Cette thèse est consacrée à l'utilisation d'information auxiliaire en théorie des sondages à l'étape de l'échantillonnage et à l'étape de l'estimation. Dans le chapitre 2, on donne une présentation des principales notions de la théorie des sondages. Au chapitre 3, on propose une extension de la famille des estimateurs par calage reposant sur l'emploi de paramètres de calage complexes. Au chapitre 4 et 5, on s'intéresse à la correction simultanée des erreurs d'échantillonnage et de non-réponse au moyen d'un calage unique. On montre qu'en dépit du fait que le calage n'utilise pas explicitement les probabilités de réponse, il est nécessaire d'écrire le modèle de réponse afin de choisir correctement la fonction de calage. A défaut, on s'expose à des estimateurs biaisés dont le biais peut dépasser le biais de l'estimateur non-ajusté. En particulier, dans le cas du calage généralisé, la variance et le biais sont amplifiés pour des variables de calage faiblement corrélées aux variables instrumentales. Au chapitre 6, on montre qu'une approche conditionnelle, par rapport au plan de sondage, permet de construire des estimateurs plus robustes aux valeurs extrêmes et aux "sauteurs de strates". Au chapitre 7, on met en évidence que la méthode du tirage réjectif de Fuller conduit un estimateur par la régression qui peut être biaisé lorsque la variable d'intérêt ne suit pas un modèle de régression linéaire en fonction des variables d'équilibrage. / This thesis is devoted to the use of auxiliary information in sampling theory at the sampling stage and estimation stage. In Chapter 2, we give an overview of the key concepts of sampling theory. In Chapter 3, we propose an extension of the family of calibration estimators based on the use of complex parameters. In Chapter 4 and 5, we are interested in the simultaneous correction of sampling errors and nonresponse using a single calibration. It shows that despite the fact that the calibration does not explicitly use the response probabilities, it is necessary to write the response model to correctly select the calibration function. Otherwise, we run the risk of biased estimators whose bias can exceed the bias of the unadjusted estimator. In particular, in the case of generalized calibration, the variance and bias are amplified for calibration variables weakly correlated with the instrumental variables. In Chapter 6, we show that a conditional approach, based on the design, leads to estimators more robust to outliers and "jumpers strata. In Chapter 7, we highlight that the Fuller rejective sampling yield to a regression estimator which can be biased when the variable of interest does not follow a linear regression with the balancing variables.

Concentrations of PCB congeners were measured in indoor/outdoor pairs of 120 residences in two communities. More than 270 passive samplers equipped with polyurethane foam disks (PAS-PUF) were deployed and collected in the urban/industrial community of East Chicago, Indiana and rural Columbus Junction, Iowa. The sampling protocol included transport and storage of pre-cleaned and exposed PUF disks to and from the laboratory in Iowa City. The potential exposure to PCBs during transport and shipping was found to contribute no more than 10% of the PCBs measured in samples, although the sealed polyethylene bags were insufficient protection from ambient air over longer time periods. The samples were extracted and analyzed for the full suite of 209 polychlorinated biphenyls (PCBs) and are reported as a set of 158 individual or coeluting compounds. The quality control measures included laboratory and travel blanks, injection of surrogate standards in every sample, and analysis of certified PCBs in standard reference materials. Although we hypothesized that homes in East Chicago would have higher PCB concentrations than in rural Columbus Junction, this was not the case: the communities had no significant difference in either indoor or outdoor PCB concentrations (0.62 ± 0.65 ng m-3 and 1.3 ± 1.6 ng m-3 for outdoor air respectively and 1.9 ± 1.4 ng m-3 and 1.9 ± 4.4 ng m-3 for indoor air respectively). In both communities, indoor air was higher in concentration, with indoor/outdoor ratios averaging 3. The samples from the two communities do exhibit statistically different congener distributions, however, with higher molecular weight congeners more enriched in East Chicago.

The current study examined a method of language sampling (the Dixit Method- Science, Math, Engineering, Arts, and Math) in early adolescents with typically developing language. The purpose of this study was to examine the effectiveness of the DM-STEAM in eliciting lexically sophisticated spoken language samples in the early adolescent population. To examine lexical sophistication, traditional measures of analysis such as mean length of utterance (MLU) and average type token ratio (AVG TTR) were applied along with a measure of low frequency vocabulary. To compare performance on the DM-STEAM, school standardized assessments were obtained to measure student skill in academic content areas. Twenty-two student participants in the sixth grade (11 years to 12 years 11 months) were recruited from a local elementary school. The data was evaluated using a paired tailed t test and a path analysis test. Although the sample size is small, results from the study indicate the DM-STEAM elicits low frequency academic vocabulary in early adolescent populations.

This paper will discuss the barriers to the elderly population and how providing in home therapy could reduce depression in order to provide a better long lasting life. There are high levels of depression related to psychological problems, aging and illness. Depression can be associated with cumulative loss, restricted sense of control and declining abilities. The main problem is that elderly individuals tend to isolate so they will not seek help to address their depression. Providing guidance and support to the elderly will allow them to be able to function longer, remain independent, and extend their life. The total number of participants that were recruited for the study was twenty two. This study examined social workers’ awareness and knowledge regarding depression among the elderly and their perception if providing in home therapy will reduce depression among the elderly. Both quantitative and qualitative methodologies were used to give the researcher a systematic illustration of their perception. Findings from this study provide an understanding of the stigma associated with depression. Participants in the study indicated various levels of knowledge regarding depression among the elderly. Researcher suggests further research and examination if older adults would be receptive to receiving therapeutic services in their home and if those services will have a significant impact in improving their overall health, function and quality of life.

Orientador: Nilza Maria Martinelli / Resumo: A cigarra da espécie Quesada gigas é considerada praga-chave na cultura do café, principalmente nos Estados de São Paulo e Minas Gerais. Atualmente, essa espécie de cigarra é a principal e a mais prejudicial ao cafeeiro. O objetivo trabalho foi determinar a distribuição espacial de posturas e ninfas de Q. gigas em três talhões de café com histórico de infestação. O experimento foi realizado utilizando as cultivares Mundo Novo, Icatu 2939 e Icatu 2944, com idades de trinta, dezessete e quinze anos, respectivamente, pertencente à Fazenda São Judas Thadeu, localizada no município de São Sebastião do Paraíso-MG. O espaçamento entre as plantas foi de 4,0 x 1,0 m entrelinhas e na linha respectivamente, totalizando cada talhão 10.000 m2. Os talhões foram divididos em 100 parcelas de 10 x 10 m, e uma planta por parcela foi marcada com o auxílio de GPS (Global Positioning System). Foram coletados quinzenalmente três ramos secos do terço superior da planta marcada com aproximadamente 20 cm, totalizando 300 ramos por talhão, nos meses de outubro, novembro e dezembro de 2014 e outubro e novembro de 2015. Esses ramos para a avaliaç foram acondicionados em saco de papel e levados ao Departamento de Fitossanidade da UNESP/FCAV. Para o estudo de ninfas foi realizado através da abertura de trincheiras realizadas no período de dezembro de 2015. A abertura de trincheira com dimensões de 0,50 x 0,50 x 0,50m, foram realizadas a partir da base do tronco e as ninfas coletadas foram acondicionadas e... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: The Quesada gigas cicada is considered a key pest in coffee growing, mainly in the States of São Paulo and Minas Gerais. Currently, these cicadas are the main and most damaging species to coffee and mainly infest the planting of these two States. The objective was to characterize the spatial distribution of Q. gigas postures and nymphs in the coffee crop. The experiment was carried out using the cultivars Mundo Novo, Icatu 2939 and Icatu 2944, aged thirty, seventeen and fifteen, respectively, belonging to Fazenda São Judas Thadeu, located in the municipality of São Sebastião do Paraíso-MG. The spacing between the plants was 4.0 x 1.0 m between lines and in the line respectively, totalizing each field 10,000 m2. The plots were divided into 100 plots of 10 x 10 m, and one plot per plot was marked with the aid of GPS (Global Positioning System). Three dry branches were collected biweekly from the upper third of the plant with approximately 20 cm, totaling 300 branches per plot, between October, November, and December 2014 and in the year 2015. These branches were packed in paper bags and taken To the Phytosanitary Department of FCAV / UNESP. For the study of nymphs was carried out through the opening of trenches held in the period of December 2015. The trench opening with dimensions of 0.50 x 0.50 x 0.50m, were carried out from the base of the trunk and the nymphs Were collected in glass containers with 70% alcohol solution for later counting. The identification of the nymphal i... (Complete abstract click electronic access below) / Doutor

Es evidente que la pobreza económica es uno de los problemas que presentan los países subdesarrollados, y que su reducción está relacionada con el aumento de la productividad en las PYME, dado el alto impacto que han representado a lo largo del tiempo. Muchas entidades han identificado la importancia de la agricultura en el sector económico del país. Por lo tanto, es necesario un diagnóstico en la zona. El propósito de este diagnóstico es tener una referencia del entorno desde el punto de vista general, en el que se pueden observar todas las interacciones, descripciones, particularidades y procesos existentes. En esta primera etapa del diagnóstico, se lleva a cabo utilizando un muestreo no probabilístico, que es un método común en la investigación. Uno de los muchos métodos utilizados para identificar el diagnóstico es el muestreo de bolas de nieve que permite encontrar el diagnóstico de poblaciones ocultas donde no hay manera de conocer todas las características de una población. La ventaja de utilizar este tipo de muestreo es que un solo informante inicial puede poner al investigador en contacto con otras fuentes. Además, sobre la base de los resultados obtenidos, se identificó que las causas del problema del sector de Chirimoya estaban asociadas a 3 procesos críticos que reflejaban la no productividad de este sector: proceso de gestión de planificación y control de la producción, proceso de gestión logística y proceso de gestión de la calidad. / It is evident that economic poverty is one of the problems presented by underdeveloped countries, and that their reduction is related to the increase in productivity in MSEs, given the high impact they have represented over time. Many entities have identified the importance of agriculture in the economic sector of the country. Therefore, a diagnosis is necessary in the area. The purpose of this diagnosis is to have a reference of the environment from the general point of view, in which all the interactions, descriptions, particularities and existing processes can be observed. In this first stage of the diagnosis, it is carried out using a non-probabilistic sampling, which is a common method in the investigation. One of the many methods used for identifying diagnosis is the snowball sampling that allows finding the diagnosis of hidden populations where there is no way to know all the characteristics of a population. The benefit of using this type of sampling is that a single initial informant can put the researcher in contact with other sources. Further, based on the results obtained, it was identified that the causes of the problem of the Cherimoya sector were associated to 3 critical processes that reflected the non-productivity of this sector: process of planning management and production control, process of logistic management and process of quality management. / Tesis

acase@tulane.edu / Extreme phenotype sampling (EPS) is a broadly-used design to identify candidate genetic factors contributing to the variation of quantitative traits. By enriching the signals in the extreme phenotypic samples within the top and bottom percentiles, EPS can boost the study power compared with the random sampling with the same sample size. The existing statistical methods for EPS data test the variants/regions individually. However, many disorders are caused by multiple genetic factors. Therefore, it is critical to simultaneously model the effects of genetic factors, which may increase the power of current genetic studies and identify novel disease-associated genetic factors in EPS. The challenge of the simultaneous analysis of genetic data is that the number (p ~10,000) of genetic factors is typically greater than the sample size (n ~1,000) in a single study. The standard linear model would be inappropriate for this p>n problem due to the rank deficiency of the design matrix. An alternative solution is to apply a penalized regression method – the least absolute shrinkage and selection operator (LASSO). LASSO can deal with this high-dimensional (p>n) problem by forcing certain regression coefficients to be zero. Although the application of LASSO in genetic studies under random sampling has been widely studied, its statistical inference and testing under EPS remain unknown. We propose a novel sparse model (EPS-LASSO) with hypothesis test for high-dimensional regression under EPS based on a decorrelated score function to investigate the genetic associations, including the gene expression and rare variant analyses. The comprehensive simulation shows EPS-LASSO outperforms existing methods with superior power when the effects are large and stable type I error and FDR control. Together with the real data analysis of genetic study for obesity, our results indicate that EPS-LASSO is an effective method for EPS data analysis, which can account for correlated predictors. / 1 / Chao Xu

The overall hypothesis of this thesis addresses the release of polychlorinated biphenyls (PCBs) in the sediments of a highly contaminated harbor. I collected, analyzed and quantified PCB congeners in more than 130 samples of air, water and sediment. Then I constructed a chemical fate model as function of chemical concentrations, physical-chemical properties, local meteorological and hydraulic conditions. Indiana Harbor and Ship Canal in East Chicago (IHSC), Indiana, was selected for its expected high levels of PCBs in the sediment and because of future plans for dredging. I found that PCB concentrations in air, water and sediment in this area were much higher than background levels in the Great Lakes region. PCB sediment concentrations were above the threshold limit to designate IHSC as a Superfund site (≥ 50 ppm), although it is not. The PCB signature in surficial sediment strongly resembles the original Aroclor 1248 but deeper layers show evidence of mixtures of Aroclors and weathering processes. The fate model showed that IHSC contaminated sediments are a continuous source of PCBs to the water and overlying air, and also produce a PCB input to Lake Michigan, even under quiescent conditions. The PCB signature in sediment, water, and air support my determination that the contaminated sediment is a major source of PCBs into the water and air above it. Simulations considering different surficial sediment concentrations post-dredging demonstrated that PCB concentrations in the sediment should be considered in the dredging operation to minimize the release of PCBs into the environment. Finally, I examined the role of the dissolved sediment porewater concentration in the prediction of sediment-water soluble fluxes, using a passive sampler technique (SPME PDMS-fiber) and calculated values from a one-parameter linear free energy relationship (op-LFER). I determined that the latter overestimates the freely dissolved porewater concentration but are nevertheless the most appropriate values for predicting PCBs soluble release from contaminated sediments.

A high-flow (10 L/min) nanoparticle respiratory deposition (NRD) sampler was designed and evaluated to facilitate lower limits of quantification (LOQ) for metal nanoparticles than a low-flow (2.5 L/min) version. The high-flow NRD consists of an inlet, impactor stage, diffusion stage, and a final filter. For the impactor stage, three nozzle sections each containing 12 nozzles were designed from theory to achieve a cut-off diameter (d50) of 300 nm. Various depths of 37-mm-diameter foam cylinders were tested for the diffusion stage to obtain a collection efficiency curve similar to the deposition of nanoparticles in the human respiratory tract, the nanoparticulate matter (NPM) criterion. The objective for the final filter was a collection efficiency of near 100% with minimal pressure drop. The collection efficiencies by size and pressure drop were measured for all components. The impactor stage with one of the nozzle plates had a d50 of 305 nm. The collection efficiency for the foam with a depth of 7 cm adjusted for presence of the impactor was the closest match to the NPM curve with a R2 value of 0.96. Chemical analysis of the metal content for foam media affirmed that the high-flow NRD would require less sampling time to meet LOQs than the 2.5 L/min NRD. The final filter with a modified support pad had a collection efficiency near 100%. The overall pressure drop of the sampler 4.4 kPa (17.5 in. H2O) limits its ability to operate with available belt-mounted personal sampling pumps, although modifications to the sampler design could eliminate this constraint.

Detection of airborne influenza virus is needed in order to determine exposure and prevent and control infections. Few researchers have successfully detected airborne influenza virus in environmental settings with current bioaerosol samplers. Therefore, new sampling strategies should be considered to increase the likelihood of detection. This study compared four bioaerosol samplers in collection of airborne influenza virus – the SKC Biosampler, NIOSH Biosampler, Andersen N6 single-stage impactor containing a liquid media, and the newly developed Next Generation Inhalable Aerosol Sampler (NGIAS). Ten 30-minute laboratory trials were completed by aerosolizing active influenza virus (H1N1) in a bioaerosol chamber to compare the ability of four bioaerosol samplers to collect aerosolized virus. Samples were analyzed using RT-qPCR. The mean total virus particles per liter of sampled air (TVP) recovered with the NGIAS was significantly less than that measured by all other samplers (p < 0.001). The TVP recovered with the SKC Biosampler (111.41) and Andersen N6 sampler (102.36) was substantially larger than that recovered with the NIOSH Biosampler (58.59), however the difference in TVP between these samplers was not statistically significant (SKC – NIOSH p-value = 0.187 ; Andersen – NIOSH p-value = 0.297). Our results demonstrated that liquid based bioaerosol samplers recovered more TVP than dry collection samplers. The high flow rate sampler, the Andersen N6, did not collect more TVP, but had a lower limit of detection than other samplers. Furthermore, the SKC Biosampler collected the most TVP. Therefore, future investigators should design a liquid based personal bioaerosol sampler to maximize the likelihood of influenza virus detection.