6 resultados para Mann–Whitney U Test
em Universidade Federal do Rio Grande do Norte(UFRN)
Resumo:
Forecast is the basis for making strategic, tactical and operational business decisions. In financial economics, several techniques have been used to predict the behavior of assets over the past decades.Thus, there are several methods to assist in the task of time series forecasting, however, conventional modeling techniques such as statistical models and those based on theoretical mathematical models have produced unsatisfactory predictions, increasing the number of studies in more advanced methods of prediction. Among these, the Artificial Neural Networks (ANN) are a relatively new and promising method for predicting business that shows a technique that has caused much interest in the financial environment and has been used successfully in a wide variety of financial modeling systems applications, in many cases proving its superiority over the statistical models ARIMA-GARCH. In this context, this study aimed to examine whether the ANNs are a more appropriate method for predicting the behavior of Indices in Capital Markets than the traditional methods of time series analysis. For this purpose we developed an quantitative study, from financial economic indices, and developed two models of RNA-type feedfoward supervised learning, whose structures consisted of 20 data in the input layer, 90 neurons in one hidden layer and one given as the output layer (Ibovespa). These models used backpropagation, an input activation function based on the tangent sigmoid and a linear output function. Since the aim of analyzing the adherence of the Method of Artificial Neural Networks to carry out predictions of the Ibovespa, we chose to perform this analysis by comparing results between this and Time Series Predictive Model GARCH, developing a GARCH model (1.1).Once applied both methods (ANN and GARCH) we conducted the results' analysis by comparing the results of the forecast with the historical data and by studying the forecast errors by the MSE, RMSE, MAE, Standard Deviation, the Theil's U and forecasting encompassing tests. It was found that the models developed by means of ANNs had lower MSE, RMSE and MAE than the GARCH (1,1) model and Theil U test indicated that the three models have smaller errors than those of a naïve forecast. Although the ANN based on returns have lower precision indicator values than those of ANN based on prices, the forecast encompassing test rejected the hypothesis that this model is better than that, indicating that the ANN models have a similar level of accuracy . It was concluded that for the data series studied the ANN models show a more appropriate Ibovespa forecasting than the traditional models of time series, represented by the GARCH model
Resumo:
Venous ulcer (VU) is a lower limbs injury resulting from inadequate return of venous blood in feet or legs. Although it is not a deadly disease, it causes chronic wounds, which seriously undermine patients´ quality of life (QOL) and sometimes leads to drastic family, social, economic and psychological changes. In this sense, there are several aspects that may influence the venous ulcers patients´ QOL. The study´s objective aimed on the association of socio-demographic and health, health care and clinical injury on UV patients‟ QOL. Analytical studies, which consider the complexity of factors involved in changes in UV patients‟ QOL has a cross-sectional and quantitative approach. The HUOL Ethics Committee approved this project (n.279/09). The collection of data lasted a period of 3 months in 2010 and it took place at the clinic of Angiology at Hospital Universitário Onofre Lopes (HUOL). The data sample consisted of 60 patients treated by UV angiologists in the HUOL Surgical Clinic. The results were analyzed with SPSS 15.0 by descriptive and inferential statistics. The study was based on UV patients that were predominantly female, average age of 61.4 years, that had low education level and low family income, with occupations requiring long periods of standing or sitting, but mostly retired, unemployed or laid off due to the disease and/or due to chronic diseases associated with the UV. The study took also into consideration patients that used inappropriate products, that were improperly treated by a professional caregiver, that lacked of adequate guidance and compression therapy, that performed no lifting of the lower limbs and regular exercise, that the time of injury were greater than or equal to six months, that were missing specific laboratory tests. The study‟s reference were on recurrent lesions, medium to large lesions area, bed of the lesion (injuries) with fibrin and/or necrosis, with amount of exudate with medium to large, odorless and no signs of infection, with tissue loss between 1st and 2nd degree, without collecting swab or biopsy and with pain. In general, QOL of researched individuals were considered low, the maximum score was 69 points, which the areas that were mostly influenced were the total scores of QOL functional capacity (0.021), emotional (0.000) and social functioning (0.080). Of the 60 individuals, 53.3% had scores between 40 and 69 points in SF-36, and they had the best scores in sociodemographic and health variables (ρ = 0.049). In respect to the assistance and injury characteristics, patients who scored between 40 and 69 points in SF-36 had better scores on these characteristics. By combining the socio-demographic variables, health, and handling characteristics of the injury, we observed a significant difference (ρ = 0.032) when linking them with the QOL total scores. When analyzing separately the domains of the SF-36 scores on the quality of life, we find that the areas that showed statistical significance were functional ability (ρ = 0.035), appearance (ρ = 0.019), emotional (ρ = 0.000), and mental health (ρ = 0.050). Among the socio-demographic characteristics studied, gender and marital status contributed more to the reduction of QOL and among the variables of assistance and the injury, orientation, reference and area of UV contributed the most. By analyzing these five variables all together in accordance with the overall score obtained in the quality of life, we found a significant correlation (ρ = 0.002); with 6.23 times more chances of patients have better QOL in the presence of these five positive factors. By conducting the Mann Whitney U test between all the five demographic variables, health, and clinical care, we found that this combination also proved to be significant (ρ = 0.006). Therefore, patients with these five variables positive tend to have a better QOL. Based on these results, we reject the null hypothesis (H0) and accept the alternative hypothesis (H1) proposed in this study because we noted that the QOL of patients with UV is associated with sociodemographic and health, health care and clinical aspects of the injury
Resumo:
The present work investigated the cognitive operation of children diagnosed with acute lymphoblastic leukaemia (ALL), accompanied at pediatric oncologic institutions at the city of Natal/RN. Had participated in this study twenty children, of both sexes, between six and twelve years old, with the ALL diagnostic, who were in treatment (n=10) and out of treatment for at least one year (n=10) and were submitted exclusively to chemotherapy as CNS prophylaxis. The utilized protocol of neuropsychological evaluation covered the following cognitive abilities: intellective capability, attentional and memory systems, and executive functions. Data was analyzed through descriptive and inferential measures, with the support of the Mann-Whitney U Test and T-test, considering the influence of the variables sex, age at diagnostic and the past time since the beginning of the treatment over children s performance. The intellective capability evaluation showed low score to the out-of-treatment groups, female and children under five years old to the diagnostic. In concern of attentional systems, groups showed the expected performance. In a relevant way, in the evaluation of executive functions, were found reduced scores within all groups, especially inside the in-treatment group. Memory evaluation pointed to reduced performance in items concerning to learning evolution and spontaneous evocation after interference to the several groups. It can be concluded, reffer to the occurrence of transitory and permanent impact associated to the intrusion of chemotherapic components during the maturational course of the CNS. It s expected that the present investigation and the development of similar studies enable major comprehension about the mode, extension and repercussion of these damages subsidizing the development of strategies which may minimize them and provide better xxiii life quality to this clinical subgroup
Resumo:
The present study investigated the impact of the treatment modalities of Acute Lymphoblastic Leukemia on neurocognitive abilities of children and adolescents survivors, aged between 6 and 16 years of age, accompanied in pediatric oncology sectors of public health services in the cities of Campina Grande-PB and Natal-RN. The study included 52 children, 13 of these being children and adolescents diagnosed with leukemia and 39 healthy children matched in relation to the study group considering gender, age, school type and level of maternal education. Later the group of children with leukemia was subdivided into two subgroups depending on treatment modality which were submitted: Group 1A (only chemotherapy) and 1B (chemotherapy and radiotherapy). All participants were subjected to a battery of neuropsychological tests that investigated the following neurocognitive abilities: intellectual ability, memory system, attention, visuospatiality and visuoconstruction, processing speed and executive functions. Data were analyzed using descriptive and inferential measurements with the aid of the U test of Mann-Whitney and T test, considering the influence of the variables: sex, age at diagnosis, time since completion of treatment and level of schooling mothers, on the performance of children. Overall, it is concluded that the illness and the treatment of acute lymphoblastic leukemia significantly favors the emergence of cognitive deficits, particularly in terms of visuospatial skills, and executive skills visoconstrutivas. In turn, the treatment modality of radiotherapy is associated with the presence of more severe deficits, highlighting the significant impact on the speed of information processing. It is hoped that the results presented here will contribute to a better understanding of the nature and extent of neurocognitive effects arising ALL treatment
Resumo:
The practices developed in the everyday life of obstetric services are sometimes out of step with the recommendations of the public health policies. Accordingly, this research had the objective of assessing the quality of the care provided to women and children during cases of natural childbirth in municipal public maternity wards of the city of Natal/RN, Brazilian Northeast. We developed a cross-sectional and quantitative study in two maternity wards that provide care actions to pregnant women at regular risk (maternity wards A and B). The participants were 314 puerperal women who were treated during the period between April and July 2014, whose children were born alive, through transpelvic way, with spontaneous or induced beginning of labor and that showed physical and emotional conditions to respond to the proposed questions. The data collection instrument was constructed on the basis of the recommendations of the World Health Organization focused on the care of normal childbirth and validated by skilled judges, and the final version has obtained optimum agreement (k = 0,96; IVC = 0,99). Associated with these recommendations, we used three indicators: percentage of women with induced labor or subjected to elective cesarean section (Indicator A); percentage of women served by a qualified health professional during labor and childbirth (Indicator B); and Bologna Index (Indicator C). The research obtained a favorable opinion of the Research Ethics Committee from the Federal University of Rio Grande do Norte, under the nº 562.313 and Certificate of Presentation for Ethics Appreciation: 25958513.0.0000.5537. The analysis of categories related to the recommendations of the World Health Organization was conducted by means of absolute and relative frequency and the Chi-square Pearson’s and Fisher’s exact tests made the comparison of the differences observed between the two maternity wards. Furthermore, we calculated the percentage of the indicators A and B and with the results of the Indicator C, the quality was assessed as follows: the closer to 5, the better will be the quality, and the closer to 0, the worst will be the quality, and the Mann-Whitney U test was used to compare the differences of the obtained averages. The significance level of 5% was considered in all statistical tests. The differences between the maternity wards were identified with regard to the provision of liquids orally (p=0,018), stimulus for non-supine positions (p=0,002), existence of partograph (p=0,001), support or welcoming by health professionals (p= 0,047), intravenous infusion (p<0,001), supine position (p<0,001), use of oxytocin (p<0,001), food and liquid restriction (p= 0,002) and, lastly, the fact of the touch is performed by more than 1 examiner (p=0,011). The indicators A and B showed percentages of 13,09% and 100%, respectively. The overall average of the Indicator C was equal to 2,07 (± 0,74). There was a statistically significant difference between the averages of the maternity wards (p<0,001). The care actions provided during the process of labor and childbirth is inappropriate, especially in the maternity ward B. It is necessary to implement improvements and redesign the obstetric model in force
Resumo:
Forecast is the basis for making strategic, tactical and operational business decisions. In financial economics, several techniques have been used to predict the behavior of assets over the past decades.Thus, there are several methods to assist in the task of time series forecasting, however, conventional modeling techniques such as statistical models and those based on theoretical mathematical models have produced unsatisfactory predictions, increasing the number of studies in more advanced methods of prediction. Among these, the Artificial Neural Networks (ANN) are a relatively new and promising method for predicting business that shows a technique that has caused much interest in the financial environment and has been used successfully in a wide variety of financial modeling systems applications, in many cases proving its superiority over the statistical models ARIMA-GARCH. In this context, this study aimed to examine whether the ANNs are a more appropriate method for predicting the behavior of Indices in Capital Markets than the traditional methods of time series analysis. For this purpose we developed an quantitative study, from financial economic indices, and developed two models of RNA-type feedfoward supervised learning, whose structures consisted of 20 data in the input layer, 90 neurons in one hidden layer and one given as the output layer (Ibovespa). These models used backpropagation, an input activation function based on the tangent sigmoid and a linear output function. Since the aim of analyzing the adherence of the Method of Artificial Neural Networks to carry out predictions of the Ibovespa, we chose to perform this analysis by comparing results between this and Time Series Predictive Model GARCH, developing a GARCH model (1.1).Once applied both methods (ANN and GARCH) we conducted the results' analysis by comparing the results of the forecast with the historical data and by studying the forecast errors by the MSE, RMSE, MAE, Standard Deviation, the Theil's U and forecasting encompassing tests. It was found that the models developed by means of ANNs had lower MSE, RMSE and MAE than the GARCH (1,1) model and Theil U test indicated that the three models have smaller errors than those of a naïve forecast. Although the ANN based on returns have lower precision indicator values than those of ANN based on prices, the forecast encompassing test rejected the hypothesis that this model is better than that, indicating that the ANN models have a similar level of accuracy . It was concluded that for the data series studied the ANN models show a more appropriate Ibovespa forecasting than the traditional models of time series, represented by the GARCH model
