published_or_final_version / Statistics and Actuarial Science / Master / Master of Philosophy

The site frequency spectrum of mutations (SFS) and linkage disequilibrium (LD) are the two major sources of information in population genetics studies. In this study we focus on the levels of LD and the SFS and on the effect of sample size on summary statistics in 10 Scandinavian populations of Norway spruce. We found that previous estimates of a low level of LD were highly influenced by both sampling strategy and the fact that data from multiple loci were analyzed jointly. Estimates of LD were in fact heterogeneous across loci and increased within individual populations compared with the estimate from the total data. The variation in levels of LD among populations most likely reflects different demographic histories, although we were unable to detect population structure by using standard approaches. As in previous studies, we also found that the SFS-based test Tajima's D was highly sensitive to sample size, revealing that care should be taken to draw strong conclusions from this test when sample size is small. In conclusion, the results from this study are in line with recent studies in other conifers that have revealed a more complex and variable pattern of LD than earlier studies suggested and with studies in trees and humans that suggest that Tajima's D is sensitive to sample size. This has large consequences for the design of future association and population genetic studies in Norway spruce.

Thesis (M.S.)--Worcester Polytechnic Institute. / Keywords: Resampling; Portfolio Optimization; Transaction Costs; Mean-Variance Optimization. Includes bibliographical references (p. 23).

Two topics related to the experimental design are considered in this thesis. On the one hand, the uniform experimental design (UD), a major kind of space-filling design, is widely used in applications. The majority of UD tables (UDs) with good uniformity are generated under the centralized {dollar}L_2{dollar}-discrepancy (CD) and the wrap-around {dollar}L_2{dollar}-discrepancy (WD). Recently, the mixture {dollar}L_2{dollar}-discrepancy (MD) is proposed and shown to be more reasonable than CD and WD in terms of uniformity. In first part of the thesis we review lower bounds for MD of two-level designs from a different point of view and provide a new lower bound. Following the same idea we obtain a lower bound for MD of three-level designs. Moreover, we construct UDs under the measurement of MD by the threshold accepting (TA) algorithm, and finally we attach two new UD tables with good properties derived from TA under the measurement of MD. On the other hand, the problem of selecting a specific number of representative points (RPs) to maintain as much information as a given distribution has raised attention. Previously, a method has been given to select type-II representative points (RP-II) from normal distribution. These point sets have good properties and minimize the information loss. Whereafter, following similar idea, Fu, 1985 have discussed RP-II for gamma distribution. In second part of the thesis, we improve the discussion of selecting Gamma RP-II and provide more RP-II tables with a number of parameters. Further in statistical simulation, we also evaluate the estimation performance of point sets resampled from Gamma RP-II by making comparison in different situations.

Made available in DSpace on 2014-06-11T19:22:25Z (GMT). No. of bitstreams: 0 Previous issue date: 2010-05-27Bitstream added on 2014-06-13T19:48:45Z : No. of bitstreams: 1 lopes_rf_me_prud.pdf: 5197639 bytes, checksum: 1c8da2ba222153e72f0e411a1ff89f69 (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP) / A utilização de imagens adquiridas por sensores CCD de médio formato, em plataformas aéreas, é uma alternativa para a redução de custos em projetos de aerolevantamento. Porém, alguns inconvenientes, como a pequena área de cobertura e a limitação às bandas do visível restringem algumas aplicações. Para resolver estes problemas podem ser usados vários sensores CCD simultaneamente, sendo necessária uma etapa posterior de fusão e registro destas imagens. Neste trabalho foram utilizados dois sistemas compostos por múltiplas câmaras, o Sistema de Aquisição e Pós-Processamento de Imagens Tomadas com Câmaras Digitais (SAAPI) e o Sistema de Câmaras Fuji. O sistema SAAPI permite diferentes configurações entre os sensores que o compõem, podendo estar nos modos duplooblíquo ou nadiral à área fotografada. A metodologia desenvolvida no trabalho trata duas questões envolvidas com a configuração de sistemas de múltiplas câmaras: o registro entre imagens IR e RGB e a fusão entre imagens RGB oblíquas, tendo como objetivo o aumento da resolução espectral e geométrica da imagem final produzida. Para isto são utilizados processos como a retificação e reamostragem de imagens. Estes, por sua vez, necessitam dos dados de calibração do sistema de câmaras, pois os parâmetros de orientação interior e exterior (POI e POE) são imprescindíveis para corrigir os efeitos das distorções nas imagens e o efeito da inclinação do sistema de câmaras. Experimentos realizados com imagens áreas, utilizando a metodologia proposta, demonstram que a discrepância nas coordenadas de pontos comuns às imagens registradas foi menor que 1 pixel. Este resultado é dependente da qualidade da calibração do sistema de câmaras / The use of images acquired by medium format CCD sensors from aerial platforms, is a cost effective alternative for aerial surveying projects. However, some drawbacks, as small coverage area and limitation to the visible spectrum bands restrict some applications. To solve these problems multiple CCD sensors can be used simultaneously, requiring a later stage for registration and fusion of these images. In this study, two systems with multiple cameras, the System for Airborne Acquisition and Processing of Digital Images (SAAPI) and Fuji Camera System were used. The SAAPI system allows different configurations between the sensors that can be either double-oblique or nadir to the area photographed. The methodology developed in this study approached two issues involved with systems with multiple cameras: the registration between IR and RGB images and oblique RGB images fusion, aiming at increasing the geometric and spectral resolution of the final image to be produced. There were used processes such as rectification and images resampling. These processes require the previous camera and system calibration, because inner and exterior orientation parameters (IOP and EOP) are essential to correct the effects of distortions in the images and the effect of camera convergence within the system. Experiments performed with real terrestrial and aerial images using the proposed methodology, showed that the discrepancy in the coordinates of common points in the registered images were less than 1 pixel. This result is dependent on the quality of the system and camera calibration

No description available.

Changepoint analysis is a useful tool in environmental statistics in that it provides a methodology for threshold detection and modeling processes subject to periodic changes in the underlying model due to anthropogenic effects or natural phenomena. Several applications of changepoint analysis are investigated here. The use of inappropriate changepoint detection methods is first discussed and the need for a simple, flexible, correct method is established and such a method is proposed for the mean-shift model. Data from the Everglades, Florida, USA is used to showcase the methodology in a real-world setting. An extension to the case of time-series data represented via transition matrices is presented as a result of joint work with Matt Williams (Department of Statistics, Virginia Tech) and rainfall data from Kenya, Africa is presented as a case-study. Finally the multivariate changepoint problem is addressed by a two-stage approach beginning with dimension reduction via principal component analysis (PCA). After the dimension reduction step the location of the changepoint in principal component space is estimated and assuming at most one change in a mean-shift setting, all possible sub-models are investigated. / Ph. D.

Optimizing forage productivity is essential to reduce pasture seasonality and ensure available forage to meet the nutritional needs of livestock. This study explores the risk-buffering ability of warm-season forages to fill the summer slump gap in production of cool-season grasses. Small plot experiments were initiated in summer of 2008 in Kentland Farm, Northern Piedmont AREC and Shenandoah AREC, Virginia. Treatments included endophyte-infected tall fescue (KY31 E+), endophyte free tall fescue (KY31 E-), novel endophyte tall fescue (MaxQ), Crabgrass in combination with endophyte-infected tall fescue, Teff, Bermudagrass (BG), and Caucasian bluestem (CB). Plots were harvested May through October of 2009 and 2010 at the late boot stage at a cutting height of 10cm. Subsamples were analyzed for dry matter and nutritive value. To assess risk, bootstrap distributions of biomass and quality data were generated by Monte Carlo simulation and compared against an objective function defined as 59 kg ha-1 d-1 forage yield; 10% CP; 60% TDN. Regardless of variability, warm-season grasses produced biomass yields and nutritional values adequate to fill the summer slump from cool-season forages and demonstrated a higher probability of meeting the minimum requirements in July, August and September. Teff was most consistent in meeting the minimum requirements in mid-summer. However, with good conditions for establishment, both BG and CB can help to fill the gap in summer months when compared to cool-season tall fescue. Bootstrap distributions provide producers with a tool that links their production goals with a measurable value of production risk. / Master of Science

This thesis develops a generalized form of Monte Carlo integration called Resampled Importance Sampling. It is based on the importance resampling sample generation technique. Resampled Importance Sampling can lead to significant variance reduction over standard Monte Carlo integration for common rendering problems. We show how to select the importance resampling parameters for near optimal variance reduction. We also combine RIS with stratification and with Multiple Importance Sampling for further variance reduction. We demonstrate the robustness of this technique on the direct lighting problem and achieve up to a 33% variance reduction over standard techniques. We also suggest using RIS as a default BRDF sampling technique.

The objective of the research is to achieve a systematic combination of acoustic echo reduction components that together achieve a robust performance of the MCAEC system as a whole. Conventional approaches to the acoustic echo reduction system typically assume that individual components would perform ideally. For example, the adaptive algorithm for AEC is often developed in the absence of strong near-end signal, the algorithm for RES is often an added module that is developed as a separate noise reduction component, and the decorrelation procedure for MCAEC is yet another add-on module that simply introduces some form of distortion to the reference signal. The main challenge is in designing a consistent criterion across all modules that can be jointly optimized to form a more consistent framework for acoustic echo reduction. The decorrelation procedure can potentially benefit from the system approach as well if it is designed by taking the near-end listener into account. The MCAEC system should be optimized not only for the echo cancellation and suppression performance, but also for the reference signal quality after the added distortion from the decorrelation procedure. Finally, a tuning strategy is presented to jointly optimize the parameters across all modules using object criteria.