Thesis (M. Phil.)--University of Hong Kong, 1999. / Includes bibliographical references (leaves 79-86).

Thesis (Ph.D.)--Baylor University, 2008. / Includes bibliographical references (p.84-86)

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / In order to construct growth curves is necessary a sequence of many samples taken during lettuce growth period. However, mainly when the trial is made in a controlled environment, sampling frequency is limited. This work was carried out with the aim to reduce sampling destruction effect without change the result precision. Two field trials were made in a controlled environment, during two season, spring (09/20/2004 a 01/12/2005) and autumn (02/27/2005 a 07/20/2005), in the UFSM experimental area, Santa Maria, RS. Different sampling frequencies were simulated, using the adjust of diary sampling model. Optimum sampling frequency was made by comparing daily sampling model with simulated sampling model, in twos, by F test (p<0,005), using the error mean square of non linear regression analysis, pondered by freedom degrees. Simulations of the following variables: total, foliar, root and foliar area phytomass, were made just considering vegetative period and complete growth period. The result shows that season and period of growth should be taken into account to establish the best sampling frequency. Trials conducted during spring season, with complete growth period, show best results with samples taken in intervals of 3 (total), 8 (foliar), 20 (roots) and 9 (foliar area) days; with vegetative period, samples should be taken in intervals of 2,2,4 and 1 days. Trials conducted during autumn season, with complete growthperiod, the sample frequency should be of 2, 11, 12 and 11 days; and for vegetative growth, should be 2, 3, 4 and 1 days / Durante o crescimento da planta de alface é necessária uma seqüência de várias coletas de amostras até a maturação de colheita para construção de curvas de crescimento, porém, a freqüência em que se coletam amostras é limitada, principalmente quando o experimento é realizado em ambientes controlados. Para isso, buscou-se reduzir o efeito destrutivo de amostragens sem comprometer a precisão dos experimentos determinando-se a freqüência de amostragem de plantas de alface em hidroponia para o ajuste de curvas de crescimento. Foram realizados dois experimentos em estufa plástica nas estações de primavera e outono, no período de 20/09/2004 a 12/01/2005 e 27/02/2005 a 20/07/2005, respectivamente, em área pertencente ao Departamento de Fitotecnia, na UFSM, Santa Maria, RS. A partir do ajuste do modelo de amostragem diária, simularam-se diferentes freqüências de amostragem. Para encontrar a freqüência ideal de amostragem, foi comparado o modelo de amostragem diária com os modelos das diferentes amostragens simulados, dois a dois, pelo teste de F em nível de 5% de probabilidade de erro, utilizando-se os quadrados médios do erro da análise de regressão não linear, ponderados pelos respectivos graus de liberdade. Foram realizadas simulações considerando apenas o período vegetativo e ciclo completo (transplante até produção de sementes), para variáveis de fitomassa seca da planta e de partes da planta e área foliar. Em experimentos realizados com alface hidropônica na primavera, para o ciclo completo, devem ser realizadas amostragens a cada 3, 8, 20 e 9 dias para fitomassa seca relativa total da planta de alface, de folhas, de raiz e área foliar, respectivamente; enquanto que, para o período vegetativo, deve ser a cada 2, 2, 4 e 1 dias, respectivamente. Para o ciclo completo, utilizando-se as variáveis fitomassa seca relativa total, de folhas, de raiz e área foliar relativa em experimentos realizados no outono é recomendável utilizar freqüências de amostragens a cada 2, 11, 12 e 11 dias, respectivamente; e, para o período vegetativo, de 2, 3, 4 e 1 dias, respectivamente

1 Abstract: The present work investigates techniques of insurence ratemaking accor- ding to the claims counts of policyholders on the basis of information contained in policies. At the beginning, we provide a closer examination of the theory of genera- lized linear models, which have wide range of applications in the field of actuarial modeling. The second chapter presents the basic Poisson regression model as well as some particular verification methods. Specifically, deviance and Wald test could be found here and furthermore also important results for residuals. The third chapter contains information on alternative approaches to modeling the claim frequencies and at the end the GEE method, that can be applied in case of panel data, is de- scribed. The numerical study based on real insurace data in last part of this diploma thesis illustrate's previously described techniques which were obtained with the help of statistical software SAS.

This master thesis deals with the analysis of housing prices in Prague. The main goal is to identify and explain the factors which have an influence on the prices of flats at the macro and micro level. Two spatial statistic methods, namely multiple linear regressions and geographically weighted regressions (GWR), are used in the first part of the thesis, which deals with the prices in Prague in general. The influence on the values of flats in Prague basic settlement units caused by several factors such as the distance from the Old Town Square, age of dwellings, the presence of migrants or air pollution was investigated using these two methods. The price map of the association of real estate agencies, the Czech Statistical Office and the Prague Institute of Planning and Development provided the data used in the presented research. Price profiles from the centre of Prague to the suburbs in various directions were also created and analyzed. Factors with an influence on housing prices at the micro level in a case study of the Prague cadastral territory of Modřany are described in the second part of the thesis. The analysis of new developer projects and older flats in panel houses investigates the influence on the housing prices caused by factors such as noise, physical condition of apartments and the quality of...

This thesis sumarizes in detail general linear regression model, including testing statistics for coefficients, submodels, predictions and mostly tests of outliers and large leverage points. It describes how to include categorial variables into regression model. This model was applied to describe saturation of photographs of bread, where input variables were, type of flour, type of addition and concntration of flour. After identification of outliers it was possible to create mathematical model with high coefficient of determination, which will be usefull for experts in food industry for preliminar identification of possible composition of bread.

Advances in molecular marker technologies have led to the development of high throughput genotyping techniques such as Genotyping by Sequencing (GBS), driving the application of genomics in crop research and breeding. They have also supported the use of novel mapping approaches, including Multi-parent Advanced Generation Inter-Cross (MAGIC) populations which have increased precision in identifying markers to inform plant breeding practices. In the first part of this thesis, a high density physical map derived from GBS was used to identify QTLs controlling key agronomic traits of wheat in a genome-wide association study (GWAS) and to demonstrate the practicability of genomic selection for predicting the trait values. The results from GBS were compared to a previous study conducted on the same association mapping panel using a less dense physical map derived from diversity arrays technology (DArT) markers. GBS detected more QTLs than DArT markers although some of the QTLs were detected by DArT markers alone. Prediction accuracies from the two marker platforms were mostly similar and largely dependent on trait genetic architecture. The second part of this thesis focused on MAGIC populations, which incorporate diversity and novel allelic combinations from several generations of recombination. Pedigrees representing a wild rice MAGIC population were used to model MAGIC populations by simulation to assess the level of recombination and creation of novel haplotypes. The wild rice species are an important reservoir of beneficial genes that have been variously introgressed into rice varieties using bi-parental population approaches. The level of recombination was found to be highly dependent on the number of crosses made and on the resulting population size. Creation of MAGIC populations require adequate planning in order to make sufficient number of crosses that capture optimal haplotype diversity. The third part of the thesis considers models that have been proposed for genomic prediction. The ridge regression best linear unbiased prediction (RR-BLUP) is based on the assumption that all genotyped molecular markers make equal contributions to the variations of a phenotype. Information from underlying candidate molecular markers are however of greater significance and can be used to improve the accuracy of prediction. Here, an existing Differentially Penalized Regression (DiPR) model which uses modifications to a standard RR-BLUP package and allows two or more marker sets from different platforms to be independently weighted was used. The DiPR model performed better than single or combined marker sets for predicting most of the traits both in a MAGIC population and an association mapping panel. Overall the work presented in this thesis shows that while these techniques have great promise, they should be carefully evaluated before introduction into breeding programmes.

The aim of this thesis is to examine women's educational attainment and social mobility in contemporary South Korea. This study seeks to answer to the following key research questions: 1) how much parents' characteristics such as occupational status and educational attainment, are important to their children's education and class; 2) the roles of educational qualification to occupational attainment in contemporary South Korea; 3) whether South Korea has become a more equal society with improved mobility chances for people of different social origins; and, 4) if there is a general pattern of social mobility and social fluidity in South Korea, how it is related to the change in the occupational positions of women. This research uses the Korean Labour and Income Panel Study (KLIPS) from 1998 to look at the changing relationship between social origin, education, and destination and what it indicates the role of education in the social mobility in Korea. The following tools are used for the analysis: I adopt Goldthorpe's class schema and CASMIN scales of educational qualifications. I then separately look at the association for men and women separately. Various statistical methods are subsequently employed to explore the substantive research questions: I use descriptive analysis for changes of Korea's educational attainment and look at absolute rates of mobility. Disparity ratios and odds ratios are used for describing the relative patterns and chances of educational attainment and mobility and regression model are used for analysing the impact of a range of factors on educational attainment and class destination. Finally, I draw on log-linear and log-multiplicative analysis for the trends in relative mobility and social fluidity. I find that access to education is still influenced by social background. Although the disparities between men and women become narrower across cohort, class and gender differentials in general educational attainment still apply to South Korea. Regarding the relative mobility rates, the results from disparity ratios show that the social class and gender differentials in class mobility still exist and the results of odds ratios confirm that social origin has a significant effect on children's social class destination. Looking at the origin-education (OE) association, class differences are still considerable and the relationship between class origins and educational attainment remains. Turning to the association between educational attainment and occupational destination (ED), qualifications continue to play a critical role in entry into the labour market remains, but there is no evidence that the association between education and destination has strengthened over time. Looking at the direct association between origins and destination (OD), the evidence shows the continuing association of origins on destinations. Regression analysis shows that the origin class effects upon educational attainment and occupational destinations were not dramatically decreased, but there were significant changes for women but not for men. The findings from the log-linear and log-multiplicative analysis suggest that there is trendless fluctuation and a stronger link between education and destination for women than for men.

The aim of this work is to get the best detailed knowledge about hardness distribution in first 60 mm below the surface of backing roll. To this end, a method for obtaining multi-dimensional polynomial regression was developed and then a computer program for its processing was written.Way of finding suitable regression surfaces and their subsequent interpretation, is a pivotal part of this work.