the result of the SBM for generalised multipartite networks, the paper draw compares with other SBMs. Generally, the paper identifies clusters of authors that are larger and less cohesive than those found in previous works. Specifically, there are three main findings. First, disciplines appear to become less important over time. Second, institutions remain central, corroborating the suggestion that Slovenian R&D policy reinforces parochial research practices. Yet, whether organisational segregation is an issue remains unclear. Third, interdisciplinarity's emergence has been slow and partial, thus supporting the idea of a 'covert interdisciplinarity.' Importantly, it seems that members of different clusters lack fluency in a meta-language enabling effective communication across cognate paradigms. And this may hinder the implementation of long-term, up-to-date research policies in the country. [ABSTRACT FROM AUTHOR]

Correlation coefficients and linear regression values computed from group averages can differ from correlation coefficients and linear regression values computed using individual scores. This observation known as the ecological fallacy often assumes that all the individual scores are available from a population. In many situations, one must use a sample from the larger population. In such cases, the computed correlation coefficient and linear regression values will depend on the sample that is chosen and the underlying sampling distribution. The sampling distribution of correlation coefficients and linear regression values for group averages will be identical to the sampling distribution for individuals for normally distributed variables for random samples drawn from infinitely large continuous distributions. However, data that is acquired in practice is often acquired when sampling without replacement from a finite population. Our objective is to demonstrate through Monte Carlo simulations that the sampling distributions for correlation and linear regression will also be similar for individuals and group averages when sampling without replacement from normally distributed variables. These simulations suggest that when a random sample from a population is selected, the correlation coefficients and linear regression values computed from individual scores will not be more accurate in estimating the entire population values compared to samples when group averages are used as long as the sample size is the same. [ABSTRACT FROM AUTHOR]

The classification of land use and land cover (LULC) from remotely sensed imagery in semi-arid Mediterranean areas is a challenging task due to the fragmentation of the landscape and the diversity of spatial patterns. Recently, the use of deep learning (DL) for image analysis has increased compared to commonly used machine learning (ML) methods. This paper compares the performance of four algorithms, Random Forest (RF), Support Vector Machine (SVM), Multilayer Perceptron (MLP) and Convolutional Network (CNN), using multi-source data, applying an exhaustive optimisation process of the hyperparameters. The usual approach in the optimisation process of a LULC classification model is to keep the best model in terms of accuracy without analysing the rest of the results. In this study, we have analysed such results, discovering noteworthy patterns in a space defined by the mean and standard deviation of the validation accuracy estimated in a 10-fold cross validation (CV). The point distributions in such a space do not appear to be completely random, but show clusters of points that facilitate the discovery of hyperparameter values that tend to increase the mean accuracy and decrease its standard deviation. RF is not the most accurate model, but it is the less sensitive to changes in hyperparameters. Neural Networks, tend to increase commission and omission errors of the less represented classes because their optimisation lead the model to learn better the most frequent classes. On the other hand, RF and MLP prediction layers are the most accurate from a general qualitative point of view. [ABSTRACT FROM AUTHOR]

In recent decades, advances in technology have led to the adaptation of business models to the connected era. This has resulted in the modification of the goals of both startup and cooperative models, leading to the emergence of a new hybrid business model combining the two and known as cooperative startups. The present study aims to investigate the evolution, functioning and characteristics of cooperative startups as a potential research area that may be of future relevance due to its potential growth. To this end, a bibliometric analysis using Web of Sciences academic database and VOSViewer software is conducted to identify specific characteristics, opportunities, and challenges that cooperative startups should understand in order to achieve business success. In this regard, a co-citation analysis, bibliographic coupling and keyword concurrency analysis are computed to understand the literature published in this research field to date. The findings of this analysis contribute to the creation of knowledge on cooperative startups identifying 19 future research questions linked to 5 research categories in cooperatives startups: strategy, members of the team, performance, finance and economy and innovation. The results provide insights on the challenges and characteristics of this new business model that is characterized by the management of investments and economy democracy while boosting innovation and handling competence. Finally, theoretical and practical implications are presented. [ABSTRACT FROM AUTHOR]

We examine whether expanded audit report (EAR) disclosures classified as the audit opinion, going concern uncertainty paragraphs (GCUPs), emphasis of matter paragraphs (EMPs) and key audit matters (KAMs) are associated with the determinants of zombie firms. Theoretically, zombies are inefficient, unprofitable and highly leveraged firms that receive subsidized credit and consume resources that should be allocated to more efficient firms, reducing productivity growth in the economy. Using a sample of Spanish firms during 2017, the period in which the expanded audit standards were implemented, univariate analysis produces support for our expectations, suggesting that zombies are smaller and more indebted, tend to report losses and have EARs that include more disclosures than non-zombies. Our regression results indicate that GCUPs, EMPs, going concern KAMs and KAMs related to the valuation of current assets are more likely to be reported for zombies. Furthermore, the economic significance of GCUPs allows us to offer a new classification of zombies, contributing to zombie theory. To the best of our knowledge, this is the first study on the identification of zombie firms using external audit data and the first to analyze other EAR disclosures apart from KAMs. Our findings may have relevant implications for financial statement users, audit firms, standard setters, financial institutions and governments regarding the usefulness and zombie explanatory ability of EARs. [ABSTRACT FROM AUTHOR]

We consider the problem of detecting distributional changes in a sequence of high dimensional data. Our approach combines two separate statistics stemming from L p norms whose behavior is similar under H 0 but potentially different under H A , leading to a testing procedure that that is flexible against a variety of alternatives. We establish the asymptotic distribution of our proposed test statistics separately in cases of weakly dependent and strongly dependent coordinates as min { N , d } → ∞ , where N denotes sample size and d is the dimension, and establish consistency of testing and estimation procedures in high dimensions under one-change alternative settings. Computational studies in single and multiple change point scenarios demonstrate our method can outperform other nonparametric approaches in the literature for certain alternatives in high dimensions. We illustrate our approach through an application to Twitter data concerning the mentions of U.S. governors. [ABSTRACT FROM AUTHOR]

Statistical matching is progressively emerging as a straightforward approach to data integration. This method of increasing importance and interest is useful to address the unsolved challenges posed by data shortage as well as the several opportunities occurring in the present data flood era. This paper offers an exhaustive review of the methodology from its early beginnings up to the most recent developments, considering also the most relevant applications. The links that statistical matching has with other integration methods are discussed, analysing how a 50-year-old method has been only recently proposed under a consistent but (yet) incomplete framework. Strengths and weaknesses of statistical matching are compared, considering different data features and sample representativeness frameworks, also, given future research ideas, always keeping an eye on uncertainty, the key problem to which statistical matching tries to answer. [ABSTRACT FROM AUTHOR]

This article examines the influence of the life context on entrepreneurial passion (EP) and performance. Drawing on the person–environment fit theory, we developed a model showing how the life context fit affects EP in the domains of founding, inventing, and developing and how this translates into performance. Using partial least squares structural equation modeling, we tested our hypotheses using a sample of 406 entrepreneurs from the cultural and creative industries. Due to the presence of unobserved heterogeneity in the overall sample, we conducted prediction-oriented segmentation, which revealed four segments in which life contexts exhibit not only positive but also adverse effects on EP. Our results showed that, in contrast to the extant literature, EP generates its overall effect on performance at the intersection of positively and negatively acting domains of founding, inventing, and developing. To explain the structural relations between the four segments, we conducted qualitative post hoc analyses to evaluate idiosyncratic data on passion and the life context and aligned our insights with the extant literature delineating four categories of entrepreneurs from the cultural and creative industries: artepreneurs, culturepreneurs, creative entrepreneurs, and lifestyle entrepreneurs. Our findings contribute to overcoming the dichotomy between passion as a personality trait and a dynamic construct and to understanding passion as an individual phenomenon with multiple sources that interacts with the proximal environment and that can impact entrepreneurial performance both positively and negatively. We extend the entrepreneurship and psychology literature, facilitating people's abilities to lead more entrepreneurial and passionate lives. [ABSTRACT FROM AUTHOR]

Measuring the impact of a publication in a fair way is a significant challenge in bibliometrics, as it must not introduce biases between fields and should enable comparison of the impact of publications from different years. In this paper, we propose a Bayesian approach to tackle this problem, motivated by empirical data demonstrating heterogeneity in citation distributions. The approach uses the a priori distribution of citations in each field to estimate the expected a posteriori distribution in that field. This distribution is then employed to normalize the citations received by a publication in that field. Our main contribution is the Bayesian Impact Score, a measure of the impact of a publication. This score is increasing and concave with the number of citations received and decreasing and convex with the age of the publication. This means that the marginal score of an additional citation decreases as the cumulative number of citations increases and increases as the time since publication of the document grows. Finally, we present an empirical application of our approach in eight subject categories using the Scopus database and a comparison with the normalized impact indicator Field Citation Ratio from the Dimensions AI database. [ABSTRACT FROM AUTHOR]

AbstractThe basketball game is rarely predictable due to the complexity of its scoring process. To deal with the complexity and forecast the game results, we develop a marked mutually exciting point process model for the scoring process. In the model, the dynamic of the scoring intensity is characterized by a mutually exciting point process. A time varying background rate is used in the intensity function to account for the non-homogeneity. The dependence between scoring events is incorporated into the model with two team-specific exponential exciting kernels. The distribution of the points obtained in each scoring event is modeled as a categorical distribution with parameters from a Dirichlet prior. An empirical Bayesian method and an expectation-maximization algorithm are developed to estimate the model parameters. We design a simulation algorithm to do pre-game and in-game predictions. An empirical study is conducted with National Basketball Association games in four seasons. It is showed that the proposed model outperforms the benchmark model both in the win-loss prediction and score prediction. Moreover, our model can obtain positive returns when betting in the point spread market. Besides forecasting, an index called added winning probability is designed based on the model to evaluate the players’ performance. [ABSTRACT FROM AUTHOR]

Sequential analysis (SA) as a sampling technique has notable advantages like smaller average sample size and reduced value of risk compared to similarly comparable fixed-sample techniques. In this study, we first propose a few models for the estimation of the regression parameters or functions of parameters under the multiple linear regression (MLR) setup using a balanced loss function (BLF). Thereafter, we obtain the expressions of risk functions and optimal fixed sample sizes for the proposed models based on the bounded risk criteria. We establish that no fixed-sample procedures can tackle these estimation problems. Hence, we propose different multistage sampling methodologies, viz. (i) two-stage sampling, (ii) three-stage sampling, (iii) purely sequential sampling, and (iv) batch sequential sampling, and corroborate the same with the detailed simulation and real data analyses. [ABSTRACT FROM AUTHOR]

The objective of this work is to elucidate the causes and ramifications of multi-authorship in science by surveying researchers working in the field of Medical Physics. During the first 6 months of 2022, an anonymous survey was disseminated among 956 medical physicists working in Asia, Europe and North America. The survey participants were chosen by using their publications in professional journals. The number of responses to the survey questions varied from 186 (19.5%) to 249 (26%). The obtained responses indicated several important causes of multi-authorship in science. In particular, the respondents indicated the importance of the quid pro quo effect, division of labor, complimentary expertise, and potential bias against 1–2 author papers. The responses also indicated the important role of multi-authorship in developing professional networks and associated career advancement. The responses suggest that besides its potential to significantly increase number of publications, multi-authorship facilitates networking and associated career advancement of researchers. As a result, multi-authorship can be used as a tool to improve chances for promotion and tenure. The negative ramifications of multi-authorship can be dealt with by employing transparent policies to properly assign credit and responsibility for multi-author studies and to restrict number of coauthors except when multi-authorship is justified by the specific needs and/or multidisciplinary nature of the study. [ABSTRACT FROM AUTHOR]

This paper studies cultural and socioeconomic factors that contribute to the scientific output of different countries. Specifically, taking into account the influential Hofstede's model, we assess the impact of cultural dimensions on the h-index. Results show the h-index is connected to the Gross Domestic Product of each nation, the degree to which individuals are dependent upon one another, the total number of researchers, and the gender roles prevalent in a specific country. A classification of the examined countries was accomplished by factoring in the significant variables, determining the characteristics shared by each group in accordance with their h-index, and singling out the distinguished Group of Seven and the Scandinavia group as particularly noteworthy examples. This study provides valuable insights for governments and policymakers, emphasizing the significance of these cultural factors in guiding countries toward excellence in science. [ABSTRACT FROM AUTHOR]

Instrumental variable (IV) analysis addresses bias owing to unmeasured confounding when comparing two nonrandomized treatment groups. To date, studies in the statistical and biomedical literature have focused on the local average treatment effect (LATE), the average treatment effect for compliers. In this article, we study the weighted local average treatment effect (WLATE), which represents the weighted average treatment effect for compliers. In the WLATE, the population of interest is determined by either the instrumental propensity score or compliance score, or both. The LATE is a special case of the proposed WLATE, where the target population is the entire population of compliers. Here, we discuss the interpretation of a few special cases of the WLATE, identification results, inference methods, and optimal weights. We demonstrate the proposed methods with two published examples in which considerations of local causal estimands that deviate from the LATE are beneficial. [ABSTRACT FROM AUTHOR]

Since the discovery and the development of many technological instruments such as modern communication and communication technologies, digital media has served widely from the technology, and thus intersected quasi all life's domains, by providing news, information, and also discussions of quasi all subjects. In social sciences, for example, a major part of digital media sites discusses the well-being of both individuals, and societies, especially with the presence of many challenging phenomena like pandemics, wars, and financial crises. A major concern for QoL index for example resides in whether it is a uniform stable index or on the contrary a non-uniform index depending strongly and point-wisely on the time scale. This motivates the consideration of a non-uniform QoL index based on non-uniform wavelets to take into account the influence of many factors issued from political, social, environmental, economic effects according to the time scale. The model developed is tested on Saudi Arabia QoL index case. Recall that the Kingdom of Saudi Arabia has fixed many aims in its 2030-vision plan including the quality of life as a major goal. For example, the KSA worldwide NEOM project necessitates surely a supportive environment to be realized. The second purpose of our paper is also to study the impact of digital media such as social one on the QoL. Therefore, the data collected is basically issued from a set of conversations on social media platforms. To obtain a suitable time series, we developed a backward-forward non-uniform wavelet forecasting model to extend the data sample suitably. The whole time series is by the next applied for the QoL index dynamics and interpretations. The findings showed that effectively, the QoL index is never a stable single index on the whole year, but on the contrary, the dependence on the time scale is non-uniform. Moreover, to interpret suitably and for a correct policy, the non-uniform behavior should be considered adequately. [ABSTRACT FROM AUTHOR]

The new Pareto-type distribution offers a compelling alternative to the traditional Pareto distribution for modeling heavy-tailed data. While maximum likelihood estimation is typically employed for parameter estimation in these statistical models, this approach can produce biased results due to its inherent sensitivity to outliers. In response to this issue, we first propose an efficient and robust estimator for the tail index of the new Pareto-type distribution, grounded in the probability integral transform statistic. Subsequently, we introduce and comprehensively evaluate a second robust method—the repeated median estimator. We scrutinize the asymptotic relative efficiency of these new estimators, as well as their robustness, based on the breakdown point and influence function. Both of these methodologies, besides being computationally straightforward, offer substantial protection against outliers. A series of Monte Carlo simulations is performed to compare the performances of these new estimators against several alternative methods in outlier-free and outlier-affected scenarios. To corroborate these results, we apply the new estimators to four real datasets: the net worth of the affluent in Singapore and China, the daily increment of NASDAQ-100, and the daily new cases rate of COVID-19. This empirical application effectively attests to the practical utility of our proposed estimators. [ABSTRACT FROM AUTHOR]

Apportionment methods are used in proportional representation systems for the apportionment of parliamentary seats among political parties proportionately to their vote counts, or for the allocation of parliamentary seats between geographical districts proportionately to their population figures. From an axiomatic viewpoint apportionment methods ought to satisfy six basic principles: anonymity, balancedness, concordance, decency, exactness, and fairness. It is well-known that the first two principles are implied by the last four. In this note it is shown that the last four principles are logically independent of each other. [ABSTRACT FROM AUTHOR]

A quick count seeks to estimate the voting trends of an election and communicate them to the population on the evening of the same day of the election. In quick counts, the sampling is based on a stratified design of polling stations. Voting information is gathered gradually, often with no guarantee of obtaining the complete sample or even information in all the strata. However, accurate interval estimates with partial information must be obtained. Furthermore, this becomes more challenging if the strata are additionally study domains. To produce partial estimates, two strategies are proposed: (1) a Bayesian model using a dynamic post-stratification strategy and a single imputation process defined after a thorough analysis of historic voting information; additionally, a credibility level correction is included to solve the underestimation of the variance and (2) a frequentist alternative that combines standard multiple imputation ideas with classic sampling techniques to obtain estimates under a missing information framework. Both solutions are illustrated and compared using information from the 2021 quick count. The aim was to estimate the composition of the Chamber of Deputies in Mexico. [ABSTRACT FROM AUTHOR]

Online English writing and peer assessment have always occupied an important place in the assessment of composition at the basic education level as an important writing style and assessment tool. Therefore, this paper constructs the IOA-English analysis model based on the intelligent optimization algorithm as the theoretical basis. An in-depth study of online English writing patterns and the time devoted to them, and the intensity and effectiveness of peer assessment among college students. The results of the study are as follows: the computational analysis shows that the time required for the pre-writing preparation stage is 5-10 minutes, with a difficulty factor of 0.3. The final draft submission phase required the least amount of time, 3-7 minutes, with a difficulty factor of only 0.1. The writing revision stage, the most important stage, takes 10-15 minutes and has a difficulty factor of 0.6. The time for the writing revision phase can be divided into two parts: the first part is the time for tasting the model essay, which is about 3-8 minutes. The second part is the writing and revision time, which is about 12-17 minutes. More than 91% of the students were aware of the importance of peer assessment and were brave enough to express their opinions in cooperative learning and to take care of each other's learning needs in peer assessment. [ABSTRACT FROM AUTHOR]

Agricultural Sciences have become one of Brazil's most efficient and sustainable research areas, where most publications benefit from scientific collaboration. The present study analyzes the influence of the designation as the corresponding author to researchers linked to Brazilian institutions on the impact of co-authored articles in the category Agronomy from the Web of Science for five-year periods from 2005 to 2019. We have observed a noticeable growth in the number of documents in collaboration between the five-year periods. However, international partnership in the area still needs to be improved, although it is higher in non-academic institutions. The study verified that the documents published by Brazilian authors with international colleagues present a higher normalized citation impact in all types of institutions and five-year periods than documents with national collaboration. The total number of articles, their normalized citation impact, and the percentage of documents as the corresponding author of academic institutions presented less variation than non-academic institutions. For Brazilian academic institutions, assuming the role of the corresponding author of co-authored articles in Agronomy has little influence on citation impact. As for non-academic institutions, we found an association between the corresponding authorship position within the scope of international collaboration and the higher impact of their scientific production. We point out some potential implications and briefly describe the limitations and future research. [ABSTRACT FROM AUTHOR]

Randomized controlled trials (RCTs) admit unconfounded design-based inference – randomization largely justifies the assumptions underlying statistical effect estimates – but often have limited sample sizes. However, researchers may have access to big observational data on covariates and outcomes from RCT nonparticipants. For example, data from A/B tests conducted within an educational technology platform exist alongside historical observational data drawn from student logs. We outline a design-based approach to using such observational data for variance reduction in RCTs. First, we use the observational data to train a machine learning algorithm predicting potential outcomes using covariates and then use that algorithm to generate predictions for RCT participants. Then, we use those predictions, perhaps alongside other covariates, to adjust causal effect estimates with a flexible, design-based covariate-adjustment routine. In this way, there is no danger of biases from the observational data leaking into the experimental estimates, which are guaranteed to be exactly unbiased regardless of whether the machine learning models are “correct” in any sense or whether the observational samples closely resemble RCT samples. We demonstrate the method in analyzing 33 randomized A/B tests and show that it decreases standard errors relative to other estimators, sometimes substantially.