Improving generalized regression analysis for the spatial prediction of forest communities

Aim This study used data from temperate forest communities to assess: (1) five different stepwise selection methods with generalized additive models, (2) the effect of weighting absences to ensure a prevalence of 0.5, (3) the effect of limiting absences beyond the environmental envelope defined by presences, (4) four different methods for incorporating spatial autocorrelation, and (5) the effect of integrating an interaction factor defined by a regression tree on the residuals of an initial environmental model. Location State of Vaud, western Switzerland. Methods Generalized additive models (GAMs) were fitted using the grasp package (generalized regression analysis and spatial predictions, http://www.cscf.ch/grasp). Results Model selection based on cross-validation appeared to be the best compromise between model stability and performance (parsimony) among the five methods tested. Weighting absences returned models that perform better than models fitted with the original sample prevalence. This appeared to be mainly due to the impact of very low prevalence values on evaluation statistics. Removing zeroes beyond the range of presences on main environmental gradients changed the set of selected predictors, and potentially their response curve shape. Moreover, removing zeroes slightly improved model performance and stability when compared with the baseline model on the same data set. Incorporating a spatial trend predictor improved model performance and stability significantly. Even better models were obtained when including local spatial autocorrelation. A novel approach to include interactions proved to be an efficient way to account for interactions between all predictors at once. Main conclusions Models and spatial predictions of 18 forest communities were significantly improved by using either: (1) cross-validation as a model selection method, (2) weighted absences, (3) limited absences, (4) predictors accounting for spatial autocorrelation, or (5) a factor variable accounting for interactions between all predictors. The final choice of model strategy should depend on the nature of the available data and the specific study aims. Statistical evaluation is useful in searching for the best modelling practice. However, one should not neglect to consider the shapes and interpretability of response curves, as well as the resulting spatial predictions in the final assessment.

Automatic classification of MR scans in Alzheimer's disease.

To be diagnostically useful, structural MRI must reliably distinguish Alzheimer's disease (AD) from normal aging in individual scans. Recent advances in statistical learning theory have led to the application of support vector machines to MRI for detection of a variety of disease states. The aims of this study were to assess how successfully support vector machines assigned individual diagnoses and to determine whether data-sets combined from multiple scanners and different centres could be used to obtain effective classification of scans. We used linear support vector machines to classify the grey matter segment of T1-weighted MR scans from pathologically proven AD patients and cognitively normal elderly individuals obtained from two centres with different scanning equipment. Because the clinical diagnosis of mild AD is difficult we also tested the ability of support vector machines to differentiate control scans from patients without post-mortem confirmation. Finally we sought to use these methods to differentiate scans between patients suffering from AD from those with frontotemporal lobar degeneration. Up to 96% of pathologically verified AD patients were correctly classified using whole brain images. Data from different centres were successfully combined achieving comparable results from the separate analyses. Importantly, data from one centre could be used to train a support vector machine to accurately differentiate AD and normal ageing scans obtained from another centre with different subjects and different scanner equipment. Patients with mild, clinically probable AD and age/sex matched controls were correctly separated in 89% of cases which is compatible with published diagnosis rates in the best clinical centres. This method correctly assigned 89% of patients with post-mortem confirmed diagnosis of either AD or frontotemporal lobar degeneration to their respective group. Our study leads to three conclusions: Firstly, support vector machines successfully separate patients with AD from healthy aging subjects. Secondly, they perform well in the differential diagnosis of two different forms of dementia. Thirdly, the method is robust and can be generalized across different centres. This suggests an important role for computer based diagnostic image analysis for clinical practice.

Taking "Galton's problem" Seriously : Towards a Theory of Policy Diffusion

This article builds on the recent policy diffusion literature and attempts to overcome one of its major problems, namely the lack of a coherent theoretical framework. The literature defines policy diffusion as a process where policy choices are interdependent, and identifies several diffusion mechanisms that specify the link between the policy choices of the various actors. As these mechanisms are grounded in different theories, theoretical accounts of diffusion currently have little internal coherence. In this article we put forward an expected-utility model of policy change that is able to subsume all the diffusion mechanisms. We argue that the expected utility of a policy depends on both its effectiveness and the payoffs it yields, and we show that the various diffusion mechanisms operate by altering these two parameters. Each mechanism affects one of the two parameters, and does so in distinct ways. To account for aggregate patterns of diffusion, we embed our model in a simple threshold model of diffusion. Given the high complexity of the process that results, strong analytical conclusions on aggregate patterns cannot be drawn without more extensive analysis which is beyond the scope of this article. However, preliminary considerations indicate that a wide range of diffusion processes may exist and that convergence is only one possible outcome.

Statistical learning theory for geospatial data. Case study: Aral sea

In recent years there has been an explosive growth in the development of adaptive and data driven methods. One of the efficient and data-driven approaches is based on statistical learning theory (Vapnik 1998). The theory is based on Structural Risk Minimisation (SRM) principle and has a solid statistical background. When applying SRM we are trying not only to reduce training error ? to fit the available data with a model, but also to reduce the complexity of the model and to reduce generalisation error. Many nonlinear learning procedures recently developed in neural networks and statistics can be understood and interpreted in terms of the structural risk minimisation inductive principle. A recent methodology based on SRM is called Support Vector Machines (SVM). At present SLT is still under intensive development and SVM find new areas of application (www.kernel-machines.org). SVM develop robust and non linear data models with excellent generalisation abilities that is very important both for monitoring and forecasting. SVM are extremely good when input space is high dimensional and training data set i not big enough to develop corresponding nonlinear model. Moreover, SVM use only support vectors to derive decision boundaries. It opens a way to sampling optimization, estimation of noise in data, quantification of data redundancy etc. Presentation of SVM for spatially distributed data is given in (Kanevski and Maignan 2004).

Comparison of the glomerular filtration rate in children by the new revised Schwartz formula and a new generalized formula.

The most widely used formula for estimating glomerular filtration rate (eGFR) in children is the Schwartz formula. It was revised in 2009 using iohexol clearances with measured GFR (mGFR) ranging between 15 and 75 ml/min × 1.73 m(2). Here we assessed the accuracy of the Schwartz formula using the inulin clearance (iGFR) method to evaluate its accuracy for children with less renal impairment comparing 551 iGFRs of 392 children with their Schwartz eGFRs. Serum creatinine was measured using the compensated Jaffe method. In order to find the best relationship between iGFR and eGFR, a linear quadratic regression model was fitted and a more accurate formula was derived. This quadratic formula was: 0.68 × (Height (cm)/serum creatinine (mg/dl))-0.0008 × (height (cm)/serum creatinine (mg/dl))(2)+0.48 × age (years)-(21.53 in males or 25.68 in females). This formula was validated using a split-half cross-validation technique and also externally validated with a new cohort of 127 children. Results show that the Schwartz formula is accurate until a height (Ht)/serum creatinine value of 251, corresponding to an iGFR of 103 ml/min × 1.73 m(2), but significantly unreliable for higher values. For an accuracy of 20 percent, the quadratic formula was significantly better than the Schwartz formula for all patients and for patients with a Ht/serum creatinine of 251 or greater. Thus, the new quadratic formula could replace the revised Schwartz formula, which is accurate for children with moderate renal failure but not for those with less renal impairment or hyperfiltration.

Inclusive fitness theory and eusociality.

Arising from M. A. Nowak, C. E. Tarnita & E. O. Wilson 466, 1057-1062 (2010); Nowak et al. reply. Nowak et al. argue that inclusive fitness theory has been of little value in explaining the natural world, and that it has led to negligible progress in explaining the evolution of eusociality. However, we believe that their arguments are based upon a misunderstanding of evolutionary theory and a misrepresentation of the empirical literature. We will focus our comments on three general issues.

Social Cognition is not Reducible to Theory of Mind. When Children use Deontic Rules to Predict Others' Behaviors

The objective of this paper is to discuss whether children have a capacity for deonticreasoning that is irreducible to mentalizing. The results of two experiments point tothe existence of such non-mentalistic understanding and prediction of the behaviourof others. In Study 1, young children (3- and 4-year-olds) were told different versionsof classic false-belief tasks, some of which were modified by the introduction of a ruleor a regularity. When the task (a standard change of location task) included a rule, theperformance of 3-year-olds, who fail traditional false-belief tasks, significantly improved.In Study 2, 3-year-olds proved to be able to infer a rule from a social situation and touse it in order to predict the behaviour of a character involved in a modified versionof the false-belief task. These studies suggest that rules play a central role in the socialcognition of young children and that deontic reasoning might not necessarily involvemind reading.

Ispol'zovanie metodov teorii vosstanovleniia v modeliakh optimal'nogo dobyvaniia pishchi [Restoration theory in models of optimal feeding behavior]

The method of stochastic dynamic programming is widely used in ecology of behavior, but has some imperfections because of use of temporal limits. The authors presented an alternative approach based on the methods of the theory of restoration. Suggested method uses cumulative energy reserves per time unit as a criterium, that leads to stationary cycles in the area of states. This approach allows to study the optimal feeding by analytic methods.

On the efficiency of recursive evaluations with applications to risk theory

On the efficiency of recursive evaluations with applications to risk theoryCette thèse est composée de trois essais qui portent sur l'efficacité des évaluations récursives de la distribution du montant total des sinistres d'un portefeuille de polices d'assurance au cours d'un période donnée. Le calcul de sa fonction de probabilité ou de quantités liées à cette distribution apparaît fréquemment dans la plupart des domaines de la pratique actuarielle.C'est le cas notamment pour le calcul du capital de solvabilité en Suisse ou pour modéliser la perte d'une assurance vie au cours d'une année. Le principal problème des évaluations récursives est que la propagation des erreurs provenant de la représentation des nombres réels par l'ordinateur peut être désastreuse. Mais, le gain de temps qu'elles procurent en réduisant le nombre d'opérations arithmétiques est substantiel par rapport à d'autres méthodes.Dans le premier essai, nous utilisons certaines propriétés d'un outil informatique performant afin d'optimiser le temps de calcul tout en garantissant une certaine qualité dans les résultats par rapport à la propagation de ces erreurs au cours de l'évaluation.Dans le second essai, nous dérivons des expressions exactes et des bornes pour les erreurs qui se produisent dans les fonctions de distribution cumulatives d'un ordre donné lorsque celles-ci sont évaluées récursivement à partir d'une approximation de la transformée de De Pril associée. Ces fonctions cumulatives permettent de calculer directement certaines quantités essentielles comme les primes stop-loss.Finalement, dans le troisième essai, nous étudions la stabilité des évaluations récursives de ces fonctions cumulatives par rapport à la propagation des erreurs citées ci-dessus et déterminons la précision nécessaire dans la représentation des nombres réels afin de garantir des résultats satisfaisants. Cette précision dépend en grande partie de la transformée de De Pril associée.

Ruin Theory with Excess of Loss Reinsurance and Reinstatements

The present paper studies the probability of ruin of an insurer, if excess of loss reinsurance with reinstatements is applied. In the setting of the classical Cramer-Lundberg risk model, piecewise deterministic Markov processes are used to describe the free surplus process in this more general situation. It is shown that the finite-time ruin probability is both the solution of a partial integro-differential equation and the fixed point of a contractive integral operator. We exploit the latter representation to develop and implement a recursive algorithm for numerical approximation of the ruin probability that involves high-dimensional integration. Furthermore we study the behavior of the finite-time ruin probability under various levels of initial surplus and security loadings and compare the efficiency of the numerical algorithm with the computational alternative of stochastic simulation of the risk process. (C) 2011 Elsevier Inc. All rights reserved.