<p>This thesis presents improvements and extensions of a previously presented threat assessment algorithm. The algorithm uses Monte Carlo simulation to find threats in a road scene. It is shown that, by using a wider sample distribution and only apply the most likely samples from the Monte Carlo simulation, for the threat assessment, improved results are obtained. By using this method more realistic paths will be chosen by the simulated vehicles and more complex traffic situations will be adequately handled.</p><p>An improvement of the dynamic model is also suggested, which improves the realism of the Monte Carlo simulations. Using the new dynamic model less false positive and more valid threats are detected.</p><p>A systematic method to choose parameters in a stochastic space, using optimisation, is suggested. More realistic trajectories can be chosen, by applying this method on the parameters that represents the human behaviour, in the threat assessment algorithm.</p><p>A new definition of obstacles in a road scene is suggested, dividing them into two groups, Hard and Soft obstacles. A change to the resampling step, in the Monte Carlo simulation, using the soft and hard obstacles is also suggested.</p>

This thesis presents improvements and extensions of a previously presented threat assessment algorithm. The algorithm uses Monte Carlo simulation to find threats in a road scene. It is shown that, by using a wider sample distribution and only apply the most likely samples from the Monte Carlo simulation, for the threat assessment, improved results are obtained. By using this method more realistic paths will be chosen by the simulated vehicles and more complex traffic situations will be adequately handled. An improvement of the dynamic model is also suggested, which improves the realism of the Monte Carlo simulations. Using the new dynamic model less false positive and more valid threats are detected. A systematic method to choose parameters in a stochastic space, using optimisation, is suggested. More realistic trajectories can be chosen, by applying this method on the parameters that represents the human behaviour, in the threat assessment algorithm. A new definition of obstacles in a road scene is suggested, dividing them into two groups, Hard and Soft obstacles. A change to the resampling step, in the Monte Carlo simulation, using the soft and hard obstacles is also suggested.

Increased attention to statistical concepts has been a prevalent trend in revised mathematics curricula across grade levels. However, the preparation of secondary school mathematics educators has not received similar attention, and learning opportunities provided to these educators is oftentimes insufficient for teaching statistics well. The purpose of this study is to analyze pre-service teachers' conceptions about confidence intervals. This research inquired about statistical reasoning from the perspective of students majoring in mathematics education enrolled in an undergraduate statistics education course who have previously completed an introductory course in statistics. We found common misconceptions among pre-service teachers participating in this study. An unanticipated finding is that all the pre-service teachers believed that the construction of a confidence interval relies on a sampling distribution that does not contain every possible sample. Instead, they believed it is necessary to take multiple samples and build a distribution of their means. I called this distribution the Multi-Sample Distribution (MSD).

Pfeffermann, Krieger e Rinott (1998) apresentaram uma metodologia para modelar processos de amostragem que pode ser utilizada para avaliar se este processo de amostragem é informativo. Neste cenário, as probabilidades de seleção da amostra são aproximadas por uma função polinomial dependendo das variáveis resposta e concomitantes. Nesta abordagem, nossa principal proposta é investigar a aplicação do teste de significância FBST (Full Bayesian Significance Test), apresentado por Pereira e Stern (1999), como uma ferramenta para testar a ignorabilidade amostral, isto é, para avaliar uma relação de significância entre as probabilidades de seleção da amostra e a variável resposta. A performance desta modelagem estatística é testada com alguns experimentos computacionais. / Pfeffermann, Krieger and Rinott (1998) introduced a framework for modeling sampling processes that can be used to assess if a sampling process is informative. In this setting, sample selection probabilities are approximated by a polynomial function depending on outcome and auxiliary variables. Within this framework, our main purpose is to investigate the application of the Full Bayesian Significance Test (FBST), introduced by Pereira and Stern (1999), as a tool for testing sampling ignorability, that is, to detect a significant relation between the sample selection probabilities and the outcome variable. The performance of this statistical modelling framework is tested with some simulation experiments.

Pfeffermann, Krieger e Rinott (1998) apresentaram uma metodologia para modelar processos de amostragem que pode ser utilizada para avaliar se este processo de amostragem é informativo. Neste cenário, as probabilidades de seleção da amostra são aproximadas por uma função polinomial dependendo das variáveis resposta e concomitantes. Nesta abordagem, nossa principal proposta é investigar a aplicação do teste de significância FBST (Full Bayesian Significance Test), apresentado por Pereira e Stern (1999), como uma ferramenta para testar a ignorabilidade amostral, isto é, para avaliar uma relação de significância entre as probabilidades de seleção da amostra e a variável resposta. A performance desta modelagem estatística é testada com alguns experimentos computacionais. / Pfeffermann, Krieger and Rinott (1998) introduced a framework for modeling sampling processes that can be used to assess if a sampling process is informative. In this setting, sample selection probabilities are approximated by a polynomial function depending on outcome and auxiliary variables. Within this framework, our main purpose is to investigate the application of the Full Bayesian Significance Test (FBST), introduced by Pereira and Stern (1999), as a tool for testing sampling ignorability, that is, to detect a significant relation between the sample selection probabilities and the outcome variable. The performance of this statistical modelling framework is tested with some simulation experiments.