Community detection is a pivotal research area in network analysis.In this context,the nodes on the borders of multiple communities are of great significance,attributed to their crucial positions in the information flow of communities.From the perspective of a special disposition of such nodes,this study proposes a novel community detection method termed the AIA(acquisition-integration-allocation)algorithm to improve community detection.The algorithm consists of three steps:① isolating certain nodes and creating multiple components to refine the structure of a network based on the principle of diminishing marginal utility and neighborhood information;② integrating the components as the base of com-munities via the spectral clustering method;and ③ allocating the unprocessed nodes through label transfer and the Graclus distance.Experimental validations on both synthetic and real-world datasets demonstrate the effectiveness of the proposed approach.

This paper investigates the parameter estimation problem for panel data with a multilayer network structure. Considering the heterogeneous behaviours or attributes exhibited by individuals, we propose a multilayer network autoregressive model with group structure. We allow individuals to have a latent group structure, whereby individuals within the same group share common slope. We assume that time-invariant fixed effects are individually heterogeneous, which endows the model with a wide range of applications. To identify the latent group structure, we use the initial MLE for clustering purposes. Our theoretical analysis demonstrates that this two-stage least squares (2SLS) estimator possesses desirable asymptotic normality properties. We conduct a detailed analysis of the factors influencing estimation errors and employ a jackknife method to reduce the bias of the momentum effect. Extensive simulation experiments and real data analyses validate the effectiveness of our proposed method.

In operations management, eco-labels have become a crucial measure to stimulate green product production and consumption. Most related research focuses on self-labeling by firms or national-labeling by external certifiers, while few studies consider the implementation of platform-label certification. After constructing a two-stage optimization model to explore the design mechanism of platform-labeling standards, we propose the optimal platform-label design policy in a platform-based supply chain. We also propose the optimal strategies for competing firms on the retail platform. When the labeling credibility is high, the platform- labeling policy benefits the platform-labeled retailer. The platform-labeling strategy achieves Pareto improvement in total profit and environmental benefit under a global (entire sales season) optimization criterion or with a profit-maximizing platform. Both the platform-labeled retailer and environment benefit more from our proposed solutions for platform-labeling than current common policies. When platform designs a higher platform-labeling standard, effective measures must be taken to improve the platform's reputation. The retailers should adopt platform-labeling when its credibility is high but retain self-labeling when it is low. Platforms can compensate the benefit-injured party through cost sharing and commission reduction while gaining more money from the beneficiary. We identify how and when the platform should intervene to stimulate green product development through platform-labeling certification and extend the base model to validate the robustness of our main results.

Social interaction with peer pressure is widely studied in social network analysis. Game theory can be utilized to model dynamic social interaction and one class of game network models assumes that peopleos decision payoff functions hinge on individual covariates and the choices of their friends. However, peer pressure would be misidentified and induce a non-negligible bias when incomplete covariates are involved in the game model. For this reason, we develop a generalized constant peer effects model based on homogeneity structure in dynamic social networks. The new model can effectively avoid bias through homogeneity pursuit and can be applied to a wider range of scenarios. To estimate peer pressure in the model, we first present two algorithms based on the initialize expand merge method and the polynomial-time two-stage method to estimate homogeneity parameters. Then we apply the nested pseudo-likelihood method and obtain consistent estimators of peer pressure. Simulation evaluations show that our proposed methodology can achieve desirable and effective results in terms of the community misclassification rate and parameter estimation error. We also illustrate the advantages of our model in the empirical analysis when compared with a benchmark model.

The Degree-Corrected Stochastic co-Block Model (DC-ScBM) is widely utilized for detecting the community structure in directed networks. It can flexibly depict the topology of edges in directed graphs. However, in practice, node attributes provide an additional source of information that can be leveraged for community detection, which is not considered in the DC-ScBM. Therefore, there is a critical need to develop models and detection methods for node-attributed directed networks, especially when the goal is to discover important nodes or special community structures. We generalize the DC-ScBM using the multiplicative form to fuse edges and node attributes and describe the extent of influence of node attributes on each community. Then, a detection algorithm based on spectral co-clustering and feature weight self-adjustment (Spcc-SA) is developed. The algorithm aims to minimize normalized cut (Ncut), and iteratively detects the sending and receiving communities and the weights of node attributes, so that node attributes with stronger signals are given greater weights. Numerical studies demonstrate that the Spcc-SA algorithm outperforms existing methods across a variety of node attributes and network topologies. Especially when attribute values differ greatly and the community structure is distinct, the normalized mutual information of Spcc-SA in the sending and receiving communities can reach 0.6 and 0.8, respectively. Furthermore, We apply this algorithm to real world datasets, including the Enron email, world trade, and Weddell Sea network, demonstrating that the algorithm can effectively detect interesting community structures.

A network-based method applied to collaborative filtering in recommender systems is introduced in this paper. Specifically, a novel mixed-membership stochastic block model with a conjugate prior from the exponential family is proposed for bipartite networks. The analytical expression of the model is derived, and a variational Bayesian algorithm that is computationally feasible for approximating the untractable posterior distributions is presented. Extensive simulations show that the proposed model provides more accurate inference than competing methods with the presence of outliers. The proposed model is also applied to a MovieLens dataset for a real data application.

In recent years, live streaming is becoming a popular channel to sell products all over the world. Compared to traditional e-commerce channel, live streaming channel may not only bring consumers more shopping convenience, but also pose consumers more privacy concern. This paper considers a supply chain consisting of a manufacturer and an e-tailer who sells through dual channels (i.e., live streaming and traditional e-commerce) to explore how shopping convenience and privacy concern affect the optimal decisions. We build game models of two pricing (exogenous and endogenous) and two incentive contracts (wholesale price and two-part tariff). We find that the optimal promotion efforts are decreasing in shopping convenience while increasing in privacy concerns under the wholesale price contract, and independent of them under the two-part tariff contract when pricing is not a decision (such as iPhone); the optimal promotion efforts are increasing in shopping convenience while decreasing in privacy concern when pricing is a decision (such as the seasonal products). Whether the retail pricing is a decision or not, supply chain coordination can be achieved by the two-part tariff contract, but not through the wholesale price contract. Further, the two-part tariff contract is more favorable to the manufacturer if the exogenously given retail price is low, and the wholesale price contract is more favorable to the manufacturer if the retail price is high; the two-part tariff contract is always more beneficial for the supply chain than the wholesale price contract. Finally, we extend our analysis to relax a more realistic form with a variable effort elasticity and verify the robustness of the theoretical results.

Obtaining consistent estimates of network effects in heterogeneous network autoregressive model presents significant challenges. These arise from the large number of target parameters, potential endogeneity, and non-identifiability issues. To overcome these challenges, we reformulate the model into a higher-order version. Our proposed two-stage estimation procedure first reduces parameter complexity by screening out nodes with negligible network effects. Then, we employ the ordinary least squares method and the instrumental variables technique for effective post-screening estimation. We further investigate the consistency and asymptotic normality of the estimators under appropriate assumptions and explore the case of heteroscedasticity. The finite sample performance of the two-stage method is evaluated by simulation studies and an empirical analysis.

Interconnection of nodes takes great challenge to the estimation of causal effect in the network. In this study, we develop a nonparametric doubly robust (NDR) estimator to identify the causal effect in the presence of general interference on network observational data. The estimator combines the strengths of doubly robust mapping and nonparametric regression. Thus, it is consistent when either the treatment or the outcome model is properly specified and is free of parametric assumptions. The asymptotic properties of the proposed estimator are also proved. We demonstrate the robustness and effectiveness of NDR by simulation studies and apply this method to investigate the impact of installation of SnCR on ambient ozone concentration of 473 power plants in America.

Consider a portfolio of n losses accompanied with n stochastic loss adjustment factors. This paper establishes some asymptotic formulas of the tail distortion risk measure for aggregate weight-adjusted heavy-tailed losses under the framework of multivariate regular variation, pairwise quasi-asymptotic independence or arbitrary dependence. As an application, the corresponding results on the asymptotics for the risk concentration based on tail distortion risk measure are also derived. Several examples and simulation studies are provided to better illustrate the obtained results.

Network effects are pivotal for understanding the mutual influence of nodes within a network. The homogeneous group structure holds significant importance across networks in various fields. This paper introduces the Classifier-L2 regularized approach for homogeneous analysis of network effects under the network autoregressive model. This approach offers high flexibility with data constraints and provides a completely data-driven procedure. Analysis of international trade data offers meaningful perspectives for refining trade policies. Empirical results derived from Chinese mutual fund data, both before and after the outbreak of the COVID-19 pandemic, provide valuable insights for mitigating potential risks.

We investigate the delivery investment decision in the context of trade credit (TC), under which the retailer applies for deferred payments from its supplier. In addition to ordering procurement, the retailer must allocate limited capital to reduce delivery time, which promotes time-sensitive demand. We develop a Stackelberg game in which the supplier determines the wholesale price and then the retailer decides the delivery investment amount and order volume. The analytical results indicate that, unless the retailer is slightly capital-constrained, the retailer's investment activity not only increases its profitability but also benefits the supplier and promotes the coordination of the supply chain. Supplier reduction in wholesale deepens the positive impact. With bank finance (BF) as a benchmark, the Pareto region that entices both parties to participate in TC exists when the investment cost is within certain limits and when the retailer is severely capital-constrained. We also provide insights on the sensitivity of participants' profits to the capital level, delivery investment features, and other price parameters.

We investigate the pricing timing strategy in the context of trade credit (TC), under which the capital-constrained retailer applies for deferred payments from its supplier. Based on the wholesale price offered by the supplier, the retailer determines the order volume before observing the random demand and the selling price after observing it (a.k.a., price postponement). We formulate the Stackelberg game to show how their equilibrium decisions and profits are affected by: the pricing timing, financing mode, the demand structure. In a multiplicative demand framework, the analytical and numerical results indicate that TC alleviates double marginalization problem, depending on price timing and demand structure. With the traditional bank finance (BF) as a benchmark, the supplier is reluctant to provide TC to the retailer without postponement when the market is extremely sensitive to price. Postponement not only benefits both members, but also enhances retailer's repayment ability and thus participants' preference for TC. They can reach an agreement on utilizing price postponement and trade credit as long as the supplier choose a suboptimal wholesale decision for deferred payment that is slightly lower the optimal one. We further extend our results to consider the additive demand structure.

Harvesting energy from the hot sun and the cold universe is being investigated and has attracted much attention due to its clean utilization. Herein, a broadband selective absorber/emitter (BS-A/E) is designed and fabricated for the hybrid utilization of diurnal solar thermal and nocturnal radiative cooling. The BS-A/E exhibits high photon absorption in the solar band (i.e., 0.3-3 mu m) with a weighted solar absorption of-0.83, a strong thermal emission mainly within the atmospheric window (i.e., 8-13 mu m), and a low thermal emissivity in other infrared wavelength bands. The outdoor experiment demonstrates that the stagnation temperature of the BS-A/E is 11.6 degrees C greater than black paint under sunshine and 0.6 degrees C lower than that of black paint under darkness, showing considerable solar thermal and radiative cooling performance. In addition, thermal prediction also reveals that the BS-A/E can not only achieve solar heating during the day but also obtain sub-ambient cooling phenomenon during the night, indicating that the BS-A/E is capable of providing continuous heating and cooling for humans in various potential applications, such as all-day thermoelectric power generation and thermal storage-based space heating/cooling.

Governments all over the world usually establish the policy of subsidies to stimulate firms' technology innovation behaviors. The participating firms may share the high risk of expense through cooperative technology innovation. Different forms of governmental subsidies may have a significant impact on the choice of firms' cooperative innovation strategies. This paper investigates the effect of government subsidies on firms' technology innovation strategies. We consider two modes of cooperative technology innovation (technology transfer or joint innovation) in a two-level supply chain including an upstream manufacturer (UM) and a downstream manufacturer (DM) in the presence of two forms of governmental subsidies (a per-unit production subsidy or an innovation subsidy). We find that in the presence of either form of governmental subsidy, technology transfer mode is better off for the UM than joint innovation mode when the UM's distribution power is greater than a threshold, otherwise joint innovation mode is better off. In the presence of a given form of governmental subsidy, the DM's response strategy is influenced by the interaction of different values of the proportion of revenue and the fraction of innovation cost. In the presence of a per-unit production subsidy, the social welfare is always more under technology transfer mode than under joint innovation mode, while in the presence of an innovation subsidy, the opposite is true. We also show that under a given cooperative innovation mode, both the UM and DM expect a per-unit production subsidy if the per-unit tax credit is high, and they expect an innovation subsidy if the proportion of governmental subsidy is high. Finally, we discuss the robustness of the theoretical results.

Comprehensive information on coauthorship from 2014 to 2018 was gathered from four top statistical journals and subsequently cleaned to provide a review in the field from the perspective of a co-authorship network analysis. Data on productivity and trends, as well as a skew analysis of publications and collaborations, was provided by the analysis. The coauthorship network was analyzed for both global and individual properties. Exponential random graph models (ERGMs) were also used to explore the formation mechanisms of collaboration while simultaneously considering exogenous covariate effects and endogenous network structure processes. It was discovered that homophily (authors from the same universities and countries) and transitivity (the tendency to collaborate with a coauthor's coauthor) have a significant positive effect on the production of collaborative studies. Finally, the kNN-walktrap was proposed, which combines the structures of the network and the homophily features of authors to detect network communities. In this method, the cosine similarity calculated by the homophily features of the nodes is utilized to build a kNN (k Nearest Neighbor) network and apply walktrap to detect communities. Thus, more detailed and comprehensive community structures can be detected than when using the walktrap method. These results have practical significance for researching collaboration models and guiding future collaboration.

Radiative cooling of solar cells has been proposed in recent years and has elicited much interest from fields of materials science to engineering science. Herein, a silica micro-grating photonic cooler is proposed, designed, and fabricated to radiatively cool solar cells. It is shown that the micro-grating silica can not only improve the thermal emissivity of the bulk silica to over 0.9 required for enhanced radiative cooling of solar cells but also exhibits a slight anti-reflection effect for sunlight. The outdoor experiment demonstrates that the proposed cooler can passively reduce the temperature of the commercial silicon cell by 3.6 degrees C when applied on the top of the cell under solar irradiance range from approximately 830 W m-2 to 990 W m2, even though the cell already possesses a strong thermal emissivity of 0.67 and such a cooler slightly enhance the light trapping effect of the cell. This work provides an alternative way to design the solar-transparent infrared-emissive cooler for enhanced radiative cooling of solar cells and shows its cooling potential.

In this paper, we investigate how spillovers from online sales to offline sales and product innovation jointly affect suppliers' optimal online channel structure strategies. By comparing equilibrium outcomes of the game between a supplier, an offline retailer and an online retailer in different scenarios, including the scenario without product innovation, the scenario with exogenous product innovation and the scenario with endogenous product innovation, we obtain some novel management implications. There exists a threshold curve such that when the supplier's marginal operating cost is below the threshold curve, the supplier is better off establishing a direct online channel, otherwise, the supplier should introduce an independent online channel. Nonetheless, the threshold curve is not a monotonic function of the spillover coefficient, but a function that decreases first and then increases with the the spillover coefficient. Exogenous product innovation does not change the supplier's optimal online channel structure strategy qualitatively, it leads to some quantitative changes, shifting the threshold curve upward. However, endogenous product innovation changes the position and shape of the threshold curve significantly and gives the supplier the flexibility to establish the direct online channel. This paper reveals an underlying trade-off between online channel operational efficiency and channel coordination, providing suppliers managerial suggestions on online channel structure strategies.

在条件密度教学中,当对某些相同零测度集取条件时,会产生不同条件密度,这就是Borel-Kolmogorov悖论.本文剖析Borel-Kolmogorov悖论的成因,并结合实例给出条件密度教学内容和教学方法的一些建议.

Significance The sun (∼6,000 K) and outer space (∼3 K) are two natural energy resources for humans. However, most of the approaches of energy harvesting from the sun and rejecting energy to outer space are achieved independently using absorbers and emitters with static spectral properties. Herein, a spectrally self-adaptive structure with strong solar absorption and switchable emissivity within the atmospheric window (i.e., 8 to 13 μm) is experimentally demonstrated to achieve diurnal solar thermal and nocturnal radiative cooling efficiently. The experiment shows that the proposed structure not only can be heated to 185°C in diurnal mode but also be cooled to −12°C in nocturnal mode. This work opens new possibilities for continuously efficient energy harvesting utilizing the sun and the universe.