Inférence robuste à la présence des valeurs aberrantes dans les enquêtes

Cette thèse comporte trois articles dont un est publié et deux en préparation. Le sujet central de la thèse porte sur le traitement des valeurs aberrantes représentatives dans deux aspects importants des enquêtes que sont : l’estimation des petits domaines et l’imputation en présence de non-réponse partielle. En ce qui concerne les petits domaines, les estimateurs robustes dans le cadre des modèles au niveau des unités ont été étudiés. Sinha & Rao (2009) proposent une version robuste du meilleur prédicteur linéaire sans biais empirique pour la moyenne des petits domaines. Leur estimateur robuste est de type «plugin», et à la lumière des travaux de Chambers (1986), cet estimateur peut être biaisé dans certaines situations. Chambers et al. (2014) proposent un estimateur corrigé du biais. En outre, un estimateur de l’erreur quadratique moyenne a été associé à ces estimateurs ponctuels. Sinha & Rao (2009) proposent une procédure bootstrap paramétrique pour estimer l’erreur quadratique moyenne. Des méthodes analytiques sont proposées dans Chambers et al. (2014). Cependant, leur validité théorique n’a pas été établie et leurs performances empiriques ne sont pas pleinement satisfaisantes. Ici, nous examinons deux nouvelles approches pour obtenir une version robuste du meilleur prédicteur linéaire sans biais empirique : la première est fondée sur les travaux de Chambers (1986), et la deuxième est basée sur le concept de biais conditionnel comme mesure de l’influence d’une unité de la population. Ces deux classes d’estimateurs robustes des petits domaines incluent également un terme de correction pour le biais. Cependant, ils utilisent tous les deux l’information disponible dans tous les domaines contrairement à celui de Chambers et al. (2014) qui utilise uniquement l’information disponible dans le domaine d’intérêt. Dans certaines situations, un biais non négligeable est possible pour l’estimateur de Sinha & Rao (2009), alors que les estimateurs proposés exhibent un faible biais pour un choix approprié de la fonction d’influence et de la constante de robustesse. Les simulations Monte Carlo sont effectuées, et les comparaisons sont faites entre les estimateurs proposés et ceux de Sinha & Rao (2009) et de Chambers et al. (2014). Les résultats montrent que les estimateurs de Sinha & Rao (2009) et de Chambers et al. (2014) peuvent avoir un biais important, alors que les estimateurs proposés ont une meilleure performance en termes de biais et d’erreur quadratique moyenne. En outre, nous proposons une nouvelle procédure bootstrap pour l’estimation de l’erreur quadratique moyenne des estimateurs robustes des petits domaines. Contrairement aux procédures existantes, nous montrons formellement la validité asymptotique de la méthode bootstrap proposée. Par ailleurs, la méthode proposée est semi-paramétrique, c’est-à-dire, elle n’est pas assujettie à une hypothèse sur les distributions des erreurs ou des effets aléatoires. Ainsi, elle est particulièrement attrayante et plus largement applicable. Nous examinons les performances de notre procédure bootstrap avec les simulations Monte Carlo. Les résultats montrent que notre procédure performe bien et surtout performe mieux que tous les compétiteurs étudiés. Une application de la méthode proposée est illustrée en analysant les données réelles contenant des valeurs aberrantes de Battese, Harter & Fuller (1988). S’agissant de l’imputation en présence de non-réponse partielle, certaines formes d’imputation simple ont été étudiées. L’imputation par la régression déterministe entre les classes, qui inclut l’imputation par le ratio et l’imputation par la moyenne sont souvent utilisées dans les enquêtes. Ces méthodes d’imputation peuvent conduire à des estimateurs imputés biaisés si le modèle d’imputation ou le modèle de non-réponse n’est pas correctement spécifié. Des estimateurs doublement robustes ont été développés dans les années récentes. Ces estimateurs sont sans biais si l’un au moins des modèles d’imputation ou de non-réponse est bien spécifié. Cependant, en présence des valeurs aberrantes, les estimateurs imputés doublement robustes peuvent être très instables. En utilisant le concept de biais conditionnel, nous proposons une version robuste aux valeurs aberrantes de l’estimateur doublement robuste. Les résultats des études par simulations montrent que l’estimateur proposé performe bien pour un choix approprié de la constante de robustesse.

Development of a Technique for Estimating Rain Parameters from Rain Noise Measurements

The measurement of global precipitation is of great importance in climate modeling since the release of latent heat associated with tropical convection is one of the pricipal driving mechanisms of atmospheric circulation.Knowledge of the larger-scale precipitation field also has important potential applications in the generation of initial conditions for numerical weather prediction models Knowledge of the relationship between rainfall intensity and kinetic energy, and its variations in time and space is important for erosion prediction. Vegetation on earth also greatly depends on the total amount of rainfall as well as the drop size distribution (DSD) in rainfall.While methods using visible,infrared, and microwave radiometer data have been shown to yield useful estimates of precipitation, validation of these products for the open ocean has been hampered by the limited amount of surface rainfall measurements available for accurate assessement, especially for the tropical oceans.Surface rain fall measurements(often called the ground truth)are carried out by rain gauges working on various principles like weighing type,tipping bucket,capacitive type and so on.The acoustic technique is yet another promising method of rain parameter measurement that has many advantages. The basic principle of acoustic method is that the droplets falling in water produce underwater sound with distinct features, using which the rainfall parameters can be computed. The acoustic technique can also be used for developing a low cost and accurate device for automatic measurement of rainfall rate and kinetic energy of rain.especially suitable for telemetry applications. This technique can also be utilized to develop a low cost Disdrometer that finds application in rainfall analysis as well as in calibration of nozzles and sprinklers. This thesis is divided into the following 7 chapters, which describes the methodology adopted, the results obtained and the conclusions arrived at.

Characterizations of Life Distributions Using Conditional Expectations of Doubly (Interval) Truncated Random Variables

In this article, we study reliability measures such as geometric vitality function and conditional Shannon’s measures of uncertainty proposed by Ebrahimi (1996) and Sankaran and Gupta (1999), respectively, for the doubly (interval) truncated random variables. In survival analysis and reliability engineering, these measures play a significant role in studying the various characteristics of a system/component when it fails between two time points. The interrelationships among these uncertainty measures for various distributions are derived and proved characterization theorems arising out of them

Characterizations of Bivariate Models Using Some Dynamic Conditional Information Divergence Measures

In this article, we study some relevant information divergence measures viz. Renyi divergence and Kerridge’s inaccuracy measures. These measures are extended to conditionally specifiedmodels and they are used to characterize some bivariate distributions using the concepts of weighted and proportional hazard rate models. Moreover, some bounds are obtained for these measures using the likelihood ratio order

Inclusive probabilities for the scattering system 16 MeV-S{^16+} on Ar

We performed ab initio calculations of many particle inclusive probabilities for the scattering system 16 MeV-S{^16+} on Ar. The solution of the time-dependent DIRAC-FOCK-SLATER-equation is achieved via a set of coupled-channel equations with energy eigenvalues and matrix elements which are given by static SCF molecular many electron calculations.

Multiple vacancy inclusive probabilities for the scattering system 16 MeV S{^16+} on Ar

To evaluate single and double K-shell inclusive charge transfer probabilities in ion-atom collisions we solve the time-dependent Dirac equation. By expanding the timedependent wavefunction in a set of molecular basis states the time-dependent equation reduces to a set of coupled-channel equations. The energy eigenvalues and matrix elements are taken from self-consistent relativistic molecular many-electron Dirac-Fock-Slater calculations. We present many-electron inclusive probabilities for different final configurations as a function of impact parameter for single and double K-shell vacancy production in collisions of bare S on Ar.

Comparison of different methods in estimating potential evapotranspiration at Muda Irrigation Scheme of Malaysia

Evapotranspiration (ET) is a complex process in the hydrological cycle that influences the quantity of runoff and thus the irrigation water requirements. Numerous methods have been developed to estimate potential evapotranspiration (PET). Unfortunately, most of the reliable PET methods are parameter rich models and therefore, not feasible for application in data scarce regions. On the other hand, accuracy and reliability of simple PET models vary widely according to regional climate conditions. The objective of the present study was to evaluate the performance of three temperature-based and three radiation-based simple ET methods in estimating historical ET and projecting future ET at Muda Irrigation Scheme at Kedah, Malaysia. The performance was measured by comparing those methods with the parameter intensive Penman-Monteith Method. It was found that radiation based methods gave better performance compared to temperature-based methods in estimation of ET in the study area. Future ET simulated from projected climate data obtained through statistical downscaling technique also showed that radiation-based methods can project closer ET values to that projected by Penman-Monteith Method. It is expected that the study will guide in selecting suitable methods for estimating and projecting ET in accordance to availability of meteorological data.

Effects of transformation processes in 'jubraka' agroforestry systems of the Nuba Mountains, Sudan, on nutrient fluxes

Intensification processes in homegardens of the Nuba Mountains, Sudan, raise concerns about strongly positive carbon (C) and nutrient balances which are expected to lead to substantial element losses from these agroecosystems, in particular via soil gaseous emissions. Therefore, this thesis aimed at the quantification of C, nitrogen (N), phosphorus (P) and potassium (K) input and output fluxes with a special focus on soil gaseous losses, and the calculation of respective element balances. A further focus in this thesis was rainfall, a valuable resource for rain-fed agriculture in the Nuba Mountains. To minimize negative consequences of the high variability of rainfall, risk reducing mechanisms were developed by rain-fed farmers that may lose their efficacy in the course of climate change effects predicted for East Africa. Therefore, the second objective of this study was to examine possible changes in rainfall amounts during the last 60 years and to provide reliable risk and probability statements of rainfall-induced events of agricultural importance to rain-fed farmers in the Nuba Mountains. Soil gaseous emissions of C (in form of CO2) and N (in form of NH3 and N2O) of two traditional and two intensified homegardens were determined with a portable dynamic closed chamber system. For C gaseous emission rates reached their peak at the onset of the rainy season (2,325 g CO2-C ha-1 h-1 in an intensified garden type) and for N during the rainy season (16 g NH3-N ha-1 h-1 and 11.3 g N2O-N ha-1 h-1, in a traditional garden type). Data indicated cumulative annual emissions of 5,893 kg CO2-C ha-1, 37 kg NH3-N ha-1, and 16 kg N2O-N ha-1. For the assessment of the long-term productivity of the two types of homegardens and the identification of pathways of substantial element losses, a C and nutrient budget approach was used. In three traditional and three intensified homegardens observation plots were selected. The following variables were quantified on each plot between June and December in 2010: soil amendments, irrigation, biomass removal, symbiotic N2 fixation, C fixation by photosynthesis, atmospheric wet and dry deposition, leaching and soil gaseous emissions. Annual balances for C and nutrients amounted to -21 kg C ha-1, -70 kg N ha-1, 9 kg P ha-1 and -117 kg K ha-1 in intensified homegardens and to -1,722 kg C ha-1, -167 kg N ha-1, -9 kg P ha-1 and -74 kg K ha-1 in traditional homegardens. For the analysis of rainfall data, the INSTAT+ software allowed to aggregate long-term daily rainfall records from the Kadugli and Rashad weather stations into daily, monthly and annual intervals and to calculate rainfall-induced events of agricultural importance. Subsequently, these calculated values and events were checked for possible monotonic trends by Mann-Kendall tests. Over the period from 1970 to 2009, annual rainfall did not change significantly for either station. However, during this period an increase of low rainfall events coinciding with a decline in the number of medium daily rainfall events was observed in Rashad. Furthermore, the availability of daily rainfall data enabled frequency and conditional probability calculations that showed either no statistically significant changes or trends resulting only in minor changes of probabilities.

Estimating Dependency Structure as a Hidden Variable

This paper introduces a probability model, the mixture of trees that can account for sparse, dynamically changing dependence relationships. We present a family of efficient algorithms that use EMand the Minimum Spanning Tree algorithm to find the ML and MAP mixtureof trees for a variety of priors, including the Dirichlet and the MDL priors.

Estimating Dependency Structure as a Hidden Variable

This paper introduces a probability model, the mixture of trees that can account for sparse, dynamically changing dependence relationships. We present a family of efficient algorithms that use EM and the Minimum Spanning Tree algorithm to find the ML and MAP mixture of trees for a variety of priors, including the Dirichlet and the MDL priors. We also show that the single tree classifier acts like an implicit feature selector, thus making the classification performance insensitive to irrelevant attributes. Experimental results demonstrate the excellent performance of the new model both in density estimation and in classification.

Conditional compositional biplots: theory and application

The biplot has proved to be a powerful descriptive and analytical tool in many areas of applications of statistics. For compositional data the necessary theoretical adaptation has been provided, with illustrative applications, by Aitchison (1990) and Aitchison and Greenacre (2002). These papers were restricted to the interpretation of simple compositional data sets. In many situations the problem has to be described in some form of conditional modelling. For example, in a clinical trial where interest is in how patients’ steroid metabolite compositions may change as a result of different treatment regimes, interest is in relating the compositions after treatment to the compositions before treatment and the nature of the treatments applied. To study this through a biplot technique requires the development of some form of conditional compositional biplot. This is the purpose of this paper. We choose as a motivating application an analysis of the 1992 US President ial Election, where interest may be in how the three-part composition, the percentage division among the three candidates - Bush, Clinton and Perot - of the presidential vote in each state, depends on the ethnic composition and on the urban-rural composition of the state. The methodology of conditional compositional biplots is first developed and a detailed interpretation of the 1992 US Presidential Election provided. We use a second application involving the conditional variability of tektite mineral compositions with respect to major oxide compositions to demonstrate some hazards of simplistic interpretation of biplots. Finally we conjecture on further possible applications of conditional compositional biplots

A process-based cost estimating tool for ship structural designs

by John M. Barentine.

Compositional analysis of bivariate discrete probabilities

A joint distribution of two discrete random variables with finite support can be displayed as a two way table of probabilities adding to one. Assume that this table has n rows and m columns and all probabilities are non-null. This kind of table can be seen as an element in the simplex of n · m parts. In this context, the marginals are identified as compositional amalgams, conditionals (rows or columns) as subcompositions. Also, simplicial perturbation appears as Bayes theorem. However, the Euclidean elements of the Aitchison geometry of the simplex can also be translated into the table of probabilities: subspaces, orthogonal projections, distances. Two important questions are addressed: a) given a table of probabilities, which is the nearest independent table to the initial one? b) which is the largest orthogonal projection of a row onto a column? or, equivalently, which is the information in a row explained by a column, thus explaining the interaction? To answer these questions three orthogonal decompositions are presented: (1) by columns and a row-wise geometric marginal, (2) by rows and a columnwise geometric marginal, (3) by independent two-way tables and fully dependent tables representing row-column interaction. An important result is that the nearest independent table is the product of the two (row and column)-wise geometric marginal tables. A corollary is that, in an independent table, the geometric marginals conform with the traditional (arithmetic) marginals. These decompositions can be compared with standard log-linear models. Key words: balance, compositional data, simplex, Aitchison geometry, composition, orthonormal basis, arithmetic and geometric marginals, amalgam, dependence measure, contingency table

Estimating the motion of an underwater robot from a monocular image sequence

When underwater vehicles perform navigation close to the ocean floor, computer vision techniques can be applied to obtain quite accurate motion estimates. The most crucial step in the vision-based estimation of the vehicle motion consists on detecting matchings between image pairs. Here we propose the extensive use of texture analysis as a tool to ameliorate the correspondence problem in underwater images. Once a robust set of correspondences has been found, the three-dimensional motion of the vehicle can be computed with respect to the bed of the sea. Finally, motion estimates allow the construction of a map that could aid to the navigation of the robot