Often the basic assumptions of the ANOVA for an experimental design are not met or the statistical model is incorrectly specified. Randomization of treatments to experimental units is expected to protect against such shortcomings. This paper uses randomization theory to examine the impact on the expectations of mean squares, treatment means, and treatment differences for two model mis·specifications: Systematic response shifts and correlated experimental units. Systematic response shifts are presented in the context of the randomized complete block design (RCBD). In particular fixed shifts are added to the responses of experimental units in the initial and final positions of each block. The fixed shifts are called border shifts. It is shown that the RCBD is an unbiased design under randomization theory when border shifts are present. Treatment means are biased but treatment differences are unbiased. However the estimate of error is biased upwards and the power of the F test is reduced. Alternative designs to the RCBD under border shifts are the Latin square, semi-Latin square, and two-column designs. Randomization analysis demonstrates that the Latin square is an unbiased design with an unbiased estimate of error and of treatment differences. The semi-Latin square has each of the t treatments occurring only once per row and column, but t is a multiple of the number of rows or columns. Thus each row-column combination contains more than one experimental unit. The semi-Latin square is a biased design with a biased estimate of error even when no border shifts are present. Row-column interaction is responsible for the bias. Border shifts do not contaminate the expected mean squares or treatment differences, and thus the semi-Latin square is a viable alternative when the border shift overwhelms the row-column interaction. The two columns of the two-column design correspond to the border and interior experimental units respectively. Results similar to that for the semi-Latin square are obtained. Simulation studies for the RCBD and its alternatives indicate that the power of the F test is reduced for the RCBD when border shifts are present. When no row-column interaction is present, the semi-Latin square and two-column designs provide good alternatives to the RCBD. Similar results are found for the split plot design when border shifts occur in the sub plots. A main effects plan is presented for situations when the number of whole plot units equals the number of sub plot units per whole plot. The analysis of designs in which the experimental units occur in a sequence and exhibit correlation is considered next. The Williams Type Il(a) design is examined in conjunction with the usual ANOVA and with the method of first differencing. Expected mean squares, treatment means, and treatment differences are obtained under randomization theory for each analysis. When only adjacent experimental units have non negligible correlation, the Type Il(a) design provides an unbiased error estimate for the usual ANOVA. However the expectation of the treatment mean square is biased downwards for a positive correlation. First differencing results in a biased test and a biased error estimate. The test is approximately unbiased if the correlation between units is close to a half. / Ph. D.

No / Autobiographical memory (AM) concerns the ability to remember past events from one's own life and consists of autobiographical knowledge (personal facts) and autobiographical incidents (personal events). The novelty of this research was to assess both personal factual and personal event AM in Parkinson's disease (PD) for specified lifetime periods. An autobiographical fluency task was used in which participants were asked to recall personal events and personal facts from five separate lifetime periods. Previous findings as well the brain regions affected in PD lead to the hypothesis that Parkinson's patients would recall less autobiographical memories especially for the most recent lifetime periods. Sixteen non-demented and non-depressed Parkinson's patients and sixteen age-education-matched controls participated. The results showed a temporal gradient for the recall of personal events in Parkinson's patients as they recalled fewer events for recent time periods. The PD group also had more difficulties in recalling autobiographical events rather than an autobiographical knowledge. The difficulty in recalling autobiographical events was characterized by overgenerality, with PD patients failing to generate specific episodic memories.

Classic parametric statistical tests, like the analysis of variance (ANOVA), are powerful tools used for comparing population means. These tests produce accurate results provided the data satisfies underlying assumptions such as homoscedasticity and balancedness, otherwise biased results are obtained. However, these assumptions are rarely satisfied in real-life. Alternative procedures must be explored. This thesis aims at investigating the impact of heteroscedasticity and unbalancedness on effect sizes in two-way fixed-effects ANOVA models. A real-life dataset, from which three different samples were simulated was used to investigate the changes in effect sizes under the influence of unequal variances and unbalancedness. The parametric bootstrap approach was proposed in case of unequal variances and non-normality. The results obtained indicated that heteroscedasticity significantly inflates effect sizes while unbalancedness has non-significant impact on effect sizes in two-way ANOVA models. However, the impact worsens when the data is both unbalanced and heteroscedastic. / Statistics / M. Sc. (Statistics)

Thesis (MCur)--Stellenbosch University, 2012. / ENGLISH ABSTRACT: Burnout is one of the challenges that nurses are faced with in their stressful and rapidly changing work environment. The vulnerability of nurses to burnout remains a major concern which affects both the individual and institution. Knowledge about burnout and associated risk factors which influence the development of burnout is vital for early recognition and intervention. The research question which guided this study was: “What are the factors influencing the degree of burnout experienced by nurses working in neonatal intensive care units?” The objectives included determining which physical, psychological, social and occupational factors influenced the degree of burnout experienced by nurses. A descriptive, explorative research design with a quantitative approach was applied. The target population consisted of (n=105) permanent nursing staff members working in the neonatal units of two different hospitals. A convenience sampling method was used. Participants (n=102) who gave voluntary consent to participate was included in the study. Validity and reliability was supported through the use of a validated questionnaire, Maslach Burnout Inventory – General Survey including a section based on demographical information and a section based on physical, psychosocial, social and occupational factors. Validity of the questionnaire was supported by the use of a research methodologist, nurse expert and a statistician in the particular field. A pilot study was done to test the feasibility of the study and to test the questionnaire for any errors and ambiguities. Ethics approval was obtained from Stellenbosch University and permission from the Heads of the hospitals where the study was conducted. The data was analyzed with the assistance of a statistician and these are presented in histograms, tables and frequencies. The relationship between response variables and nominal input variables was analysed using analysis of variance (ANOVA). Various statistical tests were applied to determine statistical associations between variables such as the Spearman test, using a 95% confidence interval. Results have shown that participants experienced an average level of emotional exhaustion, a high level of professional efficacy and a low level of cynicism. Further analyses have shown that there is a statistical significant difference between emotional exhaustion and the rank of the participant (p=<0.01), highest qualification (p=0.05) and a high workload (p=0.01). Furthermore a statistical significant difference was found between professional efficacy and rank of participants (p=<0.01). In addition a statistical significant difference was found between cynicism and the number of years participants were in the profession (p=0.05). Multiple factors were determined in this study that influences the degree of burnout nurses experience. The majority of participants (n=56/55%) experienced decreased job satisfaction and accomplishment, (n=52/51%) of participants experienced that their workload is too much for them and (n=63/62%) participants received no recognition for their work. Recommendations are based on preventative measures, because preventing burnout is easier and more cost-effective than resolving burnout once it has occurred. In conclusion, the prevention strategies, early recognition of work stress and appropriate interventions are crucial in addressing the problem of burnout. / AFRIKAANSE OPSOMMING: Uitbranding is een van die uitdagings waarmee verpleegsters te kampe het in hulle stresvolle en vinnig veranderende werkomgewing. Die kwesbaarheid van verpleegsters vir uitbranding bly ’n kritieke bekommernis wat beide die individu en die inrigting affekteer. Kennis omtrent uitbranding en verwante risiko faktore wat die ontwikkeling van uitbranding beïnvloed, is deurslaggewend vir vroeë opsporing en intervensie. Die navorsingsvraag wat hierdie studie gelei het, is: “Wat is die faktore wat die mate van uitbranding beïnvloed wat deur verpleegsters ondervind word wat in neonatale intensiewe sorgeenhede werk?” Die doelwitte wat ingesluit is, is om te bepaal watter fisiese, sielkundige, maatskaplike en beroepsfaktore die mate van uitbranding wat deur verpleegsters ervaar word, beïnvloed. ’n Beskrywende, ondersoekende navorsingsontwerp met ’n kwantitatiewe benadering is toegepas. Die teikengroep het bestaan uit (n=105) permanente verpleegpersoneel wat in die neonatale eenhede van twee verskillende hospitale werk. ’n Gerieflikheidsteekproef metode is gebruik. Deelnemers (n=102) wat vrywillige toestemming gegee het om deel te neem, is ingesluit in die navorsingstudie. Geldigheid en betroubaarheid is ondersteun deur die gebruik van ’n geldige vraelys van “Maslach Burnout Inventory – General Survey”, asook ’n afdeling gebaseer op demografiese inligting en ’n afdeling gebaseer op fisiese, sielkundige, maatskaplike en beroepsfaktore. Geldigheid van die vraelys is ondersteun deur ’n navorsingsmetodoloog, ’n verpleegspesialis en ’n statistikus op die navorsingsgebied. ’n Loodsondersoek is gedoen om die haalbaarheid van die studie te toets en om die vraelys te toets vir enige foute en dubbelsinnighede. Etiese goedkeuring is verkry van die Universiteit van Stellenbosch en goedkeuring van die Hoofde van die hospitale waar die studie uitgevoer is. Die data is geanaliseer met die hulp van ’n statistikus en is aangebied in histogramtafels en frekwensies. Die verwantskap tussen responsveranderlikes en nominale insetveranderlikes is geanaliseer deur gebruik te maak van die analise van variansie (ANOVA). Verskeie statistiese toetse is toegepas om statistiese assosiasies tussen veranderlikes te bepaal, soos deur van die Spearmantoets gebruik te maak, met ’n 95% betroubaarheidsinterval. Resultate het bewys dat deelnemers ’n gemiddelde vlak van emosionele uitputting, ’n hoë vlak van professionele effektiwiteit en ’n lae vlak van sinisme ervaar. Verdere analise het bewys dat daar ’n statistiese beduidende verskil tussen emosionele uitputting en die rang van die deelnemers (p=<0.01) is, hoogste kwalifikasie (p=0.05) en ’n hoë werklading (p=0.01). Verder is ’n statistiese beduidende verskil gevind tussen professionele effektiwiteit en rang van deelnemers (p=<0.01). Saam hiermee is ’n statistiese beduidende verskil gevind tussen siniesheid en die aantal jare wat deelnemers in die beroep is (p=0.05). Voorts, is veelvuldige faktore bepaal in hierdie studie wat die mate van uitbranding beïnvloed wat verpleegsters ervaar. Die meeste van die deelnemers (n=56/55%) het ’n afname in werksbevrediging en -verrigting ervaar, (n=52/51%) deelnemers het ervaar dat hul werklading te veel is vir hulle en (n=63/62%) deelnemers het geen erkenning vir hulle werk ontvang nie. Aanbevelings is gebaseer op voorkomende maatreëls, want om uitbranding te voorkom, is makliker en meer koste-effektief as om uitbranding te probeer oplos as dit alreeds begin het. Ten slotte, die voorkomende strategieë, vroeë identifisering van werkstres en geskikte intervensies is deurslaggewend om die probleem van uitbranding aan te spreek.

A meta principal desse trabalho foi comparar métodos de estimação para coeficientes de herdabilidade para os modelos inteiramente ao acaso e em blocos casualizados. Para os dois casos foram utilizadas as definições de coeficiente de herdabilidade (h2) no sentido restrito, dadas respectivamente, por h2=4 &#963;2t/(&#963;2+&#963;2t) e h2=4 &#963;2t/(&#963;2+&#963;2t+&#963;2b). . Portanto, é preciso estimar os componentes de variância relativos ao erro experimental (&#963;2) e ao efeito de tratamentos (&#963;2t) quando se deseja estimar h2 para o modelo inteiramente ao acaso. Para o modelo para blocos casualizados, além de estimar os últimos dois componentes, é necessário estimar o componente de variância relativo ao efeito de blocos (&#963;2b). Para atingir a meta estabelecida, partiu-se de um conjunto de dados cujo coeficiente de herdabilidade é conhecido, o que foi feito através da simulação de dados. Foram comparados dois métodos de estimação, o método da análise da variância e método da máxima verossimilhança. Foram feitas 80 simulações, 40 para cada ensaio. Para os dois modelos, as 40 simulações foram divididas em 4 casos contendo 10 simulações. Cada caso considerou um valor distinto para h2, esses foram: h2=0,10; 0,20; 0,30 e 0,40; para cada um desses casos foram fixados 10 valores distintos para o &#963;2, a saber: &#963;2=10; 20; 30; 40; 50; 60; 70; 80; 90; 100. Os valores relativos ao &#963;2 foram encontrados através da equação dada para os coeficientes de herdabilidade, sendo que, para o modelo em blocos casualizados, foi fixado &#963;2b=20 para todas os 40 casos. Após realizadas as 80 simulações, cada uma obtendo 1000 conjunto de dados, e por conseqüência 1000 estimativas para cada componente de variância e coeficiente de herdabilidade relativos a cada um dos casos, foram obtidas estatísticas descritivas e histogramas de cada conjunto de 1000 estimativas. A comparação dos métodos foi feita através da comparação dessas estatísticas descritivas e histogramas, tendo como referência os valores dos parâmetros utilizados nas simulações. Para ambos os modelos observou-se que os dois métodos se aproximam quanto a estimação de &#963;2. Para o delineamento inteiramente casualizado, o método da máxima verossimilhança forneceu estimativas que, em média, subestimaram os valores de &#963;2t, e por conseqüência, tendem a superestimar o h2, o que não acontece para o método da análise da variância. Para o modelo em blocos casualizados, ambos os métodos se assemelham, também, quanto à estimação de &#963;2t, porém o método da máxima verossimilhança fornece estimativas que tendem a subestimar o &#963;2b, e e por conseqüência, tendem a superestimar o h2, o que não acontece para o método da análise da variância. Logo, o método da análise da variância se mostrou mais confiável quando se objetiva estimar componentes de variância e coeficientes de herdabilidade para ambos os modelos considerados. / The main aim of this work was to compare methods of estimation of heritability for the 1- way classification and the 2-way crossed classification without interaction. For both cases the definition of heritability (h2) in the narrow sense was used, given respectively, by h2=4&#963;2t/(&#963;2+&#963;2t) e h2=4&#963;2t/(&#963;2+&#963;2t+&#963;2b). Therefore, there is a need to estimate the components of variance related to the residual (&#963;2) and the effect of treatments (&#963;2t) in order to estimate (h2) for the 1-way classification. For the 2-way classification without interaction, there is a need to estimate the component of variance related to the effect of blocks (&#963;2b) as well as the other two components. To achieve the established aim, a data set with known heritability was used, produced by simulation. Two methods of estimation were compared: the analysis of variance method and the maximum likelihood method. 80 simulations were made, 40 for each classification. For both models, the 40 simulations were divided into 4 different groups containing 10 simulations. Each group considered a different value for h2 (h2=0,10; 0,20; 0,30 e 0,40) and for each one of those cases there were 10 different values fixed for) &#963;2 (&#963;2=10; 20; 30; 40; 50; 60; 70; 80; 90; 100). The values for &#963;2t were found using the equations for the heritability, and for the 2-way crossed classification without interaction, &#963;2b=20 for all the 40 cases. After the 80 simulations were done, each one obtaining 1000 data sets, and therefore 1000 estimates of each component of variance and the heritability, descriptive statistics and histograms were obtained for each set of 1000 estimates. The comparison of the methods was made based on the descriptive statistics and histograms, using as references the values of the parameters used in the simulations. For both models, the estimates of &#963;2 were close to the true values. For the 1-way classification, the maximum likelihood method gave estimates that, on average, underestimated the values of &#963;2t, and therefore the values of h2. This did not happen with the analysis of variance method. For the 2-way crossed classification without interaction, both methods gave similar estimates of &#963;2t, although the maximum likelihood method gave estimates that tended to underestimate &#963;2b and therefore to overestimate h2. This did not happen with the analysis of variance method. Hence, the analysis of variance method proved to be more accurate for the estimation of variance components and heritability for both classifications considered in this work.

Submitted by Deyse Queiroz (deysequeirozz@hotmail.com) on 2018-06-01T14:35:00Z No. of bitstreams: 1 MARIA MARLENE DA SILVA VIEIRA - DISSERTAÇÃO PPGSA PROFISSIONAL 2015..pdf: 1558102 bytes, checksum: 1f1b8136d91ee8b3a7a7993d296c22d5 (MD5) / Made available in DSpace on 2018-06-01T14:35:00Z (GMT). No. of bitstreams: 1 MARIA MARLENE DA SILVA VIEIRA - DISSERTAÇÃO PPGSA PROFISSIONAL 2015..pdf: 1558102 bytes, checksum: 1f1b8136d91ee8b3a7a7993d296c22d5 (MD5) Previous issue date: 2015 / Este trabalho teve como objetivo avaliar a qualidade física, química, compostos bioativos e atividade antioxidante em oito cultivares de feijão-caupi verde. As cultivares utilizadas no experimento foram provenientes de oito cultivares de feijão-caupi, nomeadamente, Costela de Vaca, BRS Marataoã, BRS Itaim, BR 17-Gurguéia, BRS Novaera, Paulistinha, Setentão e Patativa. O trabalho foi subdividido em dois experimentos. No primeiro foram realizadas avaliações físicas de comprimento de vagens verdes, comprimento, largura, espessura, peso e número de grãos de 10 vagens verde e químicas que incluiu a composição centesimal, com determinação da umidade, cinzas, lipídios, proteínas, carboidratos e valor energético, pH, acidez, e açúcares, no segundo foram realizados as avaliações de compostos bioativos como os compostos fenólicos, ácido ascórbico, flavonóides e antocianinas, e atividade antioxidante. Para as avaliações químicas os grãos foram submetidos a dois procedimentos: cru e cozido e para as avaliações de compostos bioativos e atividade antioxidante também avaliando os grãos crus e cozido incluindo o caldo de cocção, foram avaliados de forma independentemente. Todas as análises foram realizadas em quadruplicata nas cultivares cruas, cozidas e no caldo de cocção e as análises físicas contendo 30 repetições das oito cultivares. Os dados obtidos foram submetidos à análise de variância e detectando efeito significativo no teste F, as médias foram comparadas pelo teste de Tukey ao nível de 5% de probabilidade. Verificou-se que todas as cultivares reuniram boas características físicas com exceção da cultivar BRS 17-Gurguéia. Em relação às características químicas, o conteúdo de umidade ficou na faixa de 54,31-63,99% nas cultivares cruas BR 17-Gurguéia e BRS Marataoã e aumentou nas cozidas 68,75-70,79% respectivamente. O conteúdo de cinzas, proteínas, lipídeos e valor energético diminuíram de forma significativa (p<0,05) para todas as cultivares cozidas. O teor de carboidrato diminuiu para todas as cultivares após o cozimento com exceção da cultivar Patativa. Para o conteúdo de açúcares totais as cultivares cruas apresentaram teores de 9,35-10,8 mg /100 g BRS Novaera e Costela de Vaca, após o cozimento, pode-se observar a redução destes, com teores de e de 0,73-1,49 mg/100 g Costela de Vaca e Setentão respectivamente. Para os compostos bioativos, a cultivar Costela de Vaca apresentou o maior teor de clorofila na sua forma crua, no feijão cozido o maior teor de clorofila foi observado para a cultivar BRS Novaera sendo observado também ser a cultivar que obteve a menor perda deste composto. A cultivar Costela de Vaca apresentou o maior teor de carotenoides antes e após o cozimento. Após o cozimento as cultivares apresentaram um aumento no teor de flavonoides para todas as cultivares com exceção das cultivares Costela de Vaca e Setentão. Foram constatadas pequenas concentrações de antocianinas nas cultivares cruas, cozidas e no caldo de cocção. Após o cozimento houve uma redução no teor de ácido ascórbico para todas as cultivares com exceção das cultivares BRS Itaim (4,23 mg/100g) e a cultivar Patativa (5,56 mg/100g) que apresentou um leve aumento depois de cozido. Antes do cozimento, a cultivar BRS Marataoã apresentou maior atividade antioxidante (97,71 g feijão. g DPPH-1). Os caldos de cocção também apresentaram relevante teor de compostos bioativos, com destaque para as cultivares Costela de Vaca 43,34 mg/100g e BRS Marataoã 51,88 mg/100g e atividade antioxidante com destaque para a cultivar BRS Marataoã (79,59 g feijão. g DPPH-1). Concluiu-se que as cultivares apresentaram boas características físicas com exceção da cultivar BRS 17-Gurguéia. Mesmo após o processamento térmico, as cultivares manteve características nutritivas e funcionais relevantes, sendo recomendado o seu consumo juntamente com o seu caldo de cocção para uma maior retenção de compostos com propriedade antioxidante. / This study aimed to evaluate the physical, chemical, bioactive compounds and antioxidant activity in eight cowpea green cultivars. The cultivars used in the experiment were from eight cowpea cultivars, namely, Costela de Vaca, Marataoã BRS, BRS Itaim, BR-17 Gurguéia, BRS Novaera, Paulistinha, Setentão and Patativa. The work was divided into two experiments. In the first it was conducted physical evaluations long green pods, length, width, thickness, weight and number of 10 green and chemical pods grains that included the chemical composition, with determination of moisture, ash, lipids, proteins, carbohydrates and energy value, pH, acidity and sugars in the second were conducted reviews of bioactive compounds such as phenolic compounds, ascorbic acid, flavonoids and anthocyanins, and antioxidant activity. For chemical evaluations grains underwent two procedures: raw and cooked and reviews of bioactive compounds and antioxidant activity also evaluating the raw and cooked grains including broth cooking were evaluated so independently. All analyzes were carried out in quadruplicate in raw, cooked cultivars and cooking broth and physical analysis containing 30 repetitions of the eight cultivars. The data were submitted to analysis of variance and detecting significant effect on the F test, the averages were compared by Tukey test at 5% probability. It was found that all cultivars gathered good physical characteristics except BRS 17-Gurguéia. With regard to chemical characteristics, the moisture content was in the range of 54.31 to 63.99% in raw cultivars BR-17 and BRS Gurguéia Marataoã and increased in cooked from 68.75 to 70.79% respectively. The content of ash, protein, lipids and energy value decreased significantly (p <0.05) for all cultivars cooked. The carbohydrate content decreased for all cultivars after cooking with the exception of Patativa cultivar. For total sugars content of the raw samples had levels of 9.35 to 10.8 mg / 100 g BRS Novaera and Costela de vaca, after baking, can observe the reduction thereof with contents of 0.73 and -1.49 mg / 100 g Costela de vaca and Setentão respectively. For bioactive compounds, to cultivate Costela de vaca had the highest chlorophyll content in its raw form, the baked beans the highest chlorophyll content was observed for BRS Novaera being observed also be cultivating showed the lowest loss of this compound. Cultivar Costela de vaca had the highest carotenoid content before and after cooking. After cooking the cultivars showed an increase in flavonoid content for all cultivars with the exception of Costela de vaca cultivars and Setentão. Small concentrations of anthocyanins were found in raw varieties, cooked in broth and cooking. After cooking there was a reduction in the ascorbic acid content in all cultivars except for BRS Itaim (4.23 mg / 100g) and cultivate Patativa (5.56 mg / 100g) which showed a slight increase after cooked. Before cooking, BRS Marataoã showed higher antioxidant activity (97.71 g beans. DPPH g-1). cooking broths also presented relevant content of bioactive compounds, especially the Costela de vaca cultivars 43.34 mg / 100g and BRS Marataoã 51.88 mg / 100g and antioxidant activity especially BRS Marataoã (79.59 g beans. DPPH g1). It was concluded that the cultivars showed good physical characteristics except BRS 17-Gurguéia. Even after thermal processing cultivars kept nutritional relevant functional characteristics, their consumption is recommended along with their cooking broth for greater retention of compounds with antioxidant properties.

Em experimentos que envolvam um fator quantitativo e um qualitativo, é aconselhável que, se detectado efeito significativo da interação entre os fatores na análise de variância, recorra-se a análise de regressão no desdobramento da mesma, no entanto nem sempre a utilização de modelos de regressão linear é a forma mais adequada para avaliar o efeito do fator quantitativo. Neste trabalho é apresentada a forma de ajuste de um modelo de regressão não linear em um experimento com medida repetida no tempo. No experimento considerou-se o ganho de peso, em quilos, de ovinos, machos e fêmeas, da raça Santa Inês em doze idades diferentes. Conduzido como parcela subdividida, pois fator tempo não foi aleatorizado, a análise variância necessita de correção dos graus de liberdade devido à condição de esfericidade não satisfeita. A correção de Geisser e Greenhouse (G-G) foi utilizada para os efeitos da interação e do tempo. O teste F na análise de variância apresentou resultado significativo para interação entre os fatores e, no desdobramento da interação, para avaliação do efeito do fator tempo em cada nível do fator sexo foi proposto o ajuste do modelo Gompertz bem como um teste de aderência para o modelo. Após o ajuste do modelo aos dados de peso de ovinos também foi considerado no estudo a comparação dos parâmetros das curvas de machos e fêmeas. Pela análise proposta foi possível concluir que o modelo univariado, com esquema de parcelas subdivididas, pode ser utilizado em experimentos de crescimento animal, porém sua aplicação está sujeita a verificação da condição de esfericidade. Também foi verificado que incorporar, no desdobramento de interações, o ajuste do modelo Gompertz é um procedimento viável e permitiu avaliar a real qualidade de ajuste do modelo aos dados. Com a comparação dos parâmetros das curvas ajustadas verificou-se que ovinos machos e fêmeas apresentam valores estatisticamente iguais para os parâmetros &alpha; e &gamma;, ambos relacionados com o peso ao nascer dos animais. O peso máximo esperado para fêmea (40,7kg) é estatisticamente inferior ao encontrado para os machos (57,3kg), no entanto, sua taxa de crescimento (0,011kg/dia para fêmeas) é superior (0,007kg/dia para machos), ou seja, as fêmeas atingem o peso de estabilização mais rapidamente que os machos. / In experiments involving a qualitative and a quantitative factor, it is advisable that if a significant interaction is detected between factors in the analysis of variance, one should perform regression analysis of the splitting factors. However, the use of linear regression models is not always the most appropriate way to assess the effect of the quantitative factor. This paper presents a way to fit a nonlinear regression model in an experiment with repeated measurements over time. In the experiment, the weight gain of male and female Santa Inês breed sheep, in pounds, in twelve different ages is measured. Conducted in a split-plot design, as the time factor was not randomized, the analysis of variance requires correction of the degrees of freedom, as the sphericity condition is not satisfied. The Greenhouse and Geisser correction (G-G) was used for the purposes of interaction and time. The F test in the analysis of variance showed a significant result for the interaction between the factors and the splitting of the interaction. In order to evaluate the effect of the time factor at each level of the gender factor, a Gompertz model was proposed, as well as a test of model adherence. After fitting the model to the data, a comparison study of the parameters for males and females was also made. For the proposed analysis, we concluded that the univariate model, with split-plot design, can be used in experiments of animal growth, but its application is prone to verification of the sphericity condition. They also found that the incorporation of the splitting of interactions, by adjusting the Gompertz model, is a viable procedure and allowed to evaluate the real quality of fit. By comparing the fitted parameter values, it was found that males and females have statistically identical values for the parameters &alpha; and &gamma;, both related to the birth weight of the animals. The maximum weight expected for a female (40.7 kg) is statistically lower than that found for the males (57.3 kg), however, their growth rate (0.011 kg / day for females) is greater than the males\' (0.007 kg / day for males), i.e., females reach weight stabilization faster than males.

There are four major aims of this study: Firstly, factors regarding university students&rsquo / approaches to studying, self-efficacy in mathematics, problem solving strategies, demographic profile, mathematical thinking and reasoning competencies were identified through the adopted survey and the competency test which was designed by the researcher. These scales were administered to 431 undergraduate students of mathematics, elementary and secondary mathematics education in Ankara and in Northern Cyprus and to prospective teachers of classroom teacher and early childhood education of teacher training academy in Northern Cyprus. Secondly, three structural models were proposed to explore the interrelationships among idenitified factors. Thirdly, among three models, the model yielding best fit to data was selected to evaluate the equality of the factor structure across Ankara and Northern Cyprus regions. Lastly, differences regarding pre-identified factors with respect to gender, region and grade level separately and dual, triple interaction effects were investigated through two two-way MANOVA and a three-way ANOVA analyses. Exploratory and confirmatory factor analyses were employed to determine the factors / meaning orientation, mathematics self-efficacy, motivation, disorganized study methods and surface approach for the survey and &lsquo / expressing, extracting and computing mathematically&rsquo / (fundamental skills) and &lsquo / logical inferencing and evaluating conditional statements in real life situations&rsquo / (elaborate skills) for the test. The three models commonly revealed that while mathematics self-efficacy has a significant positive effect on both fundamental and elaborate skills, motivation which is a combination of intrinsic, extrinsic and achievement motivational items was found to have a negative direct impact on fundamental skills and has a negative indirect contribution upon elaborate skills. The results generally support the invariance of the tested factor structure across two regions with some evidence of differences. Ankara region sample yielded similar factor structure to that of the entire sample&rsquo / s results whereas / no significant relationships were observed for Northern Cyprus region sample. Results of gender, grade level and region related differences in the factors of the survey and the test and on the total test indicated that, females are more meaning oriented than males. &lsquo / Fourth and fifth (senior)&rsquo / and third year university students use disorganized study methods more often than second year undergraduate students. In addition, senior students are more competent than second and third year undergraduate students in terms of both skills. Freshmen students outscored sophomore students in the elaborate skills. Students from Ankara region are more competent in terms of both skills than students from Northern Cyprus region. This last inference is also valid on the total test score for both regions. Males performed better on the total test than females. Moreover, there exist region and grade level interaction effect upon both skills. Additionally, significant interaction effects of &lsquo / region and gender&rsquo / , &lsquo / region and grade level&rsquo / , &lsquo / gender and grade level&rsquo / and &lsquo / region and gender and grade level&rsquo / were detected upon the total test score.

In this work, feasibility of utilizing municipal incinerator fly ash (MIFA) of different sources as a substitute of raw materials for steel-making in a mini-mill was studied. Also studied included the efficacy of this mode of melting treatment and recycling. Under the condition of adding 1 wt% MIFA to scrap iron/scrap steel for partial replacement of lime, the L9 orthogonal arrays of Taguchi methods were utilized to investigate the effects of MIFA melting treatment of different sources by an electric arc furnace (EAF). Four experimental factors (i.e., scrap iron mass, lime mass, coke mass, and MIFA mass) were selected to study their effects on Pb leaching of EAF dust and slag. Test results for MIFA obtained from Plants K1, K2, and K3 show that EAF dust remains hazardous as it is originally a listed waste. On the other hand, slag so generated remains nonhazardous based on the TCLP results. The experimental results of EAF dust and slag were further subjected to the analysis of variance (ANOVA) and regular analysis. Using this process, the optimal operating conditions with respect to the leached Pb concentration would be as follows: (1) Plant K1(injection mode operation)--87 tons of scrap iron, 1.4 tons of lime, 0.4 ton of coke, and 0.9 ton of MIFA; (2) Plant K2(injection mode operation)--90 tons of scrap iron, 1.4 tons of lime, 0.7 ton of coke, and 1.1 tons of MIFA; (3) Plant K2(one-time-charge mode operation)--90 tons of scrap iron, 1.4 tons of lime, 0.9 ton of coke, and 0.7 ton of MIFA; (4) Plant K3(injection mode operation)--85 tons of scrap iron, 1.4 tons of lime, 0.7 ton of coke, and 0.9 ton of MIFA; and (5) Plant K3(one-time-charge mode operation)--87 tons of scrap iron, 1.5 tons of lime, 0.4 ton of coke, and 0.7 ton of MIFA. In this study, using MIFA from Plant K2 as an example, it was found that it required 29-35 kg of lime per ton of steel billets produced when MIFA was added. Under a normal operation of EAF steel-making, however, it required 35-45 kg of lime per ton of steel billets produced based on the past experience. In average, when MIFA is added, it needs only 32 kg of lime per ton of steel billets produced as compared to 40 kg of lime for regular steel-making. In other words, it would result in a reduction of 8 kg of lime per ton of steel billets produced by using this novel process. Based on an average monthly production of 20,973 tons of steel billets and a unit cost of 2,200 NT$ per ton of lime, a monthly saving of lime cost would be 369,125 NT$. Namely, about 4.4 million NT$ per year. In addition, it was also found that using this novel process to melt MIFA would not deteriorate the quality of steel billets and bars produced.

Thesis--University of Oklahoma. / Includes bibliographical references (leaves 99-101).