The last twenty years presented increased interest for the study of cerebral processes caused by external events (stimuli). One of the most significant endogenous components of Evoked Potentials is the P600 component. The P600 component may be defined as the most positive peak in the time window between 500 and 800 msec after an eliciting stimulus. This component is thought to reflect the response selection stage of information processing. P600 component is usually less pronounced compared to other components, such as the N100 or the P300. Frequently the P600 component appears as a not-easily discernible secondary peak overlying the ascending negative-going slope of the P300 waveform. In our study we used ERP data from various groups of patients and healthy controls. Patients were recruited from the outpatient university clinic of Eginition Hospital of the University of Athens. The controls were recruited from hospital staff and local volunteer groups. The aim of the study is the implementation of classification systems for these groups, using P600 features. This is usually not achieved well using as features the ERPs amplitude and latency. So for that reason, in our study, we want to extract new features using advanced techniques for processing the original ERPs, such as the Independent Component Analysis (ICA) method. However as a precursor of ICA, is considered the Principal Component Analysis (PCA) method, which we used for comparison reasons to ICA. In the application of ICA we achieve the decomposition of the recorded signals in ICs, supposing temporally independent components and propose ICs selection techniques in order to recompose the P600 component. The next stage was the use of a classification method based on the features extracted using the original data, data extracted through PCA processing and ICA-processed data. First we applied Kolmogorov-Smirnov test to check the normality of the distribution of the features, then we used the Logistic Regression method for classification and finally we have done two implementations of classification using Probabilistic Neural Networks. The first implementation was done with the creation of 15 features from the P600 peak amplitudes from the subjects’ data and the second implementation was done with the creation of four meta-features from the subjects’ P600 amplitude data. The results show that the application of ICA, combined with the logistic regression classification technique, provides notable improvement, compared to the classification performance based on the original ERPs. The main merit of the application is that classification is based on single parameters, i.e. amplitude of the P600 component, or its latency or its termination latency, which are directly related to the brain mechanisms related to ERP generation and pathological processes. / Τα τελευταία 20 χρόνια παρουσιάζεται αυξημένο ενδιαφέρον για την μελέτη εγκεφαλικών επεξεργασιών που προκλήθηκαν από εξωτερικά γεγονότα (ερέθισμα). Ένα από τα πιο σημαντικά ενδογενή συστατικά των Προκλητών Δυναμικών είναι το συστατικό P600. Το συστατικό P600 μπορεί να οριστεί σαν η πιο θετική αιχμή στο χρονικό διάστημα μεταξύ 500 και 800 msec μετά από ένα εκλυτικό ερέθισμα. Το συστατικό αυτό θεωρείται ότι απεικονίζει το στάδιο επιλογής απόκρισης της επεξεργασίας πληροφορίας. Το συστατικό P600 είναι συνήθως λιγότερο έντονο συγκρίνοντας το με άλλα συστατικά, όπως το N100 ή το P300. Συχνά το συστατικό P600 εμφανίζεται ως μια δυσδιάκριτη δεύτερη αιχμή, επικαλύπτοντας την ανοδική αρνητική κλίση της κυματομορφής του P300. Στη μελέτη μας χρησιμοποιήσαμε δεδομένα ΠΔ από ποικίλες ομάδες ασθενών και υγιών μαρτύρων. Οι ασθενείς συλλέχθησαν από τη πανεπιστημιακή κλινική του Αιγηνήτειου Νοσοκομείου του Πανεπιστημίου Αθηνών. Οι υγιείς συλλέχθησαν από το προσωπικό του νοσοκομείου και ομάδες εθελοντών. Ο σκοπός της μελέτης είναι η εφαρμογή συστημάτων ταξινόμησης για αυτές τις ομάδες, χρησιμοποιώντας χαρακτηριστικά του P600. Αυτό συνήθως δεν επιτυγχάνεται καλά χρησιμοποιώντας σαν χαρακτηριστικά το πλάτος και τον λανθάνοντα χρόνο των ΠΔ. Για αυτό το λόγο, στην μελέτη μας, θέλουμε να εξάγουμε νέα χαρακτηριστικά χρησιμοποιώντας προηγμένες τεχνικές για επεξεργασία των αρχικών ΠΔ, όπως τη μέθοδο Ανάλυσης Ανεξαρτήτων Συνιστωσών (ICA). Εντούτοις ως πρόδρομο της ICA, θεωρείται η μέθοδος Ανάλυσης Κύριων Συνιστωσών (PCA), την οποία χρησιμοποιήσαμε για συγκριτικούς λόγους με την ICA. Στην εφαρμογή της ICA προχωρήσαμε στην αποσύνθεση των καταγραφόμενων σημάτων σε Ανεξάρτητες Συνιστώσες και διερευνήσαμε τρεις τεχνικές επιλογής ανεξαρτήτων συνιστωσών μέσω των οποίων επανασυνθέσαμε το συστατικό P600. Το επόμενο βήμα ήταν η χρήση μεθόδου ταξινόμησης βασισμένης στα χαρακτηριστικά που εξάχθηκαν χρησιμοποιώντας τα αρχικά δεδομένα, τα δεδομένα με επεξεργασία PCA και τα δεδομένα με επεξεργασία ICA. Πρώτα εφαρμόσαμε το τεστ Kolmogorov-Smirnov για τον έλεγχο της κανονικότητας της κατανομής των χαρακτηριστικών, μετά χρησιμοποιήσαμε τη μέθοδο Λογαριθμικής Παλινδρόμησης (Logistic Regression) για ταξινόμηση και τελικά πραγματοποιήσαμε δύο εφαρμογές ταξινόμησης χρησιμοποιώντας Πιθανοκρατικά Νευρωνικά Δίκτυα (Probabilistic Neural Networks). Η πρώτη εφαρμογή έγινε με την δημιουργία 15 χαρακτηριστικών από τα πλάτη των αιχμών του P600 από τα δεδομένα των ομάδων και η δεύτερη εφαρμογή έγινε με την δημιουργία τεσσάρων μετά-χαρακτηριστικών από τα δεδομένα των πλατών των ομάδων. Τα αποτελέσματα δείχνουν ότι η εφαρμογή της ICA, συνδυασμένη με την τεχνική ταξινόμησης λογαριθμικής παλινδρόμησης, παρέχει αξιοσημείωτη βελτίωση, συγκριτικά με την απόδοση ταξινόμησης βάση των αρχικών ΠΔ. Η κύρια αξία της εφαρμογής είναι ότι η ταξινόμηση πετυχαίνει ποσοστά μεγαλύτερα του 80% βασιζόμενη σε μία μόνο κάθε φορά παράμετρο, π.χ. το πλάτος του συστατικού P600, ή τον λανθάνοντα χρόνο του ή τον λανθάνοντα χρόνο τερματισμού του, οι οποίες σχετίζονται άμεσα με τους μηχανισμούς του εγκεφάλου σχετικούς με την παραγωγή ΠΔ και τις παθολογικές διαδικασίες.

2007年美國爆發次級房貸違約潮造成了其經濟、房市和股市的不景氣，也波及到持有美國房貸證券化商品的各國，使其承受重大的損失，因此房屋抵押貸款違約的影響因素和金融資產證券化機制對貸款違約風險的影響又再度成為不動產與金融市場上之重要議題。而以往針對美國次貸危機的研究多指出道德風險是造成此次危機的原因之一，但是較缺乏實證研究的支持。 有鑑於此，本研究以我國的台北市和新北市的房屋抵押貸款市場作為研究對象，探討逆選擇和道德風險這兩個資訊不對稱的問題對貸款違約率的影響。研究結果顯示「貸款成數高、貸款利率高、搭配信貸和設定二胎的貸款比較容易違約」，證實逆選擇和道德風險問題確實存在於房屋抵押貸款市場，而且會增加貸款違約的機率。為了降低違約機率，從降低資訊不對稱的角度來看，本研究建議：一、建立全國房貸資料庫；二、將信貸的金額納入房貸的貸款成數中考慮，以降低款人的道德風險。 再者，本研究認為造成次貸危機的根本原因是不當政策導致的保證機制浮濫，以及高風險的房貸證券化商品的氾濫。為了避免我國發生類似次貸危機的事件，從減少資訊不對稱的角度切入，本研究建議我國的金融資產證券化機制應該：一、將道德風險內部化，消除創始機構自利的動機以減少道德風險；二、使用外部信用增強的方式，以確實發揮分散證券風險的作用。 / The 2007 subprime mortgage crisis has severely struck the stability of the worldwide financial markets. Some researches indicate that moral hazard problems are the main factors causing the crisis. However, few studies support asymmetry problems existing in a mortgage market by empirical evidences. First, using the mortgage samples from Taipei City and New Taipei City this study would like to understand if the mortgage market are information asymmetry problems, adverse selection and moral hazard, and conduct the empirical analysis for these factors’ impact on mortgage default. The results show that mortgage default is influenced significantly by the Loan-to-Value （LTV） ratio, contract interest rates, the existence of second liens and credit loans, and jobs. It shows that adverse selection and moral hazard actually exist in the mortgage market. According to the empirical results, secondly, this study proposes suggestions for mortgage lending and financial asset securitization to reduce adverse selection and moral hazard problems and enhance the regulation environment and market’s stability. It is expected that the results of this study will be applied to avoid the occurrence of similar crisis in Taiwan.

<p>This study formed part of a larger project that is concerned with the adaptation of a test of cognitive academic language proficiency, the Woodcock Mu&ntilde / oz Language Survey (WMLS). The WMLS has been adapted from English into isiXhosa and the present study is located within the broader study that is concerned with establishing overall equivalence between the two language versions of the WMLS. It was primarily concerned with the Verbal Analogies (VA) scale. Previous research on this scale has demonstrated promising results, but continues to find evidence of some inequivalence. This study aimed to cross-validate previous research on the two language versions of the WMLS and improve on methodological issues by employing matched groups. It drew upon an existing dataset from the larger research project. The study employed a monolingual matched two-group design consisting of 150 mainly English speaking and 149 mainly isiXhosa learners in grades 6 and 7. This study had two sub aims. The first was to investigate item bias by identifying DIF items in the VA scale across the isiXhosa and English by conducting a logistic regression and Mantel-Haenszel procedure. Five items were identified by both techniques as DIF. The second sub aim was to evaluate construct equivalence between the isiXhosa and English versions of the WMLS on the VA scale by conducting a factor analysis on the tests after removal of DIF items. Two factors were requested during the factor analysis. The first factor displayed significant loadings across both language versions and was identified as a stable factor. This was confirmed by the Tucker&rsquo / s Phi and scatter plot. The second factor was stable for the English version but not for the isiXhosa version. The Tucker&rsquo / s phi and scatter plot indicated that this factor is not structurally equivalent across the two language versions</p>

Le nombre d'unions où les deux conjoints n'ont pas la même langue maternelle est en augmentation depuis les dernières décennies au Québec. Sachant que les enfants issus de ces unions gravitent dans un univers familial plurilingue, l'objectif de ce mémoire est de connaître les langues qui leur sont transmises. En utilisant les données du questionnaire long du recensement canadien de 2006, nous avons procédé à différentes analyses descriptives nous permettant de cerner les langues maternelles véhiculées aux enfants issus d'une union mixte, de vérifier si ces enfants héritent davantage de la langue maternelle de leur mère ou de leur père et s'ils opèrent des substitutions linguistiques avant l'âge de 18 ans, c'est-à-dire si leur langue maternelle diffère de leur langue d'usage. De plus, par le biais de régressions logistiques, nous avons étudié les déterminants contextuel, ethno-culturel et socio-économique les plus susceptibles d'expliquer le choix de la langue transmise aux enfants. Les résultats obtenus démontrent la place prédominante des langues officielles canadiennes, au détriment des langues non officielles, chez les familles exogames. De plus, le choix de la langue maternelle transmise s'avère principalement conditionné par le lieu de résidence, le parcours migratoire des parents et le pays de naissance des enfants. / The number of unions where both partners do not share the same mother tongue has grown substantially over the last decades in Quebec. Given that children born to these unions live in a multilingual family setting, the purpose of this research is to study the mother tongue transmitted to these children. Using the 2006 Canadian census long-form questionnaire, we first conducted various descriptive analyses. These were intended to identify the mother tongue transmitted to children born to mixed-language unions, to ascertain whether children inherit either their mother or father's mother tongue, and to determine if a language shift occurs before the age of 18 years old, in other words whether their mother tongue differs from the principal language they use at home. In addition, through logistic regressions, we examined the contextual, ethnocultural and socioeconomic determinants explaining the choice of the language transmitted to children. The results show the predominance of the two official Canadian languages in mixed-language families, at the expense of non-official languages. Furthermore, the choice of the mother tongue transmitted is mainly conditioned by the place of residence, the parent's migration path and the children's birthplace.

Cette recherche se penche sur l’impact des facteurs de contexte et des facteurs individuels sur les conditions socioéconomiques des résidants des collectivités des Premières Nations du Québec et des résidants des communautés situées à proximité. Des régressions logistiques sur les données censitaires de 2001 ont été réalisées afin de répondre aux questions d’étude. Quatre dimensions, inspirées de l’indice de bien-être (IBC), ont été étudiées : l’activité, le logement, le revenu et la scolarité. Les résultats de recherche montrent que les deux types de facteurs contribuent à l’explication des inégalités sociales. Plus spécifiquement, les inégalités scolaires apparaissent principalement déterminées par les facteurs de contexte bien que les facteurs individuels, tel que l’âge et le genre, soient aussi déterminants. Ces dernières surviennent en amont des inégalités d’emploi et de revenu et expliquent celles-ci. De plus, les inégalités relatives au logement sont expliquées par l’emplacement spatial et le type de communauté de résidence. Par ailleurs, l’ethnicité des répondants ne joue pas un rôle de premier plan dans l’explication des disparités observées, une fois les autres caractéristiques contrôlées, ce qui ne signifie pas qu’il n’existe pas d’inégalités entre Amérindien et non-Amérindien. En fait, des chances différenciées persistent lorsque les autres caractéristiques sont contrôlées. Ainsi, les résultats mettent en évidence l’utilité de déplacer le point focal de la recherche quantitative sur les conditions autochtones du principal fait d’être Amérindien ou non vers un éventail plus large de déterminants. / This research assesses the specific contribution of individual and contextual factors in explaining the socioeconomics discrepancies between members of First Nations communities and those of communities located nearby. Using logistic regression on 2001 census data, four dimensions of socioeconomic conditions, largely inspired by the Community Well-Being Index (CWB), are assessed: employment, housing, income and education. The results of the study show that social inequalities appear correlated to both types of factors. Educational inequalities are primarily due to contextual factors even if individual factors, such as age and gender, also play a role in determining the odds of living social inequalities. Educational inequalities precede employment and income inequalities and, to some extent, explain them. Moreover, housing inequalities are mainly explained by spatial location and residence in a First Nations community Furthermore, the ethnicity of respondents does not play a major role in explaining the discrepancies, once other characteristics are taken into account. This does not mean that social inequalities do not exist between Aboriginal and non-Aboriginal Canadians. Actually, significant differences between these two social categories are observed even when other characteristics are controlled for. Thus, the results of this study point out to the fact that the focus of quantitative research on Aboriginal people’s conditions should be put on additional predictors of inequalities besides “aboriginality”. Also, the review of literature shows a lack of research on social inequalities within First Nations communities in Canada.

When we develop and use species distribution models to predict species' current or potential distributions, we are faced with the trade-offs between model generality, precision, and realism. It is important to know how to improve and validate model generality while maintaining good model precision and realism. However, it is difficult for ecologists to evaluate species distribution models using field-sampled data alone because the true species response function to environmental or ecological factors is unknown. Species distribution models should be able to approximate the true characteristics and distributions of species if ecologists want to use them as reliable tools. Simulated data provide the advantage of being able to know the true species-environment relationships and control the causal factors of interest to obtain insights into the effects of these factors on model performance. I used a case study on Bythotrephes longimanus distributions from several hundred Ontario lakes and a simulation study to explore the effects on model performance caused by several factors: the choice of predictor variables, the model evaluation methods, the quantity and quality of the data used for developing models, and the strengths and weaknesses of different species distribution models. Linear discriminant analysis, multiple logistic regression, random forests, and artificial neural networks were compared in both studies. Results based on field data sampled from lakes indicated that the predictive performance of the four models was more variable when developed on abiotic (physical and chemical) conditions alone, whereas the generality of these models improved when including biotic (relevant species) information. When using simulated data, although the overall performance of random forests and artificial neural networks was better than linear discriminant analysis and multiple logistic regression, linear discriminant analysis and multiple logistic regression had relatively good and stable model sensitivity at different sample size and detection limit levels, which may be useful for predicting species presences when data are limited. Random forests performed consistently well at different sample size levels, but was more sensitive to high detection limit. The performance of artificial neural networks was affected by both sample size and detection limit, and it was more sensitive to small sample size.

When we develop and use species distribution models to predict species' current or potential distributions, we are faced with the trade-offs between model generality, precision, and realism. It is important to know how to improve and validate model generality while maintaining good model precision and realism. However, it is difficult for ecologists to evaluate species distribution models using field-sampled data alone because the true species response function to environmental or ecological factors is unknown. Species distribution models should be able to approximate the true characteristics and distributions of species if ecologists want to use them as reliable tools. Simulated data provide the advantage of being able to know the true species-environment relationships and control the causal factors of interest to obtain insights into the effects of these factors on model performance. I used a case study on Bythotrephes longimanus distributions from several hundred Ontario lakes and a simulation study to explore the effects on model performance caused by several factors: the choice of predictor variables, the model evaluation methods, the quantity and quality of the data used for developing models, and the strengths and weaknesses of different species distribution models. Linear discriminant analysis, multiple logistic regression, random forests, and artificial neural networks were compared in both studies. Results based on field data sampled from lakes indicated that the predictive performance of the four models was more variable when developed on abiotic (physical and chemical) conditions alone, whereas the generality of these models improved when including biotic (relevant species) information. When using simulated data, although the overall performance of random forests and artificial neural networks was better than linear discriminant analysis and multiple logistic regression, linear discriminant analysis and multiple logistic regression had relatively good and stable model sensitivity at different sample size and detection limit levels, which may be useful for predicting species presences when data are limited. Random forests performed consistently well at different sample size levels, but was more sensitive to high detection limit. The performance of artificial neural networks was affected by both sample size and detection limit, and it was more sensitive to small sample size.

Work stress has a substantial impact on employees, organisations and economies; especially in the fragile economic environment since the ‘Great Recession’ of 2008; which has seen employment levels drop and employees willing to endure more stress at work to avoid retrenchment. These impacts include serious health and financial consequences. Attempts should therefore be made to effectively manage and address work stress to lessen these dire consequences. Many models have been developed and theorised to assist in explaining work stress, the pinnacle of these being the job demands-resources (JD-R) model. In JD-R theory, the dual process explains that work-related well-being follows the following processes: An energetic, also called the health impairment process, in which job demands leads to ill health outcomes through burnout; and then a motivational process which presents that job resources leads to positive organisational outcomes, e.g. organisational commitment, through engagement. The main objectives of this research were 1) to investigate a JD-R model in a large South African sample with a categorical estimator; 2) to investigate the reversed causal hypotheses of burnout and engagement in job demands-resources theory over time; 3) to investigate the likelihood of reporting treatment for health conditions based on burnout and engagement, and 4) to investigate the link between burnout and objective financial outcomes, i.e. by medical aid provider expenditure. To achieve the first objective a cross-sectional design was used (n = 15 633) covering numerous sectors in South Africa. A dual process model was specified with job demands (work overload) leading to ill health through burnout, and job resources (colleague and supervisor support, communication, growth opportunities and role clarity) leading to organisational commitment through engagement. Results of structural equation modelling indicated that the proposed JD-R model was a good fit to the sample. Furthermore, burnout was found to mediate the relationship between job demands and ill health with a medium effect. Engagement was found to mediate the relationship between job resources and organisational commitment with a large effect. The second objective, concerning reversed causality, was achieved with a longitudinal design (n = 593). The hypothesized model included burnout and engagement at time one, and at time two work overload as indicator of job demands, and colleague and supervisor support, communication, growth opportunities and role clarity as indicators of job resources. Results indicated that burnout had a significant negative reversed causal effect to supervisor support and colleague support. Engagement showed only one significant result, i.e. a small negative reversed causal relationship with supervisor support. To achieve the third objective, a cross-sectional design was used (n = 7 895). Results for logistic regression analyses showed that an increase in burnout was associated with a significant increase in the estimated odds for reporting an affirmative answer for receiving treatment for any of the health conditions, i.e. cardiovascular conditions, cholesterol, depression, diabetes, hypertension and irritable bowel syndrome. In contrast, an increase in engagement was associated with a decrease in affirmative reporting for cardiovascular conditions, cholesterol and depression; but not for diabetes, hypertension or irritable bowel syndrome. Addressing the link between burnout and financial outcomes was the fourth objective; and met with a cross-sectional design (n = 3 182). Participants were divided into a high and low burnout group based on the comorbidity of exhaustion and cynicism Analysis of covariance (ANCOVA) was implemented, controlling for age and gender, to investigate the difference in medical aid provider expenditure of the two groups. Results revealed that expenditure in the high burnout group was consistently more in all cases, compared to the low burnout group. By way of conclusion, the implications of the research were discussed and recommendations for managers and for future research were made. / Thesis (PhD (Industrial Psychology))--North-West University, Potchefstroom Campus, 2013

Work stress has a substantial impact on employees, organisations and economies; especially in the fragile economic environment since the ‘Great Recession’ of 2008; which has seen employment levels drop and employees willing to endure more stress at work to avoid retrenchment. These impacts include serious health and financial consequences. Attempts should therefore be made to effectively manage and address work stress to lessen these dire consequences. Many models have been developed and theorised to assist in explaining work stress, the pinnacle of these being the job demands-resources (JD-R) model. In JD-R theory, the dual process explains that work-related well-being follows the following processes: An energetic, also called the health impairment process, in which job demands leads to ill health outcomes through burnout; and then a motivational process which presents that job resources leads to positive organisational outcomes, e.g. organisational commitment, through engagement. The main objectives of this research were 1) to investigate a JD-R model in a large South African sample with a categorical estimator; 2) to investigate the reversed causal hypotheses of burnout and engagement in job demands-resources theory over time; 3) to investigate the likelihood of reporting treatment for health conditions based on burnout and engagement, and 4) to investigate the link between burnout and objective financial outcomes, i.e. by medical aid provider expenditure. To achieve the first objective a cross-sectional design was used (n = 15 633) covering numerous sectors in South Africa. A dual process model was specified with job demands (work overload) leading to ill health through burnout, and job resources (colleague and supervisor support, communication, growth opportunities and role clarity) leading to organisational commitment through engagement. Results of structural equation modelling indicated that the proposed JD-R model was a good fit to the sample. Furthermore, burnout was found to mediate the relationship between job demands and ill health with a medium effect. Engagement was found to mediate the relationship between job resources and organisational commitment with a large effect. The second objective, concerning reversed causality, was achieved with a longitudinal design (n = 593). The hypothesized model included burnout and engagement at time one, and at time two work overload as indicator of job demands, and colleague and supervisor support, communication, growth opportunities and role clarity as indicators of job resources. Results indicated that burnout had a significant negative reversed causal effect to supervisor support and colleague support. Engagement showed only one significant result, i.e. a small negative reversed causal relationship with supervisor support. To achieve the third objective, a cross-sectional design was used (n = 7 895). Results for logistic regression analyses showed that an increase in burnout was associated with a significant increase in the estimated odds for reporting an affirmative answer for receiving treatment for any of the health conditions, i.e. cardiovascular conditions, cholesterol, depression, diabetes, hypertension and irritable bowel syndrome. In contrast, an increase in engagement was associated with a decrease in affirmative reporting for cardiovascular conditions, cholesterol and depression; but not for diabetes, hypertension or irritable bowel syndrome. Addressing the link between burnout and financial outcomes was the fourth objective; and met with a cross-sectional design (n = 3 182). Participants were divided into a high and low burnout group based on the comorbidity of exhaustion and cynicism Analysis of covariance (ANCOVA) was implemented, controlling for age and gender, to investigate the difference in medical aid provider expenditure of the two groups. Results revealed that expenditure in the high burnout group was consistently more in all cases, compared to the low burnout group. By way of conclusion, the implications of the research were discussed and recommendations for managers and for future research were made. / Thesis (PhD (Industrial Psychology))--North-West University, Potchefstroom Campus, 2013

Given the overall increase in the availability of computational resources, and the importance of forecasting the future, it should come as no surprise that prediction is considered to be one of the most compelling and challenging problems for both academia and industry in the world of data analytics. But how is prediction done, what factors make it easier or harder to do, how accurate can we expect the results to be, and can we harness the available computational resources in meaningful ways? With efforts ranging from those designed to save lives in the moments before a near field tsunami to others attempting to predict the performance of Major League Baseball players, future generations need to have realistic expectations about prediction methods and analytics. This thesis takes a broad look at the problem, including motivation, methodology, accuracy, and infrastructure. In particular, a careful study involving experiments in regression, the prediction of continuous, numerical values, and classification, the assignment of a class to each sample, is provided. The results and conclusions of these experiments cover only the included data sets and the applied algorithms as implemented by the Python library. The evaluation includes accuracy and running time of different algorithms across several data sets to establish tradeoffs between the approaches, and determine the impact of variations in the size of the data sets involved. As scalability is a key characteristic required to meet the needs of future prediction problems, a discussion of some of the challenges associated with parallelization is included. / Graduate / 0984 / erickson@uvic.ca