Search

The mathematician and bio‐scientist Sam Karlin is quoted stating that "The purpose of models is not to fit the data but to sharpen the question". In this paper, we describe a journey between questions, models and data analysis to reach specific goals. This journey is typical in industrial, engineering, biology and social science applications. It contrasts regulated clinical research where a statistical analysis plan is declared before data collection. We consider random forests, ridge regression, lasso and elastic nets. To make our point, we use a case study of 63 sensors collected in the testing of an electronic system. The paper lists a sequence of questions and how they were tackled by statistical analysis to meet the analysis goal. Eventually, we were able to provide a robust parsimonious and effective model for predicting the system condition using a subset of the 63 sensors. In handling this problem, we develop and apply several innovative methods and insights that can prove useful in other contexts. [ABSTRACT FROM AUTHOR]

An introduction is presented in which the editor discusses various articles within the issue on topics including Bayesian estimation approach for degradation process model; problem of clustering data streams using the k‐means algorithm; and detection of outlying rows in a contingency table.

Graphical models allow to represent a set of random variables together with their probabilistic conditional dependencies. Various algorithms have been proposed to estimate such models from data. The focus of this paper is on individual observations diagnosis issues. The use of an influence measure is a classical diagnostic method to measure the perturbation induced by a single element, in other terms we consider stability issue through jackknife. For a given graphical model, we provide tools to perform diagnosis on observations. In a second step we propose a filtering of the dataset to obtain a stable network. All along the paper an application to a gene expression dataset illustrates the proposals. [ABSTRACT FROM AUTHOR]

This paper describes the R package VSURF. Based on random forests, and for both regression and classification problems, it returns two subsets of variables. The first is a subset of important variables including some redundancy which can be relevant for interpretation, and the second one is a smaller subset corresponding to a model trying to avoid redundancy focusing more closely on the prediction objective. The two-stage strategy is based on a preliminary ranking of the explanatory variables using the random forests permutation-based score of importance and proceeds using a stepwise forward strategy for variable introduction. The two proposals can be obtained automatically using data-driven default values, good enough to provide interesting results, but strategy can also be tuned by the user. The algorithm is illustrated on a simulated example and its applications to real datasets are presented. [ABSTRACT FROM AUTHOR]

The authors deal with forecasting nonstationary time series using wavelets and kernel smoothing. Starting from a basic forecasting procedure based on the regression of the process on the nondecimated Haar wavelet coefficients of the past, the procedure was extended in various directions, including the use of an arbitrary wavelet or polynomial fitting for extrapolating low-frequency components. The authors study a further generalization of the prediction procedure dealing with multistep forecasting and combining kernel smoothing and wavelets. They finally illustrate the proposed procedure on nonstationary simulated and real data and then compare it to well-known competitors. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we are interested in the statistical forecasting of the daily mean PM10 concentration. Hourly concentrations of PM10 have been measured in the city of Rouen, in Haute-Normandie, France. Located at northwest of Paris, near the south side of Manche sea and heavily industrialised. We consider three monitoring stations reflecting the diversity of situations: an urban background station, a traffic station and an industrial station near the cereal harbour of Rouen. We have focused our attention on data for the months that register higher values, from December to March, on years 2004–2009. The models are obtained from the winter days of the four seasons 2004/2005 to 2007/2008 (training data) and then the forecasting performance is evaluated on the winter days of the season 2008/2009 (test data). We show that it is possible to accurately forecast the daily mean concentration by fitting a function of meteorological predictors and the average concentration measured on the previous day. The values of observed meteorological variables are used for fitting the models and are also considered for the test data. We have compared the forecasts produced by three different methods: persistence, generalized additive nonlinear models and clusterwise linear regression models. This last method gives very impressive results and the end of the paper tries to analyze the reasons of such a good behavior. [Copyright &y& Elsevier]

Abstract: This paper proposes, focusing on random forests, the increasingly used statistical method for classification and regression problems introduced by Leo Breiman in 2001, to investigate two classical issues of variable selection. The first one is to find important variables for interpretation and the second one is more restrictive and try to design a good parsimonious prediction model. The main contribution is twofold: to provide some experimental insights about the behavior of the variable importance index based on random forests and to propose a strategy involving a ranking of explanatory variables using the random forests score of importance and a stepwise ascending variable introduction strategy. [Copyright &y& Elsevier]

This paper deals with wavelets in time series, focusing on statistical forecasting purposes. Recent approaches involve wavelet decompositions in order to handle non-stationary time series in such context. A method, proposed by Renaud et al.,11 estimates directly the prediction equation by direct regression of the process on the Haar non-decimated wavelet coefficients depending on its past values. In this paper, this method is studied and extended in various directions. The new variants are used first for stationary data and after for stationary data contaminated by a deterministic trend. [ABSTRACT FROM AUTHOR]

We study a family of estimators of the fractal index of a Gaussian process based on the quadratic deviations at different aggregation scales. The estimators are convergent and asymptotically Gaussian when suitably normalized. Confidence intervals are provided. These asymptotic results hold for a large family of stationary-increment models including fractional Brownian motions with square-integrable spectral density. The estimates are applied to the analysis of an electrical signal [ABSTRACT FROM AUTHOR]

We propose a new test for linearity in time series. We consider an asymptotically stationary functional AR(p) model on ℜ[sup d] of the form X[sub n] = f(X[sub n-1] , ..., X[sub n-p] ) + ξ[sub n] (n∈ N). The testing procedure is based on a suitably normalized sum of quadratic deviations between two different estimates of the function f evaluated at q distinct points of ℜ[sup dp] . The estimators are f[sub n] , a recursive version of the non-parametric kernel estimator of f, and Â[sub n] , a least squares estimator well suited to the linear case. The main result states that the test statistic has a χ[sup 2] limit distribution under the null hypothesis. A similar result is derived under the alternative hypothesis for the test statistic corrupted by a non-linear term. Our simulations indicate that our asymptotic results hold for moderate sample sizes when the testing procedure is used carefully [ABSTRACT FROM AUTHOR]

We propose to extend CART for bivariate marked point processes to provide a segmentation of the space into homogeneous areas for interaction between marks. While usual CART tree considers marginal distribution of the response variable at each node, the proposed algorithm, SpatCART, takes into account the spatial location of the observations in the splitting criterion. We introduce a dissimilarity index based on Ripley's intertype K-function quantifying the interaction between two populations. This index used for the growing step of the CART strategy, leads to a heterogeneity function consistent with the original CART algorithm. Therefore the new variant is a way to explore spatial data as a bivariate marked point process using binary classification trees. The proposed procedure is implemented in an R package, and illustrated on simulated examples. SpatCART is finally applied to a tropical forest example. [ABSTRACT FROM AUTHOR]

Ensemble methods, such as Bagging, Boosting, or Random Forests, often enhance the prediction performance of single learners on both classification and regression tasks. In the context of regression, we propose a gradient boosting‐based algorithm incorporating a diversity term with the aim of constructing different learners that enrich the ensemble while achieving a trade‐off of some individual optimality for global enhancement. Verifying the hypotheses of Biau and Cadre's theorem (2021, Advances in contemporary statistics and econometrics—Festschrift in honour of Christine Thomas‐Agnan, Springer), we present a convergence result ensuring that the associated optimization strategy reaches the global optimum. In the experiments, we consider a variety of different base learners with increasing complexity: stumps, regression trees, Purely Random Forests, and Breiman's Random Forests. Finally, we consider simulated and benchmark datasets and a real‐world electricity demand dataset to show, by means of numerical experiments, the suitability of our procedure by examining the behavior not only of the final or the aggregated predictor but also of the whole generated sequence. [ABSTRACT FROM AUTHOR]

This paper characterizes stress levels via a self‐similarity analysis of the electrodermal activity (EDA) collected in a real‐world driving context. To characterize the EDA richness over scales, the fractional Brownian motion (FBM) process and its corresponding exponent H, estimated via a wavelet‐based approach, are used. Specifically, an automatic scale range selection is proposed in order to detect the linearity in a log scale diagram. The procedure is applied to the EDA signals, from the open database drivedb, originally captured on the foot and the hand of the drivers during a real‐world driving experiment, designed to evoke different levels of arousal and stress. The estimated Hurst exponent H offers a distinction in stress levels when driving in highway versus city, with a reference to restful state of minimal stress level. Specifically, the estimated H values tend to decrease when the driving environmental complexity increases. In addition, the estimated H values on the foot EDA signals allow a better characterization of the driving task than that of hand EDA. The self‐similarity analysis was applied to various physiological signals in literature but not to the EDA so far, a signal which was found to correlate most with human affect. The proposed analysis could be useful in real‐time monitoring of stress levels in urban driving spaces, among other applications. [ABSTRACT FROM AUTHOR]

This paper deals with measuring the influence of observations on the results obtained with CART classification trees. To define the influence of individuals on the analysis, we use influence measures to propose criterions to quantify the sensitivity of the CART classification tree analysis. The proposals are based on predictions and use jackknife trees. The analysis is extended to the pruned sequences of CART trees to produce CART specific notions of influence. Using the framework of influence functions, distributional results are derived. A numerical example, the well known spam dataset, is presented to illustrate the notions developed throughout the paper. A real dataset relating the administrative classification of cities surrounding Paris, France, to the characteristics of their tax revenues distribution, is finally analyzed using the new influence-based tools. [ABSTRACT FROM AUTHOR]

Forecasting PM10 concentrations accurately will all for improved early warning procedures, useful for safety reasons and opens for example the possibility to restrict circulation or to decide free public transportation. So the need of a statistical pollution forecasting tool from particulate matter is an important issue for the public authorities. Hourly concentrations of PM10 have been measured in three cities of Haute-Normandie (France): Rouen, Le Havre and Dieppe. The Haute-Normandie region is located at northwest of Paris, near the south side of Manche sea and is heavily industrialized. We consider six monitoring stations reflecting the diversity of situations. We have focused our attention on recent data from 2007 to 2011. We forecast the daily mean PM10 concentration by modeling it as a mixture of linear regression models involving meteorological predictors and the average concentration measured on the previous day. The values of observed meteorological variables are used for fitting the models while the corresponding predictions are considered for the test data, leading to realistic evaluations of forecasting performances, which are calculated through a leave-one-out scheme on the four years. We discuss in this paper several methodological issues including estimation schemes, introduction of the deterministic predictions of meteorological models and how to handle the forecasting at various horizons from some hours to one day ahead. [ABSTRACT FROM AUTHOR]

The understanding of many physical and engineering problems involves running complex computational models. Such models take as input a high number of numerical and physical explanatory variables. The information on these underlying input parameters is often limited or uncertain. It is therefore important, based on the relationships between the input variables and the output, to identify and prioritize the most influential inputs. One may use global sensitivity analysis (GSA) methods which aim at ranking input random variables according to their importance in the output uncertainty, or even quantify the global influence of a particular input on the output. Using sensitivity metrics to ignore less important parameters is a form of dimension reduction in the model's input parameter space. This suggests the use of meta-modeling as a quantitative approach for nonparametric GSA, where the original input/output relation is first approximated using various statistical regression techniques. Subsequently, the main goal of our work is to provide a comprehensive review paper in the domain of sensitivity analysis focusing on some interesting connections between random forests and GSA. The idea is to use a random forests methodology as an efficient non-parametric approach for building meta-models that allow an efficient sensitivity analysis. Apart its easy applicability to regression problems, the random forests approach presents further strong advantages by its ability to implicitly deal with correlation and high dimensional data, to handle interactions between variables and to identify informative inputs using a permutation based RF variable importance index which is easy and fast to compute. We further review an adequate set of tools for quantifying variable importance which are then exploited to reduce the model's dimension enabling otherwise infeasible sensibility analysis studies. Numerical results from several simulations and a data exploration on a real dataset are presented to illustrate the effectiveness of such an approach. • Global Sensitivity Analysis ranks inputs according to their importance on output. • Random Forests is an efficient non-parametric approach for building meta-models. • Random forests variable importance measure is used to define sensitivity measures. • Provide a comprehensive review paper in sensitivity analysis using random forests. • Focus on connections between random forests and Global Sensitivity Analysis. [ABSTRACT FROM AUTHOR]

We present two strategies for detecting patterns and clusters in high-dimensional timedependent functional data. The use on wavelet-based similarity measures, since wavelets are well suited for identifying highly discriminant local time and scale features. The multiresolution aspect of the wavelet transform provides a time-scale decomposition of the signals allowing to visualize and to cluster the functional data into homogeneous groups. For each input function, through its empirical orthogonal wavelet transform the first strategy uses the distribution of energy across scales to generate a representation that can be sufficient to make the signals well distinguishable. Our new similarity measure combined with an efficient feature selection technique in the wavelet domain is then used within more or less classical clustering algorithms to effectively differentiate among high-dimensional populations. The second strategy uses a similarity measure between the whole time-scale representations that is based on wavelet-coherence tools. The clustering is then performed using a k-centroid algorithm starting from these similarities. Practical performance is illustrated through simulations as well as daily profiles of the French electricity power demand [ABSTRACT FROM AUTHOR]

The field of electric vehicle charging load modelling has been growing rapidly in the last decade. In light of the Paris Agreement, it is crucial to keep encouraging better modelling techniques for successful electric vehicle adoption. Additionally, numerous papers highlight the lack of charging station data available in order to build models that are consistent with reality. In this context, the purpose of this article is threefold. First, to provide the reader with an overview of the open datasets available and ready to be used in order to foster reproducible research in the field. Second, to review electric vehicle charging load models with their strengths and weaknesses. Third, to provide suggestions on matching the models reviewed to six datasets found in this research that have not previously been explored in the literature. The open data search covered more than 860 repositories and yielded around 60 datasets that are relevant for modelling electric vehicle charging load. These datasets include information on charging point locations, historical and real-time charging sessions, traffic counts, travel surveys and registered vehicles. The models reviewed range from statistical characterization to stochastic processes and machine learning and the context of their application is assessed. [ABSTRACT FROM AUTHOR]

Smart grids require flexible data driven forecasting methods. We propose clustering tools for bottom-up short-term load forecasting. We focus on individual consumption data analysis which plays a major role for energy management and electricity load forecasting. The first section is dedicated to the industrial context and a review of individual electrical data analysis. Then, we focus on hierarchical time-series for bottom-up forecasting. The idea is to decompose the global signal and obtain disaggregated forecasts in such a way that their sum enhances the prediction. This is done in three steps: identify a rather large number of super-consumers by clustering their energy profiles, generate a hierarchy of nested partitions and choose the one that minimize a prediction criterion. Using a nonparametric model to handle forecasting, and wavelets to define various notions of similarity between load curves, this disaggregation strategy gives a 16% improvement in forecasting accuracy when applied to French individual consumers. Then, this strategy is implemented using R—the free software environment for statistical computing—so that it can scale when dealing with massive datasets. The proposed solution is to make the algorithm scalable combine data storage, parallel computing and double clustering step to define the super-consumers. The resulting software is openly available. [ABSTRACT FROM AUTHOR]