Autoregressive Panel Model Research Articles

Potentials for Reducing Spatial Inequalities in Innovation: A Spatial Econometric Perspective

ABSTRACTThis study explains disparities in regional innovation through specific features of regional knowledge bases, including recently discussed concepts such as, technological relatedness, knowledge complexity, and technological complementarity among neighboring regions and regions connected in R&D networks. We employ a spatial autoregressive panel model for 405 European regions to estimate the effects of these characteristics. While being connected to complementary regions and having a high region‐internal technological relatedness are conducive to regional innovation, knowledge complexity has no positive effect interestingly. In illustrative convergence scenarios, we demonstrate the potential of increasing relatedness and complementarity to reduce inequalities in Europe, pointing to important policy implications.

Impact of migrants on communicable diseases in Thailand

BackgroundWhile foreign migrants contribute to economic development, they may impact public health by transmitting communicable diseases to the local population. With its geopolitical position, Thailand has been a primary destination for migrants from neighbouring countries in Southeast Asia and beyond. This positioning makes it a focal point for examining the complexities of migration dynamics and its implications for public health. Through a quantitative analysis, this paper investigates the influence of foreign migrants on physical health issues in Thailand, exploring their impact on various types of communicable diseases. The utilization of provincial-level data from Thailand offers insights into the localized effects of migrant populations on public health within the country. These insights can serve as a valuable resource for researchers and policymakers who conduct comparative analyses, facilitating a deeper understanding of the complex relationship between international migration and public health worldwide.MethodsA spatial panel autoregressive model (SAR) is applied on the provincial level communicable diseases and socio-economic data in Thailand from the period 2016 to 2021.ResultsThe results indicate that the influence of foreign migrants on communicable diseases in Thailand varies depending on the type of disease. While an increase in migrants correlates with a higher prevalence of respiratory and other communicable diseases, it conversely reduces the prevalence of vaccine-preventable diseases. Additionally, we found that migrants do not significantly impact the prevalence of food- and water-borne diseases, insect-borne diseases, animal-borne diseases, or sexually transmitted diseases in Thailand. Additionally, other factors, such as GPP per capita, unemployment, poverty, and technology access, strongly correlate with most types of communicable diseases.ConclusionAs revealed by this study, the increase in migrants leads to a rise in respiratory and other communicable diseases, as well as a decrease in vaccine-preventable diseases, which carries significant policy implications. These results urge policymakers, the Ministry of Labour, and the Ministry of Public Health to implement tailored policies and measures to enhance public health and effectively mitigate the risk of communicable diseases transmitted by migrants in the future.

A Robust Approach using M-Estimation for Dynamic Panel Autoregressive Model

This paper presents a robust M-estimation approach for first-order panel autoregressive models, addressing the challenges posed by high persistence levels of the autoregressive parameter and individual heterogeneity. Generalized method of moments estimators widely used in dynamic panel models exhibit substantial finite sample biases and are sensitive to weak instruments, particularly as the autoregressive parameter gets close to unity. Our proposed weighted M-estimator, which uses a power function for the scale parameter in Huber’s loss function, offers a robust alternative. By minimizing the variance of model parameters through an optimal tuning parameter, our method enhances the efficiency and robustness of parameter estimates. We demonstrate the superiority of the proposed approach through several Monte-Carlo simulations and an application to hydro-electric power output data, providing comprehensive comparisons with existing generalized method of moments estimators.

Profile quasi-maximum likelihood estimation for semiparametric varying-coefficient spatial autoregressive panel models with fixed effects

Profile quasi-maximum likelihood estimation for semiparametric varying-coefficient spatial autoregressive panel models with fixed effects

The multi-dimensional spatial network effect on grain production resilience: evidence from China’s provinces

ABSTRACT Enhancing grain production resilience is crucial for ensuring national food security and supply stability. This study explores the roles of different types of correlation networks in regional grain production resilience from a generalized spatial distance perspective. By using the panel data of 28 Chinese provinces from 2011 to 2021, we employ spatial autoregressive panel models with convex combinations of weight matrices and Bayesian model averaging for our empirical analysis. Our findings reveal that multi-dimensional spatial networks significantly influence provincial grain production resilience. Notably, industrial distances have the greatest impact, followed by cultural, ecological, and geographic distances. Additionally, we identify positive factors, such as the marketization of agricultural capital, financial development, and the supply of rural healthcare resources, alongside negative factors, such as urbanization, that significantly affect grain production resilience both within and across provinces connected by multi-dimensional spatial networks. The theoretical framework and empirical research presented in this study provide innovative perspectives for studying regional grain production resilience and valuable insights into the mechanisms for synergistic development among regions to enhance overall resilience.

Cross-lagged relationships between exposure to intimate partner violence, depressive symptoms and suicidal thoughts among adolescent and young married women

BackgroundHigh rates of depression and suicidal ideation are found in women experiencing intimate partner violence (IPV), but their temporal relationship is unclear. This study explores the bidirectional causality between IPV victimization, depressive symptoms, and suicidal thoughts among adolescent and young married women in India. MethodsData sourced from the UDAYA longitudinal survey in India, comprising 3,965 women aged 15–22. Employing Pearson's correlation coefficient, we analyzed the relationship between variables. Additionally, a two-wave cross-lagged autoregressive panel model explored the bidirectional link between IPV, depressive symptoms, and suicidal ideation. ResultsApproximately 25 % and 45 % of the participants reported some form of partner violence at baseline and at follow-up after three years, respectively. Exposure to IPV at baseline was significantly associated with depressive symptoms at follow-up [β = 0.10, p < 0.001], and the association between depressive symptoms at baseline and IPV at follow-up was statistically not significant [β = −0.02, 95 % CI: −0.06-0.02]. Similarly, exposure to IPV at baseline was significantly associated with suicidal thoughts at follow-up [β = 0.24, p < 0.001], and the association between suicidal thoughts at baseline and IPV at follow-up was statistically not significant [β = 0.003, 95 % CI: −0.001-006]. ConclusionsThe findings suggest that exposure to IPV is consistently and strongly associated with depressive symptoms and suicidal thoughts in adolescent and young married women. However, the reciprocal relationships did not hold true in this study, implying that reducing IPV during adolescence could potentially minimize the prevalence of depressive symptoms and suicidal thoughts during young adulthood.

The interaction between corruption, bank cost efficiency and economic development in Italy

In this paper, we assess the interaction between corruption, bank cost efficiency, and economic development. Existing literature on the subject normally focuses separately on the link between corruption, financial development, and growth, and finds ambiguous results, not distinguishing between different types of credit institutions. We use Italian disaggregated data from 2004 to 2012, considering cooperative and non-cooperative banks, to determine whether controlling corruption affects banks’ cost efficiency in Italian provinces and promotes economic development. Utilizing a panel autoregressive model, we find that controlling corruption magnifies the positive impact of banks’ cost efficiency on economic development. Evidence of a positive effect of the interaction is observed, particularly in the case of non-cooperative banks and for higher values of the Control of Corruption Index.

Social media marketing activities, customer engagement, and customer stickiness: A longitudinal investigation

AbstractAlthough customer engagement has been deemed critical for optimizing social media marketing performance, prior research has mainly examined customer engagement through cross‐sectional designs, thus limiting insight into its evolving dynamics over time. To address this gap, we adopt uses‐and‐gratifications theory to explore the associations among customers' evaluations of a firm's social media marketing activities, customer engagement, and customer stickiness on a brand's social media page at three points in the post‐purchase stage of the consumption journey. Cross‐lagged autoregressive panel model analyses suggest that, first, customers' evaluations of firms' social media marketing activities, customer engagement, and customer stickiness fluctuate. Second, customer engagement has cross‐lagged longitudinal effects on stickiness over time; the same applies to the role of stickiness in customers' evaluations of the firm's social media marketing activities. However, no cross‐lagged effects arise from (a) firm‐based social media marketing activities to customer stickiness or (b) stickiness to engagement. These findings contribute to the customer engagement literature by describing the dynamics of such engagement and its interrelationships with other key constructs across time.

Cross-Border Migration and Its Influence on Mental Health Dynamics in Thailand: An Empirical Analysis of Provincial Data

While previous research has examined the impact of cross-border migrants on economic development and other social issues, limited studies have focused on the potential effects of migrants on the mental health of the native population. This paper investigates the impact of cross-border migrants on the mental health of natives in Thailand, considering various mental health disorders. This study analyzes 77 provincial data sets from 2016 to 2021 using a spatial panel autoregressive model. The findings suggest that the presence of migrants did not have an adverse influence on the mental health of the native population at a 5% significance level. Notably, there is a reduction in the prevalence of substance abuse disorders associated with the presence of migrants at the 5% significance level. Additionally, unemployment, education, public health services, technological infrastructure, health risk behavior, and age are significant contributors to the mental health of natives at a 5% significance level. The study underscores the need for a comprehensive approach to developing effective mental health policies and initiatives that address these multiple contributors.

A spatial panel autoregressive model specification with inverse quantile separation distances of locations

This paper proposes an alternative spatial weight that efficiently captures a spatial dependence. In the past, researchers often used sparse or inverse distance spatial weights. A dense spatial weight is defined by partitioning the separation distances between locations based on quantile values over large spatial scales, where each partition forms conjoint neighborhood sectors and the weights of the respective inverse quantile of separation distances are assigned to each sector. Instead of joint modeling of the spatiotemporal process, a simultaneous spatial panel model is employed after the panel component is imposed on the proposed spatial weight using Kronecker product to perform maximum likelihood estimation and Bayesian inference via MCMC Gibbs method. The specification also involves space, time, and space–time simultaneous components. The performance of the models for the proposed spatial weight is compared with the existing spatial weights using parameter bias. A smaller value of the bias close to zero indicates a stronger value of the spatial error parameter for the proposed spatial weight over the existing spatial weights. It also induces spatial auto-correlations both in the spatial panel data of neighboring locations as well as in the errors. Thus, the proposed method affirms the best efficiency for the dynamic combined spatial panel autoregressive model with random effect specification over the lag and error models, and fixed effect specification.

New results on asymptotic properties of likelihood estimators with persistent data for small and large T

This paper revisits the panel autoregressive model, with a primary emphasis on the unit-root case. We study a class of misspecified Random effects Maximum Likelihood (mRML) estimators when T is either fixed or large, and N tends to infinity. We show that in the unit-root case, for any fixed value of T, the log-likelihood function of the mRML estimator has a single mode at unity as Nrightarrow infty . Furthermore, the Hessian matrix of the corresponding log-likelihood function is non-singular, unless the scaled variance of the initial condition is exactly zero. As a result, mRML is consistent and asymptotically normally distributed as N tends to infinity. In the large-T setup, it is shown that mRML is asymptotically equivalent to the bias-corrected FE estimator of Hahn and Kuersteiner (Econometrica 70(4):1639–1657, 2002). Moreover, under certain conditions, its Hessian matrix remains non-singular.

Variable Selection of High-Dimensional Spatial Autoregressive Panel Models with Fixed Effects

This paper studies the variable selection of high-dimensional spatial autoregressive panel models with fixed effects in which a matrix transformation method is applied to eliminate the fixed effects. Then, a penalized quasi-maximum likelihood is developed for variable selection and parameter estimation in the transformed panel model. Under some regular conditions, the consistency and oracle properties of the proposed estimator are established. Some Monte-Carlo experiments and a real data analysis are conducted to examine the finite sample performance of the proposed variable selection procedure, showing that the proposed variable selection method works satisfactorily.

The Group Roots of Social Media Politics: Social Sorting Predicts Perceptions of and Engagement in Politics on Social Media

Research on political partisans suggests that social media offer ideal playing fields for the group game of politics. This study considers how political and social identities interact to influence political communication on social media. Using an original two-wave survey of Americans fielded during the 2020 election period, we analyzed how social media users’ levels of social sorting—the alignment between racial, religious, ideological, and political identities—related to perceptions of and engagement in politics on social media. Results suggest that those with higher (vs. lower) levels of social sorting were more likely to perceive their social media environments as dominated by political content and conflict, and populated with politically interested and like-minded people. Auto-regressive panel models suggested that social sorting and political use of social media may be reciprocally related. Findings indicate social sorting may be a key concept for unearthing the group roots of politics on social media.

The threshold effect of tourism economy development on the relationship between FDI and SIDS’ inclusive growth

ABSTRACT Overseas investment and tourism economy development play important roles in the inclusive growth of small island developing states (SIDS). Taking the level of tourism economy growth as a threshold, this study explores the relationship between China’s FDI to 29 SIDS and SIDS’ inclusive growth from 2005 to 2020. This connection is investigated via the entropy method, a panel autoregressive model, and a panel threshold regression model and data from the World Bank and the Ministry of Commerce of China. Several findings emerge: (1) SIDS’ inclusive growth index demonstrated an upward trend, with PROFIT-type SIDS’ inclusive growth being highest; (2) China’s FDI to SIDS could effectively promote SIDS’ inclusive growth; and (3) tourism economic growth had a threshold effect and region–type heterogeneity within the process of FDI and SIDS’ inclusive growth. The positive impact of China’s FDI on SIDS’ inclusive growth rose by 42.308% when SIDS’ tourism receipts (% of GDP) reached 25.950%. The threshold effect was strongest in the AIMS region and was not significant in the Pacific region. A double-threshold effect applied to PROFIT-type SIDS. Additionally, the threshold effect was strongest in SITEs-type SIDS and was not significant in MIRAB-type SIDS.

Innovation and organizational performance: A perspective among Chinese enterprises.

The influence of innovation on the performance of Chinese enterprises still remains inconclusive in the literature of innovation management. The aim of this research therefore is to examine the link between innovation and performance of Chinese enterprises, and explore the influence of sentiment expressed by investors in this relationship. The data for our study are drawn from 3,500 Chinese listed firms, operating within the periods, 2009-2017. Panel autoregressive models (fixed and random effects) are employed in our empirical analyses. We further performed Hausman tests in order to ascertain which of the models is more suitable for our dataset. Results from the analysis show that innovation significantly influences the performance of Chinese enterprises and it is moderated by sentiment expressed by investors. Specifically, it is found that Chinese enterprises tend to be innovative as feedback to sentiment expressed by investors and this consequently results in higher performance.

Urban life cycle and long-run violence: Colombia 1938–2018

ABSTRACT This paper revisits and improves upon the traditional urban life cycle theory, using it as a long-term conceptual baseline model to assess the effect of the Colombian internal armed conflict on urbanization during 1938–2018. The paper makes three innovations: (1) It uses a third-degree autoregressive panel estimation to detect the underlying Data Generating Process of the urban life cycle, a feature that eluded original scholarship in the field; (2) It uses the baseline urban life cycle model to assess the impact of long-term violence in Colombia; and (3) It produces an inductive conceptual approach to the relationship between urbanization and economic development. Our third-degree autoregressive panel models adequately explain the urban concentration cycles experienced by Colombia’s 20 largest metropolitan areas, regardless of using different specification structures. It also correctly controls the long-term trends of the demographic transition that the country experienced during that period: its rate of urbanization increased from 31 to 68% between 1938 and 2018; the largest 20 metro areas increased their participation in the total population from 17 to 54%; and yearly total population growth increased from 2.12% in the 1940s to its peak 3.19% in the 1970s, decreasing to 1.18% in the 2010s. The homicide rate had a controlling effect on the increasing parts of the urban life cycle, acting as a deterrent of urban concentration per metropolitan area.

Grouped spatial autoregressive model

With the development of the internet, network data with replications can be collected at different time points. The spatial autoregressive panel (SARP) model is a useful tool for analyzing such network data. However, in the traditional SARP model, all individuals are assumed to be homogeneous in their network autocorrelation coefficients, while in practice, correlations could differ for the nodes in different groups. Here, a grouped spatial autoregressive (GSAR) model based on the SARP model is proposed to permit network autocorrelation heterogeneity among individuals, while analyzing network data with independent replications across different time points and strong spatial effects. Each individual in the network belongs to a latent specific group, which is characterized by a set of parameters. Two estimation methods are studied: two-step naive least-squares estimator, and two-step conditional least-squares estimator. Furthermore, their corresponding asymptotic properties and technical conditions are investigated. To demonstrate the performance of the proposed GSAR model and its corresponding estimation methods, numerical analysis was performed on simulated and real data.

The Impact of Transport Infrastructure on Rural Industrial Integration: Spatial Spillover Effects and Spatio-Temporal Heterogeneity

Industry convergence is the future trend of industrial development in rural areas and is conducive to high-quality agriculture development. To explore the development dynamics of industry convergence. This paper selects data from 31 provincial administrative regions in China from 2009 to 2019. It uses the entropy power method to measure the development quality of rural industrial integration in China and empirically studies the impact of transportation infrastructure on rural industrial integration using a spatial panel autoregressive model. The study found that: (1) from 2009–2019, the development quality of rural industrial integration is on the rise, but the development is uneven between regions; (2) transport infrastructure strongly promotes the development of rural industrial integration; (3) with the help of transport infrastructure, rural industrial integration in this region will improve the quality of rural industrial integration in the surrounding areas; and (4) the impact of transportation facilities varies in different regions and at different stages of development of rural industrial integration. The results of this paper are beneficial to improving transportation infrastructure planning and exploring the driving force of high-quality agriculture development, enriching the research of spatial land use, and providing valuable insights for developing industry convergence in other countries and regions.

ЕКОНОМІЧНИЙ РОЗВИТОК РЕГОНІВ УКРАЇНИ: МОДЕЛЮВАННЯ НА ПАНЕЛЬНИХ ДАНИХ

At the current stage, the development of the economy of Ukraine is impossible without considering territorial features, in particular, the strengths and weaknesses of the functioning of regional economic systems, favorable and negative trends in their development. The purpose of the investigation is analyzing and modelling the specifics of economic growth, the factors that influence it, in terms of individual regions of Ukraine at a certain point in time, to develop such a model that would be suitable for further forecasting. A vector autoregression model based on longitudinal data of economic development across regions of Ukraine is used for achieving the purpose. The investigation implemented a model of economic development of the regions of Ukraine based on longitudinal or panel data. As factor variables for the model, the retail trade turnover, the volume of sold industrial products, capital investments, the volume of manufactured construction products, the volume of exports, and the number of the employed population were used. The resulting variable is gross regional product. Input information on factor variables and gross regional product was collected across the regions of Ukraine for the period 2000–2020. After conducting a number of tests (causality test and series stationarity test, Durbin-View-Hausman test, and Wald test), the model was specified as a panel autoregressive model with cross-sectional fixed effects. For such a model, it was necessary to apply the estimated generalized least squares method (panel EGLS), which is based on the assumed inequality of variance and therefore provides the opportunity to obtain the best linear estimates. In general, the quality assessment of the built model gives good results, the determination ratio is close to unity. In the regions of Ukraine, 99.69% of changes in the gross regional product are explained by changes in the values of the gross product itself, the volumes of capital investments, realized industrial products and exports, as well as the turnover of retail trade, with a corresponding lag, according to the r squared value. The proposed model of economic development of regions is adequate to reality and can be used for forecasting. Of course, russian war against Ukraine will make adjustments to the development of the economy of the country and its regions in the future. Therefore, the model characterizes the pre-war situation and may inadequately describe the development of economic processes after Ukraine's victory in the war.

Excess volatility pursuit in autoregressive GARCH model based panel data analysis at country level: BRICS context

PurposeThis particular study examined the government bond price variations in order to determine the presence of excess volatility both at country and panel group level of BRICS countries context.Design/methodology/approachThe study applied the autoregressive GARCH panel model approach proposed by Fakhry and Richter (2015) to evaluate the presence of excess volatility and then examined the diversification benefits. Further, the use of discrete wavelet transformation (DWT) has added the advantage to observe volatility across bonds along with potential diversification benefits by retaining information from the time and frequency domain perspective for both the maturities.FindingsThe main finding indicates that the excess volatility is present in BRICS countries at individual level i.e. in the case of Russia, India and China. However, the 10-year bond showing a less volatility compared to 5-year bond with the possibility of reaping out the benefits of diversification with international portfolio of sovereign bonds.Practical implicationsThe main implication of the research is related to the non-perseverance of EMH as far sovereign bonds of BRICS countries are concerned as the results indicate presence of excess volatility in the 5-year and 10-year bond markets. However, the implicit behavior of 5-year bond could benefit the active fund managers and investors by taking an advantage of a reducing systemic risk through short-medium term investments.Originality/valueThis study contributes not only to the existing studies of similar nature by examining the excess volatility in bond markets but also taking account of co-moment of distinct maturities to confirm possible international diversification benefits for BRICS countries context.