Bayesian inference for wind field retrieval

In many problems in spatial statistics it is necessary to infer a global problem solution by combining local models. A principled approach to this problem is to develop a global probabilistic model for the relationships between local variables and to use this as the prior in a Bayesian inference procedure. We show how a Gaussian process with hyper-parameters estimated from Numerical Weather Prediction Models yields meteorologically convincing wind fields. We use neural networks to make local estimates of wind vector probabilities. The resulting inference problem cannot be solved analytically, but Markov Chain Monte Carlo methods allow us to retrieve accurate wind fields.

Bayesian inference for wind field retrieval

In many problems in spatial statistics it is necessary to infer a global problem solution by combining local models. A principled approach to this problem is to develop a global probabilistic model for the relationships between local variables and to use this as the prior in a Bayesian inference procedure. We show how a Gaussian process with hyper-parameters estimated from Numerical Weather Prediction Models yields meteorologically convincing wind fields. We use neural networks to make local estimates of wind vector probabilities. The resulting inference problem cannot be solved analytically, but Markov Chain Monte Carlo methods allow us to retrieve accurate wind fields.

Equilibration through local information exchange in networks

We study the equilibrium states of energy functions involving a large set of real variables, defined on the links of sparsely connected networks, and interacting at the network nodes, using the cavity and replica methods. When applied to the representative problem of network resource allocation, an efficient distributed algorithm is devised, with simulations showing full agreement with theory. Scaling properties with the network connectivity and the resource availability are found. © 2006 The American Physical Society.

Budget participation in Malaysian local authorites

This study examines the effect of budgetary participation on departmental performance via budget adequacy, organisational commitment and role ambiguity. The responses of 108 budget preparers and budget users drawn from a cross-section of Malaysian local authorities, to a questionnaire survey were analysed by using mediation analysis, path analysis and Pearson Product-Moment Correlation technique. The results suggest that budget adequacy, organisational commitment, and role ambiguity are important links in the process. The results of this study suggest that the relationship between budget participation and departmental performance is statistically, significantly, positively and marginally correlated. Of more interest was the finding that budget adequacy, organisational commitment, and role ambiguity are important intervening variables in the relationship between budget participation and departmental performance. The test for mediation effect, demonstrated that budget adequacy, organisational commitment, and role ambiguity had partially mediated the relationship of budget participation and departmental performance. These three variables act as partial mediators when they significantly reduced or decreased the path coefficient of budget participation and departmental performance rather than eliminating the relationship. Furthermore, the test for direct and indirect effect of budget participation on departmental performance, suggests that budget participation predicted or affected departmental performance more strongly in the indirect way than it did in a direct way. This suggests that, even though the correlation between budget participation and departmental performance was significant, the path interpretation suggests that the correlation arose because budget participation was correlated with other variables that have direct effect upon departmental performance not budget participation itself directly predicted departmental performance. Therefore, there is enough evidence to suggest that budget participation of budget preparers and budget users affects departmental performance of Malaysian local authorities indirectly via budget adequacy, organisational commitment and role ambiguity. Among the indirect effects, the link between budget participation, budget adequacy, organisational commitment, role ambiguity and departmental performance may be the most important in term of this study’s contribution. The decomposition of the observed correlation between budget participation, budget adequacy, organisational commitment and role ambiguity showed that budget 3 participation of budget preparers and budget users of Malaysian local authorities in the budget setting has direct effect on budget adequacy, organisational commitment and role ambiguity. Budget adequacy and organisational commitment was directly related. However, the relationship of role ambiguity and organisational commitment in this study was indirectly related. This suggests that participation of budget preparers and budget users in the budget setting of Malaysian local authorities lead to decrease role ambiguity that provide adequate budgetary supports, which lead to increase organisational commitment and thus enhance departmental performance. In relation to the strength of the relationships of the variables undertaken for the study, the overall relationships between variables are significant and positively related except that of role ambiguity relationship. The relationships of role ambiguity with budget participation, budget adequacy, organisational performance and departmental performance are negatively related.