Bayesian model selection methodology for road safety

Road accidents are a very relevant issue in many countries and macroeconomic models are very frequently applied by academia and administrations to reduce their frequency and consequences. The selection of explanatory variables and response transformation parameter within the Bayesian framework for the selection of the set of explanatory variables a TIM and 3IM (two input and three input models) procedures are proposed. The procedure also uses the DIC and pseudo -R2 goodness of fit criteria. The model to which the methodology is applied is a dynamic regression model with Box-Cox transformation (BCT) for the explanatory variables and autorgressive (AR) structure for the response. The initial set of 22 explanatory variables are identified. The effects of these factors on the fatal accident frequency in Spain, during 2000-2012, are estimated. The dependent variable is constructed considering the stochastic trend component.

Exploring strategic farming choices to respond to mitigation and adaptation to climate change

Las alteraciones del sistema climático debido al aumento de concentraciones de gases de efecto invernadero (GEI) en la atmósfera, tendrán implicaciones importantes para la agricultura, el medio ambiente y la sociedad. La agricultura es una fuente importante de emisiones de gases de efecto invernadero (globalmente contribuye al 12% del total de GEI), y al mismo tiempo puede ser parte de la solución para mitigar las emisiones y adaptarse al cambio climático. Las acciones frente al desafío del cambio climático deben priorizar estrategias de adaptación y mitigación en la agricultura dentro de la agenda para el desarrollo de políticas. La agricultura es por tanto crucial para la conservación y el uso sostenible de los recursos naturales, que ya están sometidos a impactos del cambio climático, al mismo tiempo que debe suministrar alimentos para una población creciente. Por tanto, es necesaria una coordinación entre las actuales estrategias de política climática y agrícola. El concepto de agricultura climáticamente inteligente ha surgido para integrar todos estos servicios de la producción agraria. Al evaluar opciones para reducir las amenazas del cambio climático para la agricultura y el medio ambiente, surgen dos preguntas de investigación: • ¿Qué información es necesaria para definir prácticas agrarias inteligentes? • ¿Qué factores influyen en la implementación de las prácticas agrarias inteligentes? Esta Tesis trata de proporcionar información relevante sobre estas cuestiones generales con el fin de apoyar el desarrollo de la política climática. Se centra en sistemas agrícolas Mediterráneos. Esta Tesis integra diferentes métodos y herramientas para evaluar las alternativas de gestión agrícola y políticas con potencial para responder a las necesidades de mitigación y adaptación al cambio climático. La investigación incluye enfoques cuantitativos y cualitativos e integra variables agronómicas, de clima y socioeconómicas a escala local y regional. La investigación aporta una recopilación de datos sobre evidencia experimental existente, y un estudio integrado sobre el comportamiento de los agricultores y las posibles alternativas de cambio (por ejemplo, la tecnología, la gestión agrícola y la política climática). Los casos de estudio de esta Tesis - el humedal de Doñana (S España) y la región de Aragón (NE España) - permiten ilustrar dos sistemas Mediterráneos representativos, donde el uso intensivo de la agricultura y las condiciones semiáridas son ya una preocupación. Por este motivo, la adopción de estrategias de mitigación y adaptación puede desempeñar un papel muy importante a la hora de encontrar un equilibrio entre la equidad, la seguridad económica y el medio ambiente en los escenarios de cambio climático. La metodología multidisciplinar de esta tesis incluye una amplia gama de enfoques y métodos para la recopilación y el análisis de datos. La toma de datos se apoya en la revisión bibliográfica de evidencia experimental, bases de datos públicas nacionales e internacionales y datos primarios recopilados mediante entrevistas semi-estructuradas con los grupos de interés (administraciones públicas, responsables políticos, asesores agrícolas, científicos y agricultores) y encuestas con agricultores. Los métodos de análisis incluyen: meta-análisis, modelos de gestión de recursos hídricos (modelo WAAPA), análisis multicriterio para la toma de decisiones, métodos estadísticos (modelos de regresión logística y de Poisson) y herramientas para el desarrollo de políticas basadas en la ciencia. El meta-análisis identifica los umbrales críticos de temperatura que repercuten en el crecimiento y el desarrollo de los tres cultivos principales para la seguridad alimentaria (arroz, maíz y trigo). El modelo WAAPA evalúa el efecto del cambio climático en la gestión del agua para la agricultura de acuerdo a diferentes alternativas políticas y escenarios climáticos. El análisis multicriterio evalúa la viabilidad de las prácticas agrícolas de mitigación en dos escenarios climáticos de acuerdo a la percepción de diferentes expertos. Los métodos estadísticos analizan los determinantes y las barreras para la adopción de prácticas agrícolas de mitigación. Las herramientas para el desarrollo de políticas basadas en la ciencia muestran el potencial y el coste para reducir GEI mediante las prácticas agrícolas. En general, los resultados de esta Tesis proporcionan información sobre la adaptación y la mitigación del cambio climático a nivel de explotación para desarrollar una política climática más integrada y ayudar a los agricultores en la toma de decisiones. Los resultados muestran las temperaturas umbral y la respuesta del arroz, el maíz y el trigo a temperaturas extremas, siendo estos valores de gran utilidad para futuros estudios de impacto y adaptación. Los resultados obtenidos también aportan una serie de estrategias flexibles para la adaptación y la mitigación a escala local, proporcionando a su vez una mejor comprensión sobre las barreras y los incentivos para su adopción. La capacidad de mejorar la disponibilidad de agua y el potencial y el coste de reducción de GEI se han estimado para estas estrategias en los casos de estudio. Estos resultados podrían ayudar en el desarrollo de planes locales de adaptación y políticas regionales de mitigación, especialmente en las regiones Mediterráneas. ABSTRACT Alterations in the climatic system due to increased atmospheric concentrations of greenhouse gas emissions (GHG) are expected to have important implications for agriculture, the environment and society. Agriculture is an important source of GHG emissions (12 % of global anthropogenic GHG), but it is also part of the solution to mitigate emissions and to adapt to climate change. Responses to face the challenge of climate change should place agricultural adaptation and mitigation strategies at the heart of the climate change agenda. Agriculture is crucial for the conservation and sustainable use of natural resources, which already stand under pressure due to climate change impacts, increased population, pollution and fragmented and uncoordinated climate policy strategies. The concept of climate smart agriculture has emerged to encompass all these issues as a whole. When assessing choices aimed at reducing threats to agriculture and the environment under climate change, two research questions arise: • What information defines smart farming choices? • What drives the implementation of smart farming choices? This Thesis aims to provide information on these broad questions in order to support climate policy development focusing in some Mediterranean agricultural systems. This Thesis integrates methods and tools to evaluate potential farming and policy choices to respond to mitigation and adaptation to climate change. The assessment involves both quantitative and qualitative approaches and integrates agronomic, climate and socioeconomic variables at local and regional scale. The assessment includes the collection of data on previous experimental evidence, and the integration of farmer behaviour and policy choices (e.g., technology, agricultural management and climate policy). The case study areas -- the Doñana coastal wetland (S Spain) and the Aragón region (NE Spain) – illustrate two representative Mediterranean regions where the intensive use of agriculture and the semi-arid conditions are already a concern. Thus the adoption of mitigation and adaptation measures can play a significant role for reaching a balance among equity, economic security and the environment under climate change scenarios. The multidisciplinary methodology of this Thesis includes a wide range of approaches for collecting and analysing data. The data collection process include revision of existing experimental evidence, public databases and the contribution of primary data gathering by semi-structured interviews with relevant stakeholders (i.e., public administrations, policy makers, agricultural advisors, scientist and farmers among others) and surveys given to farmers. The analytical methods include meta-analysis, water availability models (WAAPA model), decision making analysis (MCA, multi-criteria analysis), statistical approaches (Logistic and Poisson regression models) and science-base policy tools (MACC, marginal abatement cost curves and SOC abatement wedges). The meta-analysis identifies the critical temperature thresholds which impact on the growth and development of three major crops (i.e., rice, maize and wheat). The WAAPA model assesses the effect of climate change for agricultural water management under different policy choices and climate scenarios. The multi-criteria analysis evaluates the feasibility of mitigation farming practices under two climate scenarios according to the expert views. The statistical approaches analyses the drivers and the barriers for the adoption of mitigation farming practices. The science-base policy tools illustrate the mitigation potential and cost effectiveness of the farming practices. Overall, the results of this Thesis provide information to adapt to, and mitigate of, climate change at farm level to support the development of a comprehensive climate policy and to assist farmers. The findings show the key temperature thresholds and response to extreme temperature effects for rice, maize and wheat, so such responses can be included into crop impact and adaptation models. A portfolio of flexible adaptation and mitigation choices at local scale are identified. The results also provide a better understanding of the stakeholders oppose or support to adopt the choices which could be used to incorporate in local adaptation plans and mitigation regional policy. The findings include estimations for the farming and policy choices on the capacity to improve water supply reliability, abatement potential and cost-effective in Mediterranean regions.

Operational short term health impact assessment of air pollution modelling system over Europe

The last decade, scientific studies have indicated an association between air pollution to which people are exposed and wide range of adverse health outcomes. We have developed a tool which is based on a model (MM5-CMAQ) running over Europe with 50 km spatial resolution, based on EMEP annual emissions, to produce a short-term forecast of the impact on health. In order to estimate the mortality change (forecasted for the next 24 hours) we have chosen a log-linear (Poisson) regression form to estimate the concentration-response function. The parameters involved in the C-R function have been estimated based on epidemiological studies, which have been published. Finally, we have derived the relationship between concentration change and mortality change from the C-R function which is the final health impact function.

WGTTEST: Stata module to test the impact of sampling weights in regression analysis

wgttest performs a test proposed by DuMouchel and Duncan (1983) to evaluate whether the weighted and unweighted estimates of a regression model are significantly different.

Assessing the impacts of grazing levels on bird density in woodland habitat: a Bayesian approach using expert opinion

Many studies on birds focus on the collection of data through an experimental design, suitable for investigation in a classical analysis of variance (ANOVA) framework. Although many findings are confirmed by one or more experts, expert information is rarely used in conjunction with the survey data to enhance the explanatory and predictive power of the model. We explore this neglected aspect of ecological modelling through a study on Australian woodland birds, focusing on the potential impact of different intensities of commercial cattle grazing on bird density in woodland habitat. We examine a number of Bayesian hierarchical random effects models, which cater for overdispersion and a high frequency of zeros in the data using WinBUGS and explore the variation between and within different grazing regimes and species. The impact and value of expert information is investigated through the inclusion of priors that reflect the experience of 20 experts in the field of bird responses to disturbance. Results indicate that expert information moderates the survey data, especially in situations where there are little or no data. When experts agreed, credible intervals for predictions were tightened considerably. When experts failed to agree, results were similar to those evaluated in the absence of expert information. Overall, we found that without expert opinion our knowledge was quite weak. The fact that the survey data is quite consistent, in general, with expert opinion shows that we do know something about birds and grazing and we could learn a lot faster if we used this approach more in ecology, where data are scarce. Copyright (c) 2005 John Wiley & Sons, Ltd.

A Score Test for Zero-Inflation in Correlated Count Data

To account for the preponderance of zero counts and simultaneous correlation of observations, a class of zero-inflated Poisson mixed regression models is applicable for accommodating the within-cluster dependence. In this paper, a score test for zero-inflation is developed for assessing correlated count data with excess zeros. The sampling distribution and the power of the test statistic are evaluated by simulation studies. The results show that the test statistic performs satisfactorily under a wide range of conditions. The test procedure is further illustrated using a data set on recurrent urinary tract infections. Copyright (c) 2005 John Wiley & Sons, Ltd.

Optimal crossover designs for logistic regression models in pharmacodynamics

Pharmacodynamics (PD) is the study of the biochemical and physiological effects of drugs. The construction of optimal designs for dose-ranging trials with multiple periods is considered in this paper, where the outcome of the trial (the effect of the drug) is considered to be a binary response: the success or failure of a drug to bring about a particular change in the subject after a given amount of time. The carryover effect of each dose from one period to the next is assumed to be proportional to the direct effect. It is shown for a logistic regression model that the efficiency of optimal parallel (single-period) or crossover (two-period) design is substantially greater than a balanced design. The optimal designs are also shown to be robust to misspecification of the value of the parameters. Finally, the parallel and crossover designs are combined to provide the experimenter with greater flexibility.

Guiding local regression using visualisation

Solving many scientific problems requires effective regression and/or classification models for large high-dimensional datasets. Experts from these problem domains (e.g. biologists, chemists, financial analysts) have insights into the domain which can be helpful in developing powerful models but they need a modelling framework that helps them to use these insights. Data visualisation is an effective technique for presenting data and requiring feedback from the experts. A single global regression model can rarely capture the full behavioural variability of a huge multi-dimensional dataset. Instead, local regression models, each focused on a separate area of input space, often work better since the behaviour of different areas may vary. Classical local models such as Mixture of Experts segment the input space automatically, which is not always effective and it also lacks involvement of the domain experts to guide a meaningful segmentation of the input space. In this paper we addresses this issue by allowing domain experts to interactively segment the input space using data visualisation. The segmentation output obtained is then further used to develop effective local regression models.

Guiding local regression using visualisation

Solving many scientific problems requires effective regression and/or classification models for large high-dimensional datasets. Experts from these problem domains (e.g. biologists, chemists, financial analysts) have insights into the domain which can be helpful in developing powerful models but they need a modelling framework that helps them to use these insights. Data visualisation is an effective technique for presenting data and requiring feedback from the experts. A single global regression model can rarely capture the full behavioural variability of a huge multi-dimensional dataset. Instead, local regression models, each focused on a separate area of input space, often work better since the behaviour of different areas may vary. Classical local models such as Mixture of Experts segment the input space automatically, which is not always effective and it also lacks involvement of the domain experts to guide a meaningful segmentation of the input space. In this paper we addresses this issue by allowing domain experts to interactively segment the input space using data visualisation. The segmentation output obtained is then further used to develop effective local regression models.

Local-Median Method of Forecasting for Regression Time Series under Outliers

2002 Mathematics Subject Classification: 62M20, 62-07, 62J05, 62P20.

Application of the D-Fullness Technique for Breakdown Point Study of the Trimmed Likelihood Estimator to a Generalized Logistic Model

2000 Mathematics Subject Classification: 62J12, 62F35

Regression games

The solution of a TU cooperative game can be a distribution of the value of the grand coalition, i.e. it can be a distribution of the payo (utility) all the players together achieve. In a regression model, the evaluation of the explanatory variables can be a distribution of the overall t, i.e. the t of the model every regressor variable is involved. Furthermore, we can take regression models as TU cooperative games where the explanatory (regressor) variables are the players. In this paper we introduce the class of regression games, characterize it and apply the Shapley value to evaluating the explanatory variables in regression models. In order to support our approach we consider Young (1985)'s axiomatization of the Shapley value, and conclude that the Shapley value is a reasonable tool to evaluate the explanatory variables of regression models.

Development of safety performance functions for empirical Bayes estimation of crash reduction factors

Crash reduction factors (CRFs) are used to estimate the potential number of traffic crashes expected to be prevented from investment in safety improvement projects. The method used to develop CRFs in Florida has been based on the commonly used before-and-after approach. This approach suffers from a widely recognized problem known as regression-to-the-mean (RTM). The Empirical Bayes (EB) method has been introduced as a means to addressing the RTM problem. This method requires the information from both the treatment and reference sites in order to predict the expected number of crashes had the safety improvement projects at the treatment sites not been implemented. The information from the reference sites is estimated from a safety performance function (SPF), which is a mathematical relationship that links crashes to traffic exposure. The objective of this dissertation was to develop the SPFs for different functional classes of the Florida State Highway System. Crash data from years 2001 through 2003 along with traffic and geometric data were used in the SPF model development. SPFs for both rural and urban roadway categories were developed. The modeling data used were based on one-mile segments that contain homogeneous traffic and geometric conditions within each segment. Segments involving intersections were excluded. The scatter plots of data show that the relationships between crashes and traffic exposure are nonlinear, that crashes increase with traffic exposure in an increasing rate. Four regression models, namely, Poisson (PRM), Negative Binomial (NBRM), zero-inflated Poisson (ZIP), and zero-inflated Negative Binomial (ZINB), were fitted to the one-mile segment records for individual roadway categories. The best model was selected for each category based on a combination of the Likelihood Ratio test, the Vuong statistical test, and the Akaike's Information Criterion (AIC). The NBRM model was found to be appropriate for only one category and the ZINB model was found to be more appropriate for six other categories. The overall results show that the Negative Binomial distribution model generally provides a better fit for the data than the Poisson distribution model. In addition, the ZINB model was found to give the best fit when the count data exhibit excess zeros and over-dispersion for most of the roadway categories. While model validation shows that most data points fall within the 95% prediction intervals of the models developed, the Pearson goodness-of-fit measure does not show statistical significance. This is expected as traffic volume is only one of the many factors contributing to the overall crash experience, and that the SPFs are to be applied in conjunction with Accident Modification Factors (AMFs) to further account for the safety impacts of major geometric features before arriving at the final crash prediction. However, with improved traffic and crash data quality, the crash prediction power of SPF models may be further improved.

Variables affecting the success of older applicants for employment in a public organization: An age -cued cognitive model of administrative decision-making

The dissertation takes a multivariate approach to answer the question of how applicant age, after controlling for other variables, affects employment success in a public organization. In addition to applicant age, there are five other categories of variables examined: organization/applicant variables describing the relationship of the applicant to the organization; organization/position variables describing the target position as it relates to the organization; episodic variables such as applicant age relative to the ages of competing applicants; economic variables relating to the salary needs of older applicants; and cognitive variables that may affect the decision maker's evaluation of the applicant. ^ An exploratory phase of research employs archival data from approximately 500 decisions made in the past three years to hire or promote applicants for positions in one public health administration organization. A logit regression model is employed to examine the probability that the variables modify the effect of applicant age on employment success. A confirmatory phase of the dissertation is a controlled experiment in which hiring decision makers from the same public organization perform a simulated hiring decision exercise to evaluate hypothetical applicants of similar qualifications but of different ages. The responses of the decision makers to a series of bipolar adjective scales add support to the cognitive component of the theoretical model of the hiring decision. A final section contains information gathered from interviews with key informants. ^ Applicant age has tended to have a curvilinear relationship with employment success. For some positions, the mean age of the applicants most likely to succeed varies with the values of the five groups of moderating variables. The research contributes not only to the practice of public personnel administration, but is useful in examining larger public policy issues associated with an aging workforce. ^

Prevalência e fatores associados à morbidade materna: inquérito populacional em Natal/RN

INTRODUCTION: Severe maternal morbidity , also known as maternal near miss , has been used as an alternative to the study of maternal mortality , since being more frequent shares the same determinants and enables the implementati on of epidem iological surveillance of cases . Since then, hospital audits ha ve been carried out to determine the rates of maternal near miss, its mai n causes and associated factors . More recently, population surveys based on self - reported morbidity have als o been presented as vi able in identifying these cases . OBJECTIVE: The aim of this study was to determine the prevalence and associated factors of maternal near miss and complications during pregnancy and puerperal period in Natal/RN. METHODS: A cross - secti onal population - based study was conducted in Natal /RN , Brazil, which has as its target population women aged 15 to 49 years who were pregnant in the last five years. It was carried out a probabilistic sam pling design based on a multi - stage complex sample , in which 60 census tracts were selected from three strata (north , south - east and west). Afterwards, domiciles were visited in order to obtain a sample of the 908 eligible women in whom a questionnaire was applied. The descriptive analyzes and bivariate ass ociations were performed using the Chi - square test and the estimate of the prevalence ratio (PR ) with 95% confidence interval (CI) and considering the weights and design effects . The Poisson regression analysis , also with 5% significance and 95% CI, was us ed for analyzes of associated factors. RESULTS: 848 women were identified and interviewed after visits in 8.227 households corresponding to a response rate of 93 . 4 %. The prevalence of maternal near miss was 41 . 1 /1 000NV, being the Intensive Care Unity stay i ng (19 . 1 /1 000 LB ) and eclampsia (13 . 5/1000LB) the most important marker s . The prevalence of complications in the puerperal peri od was 21 . 2 %, and hemorrhage (10 . 7%) and urinary tract infection (10 . 7%) the most frequently reported clinical conditions and rema in ing in the hospital for over a week after delivery the mo st frequent intervention (5.4%) . Regarding associated factors , the bivariate analysis showed an association between the increased number of complications in women of black/brown race ( PR= 1 . 23; CI95 % : 1 . 04 - 1 . 46) and lower socioeconomic status ( PR= 1 . 33; CI95%: 1 . 12 - 1 . 58) in women who had pre natal care in public service ( PR= 1 . 42; CI95%: 1 . 16 to 1 . 72 ) and that were not advised during prenatal about where they should do the d elivery (PR= 1 . 24; CI95%: 1 . 05 - 1 . 46), made the del ivery in the public service (PR= 1 . 63; CI95%: 1 . 30 - 2 . 03), had to search for more than one hospital for delivery (PR=1 . 22; CI95%: 1 . 03 - 1 . 45) and had no companion during childbirth ( PR =1 . 19; CI95%: 1 . 01 - 1 . 41) or at all times of childbirth c are - before, during and after childbirth - ( PR= 1 . 25, CI95%: 1 . 05 - 1 . 48) . Moreover, the number of days postpartum hospitalization was higher in women who had more complications (P R= 1 . 59 ; CI95%: 1 . 36 - 1 . 86). In the final regression model for both birth place (P R= 1 . 21 ; CI 95% : 1 . 02 to 1 . 44 ) and socioeconomic status (PR = 1.54 ; CI95%: 1 . 25 - 1 . 90 ) the association remained. CONCLUSION : Conducting population surveys using the pragmatic definition of near miss is feasible and may add importa nt information about this ev ent . It was possible to find the expression of health inequalities related to maternal health in the analysis of both socioeconomic conditions and on the utilization of health services.