Empirical Application Research Articles

Sparse generalized Yule–Walker estimation for large spatio-temporal autoregressions with an application to NO2 satellite data

We consider a high-dimensional model in which variables are observed over time and space. The model consists of a spatio-temporal regression containing a time lag and a spatial lag of the dependent variable. Unlike classical spatial autoregressive models, we do not rely on a predetermined spatial interaction matrix, but infer all spatial interactions from the data. Assuming sparsity, we estimate the spatial and temporal dependence fully data-driven by penalizing a set of Yule–Walker equations. This regularization can be left unstructured, but we also propose customized shrinkage procedures when observations originate from spatial grids (e.g. satellite images). Finite sample error bounds are derived and estimation consistency is established in an asymptotic framework wherein the sample size and the number of spatial units diverge jointly. Exogenous variables can be included as well. A simulation exercise shows strong finite sample performance compared to competing procedures. As an empirical application, we model satellite measured nitrogen dioxide (NO2) concentrations in London. Our approach delivers forecast improvements over a competitive benchmark and we discover evidence for strong spatial interactions.

Conformity versus credibility: A coupled rumor-belief model

The opinion individuals hold about circulating information moderates their spreading behavior, as they may choose to spread rumors they believe in and remain silent about those they do not. Meanwhile, these opinions may be influenced by peers’ opinions and observed behaviors. We present coupled dynamics that integrate opinion formation and information spreading within two-layer multiplex social networks. In an influence layer, opinions are shaped by information credibility and social influence, the degree of which is determined by individual tendencies to conform. In a communication layer, information spreads conditioned on whether individuals believe in it. Using analytical and numerical tools, we demonstrate consistent behavior of the model by identifying the criteria for an evolutionary advantage in opinion formation and a critical spreading rate for rumor outbreaks. We then proceeded to examine two scenarios distinguished by considering credibility as either an intrinsic or a social property of information. Our results show that, for intrinsic credibility, higher degrees of conformity promote the spread of incredible information and inhibit the diffusion of credible information; for social credibility, higher degrees of conformity have an amplifying effect on the evolution of belief and rumor spreading. Additionally, the former scenario exhibits rich behaviors in the interplay between opinion evolution and information spreading, including paradigm shift, passive support, and fringe belief. We thus contribute to the understanding of the dynamics of opinion formation and information propagation in social groups. Empirical application may inform efforts to assess and combat the spread of misinformation.

Bootstrap Inference in Cointegrating Regressions: Traditional and Self-Normalized Test Statistics

Traditional tests of hypotheses on the cointegrating vector are well known to suffer from severe size distortions in finite samples, especially when the data are characterized by large levels of endogeneity or error serial correlation. To address this issue, we combine a vector autoregressive (VAR) sieve bootstrap to construct critical values with a self-normalization approach that avoids direct estimation of long-run variance parameters when computing test statistics. To asymptotically justify this method, we prove bootstrap consistency for the self-normalized test statistics under mild conditions. In addition, the underlying bootstrap invariance principle allows us to prove bootstrap consistency also for traditional test statistics based on popular modified OLS estimators. Simulation results show that using bootstrap critical values instead of asymptotic critical values reduces size distortions associated with traditional test statistics considerably, but combining the VAR sieve bootstrap with self-normalization can lead to even less size distorted tests at the cost of only small power losses. We illustrate the usefulness of the VAR sieve bootstrap in empirical applications by analyzing the validity of the Fisher effect in 19 OECD countries.

Convergence of artificial intelligence research in healthcare: Trends and approaches

A value-based strategy relies on the implementation of a patient-centered care system that will directly benefit patient care outcomes and reduce costs of care. This paper identifies the trends and approaches to artificial intelligence (AI) research in healthcare. The convergence of multiple disciplines in the conduct of healthcare research requires partnerships to be established among academic scholars, healthcare practitioners, and industrial experts in software design and data science. This collaborative work will greatly enhance the formulation of theoretically relevant frameworks to guide empirical research and application, particularly relevant in the search for causal mechanisms to reduce costly and avoidable hospital readmissions for chronic conditions. An example of implementing patient-centered care at the community level is presented and entails the influence of the context, design, process, performance and outcomes on personal and population health, employing AI research and informational technology.

A weighted average limited information maximum likelihood estimator

In this article, a Stein-type weighted limited information maximum likelihood (LIML) estimator is proposed. It is based on a weighted average of the ordinary least squares (OLS) and LIML estimators, with weights inversely proportional to the Hausman test statistic. The asymptotic distribution of the proposed estimator is derived by means of local-to-exogenous asymptotic theory. In addition, the asymptotic risk of the Stein-type LIML estimator is calculated, and it is shown that the risk is strictly smaller than the risk of the LIML under certain conditions. A Monte Carlo simulation and an empirical application of a green patent dataset from Nordic countries are used to demonstrate the superiority of the Stein-type LIML estimator to the OLS, two-stage least squares, LIML and combined estimators when the number of instruments is large.

APPLICATION OF VECTOR AUTOREGRESSIONS FOR FORECASTING MONETARY POLICY

The purpose of the study is to consider the theoretical and empirical application of methods and models of vector autoregressions to analyze the infl uence of various macroeconomic variables in the construction of a monetary policy model.Methodology. The research methods used are generalization of experience regarding the use of vector autoregressions, factor analysis, methodology for evaluating VAR models containing fi fteen real, price, monetary and external variables. A number of tests were conducted to assess the quality of the analyzed model: impulse response analysis, forecasting and simulations.This article analyzes the infl uence of factors on each other, as well as the interpretation of the results, which can be further used to obtain practical recommendations for improving the methods of research and forecasting monetary policy.Originality / value of the research. The paper analyzes the advantages and disadvantages of diff erent approaches in the construction of vector autoregressive models, both in the selection of factors and their preparation for use in the model. This article examines the observation period from 2010 to 2021, that is, before and after the introduction of the infl ation targeting regime, and the assessment of the pandemic shock in Kazakhstan, without aff ecting the shocks of 2022.Findings. The work carried out made it possible to verify the applicability of vector autoregression methods, this statement is confi rmed by the inverse predictive power of the models. In this paper, the eff ectiveness of the proposed models was evaluated on macro factors in Kazakhstan.

A novel fuzzy inference method for urban incomplete road weight assignment

ABSTRACT One of the keys in time-dependent routing is determining the weight of each road network link based on traffic information. To facilitate the estimation of the road’s weight, Global Position System (GPS) data are commonly used in obtaining real-time traffic information. However, the information obtained by taxi-GPS does not cover the entire road network. Aiming at incomplete traffic information on urban roads, this paper proposes a novel fuzzy inference method. It considers the combined effect of road grade, traffic information, and other spatial factors. Taking the third law of geography as the basic premise, that is, the more similar the geographical environment, the more similar the characteristics of the geographical target will be. This method uses a Typical Link Pattern (TLP) model to describe the geographical environment. The TLP represents typical road sections with complete information. Then, it determines the relationship between roads lacking traffic information and the TLPs according to their related factors. After obtaining the TLPs, this method ascertains the weight of road links by calculating their similarities with TLPs based on the theory of fuzzy inference. Aiming at road links at different places, the dividing – conquering strategy and globe algorithm are also introduced to calculate the weight. These two strategies are used to address the excessively fragmented or lengthy links. The experimental results with the case of Newcastle show robustness in that the average Root Mean Square Error (RMSE) is 1.430 mph, and the bias is 0.2%; the overall RMSE is 11.067 mph, and the bias is 0.6%. This article is the first to combine the third law of geography with fuzzy inference, which significantly improves the estimation accuracy of road weights with incomplete information. Empirical application and validation show that the method can accurately predict vehicle speed under incomplete information.

Dutch dairy farmers’ adoption of climate mitigation measures – The role of socio-psychological and socio-demographical factors

Mitigating greenhouse gas emissions is an essential element of climate change policies. This paper explores Dutch dairy farmers' adoption behaviour of climate change mitigation measures using a Self-regulated Stage model of Behavioural Change. It tests the statistical relationship of stage-specific socio-psychological factors with individual farmer's intentions of planning or adopting on-farm climate mitigation measures. In addition, it tests the statistical relationship of intentions on four stages (pre-decisional, pre-actional, actional, post-actional). The empirical application focuses on data from specialised Dutch dairy farmers registered with the Farm Accountancy Data Network. Our findings suggest that negative emotion, personal norm, perceived goal feasibility, action planning, and coping planning vary significantly by stage. Furthermore, personal norm, attitude, goal intention, behavioural intention, and implementation intention are found to be statistically significant and positive influencing factors on adopting climate mitigation measures. Lastly, farmers younger than 45 years old with full agricultural education and farms with high livestock density are more likely to have taken steps in adopting mitigation measures.

A decision-making framework for classroom teaching quality evaluation of college badminton training with 2-tuple linguistic neutrosophic numbers

How to guarantee the quality of college physical education (PE) teaching and reverse the declining trend of college students’ physique year by year has become a hot topic for the research of higher education and school PE workers. The quality assurance of higher education in China should give full play to the role of colleges in teaching quality assurance activities, constantly improve the level of school running and improve the efficiency of school running. Because colleges themselves are the main body of higher education and teaching activities, they have the most power, qualification and responsibility to explain the quality of higher education. The classroom teaching quality (CTQ) evaluation of college badminton training is regarded as multi-attribute decision-making (MADM). The 2-tuple linguistic neutrosophic sets (2TLNSs) which the truth-membership, indeterminacy-membership and the falsity-membership are assessed by using the 2-tuple linguistic term sets is an appropriate form to express the indeterminate decision-making information in the classroom teaching quality (CTQ) evaluation of college badminton training. In this paper, the Hamy mean (HM) and the power average (PA) are connected with 2-tuple linguistic neutrosophic sets (2TLNSs) to propose the 2-tuple linguistic neutrosophic numbers weighted power HM (2TLNWPHM) operator. Then, use the 2TLNWPHM operator to handle MADM with 2TLNS. Finally, taking the CTQ evaluation of college badminton training as an example, the proposed method is explained. The main contributions of this study are summarized: the establishment of the 2TLNWPHM operator; (2) The 2TLNWPHM operator was developed to handle MADM with 2TLNS; (3) Through the empirical application of the CTQ evaluation of badminton training in universities, the proposed method is validated; (4) Some comparative studies have shown the rationality of the 2TLNWPHM operator.

A multi-attribute decision-making framework for enterprise competitive intelligence system evaluation with 2-tuple linguistic neutrosophic information

Big data is changing our lives and the way we understand the world, as well as the operational patterns of business and social organizations. Fully understanding the value of data and knowing how to use big data to provide a basis for business decision-making has gradually become the most basic thinking that business organizations should possess in the era of big data. Under the thinking mode of data-driven decision-making, many information science researchers have discussed the model, architecture, operation mechanism and other aspects of big data competitive intelligence system. At the same time, more and more enterprises, such as IBM, Amazon, Google, Microsoft, Wal Mart, etc., have begun to attach importance to the development and construction of big data competitive intelligence software systems, and have achieved certain results. The enterprise competitive intelligence system evaluation in the context of big data is regarded as multi-attribute decision-making (MADM). In this paper, the Hamy mean (HM) and the power average (PA) are connected with 2-tuple linguistic neutrosophic sets (2TLNSs) to propose the 2-tuple linguistic neutrosophic numbers power HM (2TLNPHM) operator. Then, use the 2TLNPHM operator to handle MADM with 2TLNS. Finally, taking the enterprise competitive intelligence system evaluation in the context of big data as an example, the proposed method is explained. The main contributions of this study are summarized: the establishment of the 2TLNPHM operator; (2) The 2TLNPHM operator was developed to handle MADM with 2TLNS; (3) Through the empirical application of the enterprise competitive intelligence system evaluation, the proposed method is validated; (4) Some comparative studies have shown the rationality of the 2TLNPHM operator.

Comparing experimental auctions and real choice experiments in food choice: a homegrown and induced value analysis

Abstract This study compares a real choice experiment (RCE) with three commonly used experimental auction (EA) mechanisms (Becker–DeGroot–Marschak, random nth price auction (RNPA), second price auction (SPA)) to determine whether willingness to pay (WTP) estimates differ across these elicitation methods. We use quality labels on eggs as the empirical application and find that the SPA, RNPA and RCE yield similar WTP estimates, while the BDM mechanism generally produces higher WTP estimates. We also compare these EAs and the RCE in an induced value setting and find that the BDM auction produces greater deviations from the underlying value than the other EAs and RCE. We suggest that RCEs may be preferable to BDMs for collecting WTP estimates in logistically difficult experimental settings.

Actors, concepts, controversies: the conceptual politics of European integration

ABSTRACT The paper is a contribution to research methodology. It proposes a useful methodological import into the range of interpretative approaches in Political Science – the study of Conceptual Politics. Drawing on methodology and categories developed in Conceptual History, Conceptual Politics is understood as the political and rhetorical moves, strategies, debates and their actors, that coin, shape or reflect political concepts in both institutional and social reality and its perception, and with regard to their past and present meanings, understandings and practices. The main methodological premise and also the distinguishing trait with regard to other interpretative approaches is this analytical focus on concepts: A concept is a word or a cluster of words that functions as a nodal point in a political controversy. Concepts are socially constructed factors and indicators of the reality they describe, interpret and modify. Concepts have different layers of meaning that are studied in their temporality and historicity. The different, past and present, layers require the researcher´s prior knowledge and an interpretative approach. The article presents the theoretical and methodological backgrounds and premises of the approach of Conceptual Politics, its added value, the heuristic and analytical tools for analysing it, and the empirical application of the tools proposed. It is argued that the approach is especially beneficial in analysing European integration.

Supervised latent Dirichlet allocation with covariates: A Bayesian structural and measurement model of text and covariates.

Text is a burgeoning data source for psychological researchers, but little methodological research has focused on adapting popular modeling approaches for text to the context of psychological research. One popular measurement model for text, topic modeling, uses a latent mixture model to represent topics underlying a body of documents. Recently, psychologists have studied relationships between these topics and other psychological measures by using estimates of the topics as regression predictors along with other manifest variables. While similar two-stage approaches involving estimated latent variables are known to yield biased estimates and incorrect standard errors, two-stage topic modeling approaches have received limited statistical study and, as we show, are subject to the same problems. To address these problems, we proposed a novel statistical model-supervised latent Dirichlet allocation with covariates (SLDAX)-that jointly incorporates a latent variable measurement model of text and a structural regression model to allow the latent topics and other manifest variables to serve as predictors of an outcome. Using a simulation study with data characteristics consistent with psychological text data, we found that SLDAX estimates were generally more accurate and more efficient. To illustrate the application of SLDAX and a two-stage approach, we provide an empirical clinical application to compare the application of both the two-stage and SLDAX approaches. Finally, we implemented the SLDAX model in an open-source R package to facilitate its use and further study. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

A general framework for the inclusion of time-varying and time-invariant covariates in latent state-trait models.

Latent state-trait (LST) models are increasingly applied in psychology. Although existing LST models offer many possibilities for analyzing variability and change, they do not allow researchers to relate time-varying or time-invariant covariates, or a combination of both, to loading, intercept, and factor variance parameters in LST models. We present a general framework for the inclusion of nominal and/or continuous time-varying and time-invariant covariates in LST models. The new framework builds on modern LST theory and Bayesian moderated nonlinear factor analysis and is termed moderated nonlinear LST (MN-LST) framework. The MN-LST framework offers new modeling possibilities and allows for a fine-grained analysis of trait change, person-by-situation interaction effects, as well as inter- or intraindividual variability. The new MN-LST approach is compared to alternative modeling strategies. The advantages of the MN-LST approach are illustrated in an empirical application examining dyadic coping in romantic relationships. Finally, the advantages and limitations of the approach are discussed, and practical recommendations are provided. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Powerful Backtests for Historical Simulation Expected Shortfall Models

Since 2016, the Basel Committee on Banking Supervision has regulated banks to switch from a Value-at-Risk (VaR) to an Expected Shortfall (ES) approach to measuring the market risk and calculating the capital requirement. In the transition from VaR to ES, the major challenge faced by financial institutions is the lack of simple but powerful tools for evaluating ES forecasts (i.e., backtesting ES). This article first shows that the unconditional backtest is inconsistent in evaluating the most popular Historical Simulation (HS) and Filtered Historical Simulation (FHS) E S models, with power even less than the nominal level in large samples. To overcome this problem, we propose a new class of conditional backtests for E S that are powerful against a large class of alternatives. We establish the asymptotic properties of the tests, and investigate their finite sample performance through some Monte Carlo simulations. An empirical application to stock indices data highlights the merits of our method.

Comparing forecasting performance with panel data

We develop new methods for testing equal predictive accuracy for panels of forecasts, exploiting information in both the time-series and cross-sectional dimensions of the data. We examine general tests of equal forecasting performance averaged across all time periods and individual units, along with tests that focus on subsets of time or clusters of units. Properties of our tests are demonstrated through Monte Carlo simulations and in an empirical application that compares International Monetary Fund forecasts of country-level real gross domestic product growth and inflation to private-sector survey forecasts and forecasts from a simple time-series model.

Wittgenstein and Stenlund on Mathematical Symbolism

In recent work, Sören Stenlund (2015) contextualizes Wittgenstein’s philosophy of mathematics as aligned with the tradition of symbolic mathematics. In the early modern era, mathematicians began using purely formal methods disconnected from any obvious empirical applications, transforming their subject into a symbolic discipline. With this, Stenlund argues, they were freeing themselves of ancient ontological presuppositions and discovering the ultimately autonomous nature of mathematical symbolism, which eventually formed the basis for Wittgenstein’s thinking. A crucial premise of Wittgenstein’s philosophy of mathematics, on this view, is that the development of mathematical concepts is independent of any ontological implications and occurs in principle without normative connections to empirical applicability. This paper critically examines this narrative and arrives at the conclusion that Stenlund’s view of mathematical progress is in stark contrast to the later Wittgenstein’s writing, which emphasizes links between symbolisms and their applications.

The role of local institutions in the technological trajectory of the Brazilian rice industry

PurposeDespite the growing interest regarding the Brazilian rice industry, there is not much literature focusing on the role of the institutions in the process of technological capability accumulation and in the formation of the technological trajectories within this industry. This paper aims to discover the role of local institutions in the generation and dissemination of knowledge for creating the technological capability that can define different technological trajectories, using the Brazilian rice industry as an empirical field.Design/methodology/approachTo achieve said objective, this paper uses secondary data (documental research) and a multiple case study design based on primary empirical evidence (content analysis and direct observation) about the Brazilian rice industry.FindingsThe paper’s main contribution is the empirical application of a framework that allows us to evaluate the institutions’ roles and activities and how these capabilities evolve as the firms’ technological levels progress and the technological trajectory is formed. Regarding aspects related to public policy, the authors found some implications that are mainly related to the need to consolidate this type of institution in developing countries with the goal of strengthening its technological capabilities, allowing these countries to operate on the technological boundary and to compete with developed countries.Originality/valueThere are few attempts to relate the technological capability, technological trajectories and institutions in the Brazilian rice industry. Therefore, to the best of the authors’ knowledge, the novelty of this study lies in the analysis of these theoretical approaches in this industrial sector, more specifically, in the Brazilian rice industry.

A New Odd Beta Prime-Burr X Distribution with Applications to Petroleum Rock Sample Data and COVID-19 Mortality Rate

In this article, we pioneer a new Burr X distribution using the odd beta prime generalized (OBP-G) family of distributions called the OBP-Burr X (OBPBX) distribution. The density function of this model is symmetric, left-skewed, right-skewed, and reversed-J, while the hazard function is monotonically increasing, decreasing, bathtub, and N-shaped, making it suitable for modeling skewed data and failure rates. Various statistical properties of the new model are obtained, such as moments, moment-generating function, entropies, quantile function, and limit behavior. The maximum-likelihood-estimation procedure is utilized to determine the parameters of the model. A Monte Carlo simulation study is implemented to ascertain the efficiency of maximum-likelihood estimators. The findings demonstrate the empirical application and flexibility of the OBPBX distribution, as showcased through its analysis of petroleum rock samples and COVID-19 mortality data, along with its superior performance compared to well-known extended versions of the Burr X distribution. We anticipate that the new distribution will attract a wider readership and provide a vital tool for modeling various phenomena in different domains.

Cultural adaptations and methodological innovations to group model building for the systems actions to reduce malnutrition in all its forms in Southeast Asian countries and China (SYSTAM CHINA-SEACS International Consortium) project

BackgroundGroup Model Building (GMB) is a participatory system dynamics method increasingly used to address complex public health issues like obesity. GMB represents a set of well-defined steps to engage key stakeholders to identify shared drivers and solutions of a given problem. However, GMB has not yet been applied specifically to develop multi-duty interventions that address multiple inter-related issues such as malnutrition in all its forms (MIAIF). Moreover, a recent systematic review of empirical applications of a systems approach to developing obesity interventions found no published work from non-western, low- and middle-income countries (LMICs). In this paper we describe adaptations and innovations to a common GMB process to co-develop systemic MIAIF interventions with Chinese decision-makers.MethodsWe developed, piloted and implemented multiple cultural adaptations and two methodological innovations to the commonly used GMB process in Fang Cheng Gang city, China. We included formal, ceremonial and policy maker engagement events before and between GMB workshops, and incorporated culturally tailored arrangements during participant recruitment (officials of the same seniority level joined the same workshop) and workshop activities (e.g., use of individual scoring activities and hand boards). We made changes to the commonly used GMB activities which enabled mapping of shared drivers of multiple health issues (in our case MIAIF) in a single causal loop diagram. We developed and used a ‘hybrid’ GMB format combining online and in person facilitation to reduce travel and associated climate impact.ResultsOur innovative GMB process led to high engagement and support from decision-makers representing diverse governmental departments across the whole food systems. We co-identified and prioritised systemic drivers and intervention themes of MIAIF. The city government established an official Local Action Group for long-term, inter-departmental implementation, monitoring and evaluation of the co-developed interventions. The ‘hybrid’ GMB format enabled great interactions while reducing international travel and mitigating limitations of fully online GMB process.ConclusionsCultural and methodological adaptations to the common GMB process for an Asian LMIC setting were successful. The ‘hybrid’ GMB format is feasible, cost-effective, and more environmentally friendly. These cultural adaptations could be considered for other Asian settings and beyond to address inter-related, complex issues such as MIAIF.