Fung, Chun Yip. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2009. / Includes bibliographical references (leaves 53-54). / Abstract also in Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 2 --- The Exchange Algorithm Framework --- p.4 / Chapter 2.1 --- Ordinary Least Squares Linear Regression --- p.5 / Chapter 2.2 --- The Exchange Algorithm --- p.6 / Chapter 3 --- Methodology --- p.12 / Chapter 3.1 --- Least Median Squares Linear Regression --- p.12 / Chapter 3.2 --- Least Median Squares Algorithm for Clusterwise Linear Re- gression --- p.16 / Chapter 3.3 --- Measures of Performance --- p.20 / Chapter 3.4 --- An Illustrative Example --- p.24 / Chapter 4 --- Monte Carlo Simulation Study --- p.34 / Chapter 4.1 --- Simulation Plan --- p.34 / Chapter 4.2 --- Simulation Results --- p.41 / Chapter 4.2.1 --- Effects of the Six factors --- p.41 / Chapter 4.2.2 --- Comparisons between LMSA and the Exchange Algorithm --- p.47 / Chapter 4.2.3 --- Evaluation of the Improvement of Regression Parame- ters by Performing Stage 3 in LMSA --- p.50 / Chapter 5 --- Concluding Remarks --- p.51 / Bibliography --- p.52

Zhou, Tu. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2008. / Includes bibliographical references (leaves 61-70). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.0 / Chapter 1.1 --- Motivation and Objective --- p.0 / Chapter 1.2 --- Major Contribution --- p.2 / Chapter 1.3 --- Thesis Organization --- p.4 / Chapter 2 --- Measurement of Relationship between financial time series --- p.5 / Chapter ´ب2.1 --- Linear Correlation --- p.5 / Chapter 2.1.1 --- Pearson Correlation Coefficient --- p.6 / Chapter 2.1.2 --- Rank Correlation --- p.6 / Chapter 2.2 --- Mutual Information --- p.7 / Chapter 2.2.1 --- Approaches of Mutual Information Estimation --- p.10 / Chapter 2.3 --- Copula --- p.12 / Chapter 2.4 --- Analysis from Experimental Data --- p.14 / Chapter 2.4.1 --- Experiment 1: Nonlinearity --- p.14 / Chapter 2.4.2 --- Experiment 2: Sensitivity of Outliers --- p.16 / Chapter 2.4.3 --- Experiment 3: Transformation Invariance --- p.20 / Chapter 2.5 --- Chapter Summary --- p.23 / Chapter 3 --- Clustered Dynamic Conditional Correlation Model --- p.26 / Chapter 3.1 --- Background Review --- p.26 / Chapter 3.1.1 --- GARCH Model --- p.26 / Chapter 3.1.2 --- Multivariate GARCH model --- p.29 / Chapter 3.2 --- DCC Multivariate GARCH Models --- p.31 / Chapter 3.2.1 --- DCC GARCH Model --- p.31 / Chapter 3.2.2 --- Generalized DCC GARCH Model --- p.32 / Chapter 3.2.3 --- Block-DCC GARCH Model --- p.32 / Chapter 3.3 --- Clustered DCC GARCH Model --- p.34 / Chapter 3.3.1 --- Minimum Distance Estimation (MDE) --- p.36 / Chapter 3.3.2 --- Clustered DCC (CDCC) based on MDE --- p.37 / Chapter 3.4 --- Clustering Method Selection --- p.40 / Chapter 3.5 --- Model Estimation and Testing Method --- p.42 / Chapter 3.5.1 --- Maximum Likelihood Estimation --- p.42 / Chapter 3.5.2 --- Box-Pierce Statistic Test --- p.44 / Chapter 3.6 --- Chapter Summary --- p.44 / Chapter 4 --- Experimental Result and Applications on CDCC --- p.46 / Chapter 4.1 --- Model Comparison and Analysis --- p.46 / Chapter 4.2 --- Portfolio Selection Application --- p.50 / Chapter 4.3 --- Value at Risk Application --- p.52 / Chapter 4.4 --- Chapter Summary --- p.55 / Chapter 5 --- Conclusion --- p.57 / Bibliography --- p.61

Rapid population growth and climate variability have been posing pressure on groundwater management, especially in regions dominated by irrigation agriculture. Effective management practices require a better understanding of groundwater dynamics and its contributing factors, such as recharge, groundwater-surface water interactions, soil and unsaturated zone characteristics. Although groundwater models can provide valuable insights into these questions, these models are often nonexistent or cost prohibitive.

Licensed valuers in the State of Victoria, Australia currently appraise rural land using manual techniques. Manual techniques typically involve site visits to the property, liaison with property owners through interview, and require a valuer experienced in agricultural properties to determine a value. The use of manual techniques typically takes longer to determine a property value than for valuations performed using automated techniques, providing appropriate data are available. Manual methods of valuation can be subjective and lead to bias in valuation estimates, especially where valuers have varying levels of experience within a specific regional area. Automation may lend itself to more accurate valuation estimates by providing greater consistency between valuations. Automated techniques presently in use for valuation include artificial neural networks, expert systems, case based reasoning and multiple regression analysis. The latter technique appears mo st widely used for valuation. The research aimed to develop a conceptual rural property valuation model, and to develop and evaluate quantitative models for rural property valuation based on the variables identified in the conceptual model. The conceptual model was developed by examining peer research, Valuation Best Practice Standards, a standard in use throughout Victoria for rating valuations, and rural property valuation texts. Using data that are only available digitally and publicly, the research assessed this conceptualisation using properties from four LGAs in the Wellington and Wimmera Catchment Management Authority (CMAs) areas in Victoria. Cluster analysis was undertaken to assess if the use of sub-markets, that are determined statistically, can lead to models that are more accurate than sub-markets that have been determined using geographically defined areas. The research is divided into two phases; the 'available data phase' and the 'restricted data phase'. The 'available data phase' used publicly available digital data to build quantitative models to estimate the value of rural properties. The 'restricted data phase' used data that became available near the completion of the research. The research examined the effect of using statistically derived sub-markets as opposed to geographically derived ones for property valuation. Cluster analysis was used during both phases of model development and showed that one of the clusters developed in the available data phase was superior in its model prediction compared to the models produced using geographically derived regions. A number of limitations with the digital property data available for Victoria were found. Although GIS analysis can enable more property characteristics to be derived and measured from existing data, it is reliant on having access to suitable digital data. The research also identified limitations with the metadata elements in use in Victoria (ANZMETA DTD version 1). It is hypothesised that to further refine the models and achieve greater levels of price estimation, additional properties would need to be sourced and added to the current property database. It is suggested that additional research needs to address issues associated with sub-market identification. If results of additional modelling indicated significantly different levels of price estimation, then these models could be used with manual techniques to evaluate manually derived valuation estimates.

Thesis (Ph. D.)--University of Hong Kong, 2006. / Title proper from title frame. Also available in printed format.

Under the Clean Water Act (CWA) program the Texas Commission on Environmental Quality (TCEQ) listed 110 stream segments with pathogenic bacteria impairment in 2000. The current study was conducted to characterize the watersheds associated with the impaired waterbodies. The main characteristics considered for the classification of waterbodies were designated use of the waterbody, land use distribution, density of stream network, average distance of a land of a particular use to the closest stream, household population, density of on-site sewage facilities (OSSF), bacterial loading due to the presence of different types of farm animals and wildlife, and average climatic conditions. The availability of observed in-stream fecal coliform bacteria concentration data was evaluated to obtain subgroups of data-rich and data-poor watersheds within a group. The climatic data and observed in-stream fecal coliform bacteria concentrations were analyzed to find out seasonal variability of the water quality. The watershed characteristics were analyzed using the multivariate statistical analysis techniques such as factor analysis/principal component analysis, cluster analysis, and discriminant analysis. Six groups of watersheds were formed as result of the statistical analysis. The main factors that differentiate the clusters were found to be bacterial contribution from farm animals and wildlife, density of OSSF, density of households connected to public sewers, and the land use distribution. Two watersheds were selected each from two groups of watersheds. Hydrological Simulation Program-FORTRAN (HSPF) model was calibrated for one watershed within each group and tested for the other watershed in the same group to study the similarity in the parameter sets due to the similarity in watershed characteristics. The study showed that the watersheds within a given cluster formed during the multivariate statistical analysis showed similar watershed characteristics and yielded similar model results for similar model input parameters. The effect of parameter uncertainty on the in-stream bacterial concentration predictions by HSPF was evaluated for the watershed of Salado Creek, in Bexar County. The parameters that control the HSPF model hydrology contributed the most variance in the in-stream fecal coliform bacterial concentrations corresponding to a simulation period between 1 January 1995 and 31 December 2000.

Much is known about childbirth fear in Sweden including its relationship to caesarean birth. Less is understood about this in Australia. Sweden has half the rate of caesarean birth compared to Australia. Little has been reported about women’s beliefs and attitudes to birth in either country. The contribution of psychosocial factors such as fear, attitudes and beliefs about childbirth to the global escalation of caesarean birth in high-income countries is an important topic of debate. The overall aim of this thesis is to investigate the prevalence and impact of fear on birthing outcomes in two cohorts of pregnant women from Australia and Sweden and to explore the birth attitudes and beliefs of these women.   A prospective longitudinal cohort study from two towns in Australia and Sweden (N=509) was undertaken in the years 2007-2009. Pregnant women completed self-report questionnaires at mid-pregnancy, late pregnancy and two months after birth. Fear of birth was measured in mid-pregnancy with a tool developed in this study: the Fear of Birth Scale (FOBS). The FOBS showed promise as a clinically practical way to identify women with significant fear. A similar prevalence of fear of birth (30 percent) was found in the Australian and Swedish cohorts (Paper I).  The Swedish women had attitudes indicating a greater concern for the personal impacts of birth and a belief system that situated birth as a natural event when compared to the Australian women (Paper II). Finally, when women’s attitudes and levels of fear were combined, three profiles were identified: Self determiners, Take it as it comes and Fearful (Paper III). Belonging to the Fearful profile had the most negative outcomes for women including higher rates of elective caesarean, more negative feelings in pregnancy and post birth and poorer perceptions of the quality of their antenatal and intra-partum care (Paper IV).

In the aftermath of the events of 9/11, the U.S. executive branch has repeatedly maintained that its need for action to secure the nation requires a revised interpretation of individual liberties. This study will explore the tensions between the positive ideographs and in response to the negative ideograph in a contemporary United States court ruling. Using Burke’s pentad, and cluster analysis, as well as Brummett’s notion of strategic silence, the study examines how the FISCR substantially changed the interrelationship between the two ideographs. The study concludes that the FISCR situated strengthening national security as the purpose of the case it ruled on, which privileged national security over privacy. Throughout the expansion of security,> the court used silence to justify its decision. This analysis both adds to our understanding of the synchronic relationship between ideographs, and examines how the courts utilize such interplays to reconstitute community.

The structure and function of coastal marshes results from a complex interaction of biotic and abiotic processes that continually influence the characteristics of marsh vegetation. A great deal of research has focused on how tidal processes influence vegetation dynamics along the Atlantic coast, but few studies have investigated the influence of similar processes in the marshes along the Gulf of Mexico. This study aims to identify the characteristic vegetation assemblages of the coastal marshes bordering the East Bay of Galveston Bay, Texas, and identify if elevation, inundation frequency and burning frequency are important to their structure. To identify characteristic vegetation assemblages, hierarchical cluster analysis was used. The cluster analysis resulted in seven statistically different vegetation assemblages that were used in diversity analysis and classification and regression analysis (CART) as dependent variables. Diversity measures were calculated at both the plot and assemblage scale using Shannon's diversity index and species richness. The resulting diversity measures were used as predictor variables in the CART analysis as well as regression analysis. Hydrologic modeling was accomplished using Mike 21, a flow and wave simulation model, along with a geographic information system (GIS), to model hourly inundation frequency at each of the sampled plots. The inundation frequency was then used as a predictor variable in the CART analysis and regression analysis. This study found that the main factor contributing to species richness was elevation. Vegetation assemblages at high elevations generally had high diversity, and assemblages at low elevations had lower diversity. Elevation and inundation frequency are inversely related, and the strong correlation between species richness and elevation also assumes that inundation frequency is important in structuring the marsh. Burn frequencies had no influence on diversity in general, but more frequent burning did result in monospecific stands of Spartina patens at Anahuac NWR.

In this thesis I examine clustering evaluation, with a subfocus on text clusterings specifically. The principal work of this thesis is the development, analysis, and testing of a new internal clustering quality measure called informativeness. I begin by reviewing clustering in general. I then review current clustering quality measures, accompanying this with an in-depth discussion of many of the important properties one needs to understand about such measures. This is followed by extensive document clustering experiments that show problems with standard clustering evaluation practices. I then develop informativeness, my new internal clustering quality measure for estimating the clarity of clusterings. I show that informativeness, which uses classification accuracy as a proxy for human assessment of clusterings, is both theoretically sensible and works empirically. I present a generalization of informativeness that leverages external clustering quality measures. I also show its use in a realistic application: email spam filtering. I show that informativeness can be used to select clusterings which lead to superior spam filters when few true labels are available. I conclude this thesis with a discussion of clustering evaluation in general, informativeness, and the directions I believe clustering evaluation research should take in the future.