>Magister Scientiae - MSc / Most standard statistical techniques illustrated in text books assume that the data are collected from a simple random sample (SRS) and hence are independently and identically distributed (i.i.d.). In reality, data are often sourced through complex sampling (CS) designs, with a combination of stratification and clustering at different levels of the design. Consequently, the CS data are not i.i.d. and sampling weights that are developed over different stages, are calculated and included in the analysis of this data to account for the sampling design. Logistic regression is often employed in the modelling of survey data since the response under investigation typically has a dichotomous outcome. Furthermore, since the logistic regression model has no homogeneity or normality assumptions, it is appealing when modelling a dichotomous response from survey data. This research considers the comparison of the estimates of the logistic regression model parameters when the CS design is accounted for, i.e. weighting is present, to when the data are modelled using an SRS design, i.e. no weighting. In addition, the standard errors of the estimators will be obtained using three different variance techniques, viz. Taylor series linearization, the jackknife and the bootstrap. The different estimated standard errors will be used in the calculation of the standard (asymptotic) interval which will be compared to the bootstrap percentile interval in terms of the interval coverage probability. A further level of comparison is obtained when using only design weights to those obtained using calibrated and integrated sampling weights. This simulation study is based on the Income and Expenditure Survey (IES) of 2005/2006. The results showed that generally when weighting was used the estimators performed better as opposed to when the design was ignored, i.e. under the assumption of SRS, with the results for the Taylor series linearization being more stable.

An integral part of the Victorian land registration system is the lodgement of cadastral data.Originally data was lodged to support the operation of the land market and the legal rights ofthe individual owner. The purpose for which it was designed, coupled with the technologythat was available at the time, resulted in a paper based system of plans and indexes. Due tomany external factors, the current land registration system has essentially remained the samefor the past 130 years. However the need for cadastral information means that plan lodgementnow serves a wider range of needs, and although changes have been made to the system, itwould seem that document-based systems are reaching the limit of cost-effectiveimprovement.A detailed study of the Victorian system of data lodgement has shown there to be severalinefficiencies within the system, many of which would benefit by the shift to a digitalenvironment. Research has also shown that the Victorian surveying profession is actuallyquite prepared to adapt to a digital environment, with many surveyors already preparing orsubmitting plans digitally.Other jurisdictions that are experiencing similar problems to Victoria have progressedsubstantially in this area and form ideal examples to learn from. The study of thesejurisdictions has shown that although technically the process of lodging data in a digitalformat is quite straightforward, there are still many technical and legal problems that must beresolved.It is envisaged that in the future, data be lodged in a digital format, which would involve there-engineering of the Victorian land registration system as we know it. This thesis exploresthe concept of the lodgement of cadastral survey data in a digital format, the issues associatedwith such a change and the long term benefits it will provide to the surveying, mapping andland development industries.

The classic time geography concept (space-time path) provides a powerful framework to study travel survey data which is an important source for travel behavior studies. Based on the space-time concept, this research will present a visualizing approach to analyze travel survey data. By inputting the data into GIS software such as TransCAD and ArcGIS and editing the needed information, this study will explain how to create 3D images of travel paths for showing the variation of trip distribution in relation to different social-economic factors deemed as the driving forces of such patterns. Also, this report will address the technical challenges involved in this kind of study and will discuss directions of future research. / text

>Magister Scientiae - MSc / The Cosmological Principle forms part of one of the most fundamental hypotheses of modern Cosmology. So it is very important to assess whether it holds true using observational data, or whether it consists of a mathematical simplification. We probe the statistical isotropy of the Universe using the existing radio continuum data, by means of a local variance estimator. In order to investigate this, we analyse the number count variance of the radio catalog by looking at patches of approximately 10, 15, 20 & 25 degrees in radii, and thus comparing it to mock catalogs which reproduce the matter density power spectrum, as well as the same sky coverage of the real data. We establish criteria for accepting patches that have more than 90%, 70% & 50% of their pixels not masked. We make use of the NRAO VLA Sky Survey (NVSS), whose operational frequency is 1.4 GHz. We perform statistical tests for detecting possible departures from statistical isotropy using galaxy number counts with flux limits of 20 < SNVSS < 1000 mJy. We also compare the real data to the mock catalogs of the radio data in order to assess the statistical significance of our results. We use the local variance estimator for testing the statistical isotropy of our data sample. We find that the statistical properties of our sample are in reasonable agreement with the standard cosmological model. The mean of the distribution for the data falls well within the 95% confidence interval of the average of the simulated mocks. For all the radii and acceptance criteria for the patches, we found no significant deviations beyond those allowed by the standard model. As expected there were no large discrepancies between our mocks and the data. The results are consistent with statistical isotropy.

Bullying is a common problem among children and adolescents in which the consequences can be severe. Bullying is associated with a variety of negative outcomes and can lead to a variety of mental and physical health problems. The purpose of this study was to examine forms of bullying behaviors that were most predictive of student-reported bullying and the frequency of student-reported bullying in response to a variety of bullying behaviors. In this study, an archival dataset was utilized. Data collected in the fall of 2012 came from 8387 6th through 12th grade students who attended 124 public middle and high schools in Anne Arundel County Public Schools, Maryland. The web-based bullying survey, designed as a component of a district-wide bullying prevention initiative, was intended to assess the prevalence, type, and social norms associated with bullying and school violence.&lt;br&gt;For the first research question, logistic regression analyses indicated that teasing and name-calling were the most frequent forms of bullying and were the two primary predictors of student-reported bullying. Social and/or relational forms of bullying were overall the most frequently reported forms of bullying. In contrast, physical or direct forms of bullying and cyberbullying were the least frequent forms of bullying reported.&lt;br&gt;For the second research question, a series of chi-square analyses indicated significant differences for all types of bullying behavior and whether or not student reported being bullied. Specifically, compared to student who did not report being bullied in the past month, those students who did report being bullied within the last month were more likely to report (a) being called names, (b) being threatened, (c) being teased or picked on, (d) being pushed or shoved, (e) having emails or messages sent to others about them, (f) having rumors or lied spread about them, (g) being ignored or left on purpose, (h) having sexual comments or gestures made toward them; and (i) having their property stolen. Based on the results of this current study, several different proposals for future research can be proposed, including (a) examination of the changes in bullying behaviors and reporting of bullying longitudinally, from elementary to high school and (b) comparisons between schools with and without bullying prevention programs in regard to type and frequency of student bullying behaviors and student reporting of bullying. / School of Education; / School Psychology / PhD; / Dissertation;

No description available.

No description available.

Artificial intelligence techniques have produced excellent results in many diverse fields of engineering. Techniques such as neural networks and fuzzy systems have found their way into transportation engineering. In recent years, neural networks are being used instead of regression techniques for travel demand forecasting purposes. The basic reason lies in the fact that neural networks are able to capture complex relationships and learn from examples and also able to adapt when new data become available. The primary goal of this thesis is to develop mode choice models using artificial neural networks and compare the results with traditional mode choice models like the multinomial logit model and linear regression method. The data used for this modeling is extracted from the American Travel Survey data. Data mining procedures like clustering are used to process the extracted data. The results of three models are compared based on residuals and error criteria. It is found that neural network approach produces the best results for the chosen set of explanatory variables. The possible reasons for such results are identified and explained to the extent possible. The three major objectives of this thesis are to: present an approach to handle the data from a survey database, address the mode choice problem using artificial neural networks, and compare the results of this approach with the results of traditional models vis-à-vis logit model and linear regression approach. The results of this research work should encourage more transportation researchers and professionals to consider artificial intelligence tools for solving transportation planning problems. / Master of Science

In regions characterized by semi-arid climates where households’ welfare primarily relies on rainfed agricultural activities, extreme weather events such as droughts can present existential challenges to their livelihoods. To mitigate these risks, numerous social protection programs have been established to assist vulnerable households affected by weather events. Despite efforts to monitor environmental changes through remotely sensed technology, estimating the impact of weather variability on livelihoods remains challenging. This is compounded by the need to select appropriate statistical distribution for weather anomaly measures and household characteristics. We address these challenges by analyzing household consumption data from the Living Standards Measurement Study survey in Niger and systematically evaluating how each input factor affects vulnerability estimates. Our findings show that the choice of statistical distribution can significantly alter outcomes. For instance, using alternative statistical distribution for vegetation index readings could lead to differences of up to 0.7%, which means around 150,000 more households might be misclassified as not vulnerable. Similarly, variations in household characteristics could result in differences of up to 10 percentage points, equivalent to approximately 2 million households. Understanding these sensitivities helps policymakers refine targeting and intervention strategies effectively. By tailoring assistance programs more precisely to the needs of vulnerable households, policymakers ensure that resources are directed where they can make the most impact in lessening the adverse effects of extreme weather events. This enhances the resilience of communities in semi-arid regions. / Master of Science / In drought-prone regions where many families rely on rainfed farming, extreme weather can devastate livelihoods. Governments have created aid programs to assist the most vulnerable households during these climate crises, but identifying who needs help is extremely challenging. Part of this difficulty lies in selecting the right statistical methods for analyzing weather data and household information. In this paper, we focus on Niger, a country that experiences frequent droughts and where over 80% of the population depends on rainfed agriculture. By evaluating household consumption data, we aim to assist in identifying the households who has high probability of becoming poor as a result of unfavorable weather events and thus needs support from social protection programs. In our analysis, we systematically evaluate how each input factor (including household characteristics and statistical distributions) affects households likelihood of becoming poor in the event of weather crises. We find that compared to alternative statistical distributions, using a conventional normal distribution could lead to misclassifying around 150,000 households as non-vulnerable, leaving them without vital assistance. Similarly, using different sets of household characteristics can result in up to 10 percentage points which equivalents to 2 million households that would miss out on much-needed support. Understanding these sensitivities is crucial for policymakers in refining how aid programs identify the vulnerable populations and include them into the protection programs. The improved targeting approach will enhance the resilience of communities in semi-arid regions facing increasing weather variability.

No / Passenger rail overcrowding is fast becoming a problem in major cities worldwide. This problem therefore calls for efficient, cheap and prompt solutions and policies, which would in turn require accurate modelling tools to effectively forecast the impact of transit demand management policies. To do this, we developed an agent-based model of a particular passenger rail system using an activity based simulation approach to predict the impact of public transport demand management pricing strategies. Our agent population was created using a customer/passenger mobility survey dataset. We modelled the temporal flexibility of passengers, based on patterns observed in the departure and arrival behavior of real travelers. Our model was validated using real life passenger count data from the passenger rail transit company, after which we evaluated the use of peak demand management instruments such as ticketing fares strategies, to influence peak demand of a passenger rail transport system. Our results suggest that agent-based simulation is effective in predicting passenger behavior for a transportation system, and can be used in predicting the impact of demand management policies.