A General Multivariate Threshold GARCH Model With Dynamic Conditional Correlations

We introduce a new multivariate GARCH model with multivariate thresholds in conditional correlations and develop a two-step estimation procedure that is feasible in large dimensional applications. Optimal threshold functions are estimated endogenously from the data and the model conditional covariance matrix is ensured to be positive definite. We study the empirical performance of our model in two applications using U.S. stock and bond market data. In both applications our model has, in terms of statistical and economic significance, higher forecasting power than several other multivariate GARCH models for conditional correlations.     

Supply chain management: a supplier perspective

A new way of researching into supply chain management is introduced by adopting a supplier perspective. Details are given of mixed integer linear planning and simulation models. The planning model takes into consideration firm and forecast orders (customer's forecast purchasing orders) and the behaviour of the supplier's suppliers and suppliers' subcontractors. The simulation model takes into account the dynamic behaviour of the supply chain and includes the planning production behaviour of a supplying company based on the planning model. The supplier manager can use the simulation model to determine what kind of parameters most affect company performances and then propose new management rules. Quantitative results that prove the benefits of integrating forecast orders for an aeronautic supplier have been provided.     

Multivariate forests with missing mixed outcomes

In this article, we propose a multivariate random forest method for multiple responses of mixed types with missing responses. Imputation is performed for each bootstrap sample used to build the individual trees that form the forest. The individual trees are built using a weighted splitting rule allowing downweighting of imputed observations. A simulation study shows the benefits of this approach over complete case analysis when missing responses are missing completely at random and missing at random (MAR). In particular, the gain in prediction accuracy of the proposed method is larger in the MAR case and also increases as the proportion of missing increases.     

Pointwise and uniform convergence of multivariate kernel density estimators using random bandwidths

We obtain the rates of pointwise and uniform convergence of multivariate kernel density estimators using a random bandwidth vector obtained by some data-based algorithm. We are able to obtain faster rate for pointwise convergence. The uniform convergence rate is obtained under some moment condition on the marginal distribution. The rates are obtained under i.i.d. and strongly mixing type dependence assumptions.     

论《书谱》的儒家艺术精神

儒家的艺术观在孙过庭的《书谱》里得到了比较完整的继承。《书谱》的书法理想是"中和美",即提倡书法中"情"与"法"、"骨力"与"妍媚"等的和谐统一。《书谱》对书法的人格主义批评也受儒家艺术观的影响。此外,《书谱》"质以代兴"、"异质同妍"的书法风格观也来自儒家美学。     

A note on connectedness in fixed effects manova and gmanova models withmissing cells

Murray and Smith (1985) and Hocking (1985) give a generalized definition and test of connectedness in the case of missing cells using the univariate cell-means model with linear restrictions on the cell-means. The test of connectedness is here extended to multivariate fixed effects models, including the usual MANOVA model with linear restrictions, the MANOVA model with double linear restrictions, and the GMANOVA model.     

Biased Bootstrap Methods for Reducing the Effects of Contamination

Contamination of a sampled distribution, for example by a heavy-tailed distribution, can degrade the performance of a statistical estimator. We suggest a general approach to alleviating this problem, using a version of the weighted bootstrap. The idea is to 'tilt' away from the contaminated distribution by a given (but arbitrary) amount, in a direction that minimizes a measure of the new distribution's dispersion. This theoretical proposal has a simple empirical version, which results in each data value being assigned a weight according to an assessment of its influence on dispersion. Importantly, distance can be measured directly in terms of the likely level of contamination, without reference to an empirical measure of scale. This makes the procedure particularly attractive for use in multivariate problems. It has several forms, depending on the definitions taken for dispersion and for distance between distributions. Examples of dispersion measures include variance and generalizations based on high order moments. Practicable measures of the distance between distributions may be based on power divergence, which includes Hellinger and Kullback–Leibler distances. The resulting location estimator has a smooth, redescending influence curve and appears to avoid computational difficulties that are typically associated with redescending estimators. Its breakdown point can be located at any desired value ε∈ (0, ½) simply by 'trimming' to a known distance (depending only on ε and the choice of distance measure) from the empirical distribution. The estimator has an affine equivariant multivariate form. Further, the general method is applicable to a range of statistical problems, including regression.     

The association between job skill discretion, decision authority and burnout

This paper reports on the relationship between dimensions of control (skill discretion and decision authority) and burnout (emotional exhaustion, depersonalization, and reduced personal accomplishment) among 164 human service workers. It examines the differential influence of job demands, control (skill discretion and decision authority) and social support (supervisor, co-workers, others) on each burnout dimension. Then it examines the moderating effects of higher skill discretion, higher decision authority, and higher social support on burnout. Low skill discretion was found to be associated with high emotional exhaustion and depersonalization and low personal accomplishment. The effects of decision authority were not statistically significant. High job demands were associated with high emotional exhaustion only. Social support (supervisor, co-worker, and others) was not associated with burnout when demographic variables and job characteristics were controlled for. Neither dimension of control moderated the impact of high job demands on burnout. Social support did not moderate the impact of high demands, low skill discretion, or low decision authority on any burnout dimension. The full model explained 44% of the variance in emotional exhaustion, 25% in depersonalization, and 42% in personal accomplishment. Despite its limitations, the study suggests that the Job Demand-Control model may provide a useful theoretical foundation for the study of burnout, but that the control dimensions need to be evaluated independently since they appear to be differentially related to the burnout dimensions.     

Employee reactions to behavioural control under conditions of stress: the moderating role of self-efficacy

Extensive research conducted in the occupational stress literature has failed to provide convincing support for the stress-buffering effects of work control on employee adjustment. Drawing on research conducted in the laboratory context, it was proposed that the stress-buffering effects of work control on employee adjustment would be more marked at high, rather than low, levels of self-efficacy. In a sample of 100 customer service representatives, a significant three-way interaction among role conflict, work control and self-efficacy (measured at Time 1) was observed on (low) depersonalization (measured at Time 2). Consistent with expectations, work control reduced the negative effects of work stress on this outcome measure only for employees who perceived high levels of self-efficacy at work. In addition, there was evidence to suggest that self-efficacy moderated the main effects of work control on job satisfaction and somatic health. These findings are discussed in terms of their theoretical contribution to the job strain model, and also in relation to workplace interventions designed to improve levels of employee adjustment.     

Robust models in probability sampling

In the estimation of a population mean or total from a random sample, certain methods based on linear models are known to be automatically design consistent, regardless of how well the underlying model describes the population. A sufficient condition is identified for this type of robustness to model failure; the condition, which we call 'internal bias calibration', relates to the combination of a model and the method used to fit it. Included among the internally bias-calibrated models, in addition to the aforementioned linear models, are certain canonical link generalized linear models and nonparametric regressions constructed from them by a particular style of local likelihood fitting. Other models can often be made robust by using a suboptimal fitting method. Thus the class of model-based, but design consistent, analyses is enlarged to include more realistic models for certain types of survey variable such as binary indicators and counts. Particular applications discussed are the estimation of the size of a population subdomain, as arises in tax auditing for example, and the estimation of a bootstrap tail probability.