No description available.

Many studies have conducted in the past that related to the domestic energy sector and households' appliances. These previous studies have explained the energy trends in the United Kingdom. In addition to this, the past studies have also provided wealth of information. However, all of these studies had some limitations. In addition, there were many gaps in the past studies regarding to the timing of usage the household's appliances and their daily contribution to the daily and peak demand. In this study, the researcher intended to overcome the limitations and gaps regarding the appliances time of use in the UK. In the present study, the data collected from Hillingdon Borough of London to ensure the study use the most reliable and valid data. Most importantly, suitable sampling and data collection technique applied in this study, which helped to obtain the appropriate data and outcome. All respondents were from the domestic sectors of the United Kingdom. Apart from this, to measure energy consumption in a more accurate manner, home appliances were categorised into several categories based on their functionality. Moreover, the household's appliances were categorised into time categories based on the time of use the appliances in order to determine the contribution of individual appliances at a certain time slot of the day to the total household consumption. Finally, the recommendations that have suggested in this study based on the current study as well as past studies. This means that the recommendations are a combination of all the major studies conducted. Additionally, based on the time a category of the household's appliances, a model was introduced that helped to determine how much of electrical appliances energy consuming in the UK households. Based on this model, the appliances consumption can managed and controlled. Thus, the model will help in mitigating the chances of the energy peak demand and will contribute towards energy and cost savings. Further, this study provides a valuable contribution to the field of smart homes as through the developed model, people can design a more efficient smart home. This specific method of determining energy demand has made the study more appropriate to forecast the 24h electricity demand and electricity price.

In the early feasibility study stage, the information concerning the target project is very limited. It is very common in practice for a Quantity Surveyor (Q.S.) to use the mean value of the historical building price data (with similar characteristics to the target project) to forecast the early construction cost for a target project. Most clients rely heavily on this early cost forecast, provided by the Q.S., and use it to make their investment decision and advance financial arrangement. The primary aim of this research is to develop a statistical model and demonstrate through this developed model how to measure the accuracy of mean value forecast. A secondary aim is to review the homogeneity of construction project cost. The third aim is to identify the best data pooling for mean value cost forecast in early construction stages by making the best use of the data available. Three types of mean value forecasts are considered: (1) the use of the target base group (relating to a source with similar characteristics to the target project), (2) the use of a non-target base group (relating to sources with less or dissimilar characteristics to the target project) and (3) the use of a combined target and non-target base group. A formulation of mean square error is derived for each to measure the forecasting accuracy. To accomplish the above research aims, this research uses cost data from 450 completed Hong Kong projects. The collected data is clustered into two levels as: (1) Level one - by project nature (i.e. Residential, Commercial centre, Car parking, Social community centre, School, Office, Hotel, Industrial, University and Hospital), (2) Level two -by project specification and construction floor area. In this research, the accuracy of mean value forecast (i.e. mean square error) for a total number of 10,539 of combined data groups is measured. From their performance, it may reasonably be concluded that (1) the use of a non-target base group (relating to sources with less or dissimilar characteristics to the target project) never improves the forecasting performance, (2) the use of a target base group (relating to a source with similar characteristics to the target project) cannot always provide the best forecasting performance, (3) the use of a combined target and non-target base group in some cases can furnish a better forecasting performance, and (4) when the cost data groups are clustered into a more detailed level, it can improve the forecasting performance.

"Due to the high variation of critical device parameters inherent in integrated circuit manufacturing, modern integrated circuit designs have evolved to rely on the ratios of similar devices for their performance rather than on the absolute characteristics of any individual device. Today's high performance analog integrated circuits depend on the ability to make identical or matched devices. Circuits are designed using a tolerance based on the overall matching characteristics of their particular manufacturing process. Circuit designers also follow a general rule of thumb that larger devices offer better matching characteristics. This results in circuits that are over designed and circuit layouts that are generally larger than necessary. In this project we develop a model to predict the mismatch in a pair of NPN bipolar transistors. Precise prediction of device mismatch will result in more efficient circuit deigns, smaller circuit layouts and higher test yields, all of which lead to into more reliable and less expensive products."

The horseshoe prior has been shown to successfully handle high-dimensional sparse estimation problems. It both adapts to sparsity efficiently and provides nearly unbiased estimates for large signals. In addition, efficient sampling algorithms have been developed and successively applied to a vast array of high-dimensional sparse estimation problems. In this dissertation, we investigate the prediction performance of the horseshoe prior in sparse regression, and extend the horseshoe prior to two multivariate settings.<br><br>We begin with a study of the finite sample prediction performance of shrinkage regression methods, where the risk can be unbiasedly estimated using Stein's approach. We show that the horseshoe prior achieves an improved prediction risk over global shrinkage rules, by using a component-specific local shrinkage term that is learned from the data under a heavy-tailed prior, in combination with a global term providing shrinkage towards zero. We demonstrate improved prediction performance in a simulation study and in a pharmacogenomics data set, confirming our theoretical findings.<br><br>We then shift to extending the horseshoe prior to handle two high-dimensional multivariate problems. First, we develop a new estimator of the inverse covariance matrix for high-dimensional multivariate normal data. The proposed graphical horseshoe estimator has attractive properties compared to other popular estimators. The most prominent benefit is that when the true inverse covariance matrix is sparse, the graphical horseshoe estimator provides estimates with small information divergence from the sampling model. The posterior mean under the graphical horseshoe prior can also be almost unbiased under certain conditions. In addition to these theoretical results, we provide a full Gibbs sampler for implementation. The graphical horseshoe estimator compares favorably to existing techniques in simulations and in a human gene network data analysis.<br><br>In our second setting, we apply the horseshoe prior to the joint estimation of regression coefficients and the inverse covariance matrix in normal models. The computational challenge in this problem is due to the dimensionality of the parameter space that routinely exceeds the sample size. We show that the advantages of the horseshoe prior in estimating a mean vector, or an inverse covariance matrix, separately are also present when addressing both simultaneously. We propose a full Bayesian treatment, with a sampling algorithm that is linear in the number of predictors. Extensive performance comparisons are provided with both frequentist and Bayesian alternatives, and both estimation and prediction performances are verified on a genomic data set.

本文主要以統計模型為主，應用在團體醫療險給付金額方面，以實證方式找出影響給付金額的重要因素。內容如下：第一章緒論。分為研究動機與目的、研究範圍與限制及本文架構四節。第二章團體醫療險概述。第一節介紹團體醫療險的發展經過；第二節闡述團體醫療險所具備的特性；第三節說明團體醫療險的保障範圍。第三章文獻探討與理論基礎。第一節就相關的的文獻作探討。第二節針對本研究所使用的方法，其所根據的「迴歸模型」理論作一介紹，同時亦針對相關之理論進行探討。第四章實證研究。第一節敘述資料收集的情形並對解釋變數之選取作一分析；第二節則建立合適的迴歸模型。第三節就所建立的迴歸模型進行分析，找出影響團體醫療險給付金額之因素。第五章結論與建議。此章為所有結果作一總結，透過實際的理賠經驗探討現行費率的公平性，並對現行費率提出建議。

本文主要以統計模型為主，應用在團體傷害險給付金額方面，以實證方式找出影響給付金額的重要因素。內容如下：第一章緒論。分為研究動機與目的、研究範圍與限制及本文架構三節。第二章團體傷害險概述。第一節介紹團體傷害險的發展經過；第二節闡述團體傷害險所具備的特性；第三節說明團體傷害險的保障範圍；第四節探討影響團體傷害險給付金額因素之分析。第三章文獻探討與理論基礎。第一節就相關的的文獻作探討；第二節針對本研究所使用的方法，其所根據的「迴歸模型」理論作一介紹，同時亦針對相關之理論進行探討。第四章實證研究。第一節敘述資料收集的情形並對解釋變數之選取作一分析；第二節則建立合適的迴歸模型。第三節就所建立的迴歸模型進行分析，找出影響團體傷害險給付金額之因素。第五章結論與建議。此章為所有研究結果作一總結，透過實際的理賠經驗探討現行費率的公平性，並對現行費率提出建議。

The hypoxic area in the Gulf of Mexico is the second largest in the world, which has received extensive scientific study and management interest. Previous modeling studies have concluded that the increased hypoxic area in the Gulf of Mexico was caused by the increased anthropogenic nitrogen loading of the Mississippi River; however, the nitrogen-area relationship is complicated by many other factors, such as wind, river discharge, and the ratio of Mississippi to Atchafalaya River flow. These factors are related to large-scale climate variability, and thus will not be affected by regional nitrogen reduction efforts. In the research presented here, both statistical (regression) and numerical models are used to study the influence of anthropogenic and climate factors on the hypoxic area variability in the Gulf of Mexico. The numerical model is a three-dimensional, coupled hydrological-biogeochemical model (ROMS-Fennel). Results include: (1) the west wind duration during the summer explain 55% of the hypoxic area variability since 1993. Combined wind duration and nitrogen loading explain over 70% of the variability, and combined wind duration and river discharge explain over 85% of the variability. (2) The numerical model captures the temporal variability, but overestimates the bottom oxygen concentrations. The model shows that the simulated hypoxic area is in agreement with the observations from the year 1991, as long as hypoxia is defined as oxygen concentrations below 3 mg/L rather than below 2 mg/L. (3) The first three modes from an Empirical Orthogonal Function (EOF) analysis of the numerical model output results explain 62%, 8.1% and 4.9% of the variability of the hypoxic area. The Principle Component time series is cross-correlated with wind, dissolved inorganic nitrogen concentration and river discharge. (4) Scenario experiments with the same nitrogen loading, but different duration of upwelling favorable wind, indicate that the upwelling favorable wind is important for hypoxic area development. However, a long duration of upwelling wind decreases the area. (5) Scenario experiments with the same nitrogen loading, but different discharges, indicate that increasing river discharge by 50% increases the area by 42%. Additionally, scenario experiments with the same river discharge, but different nitrogen concentrations, indicate that reducing the nitrogen concentration by 50% decreases the area by 75%. (6) Scenario experiments with the same nitrogen loading, but different flow diver- sions, indicate that if the Atchafalaya River discharges increased to 66.7%, the total hypoxic area increases the hypoxic area by 30%, and most of the hypoxic area moved from east to west Louisiana shelf. Additionally, if the Atchafalaya River discharge decreased to zero, the total hypoxic area increases by 13%. (7) Scenario experiments with the same nitrogen loading, but different nitrogen forms, indicate that if all the nitrogen was in the inorganic forms, the hypoxic area increases by 15%. These results have multiple implications for understanding the mechanisms that control the oxygen dynamics, reevaluating management strategies, and improving the observational methods.

Prediction of flow is necessary for planning and management of water resources. The objective of this study is to estimate mean annual flows for the USA and mean monthly flows for the rivers of central Texas based on the precipitation and their watershed characteristics. Flow varies largely with topographic and climatic parameters and hence generalization of runoff models is difficult. This model aims at providing a prediction at ungaged locations with very few parameters that are easily available and measurable. Scatter in predicted data will be seen at the annual and monthly time scale in the range selected for each data. This model will work on annual and monthly means to reduce the scatter and produce better estimates.

Within this thesis, I performed a systematic review of approaches to broad-scale modelling of disease vector distributions and determined the most widely used methods predict current species niches and project the models forward under future climate scenarios without temporal validation. I then provided a forward-looking summary of emerging techniques to improve the reliability and transferability of those models, including historical calibration. I then predicted Anopheles mosquito distributions across Tanzania in 2001 (before large-scale ITN distributions) and compared this model with countrywide ITN use by 2012 to assess where the most suitable mosquito habitats were located and whether ITN rollouts in Tanzania ensured coverage of such areas. I concluded that ITNs in Tanzania did not optimally target areas most at risk of malaria. In doing so, I provided a new approach to monitoring and evaluating vector control interventions across large spatial scales.