Thesis (Ph. D.)--Rutgers University, 1979. / Vita. eContent provider-neutral record in process. Description based on print version record. Includes bibliographical references (leaves 231-238).

Thesis (M.S. in L.S.)--University of North Carolina. / eContent provider-neutral record in process. Description based on print version record. Includes bibliographical references.

Thesis (Ph. D.)--University of California, San Diego and San Diego State University, 2003. / Vita. Includes bibliographical references (leaves 219-228).

Many applications of analysis of ranking data arise from different fields of study, such as psychology, economics, and politics. Over the past decade, many ranking data models have been proposed. AdaBoost is proved to be a very successful technique to generate a stronger classifier from weak ones; it can be viewed as a forward stagewise additive modeling using the exponential loss function. Motivated by this, a new AdaBoost algorithm is developed for ranking data. Taking into consideration the ordinal structure of the ranking data, I propose measures based on the Spearman/Kendall distance to evaluate classifier instead of the usual misclassification rate. Some ranking datasets are tested by the new algorithm, and the results show that the new algorithm outperforms traditional algorithms. The distance-based model assumes that the probability of observing a ranking depends on the distance between the ranking and its central ranking. Prediction of ranking data can be made by combining distance-based model with the famous k-nearest-neighbor (kNN) method. This model can be improved by assigning weights to the neighbors according to their distances to the central ranking and assigning weights to the features according to their relative importance. For the feature weighting part, a revised version of the traditional ReliefF algorithm is proposed. From the experimental results we can see that the new algorithm is more suitable for ranking data problem. Error-correcting output codes (ECOC) is widely used in solving multi-class learning problems by decomposing the multi-class problem into several binary classification problems. Several ECOCs for ranking data are proposed and tested. By combining these ECOCs and some traditional binary classifiers, a predictive model for ranking data with high accuracy can be made. While the mixture of factor analyzers (MFA) is useful tool for analyzing heterogeneous data, it cannot be directly used for ranking data due to the special discrete ordinal structures of rankings. I fill in this gap by extending MFA to accommodate for complete and incomplete/partial ranking data. Both simulated and real examples are studied to illustrate the effectiveness of the proposed MFA methods. / published_or_final_version / Statistics and Actuarial Science / Doctoral / Doctor of Philosophy

M. Tech. Information Networks / This dissertation reports on the development of an algorithm based on e-commerce matchmaking to select students. The student selection is an important strategic decision making task for the management of higher educational institutions and human resource departments of corporate organizations. The selection task has proven to be tedious mainly because of the decision process, the fundamental assumptions made and the level of accuracy achieved. The decision error that results from inaccurate student selection process is one source of skill mismatch. This work therefore seeks to improve the student selection accuracy using matchmaking approach. In doing so, e-commerce matchmaking method is applied to student selection and offered as an effective way of integrating cognitive and noncognitive skills to improve the selection accuracy. The efficacy of the matchmaking algorithm is demonstrated through a prototype implementation of the algorithm and specifically applied to university student selection.

The prey selection and predatory behaviour of a single pride of lions (Panthera leo) was studied in the 8500 ha Karongwe Game Reserve from 1999–2005. The study focused on the difference between prey selection in the first three years when a two-male coalition was present with a similar period thereafter when one of the males was removed and subadult males dispersed from the pride. A total of 662 kills were recorded, with blue wildebeest (Connochaetes taurinus), warthog (Phacochoerus africanus), waterbuck (Kobus ellipsiprymnus), zebra (Equus burchelli) and impala (Aepyceros melampus) being the most preferred species. Although there was preference for these species, and adult prey were favoured, there was no significant selection for prey size, age or gender. There was a significant difference in the number of kills made when the two-male coalition was present as opposed to the single pride male. The solitary pride male spent significantly more time with the females and shared most of their kills, and during this period dispersing subadult males killed a substantial amount of prey when separated from the pride. Knowledge on predator feeding behaviour is important for managers to assess impact on prey populations in small reserves in order to manage them correctly, thereby preventing depletion of such populations.

The elevenp apersa ssociatedw ith this submissionre flect a researchp rogrammeth at has as its centralc onceptualf rameworka synthesiso f the traditionally competing perspectiveosf the 'externalla bour market'andt he 'internall abourm arketýT he Holt and David 'stock! and 'flow' model of the former is integrated with Doeringer and Piore'sm odelo f labour allocationa nd utilisation within the organisationto createa 'syntheticp aradigmt!h at offers, it is argued,a moreh olistic insighti nto the operation of labour markets.O ne especialc onsequenceo f the use of this paradigm is the opening up of the 'black box! that is the f= in much of the traditional labour economics literature. Not only are policies of company recruitment and selection transformedto becomee ssential,in tegral elementsw ithin the researchp rogramme, the externall abourm arketc onsequenceosf thesep oliciesa re seent o havei mportant implications for the identification and analysis of 'problems' of the external labour market. For purposes of the introductory, synthesising chapter, the eleven papers are subdivided into three themes. After an essential, preliminary quasi-ideological discussion of the role of perspectives in the literature pertaining to labour markets, the subsequent, predominantly empirical papers focus upon two aspects of the interrelationships between internal and external labour markets viz. engagements i. e. flows, principally from the external labour market, into organisations; and separations ie. flows from organisations, principally but not exclusively to, the external labour market. The synthesising chapter demonstrates - and the accompanying papers evidence - both the viability and the efficacy of the 'synthetic paradigm! and illustrates the additional insights into the problems and policies of employment and Iabour markets which accrue from its application.

Concrete overlays have been a rehabilitation method for many years. It has been extensively utilized and studied in other states, but Texas is still at an initial stage of fully implementing the method. The large volume of concrete highways in Texas makes bonded concrete overlays, unbonded concrete overlays, and whitetoppings very viable options. However, there is a lack of educational guidelines for pavement engineers for concrete overlay construction. This research presents the information gathered from literature review, condition survey, and evaluation of existing concrete overlays in Texas. Also, a laboratory research was performed for recommendations for materials selection and construction for concrete overlays. From these, guidelines for materials selection and construction method developed that will assist in future concrete overlays in Texas are presented. / text

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

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