Varying-time random effects models for longitudinal data: unmixing and temporal interpolation of remote-sensing data

Remote sensing is a helpful tool for crop monitoring or vegetation-growth estimation at a country or regional scale. However, satellite images generally have to cope with a compromise between the time frequency of observations and their resolution (i.e. pixel size). When concerned with high temporal resolution, we have to work with information on the basis of kilometric pixels, named mixed pixels, that represent aggregated responses of multiple land cover. Disaggreggation or unmixing is then necessary to downscale from the square kilometer to the local dynamic of each theme (crop, wood, meadows, etc.).

Assuming the land use is known, that is to say the proportion of each theme within each mixed pixel, we propose to address the downscaling issue through the generalization of varying-time regression models for longitudinal data and/or functional data by introducing random individual effects. The estimators are built by expanding the mixed pixels trajectories with B-splines functions and maximizing the log-likelihood with a backfitting-ECME algorithm. A BLUP formula allows then to get the ‘best possible’ estimations of the local temporal responses of each crop when observing mixed pixels trajectories. We show that this model has many potential applications in remote sensing, and an interesting one consists of coupling high and low spatial resolution images in order to perform temporal interpolation of high spatial resolution images (20 m), increasing the knowledge on particular crops in very precise locations.

The unmixing and temporal high-resolution interpolation approaches are illustrated on remote-sensing data obtained on the South-Western France during the year 2002.     

The Consistency and Robustness of Modified Cramér–Von Mises and Kolmogorov–Cramér Estimators

This article focuses on the minimum distance estimators under two newly introduced modifications of Cramér–von Mises distance. The generalized power form of Cramér–von Mises distance is defined together with the so-called Kolmogorov–Cramér distance which includes both standard Kolmogorov and Cramér–von Mises distances as limiting special cases. We prove the consistency of Kolmogorov-Cramér estimators in the (expected) L₁-norm by direct technique employing domination relations between statistical distances. In our numerical simulation we illustrate the quality of consistency property for sample sizes of the most practical range from n = 10 to n = 500. We study dependence of consistency in L₁-norm on ?-contamination neighborhood of the true model and further the robustness of these two newly defined estimators for normal families and contaminated samples. Numerical simulations are used to compare statistical properties of the minimum Kolmogorov–Cramér, generalized Cramér–von Mises, standard Kolmogorov, and Cramér–von Mises distance estimators of the normal family scale parameter. We deal with the corresponding order of consistency and robustness. The resulting graphs are presented and discussed for the cases of the contaminated and uncontaminated pseudo-random samples.     

Statistics,images, and pattern recognition

Data are increasingly being collected in the form of images, especially in fields using remote sensing and microscopy. Statisticians are becoming interested in developing techniques to handle the highly structured data of images. Statistical work in this area is surveyed, and two problems discussed in more detail. The first is a form of image segmentation, classifying the pixels of a satellite picture by land use. The second is the summarization of electron micrographs.     

Large-scale Bayesian spatial modelling of air pollution for policy support

The potential effects of air pollution are a major concern both in terms of the environment and in relation to human health. In order to support environmental policy, there is a need for accurate measurements of the concentrations of pollutants at high geographical resolution over large regions. However, within such regions, there are likely to be areas where the monitoring information will be sparse and so methods are required to accurately predict concentrations. Set within a Bayesian framework, models are developed which exploit the relationships between pollution and geographical covariate information, such as land use, climate and transport variables together with spatial structure. Candidate models are compared based on their ability to predict a set of validation sites. The chosen model is used to perform large-scale prediction of nitrogen dioxide at a 1×1 km resolution for the entire EU. The models allow probabilistic statements to be made with regard to the levels of air pollution that might be experienced in each area. When combined with population data, such information can be invaluable in informing policy by indicating areas for which improvements may be given priority.     

Estimation and goodness-of-fit procedures for Farlie–Gumbel–Morgenstern bivariate copula of order statistics

In this study, we provide the Farlie–Gumbel–Morgenstern bivariate copula of rth and sth order statistics. The main emphasis in this study is on the inference procedure which is based on the maximum pseudo-likelihood estimate for the copula parameter. As for the methodology, goodness-of-fit test statistic for copulas which is based on a Cramér–von Mises functional of the empirical copula process is applied for selecting an appropriate model by bootstrapping. An application of the methodology to simulated data set is also presented.     

The modified Fréchet distribution and its properties

The Fréchet distribution is an absolutely continuous model which has wide applicability in extreme value theory. In this paper, we propose a new three-parameter model, so-called the modified Fréchet distribution, to extend the Fréchet distribution. By using the Lambert function, we obtain some properties of the new distribution. We provide a simulation study to illustrate the performance of the maximum likelihood estimates. The flexibility of the introduced distribution is illustrated by means of a real data set. We use some goodness-of-fit statistics to verify the adequacy of the proposed model. We prove empirically that it is appropriate for lifetime applications.     

Spatial Modeling of Habitat Preferences of Biological Species using Markov Random Fields

Spatial modeling has gained interest in ecology during the past two decades, especially in the area of biodiversity, where reliable distribution maps are required. Several methods have been proposed to construct distribution maps, most of them acknowledging the presence of spatial interactions. In many cases, a key problem is the lack of true absence data. We present here a model suitable for use when true absence data are missing. The quality of the estimates obtained from the model is evaluated using ROC curve analysis as well as a quadratic cost function, computed from the false positive and false negative error rates. The model is also tested under random and clustered scattering of the presence records. We also present an application of the model to the construction of distribution maps of two endemic bird species in México.     

Pricing longevity-linked derivatives using a stochastic mortality model

Abstract

We propose a 2-factor MBMM model with exponential Lévy process to develop a stochastic mortality process. The two components are fitted by two independent NIG distributions. Compared to Lee–Carter model or 1-factor MBMM model, our mortality model explains more variation and improves the goodness of fit by including the second time component. Based on the improved model, we price three longevity-linked financial instruments, namely the longevity bond, q-forward and s-forward. The pricing is demonstrated on English and Welsh males aged 65 in 2013. Results indicate that the 2-factor MBMM model gives the highest price for mortality-related type of contract.     

Curve prediction and clustering with mixtures of Gaussian process functional regression models

Shi, Wang, Murray-Smith and Titterington (Biometrics 63:714–723, 2007) proposed a Gaussian process functional regression (GPFR) model to model functional response curves with a set of functional covariates. Two main problems are addressed by their method: modelling nonlinear and nonparametric regression relationship and modelling covariance structure and mean structure simultaneously. The method gives very good results for curve fitting and prediction but side-steps the problem of heterogeneity. In this paper we present a new method for modelling functional data with ‘spatially’ indexed data, i.e., the heterogeneity is dependent on factors such as region and individual patient’s information. For data collected from different sources, we assume that the data corresponding to each curve (or batch) follows a Gaussian process functional regression model as a lower-level model, and introduce an allocation model for the latent indicator variables as a higher-level model. This higher-level model is dependent on the information related to each batch. This method takes advantage of both GPFR and mixture models and therefore improves the accuracy of predictions. The mixture model has also been used for curve clustering, but focusing on the problem of clustering functional relationships between response curve and covariates, i.e. the clustering is based on the surface shape of the functional response against the set of functional covariates. The model is examined on simulated data and real data.     

Explaining and Forecasting Online Auction Prices and Their Dynamics Using Functional Data Analysis

Online auctions have become increasingly popular in recent years, and as a consequence there is a growing body of empirical research on this topic. Most of that research treats data from online auctions as cross-sectional, and consequently ignores the changing dynamics that occur during an auction. In this article we take a different look at online auctions and propose to study an auction's price evolution and associated price dynamics. Specifically, we develop a dynamic forecasting system to predict the price of an ongoing auction. By dynamic, we mean that the model can predict the price of an auction “in progress” and can update its prediction based on newly arriving information. Forecasting price in online auctions is challenging because traditional forecasting methods cannot adequately account for two features of online auction data: (1) the unequal spacing of bids and (2) the changing dynamics of price and bidding throughout the auction. Our dynamic forecasting model accounts for these special features by using modern functional data analysis techniques. Specifically, we estimate an auction's price velocity and acceleration and use these dynamics, together with other auction-related information, to develop a dynamic functional forecasting model. We also use the functional context to systematically describe the empirical regularities of auction dynamics. We apply our method to a novel set of Harry Potter and Microsoft Xbox data and show that our forecasting model outperforms traditional methods.     

Residual Kriging for Functional Spatial Prediction of Salinity Curves

Recently, several methodologies to perform geostatistical analysis of functional data have been proposed. All of them assume that the spatial functional process considered is stationary. However, in practice, we often have nonstationary functional data because there exists an explicit spatial trend in the mean. Here, we propose a methodology to extend kriging predictors for functional data to the case where the mean function is not constant through the region of interest. We consider an approach based on the classical residual kriging method used in univariate geostatistics. We propose a three steps procedure. Initially, a functional regression model is used to detrend the mean. Then we apply kriging methods for functional data to the regression residuals to predict a residual curve at a non-data location. Finally, the prediction curve is obtained as the sum of the trend and the residual prediction. We apply the methodology to salinity data corresponding to 21 salinity curves recorded at the Ciénaga Grande de Santa Marta estuary, located in the Caribbean coast of Colombia. A cross-validation analysis was carried out to track the performance of the proposed methodology.     

On Cramér–von Mises type test based on local time of switching diffusion process

We consider a Cramér–von Mises type test for hypothesis that the observed diffusion process has sign-type trend coefficient based on empirical density function. It is shown that the limit distribution of the proposed test statistic is defined by the integral type functional of continuous Gaussian process. We provide the Karhunen–Loève expansion of the corresponding limiting process. Approximation of the threshold is given through the representation for the limit statistic.     

Determinants of Contraceptive Use in Egypt: A Multilevel Approach

The increasing use of family planning methods seems to be the intermediate determinant which mostly influences the fertility decline in developing countries, and in particular in those countries which are in an advanced phase of demographic transition such as Egypt. Moreover large countries, like Egypt, are characterized by very different geographical realities and even by strong regional heterogeneities. The aim of this study is the analysis of the determinants of contraceptive use in Egypt, with particular reference to the differentials due to the socio-economic context and to the area of residence. To estimate each individual and regional factors’ effect on contraceptive use, a logistic two-level random intercept model is fitted to EDHS 2000 data; the use of a multilevel analysis is suggested by the two-level data structure: the first level units are the women, the second level units are their regions of residence.     

Nonlinear mixed-effects scalar-on-function models and variable selection

This paper is motivated by our collaborative research and the aim is to model clinical assessments of upper limb function after stroke using 3D-position and 4D-orientation movement data. We present a new nonlinear mixed-effects scalar-on-function regression model with a Gaussian process prior focusing on the variable selection from a large number of candidates including both scalar and function variables. A novel variable selection algorithm has been developed, namely functional least angle regression. As it is essential for this algorithm, we studied the representation of functional variables with different methods and the correlation between a scalar and a group of mixed scalar and functional variables. We also propose a new stopping rule for practical use. This algorithm is efficient and accurate for both variable selection and parameter estimation even when the number of functional variables is very large and the variables are correlated. And thus the prediction provided by the algorithm is accurate. Our comprehensive simulation study showed that the method is superior to other existing variable selection methods. When the algorithm was applied to the analysis of the movement data, the use of the nonlinear random-effect model and the function variables significantly improved the prediction accuracy for the clinical assessment.

     

A neighbourhood-based classifier for landsat data

A classifier is developed which uses information from all pixels in a neighbourhood to classify the pixel at the center of the neighbourhood. It is not a smoother in that it tries to recognize boundaries. and it makes explieite use of the relative positions of pixels in the neighbourhood. It is based on a geometric probability model for the distribution of the classes in the plane. The neighbourhood-based classifier is shown to outperform linear discriminant analysis on some LANDSAT data.     

Corrected empirical Bayes confidence intervals in nested error regression models

In the small area estimation, the empirical best linear unbiased predictor (EBLUP) or the empirical Bayes estimator (EB) in the linear mixed model is recognized to be useful because it gives a stable and reliable estimate for a mean of a small area. In practical situations where EBLUP is applied to real data, it is important to evaluate how much EBLUP is reliable. One method for the purpose is to construct a confidence interval based on EBLUP. In this paper, we obtain an asymptotically corrected empirical Bayes confidence interval in a nested error regression model with unbalanced sample sizes and unknown components of variance. The coverage probability is shown to satisfy the confidence level in the second-order asymptotics. It is numerically revealed that the corrected confidence interval is superior to the conventional confidence interval based on the sample mean in terms of the coverage probability and the expected width of the interval. Finally, it is applied to the posted land price data in Tokyo and the neighboring prefecture.     

Functional principal component analysis of spatially correlated data

This paper focuses on the analysis of spatially correlated functional data. We propose a parametric model for spatial correlation and the between-curve correlation is modeled by correlating functional principal component scores of the functional data. Additionally, in the sparse observation framework, we propose a novel approach of spatial principal analysis by conditional expectation to explicitly estimate spatial correlations and reconstruct individual curves. Assuming spatial stationarity, empirical spatial correlations are calculated as the ratio of eigenvalues of the smoothed covariance surface Cov\((X_i(s),X_i(t))\) and cross-covariance surface Cov\((X_i(s), X_j(t))\) at locations indexed by i and j. Then a anisotropy Matérn spatial correlation model is fitted to empirical correlations. Finally, principal component scores are estimated to reconstruct the sparsely observed curves. This framework can naturally accommodate arbitrary covariance structures, but there is an enormous reduction in computation if one can assume the separability of temporal and spatial components. We demonstrate the consistency of our estimates and propose hypothesis tests to examine the separability as well as the isotropy effect of spatial correlation. Using simulation studies, we show that these methods have some clear advantages over existing methods of curve reconstruction and estimation of model parameters.     

Applications of Marshall–Olkin Fréchet Distribution

In this article, we consider the applications of Marshall–Olkin Fréchet distribution. The reliability of a system when both stress and strength follows the new distribution is discussed and related characteristics are computed for simulated data. The model is applied to a real data set on failure times of air-conditioning systems in jet planes and reliability is estimated. We also develop acceptance sampling plan for the acceptance of a lot whose lifetime follows this distribution. Four different autoregressive time series models of order 1 are developed with minification structure as well as max-min structure having these stationary marginal distributions. Some properties of the models are also established.     

Asymmetric exchange between populations differing in habitat quality: A metapopulation study on the citril finch

The citril finch ( Serinus citrinella ) is a Cardueline finch restricted to the high mountains of western Europe. Since 1991 we have captured-recaptured about 6000 birds in two contrasting subpopulations located on the same mountain but separated by 5 km in distance. Citril finches, at the north-facing locality (La Vansa), rely more on Pine trees ( Pinus uncinata ) as their main food source, than birds at the south-facing locality (La Bofia), which rely more on herb seeds, which are of lower energetic content. Birds at La Vansa had higher body mass and fat score than those at La Bofia, suggesting that La Vansa was a site of higher-quality than La Bofia. By the use of a metapopulation approach and multistate models, we found that citril finches at the high-quality locality (La Vansa) showed higher survival rates than those at the low-quality one (La Bofia) (Vansa adults: φ = 0.42 - 0.04, juveniles: φ = 0.34 - 0.05; Bofia adults: φ = 0.35 - 0.04, juveniles: φ = 0.28 - 0.05). Dispersal was also asymmetric and higher for juvenile birds, with movement rates for juvenile citril finches from the low-quality to the higher-quality locality (Bofia to Vansa: é = 0.38 - 0.10) higher than the reverse (Vansa to Bofia: é = 0.09 - 0.03). We also investigated time-specific factors (e.g. meteorological data and fructification rate of Pinus ) as potential predictors of overall mortality and dispersal patterns. The results do not allow strong conclusions regarding the impact of these factors on survival and movement rates. Patterns of movement found in the Citril Finch between localities document a new model for the dispersal of species from low to high quality habitats, which we label of 'sources and pools'. This contrasts with currently accepted models of 'sources and sinks', in which movement is from high to low quality habitats, and 'Ideal Free Distributions', in which there is a balanced dispersal between habitats of different quality.     

Investigation of the performance of trimmed estimators of life time distributions with censoring

For the lifetime (or negative) exponential distribution, the trimmed likelihood estimator has been shown to be explicit in the form of a β‐trimmed mean which is representable as an estimating functional that is both weakly continuous and Fréchet differentiable and hence qualitatively robust at the parametric model. It also has high efficiency at the model. The robustness is in contrast to the maximum likelihood estimator (MLE) involving the usual mean which is not robust to contamination in the upper tail of the distribution. When there is known right censoring, it may be perceived that the MLE which is the most asymptotically efficient estimator may be protected from the effects of ‘outliers’ due to censoring. We demonstrate that this is not the case generally, and in fact, based on the functional form of the estimators, suggest a hybrid defined estimator that incorporates the best features of both the MLE and the β‐trimmed mean. Additionally, we study the pure trimmed likelihood estimator for censored data and show that it can be easily calculated and that the censored observations are not always trimmed. The different trimmed estimators are compared by a modest simulation study.