Fundação de Amparo a Pesquisa no Estado do Rio Grande do Sul / Knowing the consumer and their attitudes at the completion of purchases is a behavior that has been studied for several decades. Based on the theory of consumer behavior this study is to spend one more contribution to academia and industry, to present the factors that influence young people to the habit of doing or not planning ahead to situations of purchase. Thus the problem of research proposed in this study was: "What are the factors that influence the act of performing and non-planned purchases planned?". For this was a descriptive study of the quantitative type, involving a survey of field of 600 respondents, a stratified sample covering the proportion of graduate students from four institutions of higher education. Was extracted from the literature review some factors that could be linked to the fact that the purchases are made in a planned or not and, therefore, could be investigated. Bearing in mind that each factor was chosen consisting of many variables realized the need to reduce the initial set of variables, but without compromising the original meaning of each factor and, therefore, appealed to the statistical technique of cluster analysis. For a better understanding of the phenomenon it was studied by logistic regression analysis applied to other variables of the previous technique, there are aspects that are related to the increased likelihood that the purchases are planned and implemented in a Nor -planned. Thus, it was found that self-esteem and age tend to increase the chance of occurring and that the purchases planned income, materialism and compulsive buying behavior increases the likelihood of non-planned purchases occur. Furthermore, no relationship was found between any of the family structure and social factors to the act of planning or not purchasing the university. How the results can not be generalized, taking into view that was conducted among a specific audience, they become further research to better understanding and deeper in this area of study. / Conhecer o consumidor e suas atitudes no momento da realização de compras é um comportamento que vem sendo estudado há várias décadas. Com base na teoria do comportamento do consumidor este estudo tem como finalidade passar mais uma contribuição para o meio acadêmico e empresarial, ao apresentar aspectos que influenciam os jovens no hábito de realizar planejamento ou não frente a situações de compra. Dessa forma, o problema de pesquisa proposto nesse estudo foi: Quais são os fatores influenciadores do ato de realizar compras planejadas e não-planejadas? . Para isso foi realizada uma pesquisa descritiva do tipo quantitativa, envolvendo um levantamento de campo de 600 respondentes, de uma amostra estratificada proporcional abrangendo os estudantes de graduação de quatro Instituições de Ensino Superior. Foi extraído da revisão de literatura alguns fatores que poderiam estar vinculados ao fato de as compras serem efetuadas de forma planejada ou não e que, por isso, mereciam ser investigados. Tendo-se em vista que cada fator escolhido era constituído por muitas variáveis, percebeu-se a necessidade de reduzir esse conjunto inicial de variáveis sem, no entanto, comprometer o significado original de cada fator e, para isso, recorreu-se a técnica estatística de análise de cluster. Para um melhor entendimento do fenômeno estudado buscou-se por meio da análise de regressão logística, aplicada às variáveis restantes da técnica anterior, verificar quais são os aspectos que estariam relacionados com o aumento da probabilidade de as compras serem executadas de forma planejada e também nãoplanejadas. Desse modo, constatou-se que a auto-estima e a idade tendem a aumentar a chance de ocorrer compras planejadas e que a renda, o materialismo e o comportamento compulsivo de compra aumentam a probabilidade de ocorrer compras não-planejadas. Além disso, não foi evidenciada relação linear alguma entre os fatores estrutura familiar e socialização ao ato de planejamento ou não de compras pelos universitários. Como os resultados obtidos não podem ser generalizados, tendo-se em vista que fora realizado junto a um público específico, tornam-se necessárias novas pesquisas para uma melhor compreensão e aprofundamento nessa área de estudo.

Enterococci levels are measured to assess water safety in recreational beaches through a state surveillance program. This surveillance informs the public of beach safety, yet the sampling methodology is limited to only making an advisory posting one sample at a time. This methodology poses a challenge for managers such as: 24 hour advisory waiting period, untested days and extreme variability of enterococci levels in the environment. Therefore, there is a need to integrate adaptive management methodologies that can assist managers to proactively assess beach water safety. This study explored the utility of a historical analysis and logistic regression modeling as a method and as an advisory tool. The analysis utilized 10 years of enterococci surveillance data (7,422 samples) from 15 sub-tropical beaches in Miami-Dade County, Florida. It was determined that Miami beaches have historical low enterococci exceedance counts (3% of total data), that there are some beaches that are more propense to higher exceedance counts than others and that the wet season overall did not readily appear to affect exceedances counts. The logistic regression model utilized an exceedance/ non-exceedance dichotomy and spatial, temporal and annual variables. The model indicated that the overall range of probability of having an exceedance for the sampled beaches under each variable was less than 10%. The ability to use this model and get probability results showed that logistic regression is an accurate statistical tool that provides the historical probabilities of an exceedance on a beach and can complement a random sampling methodology. Furthermore it’s a simple and inexpensive methodology that provides the ability to categorize and recognize patterns estimating the surveillance-managed sample sites probabilities that provides foresight as to where to focus resources in order to reduce risk and facilitating beach management. Through the use of a historical analysis and a logistic regression model, it is possible to address dynamic recreational beach environments with a large-scale view and in a historically comprehensive manner, instead of only making management choices sample by sample.

The rainbow parrotfish Scarus guacamaia is a prominent herbivore in the coastal waters of southeastern Florida whose life history is strongly linked to a dependence on both mangrove and coral reef habitats. Rainbow parrotfish in turn serve in maintaining the health of coral reefs by keeping algal populations in check. This study used NOAA Fisheries data from the Mangrove Visual Census and the Reef Visual Census in Biscayne Bay and Upper Florida Bay. Observations of abiotic factors at individual sites were used to correlate and predict presence and absence of this species. This was done to visualize habitat presence and ontogenetic shifts present in this species between juvenile and adult stages through ArcGIS mapping. Logistic regression analysis was used to predict presence or absence using the environmental variables of temperature, dissolved oxygen, salinity, average depth, distance from channel openings, mangrove presence, temperature Δ, and salinity Δ. Average depth, distance from channel openings, temperature Δ and salinity Δ were significant in predicting the presence of this species, while salinity, temperature, dissolved oxygen, and mangrove presence were not. Conservation efforts for this species, listed as vulnerable under the IUCN, need to be given greater consideration. The health of this and other parrotfish may have a greater impact on coral reef ecosystems across the Caribbean Sea than currently acknowledged and management breadth and priorities should be adjusted to reflect this role.

In marketing, behaviour of users is analysed in order to discover which channels (for instance TV, Social media etc.) are important for increasing the user’s intention to buy a product. The search for better channel attribution models than the common last-click model is of major concern for the industry of marketing. In this thesis, a probabilistic model for channel attribution has been developed, and this model is demonstrated to be more data-driven than the conventional last- click model. The modelling includes an attempt to include the time aspect in the modelling which have not been done in previous research. Our model is based on studying different sequence length and computing conditional probabilities of conversion by using logistic regression models. A clickstream dataset from an online store was analysed using the proposed model. This thesis has revealed proof of that the last-click model is not optimal for conducting these kinds of analyses.

Beaches can provide a natural barrier between the ocean and inland communities, ecosystems, and resources. These environments can move and change in response to winds, waves, and currents. When a hurricane occurs, these changes can be rather large and possibly catastrophic. The high waves and storm surge act together to erode beaches and inundate low-lying lands, putting inland communities at risk. There are thousands of buoys in the Atlantic Basin that record and update data to help predict climate conditions in the state of Florida. The data that was compiled and used into a larger data set came from two different sources. First, the hurricane data for the years 1992 – 2014 came from Unisys Weather site (Atlantic Basin Hurricanes data, last 40 years) and the buoy data has been available from the national buoy center. Using various statistical methods, we will analyze the probability of a storm being present, given conditions at the buoy; determine the probability of a storm being present categorically. There are four different types of sinkholes that exist in Florida and they are: Collapse Sinkholes, Solution Sinkholes, Alluvial Sinkholes, and Raveling Sinkholes. In Florida there are sinkholes that occur, because of the different soil types that are prevalent in certain areas. The data that was used in this study came from the Florida Department of Environmental Protection, Subsidence Incident Reports. The size of the data was 926 with 15 variables. We will present a statistical analysis of a sinkholes length and width relationship, determine the average size of the diameter of a sinkhole, discuss the relationship of sinkhole size depending upon their soil types, and acknowledge the best probable occurrence of when a sinkhole occurs. There will be five research chapters in this dissertation. In Chapter 2, the concept of Exploratory Factor Analysis and Non-Response Analysis will be introduced, in accordance of analyzing hurricanes. Chapter 3 will also address the topic of hurricanes that have formed from the Atlantic Basin from 1992 – 2014. The discussion of the probability of a storm being present (also categorically) will be addressed. In Chapter 4 a study of sinkholes in Florida will be addressed. In Chapter 5 we will continue our discussion on sinkholes in Florida, but focus on the time to event between the occurrences of the sinkholes. In the last chapter, Chapter 6, we will conclude with a future works and projects that can be created from the foundations of this dissertation.

In the industry, a lot of companies are facing the explosion of big data. With this much information stored, companies want to make sense of the data and use it to help them for better decision making, especially for future prediction. A lot of money can be saved and huge revenue can be generated with the power of big data. When building statistical learning models for prediction, companies in the industry are aiming to build models with efficiency and high accuracy. After the learning models have been developed for production, new data will be generated. With the updated data, the models have to be updated as well. Due to this nature, the model performs best today doesn’t mean it will necessarily perform the same tomorrow. Thus, it is very hard to decide which algorithm should be used to build the learning model. This paper introduces a new method that ensembles the information generated by two different classification statistical learning algorithms together as inputs for another learning model to increase the final prediction power. The dataset used in this paper is NASA’s Turbofan Engine Degradation data. There are 49 numeric features (X) and the response Y is binary with 0 indicating the engine is working properly and 1 indicating engine failure. The model’s purpose is to predict whether the engine is going to pass or fail. The dataset is divided in training set and testing set. First, training set is used twice to build support vector machine (SVM) and neural network models. Second, it used the trained SVM and neural network model taking X of the training set as input to predict Y1 and Y2. Then, it takes Y1 and Y2 as inputs to build the Penalized Logistic Regression model, which is the ensemble model here. Finally, use the testing set follow the same steps to get the final prediction result. The model accuracy is calculated using overall classification accuracy. The result shows that the ensemble model has 92% accuracy. The prediction accuracies of SVM, neural network and ensemble models are compared to prove that the ensemble model successfully captured the power of the two individual learning model.

Objective: This study aims to derive a clinically-applicable decision rule to predict the risk of symptomatic vasospasm, a neurological deficit primarily due to abnormal narrowing of cerebral arteries supplying an attributable territory, in aneurysmal subarachnoid hemorrhage (SAH). Methods: SAH patients presenting from 2002 to 2011 were analyzed using logistic regression and recursive partitioning to identify clinical, radiological, and laboratory features that predict the occurrence of symptomatic vasospasm. Results: The incidence of symptomatic vasospasm was 21.0%. On multivariate logistic regression analysis, significant predictors of symptomatic vasospasm included age 40-59 years, high Modified Fisher Grade (Grades 3 and 4), and anterior circulation aneurysms. Conclusion: Development of symptomatic vasospasm can be reliably predicted using a clinical decision rule created by logistic regression. It exhibits increased accuracy over the Modified Fisher Grade alone and may serve as a useful clinical tool to individualize vasospasm risk once prospectively validated in other neurosurgical centres.

This thesis treats with the theory, interpretation and application of the Discrete Choice Models. The theoretical part contains the Fitting the Logistic Regression Model, Testing for the Significance of the Coefficients, Testing for the Significance of the Model. The Multiple Logistic Regression is mentioned too. The model was applied to interview data from the International research called Reflex.

The aim of the present work is to describe the application of the logistic regression model to the field of probability of default modeling, and provide a brief introduction to the scoring development process used in financial practice. We start by introducing the theoretical background of the logistic regression model; followed by a consequent derivation of three most common scoring models. Then we present a formal definition of the Gini coefficient as a diversification power measure and derive the Somers-type formulas for its estimation. Finally, the key part of this work gives an overview of the whole scoring development process illustrated on the examples of real business data.

This diploma project is focused on the estimation of incurred value of claim and probability of the claim remaining opened (not settled) in the specific stage of the insurance settlement process. The change of incurred value of claim means the change of settlement process stage. Generalized linear model is used for modelling these changes. Classical linear regression model also belongs into this theory, which is its special case, just with stricter premises. Generalized linear model among others allows solving the problem of heteroscedasticity in the unusual way using joint model. This model is applied in the practical part of this piece of work. Logistic regression is the part of the generalized linear model theory, which helps to model the probability of the claim remaining opened in this piece of work. The model outcome is presented in graphic way, especially the graphs containing probability that levels of given claim will occur in certain range.