Fixed T dynamic panel data estimators with multifactor errors

This article analyzes a growing group of fixed T dynamic panel data estimators with a multifactor error structure. We use a unified notational approach to describe these estimators and discuss their properties in terms of deviations from an underlying set of basic assumptions. Furthermore, we consider the extendability of these estimators to practical situations that may frequently arise, such as their ability to accommodate unbalanced panels and common observed factors. Using a large-scale simulation exercise, we consider scenarios that remain largely unexplored in the literature, albeit being of great empirical relevance. In particular, we examine (i) the effect of the presence of weakly exogenous covariates, (ii) the effect of changing the magnitude of the correlation between the factor loadings of the dependent variable and those of the covariates, (iii) the impact of the number of moment conditions on bias and size for GMM estimators, and finally (iv) the effect of sample size. We apply each of these estimators to a crime application using a panel data set of local government authorities in New South Wales, Australia; we find that the results bear substantially different policy implications relative to those potentially derived from standard dynamic panel GMM estimators. Thus, our study may serve as a useful guide to practitioners who wish to allow for multiplicative sources of unobserved heterogeneity in their model.     

From the Digital Divide to the Connectivity Dividend Difference: A Connectivity Capital Perspective*

The access divide was once the basic form of the digital divide. The development of Internet infrastructure has narrowed the access divide and increased application coverage, but it has also touched off a connectivity dividend difference. Taking the online market as an example, we examine the sources of the dividend difference and the factors influencing it with in a connectivity framework. We found that the narrowing of the access divide has resulted in enhanced connectivity and platform development, giving people the chance to benefit from transforming the various assets in which they have previously invested into differentiated compound connectivity capital. In the course, the scale and rate of the conversion are affected by two multiplier effects and especially by online platforms. The process is ultimately expressed in the dividend difference.     

Load-Oriented Order Release (LOOR) revisited: bringing it back to the state of the art

In the workload control literature, the Load-Oriented Order Release (LOOR) approach has been neglected since its robustness was questioned at the end of the 1990s. This paper revisits LOOR and evaluates whether its performance can be improved in two ways. First, an intermediate pull release mechanism is added to avoid starvation between periodic release events. This mechanism was recently shown to be effective at improving the performance of a state-of-the-art release method known as LUMS COR. Second, an integer linear programming model is used to manage the trade-off between the timing and load balancing functions of order release. The two refinements are assessed using simulations of different shop configurations, which allow us to evaluate robustness. Results demonstrate that the refinements contribute to improving the performance of LOOR such that it can even outperform LUMS COR. Perhaps counter-intuitively, putting more emphasis on load balancing than on the urgency of individual orders is shown to lead to a lower percentage of tardy orders. Overall, the improvements mean that concerns about LOOR’s robustness are no longer valid – it now appears suitable for a wide range of shops found in practice.     

浅析我国数字图书馆的发展

随着经济与科技的迅猛发展，我国图书馆馆藏有了突破性的发展，数字图书馆使图书馆的办馆模式和性质从根本上发生了变化，由独立办馆变成了馆际合作，由藏书借阅变成了为读者服务。同时面临新的形势和瓶颈，为了适应时代发展的需要，我们只有让各个系统条件共同发挥作用，来实现数字环境下的信息资源建设。     

基于蚁群算法参数的最优选择问题研究

蚁群算法是受现实蚂蚁群体行为启发而得出的一类仿生算法。通过对蚁群算法中影响算法性能的参数进行分析和研究,并对蚁群算法中参数的最优选择问题进行实验分析,从而给出算法参数的最佳取值范围,以利于算法在实际问题中的应用和推广.     

Size distortion of asymmetric unit root tests in the presence of level shifts

The finite-sample size properties of momentum-threshold autoregressive (MTAR) asymmetric unit root tests are examined in the presence of level shifts under the null hypothesis. The original MTAR test using a fixed threshold is found to exhibit severe size distortion when a break in level occurs early in the sample period, leading to an increased probability of an incorrect inference of asymmetric stationarity. For later breaks the test is also shown to suffer from undersizing. In contrast, the use of consistent-threshold estimation results in a test which is relatively robust to level shifts.     

Simulating random variables using moment-generating functions and the saddlepoint approximation

When we are given only a transform such as the moment-generating function of a distribution, it is rare that we can efficiently simulate random variables. Possible approaches such as the inverse transform using numerical inversion of the transform are computationally very expensive. However, the saddlepoint approximation is known to be exact for the Normal, Gamma, and inverse Gaussian distribution and remarkably accurate for a large number of others. We explore the efficient use of the saddlepoint approximation for simulating distributions and provide three examples of the accuracy of these simulations.     

A note on efficient simulation of multidimensional spatial autoregressive processes

In applications of spatial statistics, it is necessary to compute the product of some matrix W of spatial weights and a vector y of observations. The weighting matrix often needs to be adapted to the specific problems, such that the computation of Wy cannot necessarily be done with available R-packages. Hence, this article suggests one possibility treating such issues. The proposed technique avoids the computation of the matrix product by calculating each entry of Wy separately. Initially, a specific spatial autoregressive process is introduced. The performance of the proposed program is briefly compared to a basic program using the matrix multiplication.     

Flexible simulation of competing risks data following prespecified subdistribution hazards

In recent years different approaches for the analysis of time-to-event data in the presence of competing risks, i.e. when subjects can fail from one of two or more mutually exclusive types of event, were introduced. Different approaches for the analysis of competing risks data, focusing either on cause-specific or subdistribution hazard rates, were presented in statistical literature. Many new approaches use complicated weighting techniques or resampling methods, not allowing an analytical evaluation of these methods. Simulation studies often replace analytical comparisons, since they can be performed more easily and allow investigation of non-standard scenarios. For adequate simulation studies the generation of appropriate random numbers is essential. We present an approach to generate competing risks data following flexible prespecified subdistribution hazards. Event times and types are simulated using possibly time-dependent cause-specific hazards, chosen in a way that the generated data will follow the desired subdistribution hazards or hazard ratios, respectively.