Emergency department (ED) overcrowding is a challenge faced by many hospitals. One approach to mitigate overcrowding is to anticipate high levels of overcrowding. The purpose of this study was to forecast a measure of ED overcrowding four hours in advance to allow clinicians to prepare for high levels of overcrowding. The chosen measure of ED overcrowding was ED length of stay compliance measures set by the Ontario government. A feed-forward artificial neural network (ANN) was designed to perform a time series forecast on the number of patients that were non-compliant. Using the ANN compared to historical averages, a 70% reduction in the root mean squared error was observed as well as good discriminatory ability of the ANN model with an area under the receiver operating characteristic curve of 0.804. Therefore, using ANNs to forecast ED overcrowding gives clinicians an opportunity to be proactive, rather than reactive, in ED overcrowding crises.

This dissertation collects five independent essays. The first essay is An Alternative Explanation of the Price Puzzle. The most widely accepted explanation of the price puzzle points to an inadequate performance of the VAR in forecasting inflation. This essay suggests that the finding of a price puzzle is due to a seemingly innocent misspecification in taking the theoretical model to the data: a measure of output gap is not included in the VAR (output alone being used instead), while this variable is a crucial element in every equation of the theoretical models. When the VAR is correctly specified, the price puzzle disappears. Building on results contained in the first paper, the second-- Stronger Evidence of Long-Run Neutrality: A comment on Bernanke and Mihov---improves the empirical performance of standard models on the prediction that a monetary policy shock should have temporary effects on output. It turns out that the same misspecification causing the price puzzle is also responsible for overestimation of the time needed for the effects on output of a monetary policy shock to die out. The point can be proven in a theoretical economy, and is confirmed on US data. Monetary Policy Without Monetary Aggregates: Some (Surprising) Evidence , joint with Giovanni Favara) is the third essay. It points to what seems to be a falsified prediction of models in the New-Keynesian framework. In this framework monetary aggregates are reserved a pretty boring role, so boring that they can be safely excluded from the final lay out of the model. These models predict that a money demand shock should have no effect on output, inflation and interest rate. However, the prediction seems to be quite wrong Inflation Forecast Targeting, joint with Paul Söderlind, takes a step outside the representative-agent framework. In RE models, all agents typically have the same information set, and therefore make the same predictions. However, in the real even professional forecasters show substantial disagreement. This disagreement can have an impact on asset prices and transaction volumes, among other things. However, there is no unique way of aggregating forecasts (or forecast probability density functions) into a measure of disagreement. The paper deals with this problem, surveying some proposed methods. The most appropriate measure of disagreement turns out to depend on the intended use, that is, on the model. Moreover, forecasters underestimate uncertainty. Constitutions and Central-Bank Independence: An Objection to McCallum's Second Fallacy, joint with Giancarlo Spagnolo , is an excursion into the field of Political Economy. The essay provides some foundations for the assumption that renegotiating a delegation contract can be costly by illustrating how political institutions can generate inertia in re-contracting, reduce the gains from it or prevent it altogether. Once the nature of renegotiation costs has been clarified, it is easier to see why certain institutions can mitigate or solve dynamic inconsistencies better than others. / Diss. Stockholm : Handelshögsk., 2001

京都大学 / 新制・課程博士 / 博士(理学) / 甲第23711号 / 理博第4801号 / 新制||理||1688(附属図書館) / 京都大学大学院理学研究科地球惑星科学専攻 / (主査)教授 王 功輝, 教授 釜井 俊孝, 教授 久家 慶子 / 学位規則第4条第1項該当 / Doctor of Science / Kyoto University / DGAM

Hydrologic and climate models predict variables through a simplification of the underlying complex natural processes. Model development involves minimising predictive uncertainty. Predictive uncertainty arises from three broad sources which are measurement error in observed responses, uncertainty of input variables and model structural error. This thesis introduces ways to improve predictive accuracy of hydroclimatic models by considering input and structural uncertainties. The specific methods developed to reduce the uncertainty because of erroneous inputs and model structural errors are outlined below. The uncertainty in hydrological model inputs, if ignored, introduces systematic biases in the parameters estimated. This thesis presents a method, known as simulation extrapolation (SIMEX), to ascertain the extent of parameter bias. SIMEX starts by generating a series of alternate inputs by artificially adding white noise in increasing multiples of the known input error variance. The resulting alternate parameter sets allow formulation of an empirical relationship between their values and the level of noise present. SIMEX is based on the theory that the trend in alternate parameters can be extrapolated back to the notional error free zone. The case study relates to erroneous sea surface temperature anomaly (SSTA) records used as input variables of a linear model to predict the Southern Oscillation Index (SOI). SIMEX achieves a reduction in residual errors from the SOI prediction. Besides, a hydrologic application of SIMEX is demonstrated by a synthetic simulation within a three-parameter conceptual rainfall runoff model. This thesis next advocates reductions of structural uncertainty of any single model by combining multiple alternative model responses. Current approaches for combining hydroclimatic forecasts are generally limited to using combination weights that remain static over time. This research develops a methodology for combining forecasts from multiple models in a dynamic setting as an improvement of over static weight combination. The model responses are mixed on a pair wise basis using mixing weights that vary in time reflecting the persistence of individual model skills. The concept is referred here as the pair wise dynamic weight combination. Two approaches for forecasting the dynamic weights are developed. The first of the two approaches uses a mixture of two basis distributions which are three category ordered logistic regression model and a generalised linear autoregressive model. The second approach uses a modified nearest neighbour approach to forecast the future weights. These alternatives are used to first combine a univariate response forecast, the NINO3.4 SSTA index. This is followed by a similar combination, but for the entire global gridded SSTA forecast field. Results from these applications show significant improvements being achieved due to the dynamic model combination approach. The last application demonstrating the dynamic combination logic, uses the dynamically combined multivariate SSTA forecast field as the basis of developing multi-site flow forecasts in the Namoi River catchment in eastern Australia. To further reduce structural uncertainty in the flow forecasts, three forecast models are formulated and the dynamic combination approach applied again. The study demonstrates that improved SSTA forecast (due to dynamic combination) in turn improves all three flow forecasts, while the dynamic combination of the three flow forecasts results in further improvements.

A obtenção de previsões com maior acuracidade é uma necessidade constantemente requerida, em tempos onde há imensa disponibilidade de dados e recursos computacionais cada dia mais eficientes. Tais critérios possibilitaram o desenvolvimento de muitas técnicas de previsão individual ou de métodos de combinação que são considerados eficientes no intuito de reduzir erros. O desenvolvimento de novas técnicas, por sua vez, promove questionamentos quanto à identificação de quantas ou quais técnicas de previsão individual combinar. A literatura não é unânime ao tentar responder a estes questionamentos e indica a importância da correlação entre os erros de previsão na precisão da combinação. Posto isso, esta tese apresenta uma alternativa aos métodos atuais de combinar previsões, contemplando a correlação entre os erros de previsão, além de propor uma forma de identificar técnicas de previsão que sejam distintas quanto à modelagem de características da série de dados. Para identificar grupos de técnicas de previsão individual que sejam similares, utilizou-se a Análise de Agrupamentos em erros gerados por 15 técnicas de previsão que modelaram uma mesma série de dados real com tendência e sazonalidade. O resultado indicou a formação de 3 agrupamentos. Como alternativa aos métodos atuais de combinar previsão e selecionar a quantidade adequada de técnicas, utilizou-se a Análise de Componentes Principais. O método proposto mostrou-se viável quando comparado com outros métodos de combinação e quando submetido à modelagem de séries com maior variabilidade. / The obtaining of more accurate forecasts is a necessity often required in times where there is a huge availability of data and computing resources becoming more efficient every day. These criteria allowed the development of many individual forecasting techniques or combination methods that are considered efficient in order to reduce errors. The development of new techniques, in turn, promotes questioning as the identification of how many or which techniques to combine individual forecasts. The literature is not unanimous when trying to answer these questions and indicates the importance of the correlation between forecast errors on the accuracy of the combination. That said, this presents an alternative to current methods of combining forecasts, considering the correlation between forecast errors, and propose a way to identify predictive techniques that are different about the modeling features of the data series. To identify groups of individual forecasting techniques that are similar, it was used the cluster analysis on errors generated by 15 forecasting techniques that shaped the same series of real data with trend and seasonality. The result indicated the formation of 3 clusters. As an alternative to current methods of combining forecasting and selecting the appropriate amount of techniques, it was used the Principal Component Analysis. The proposed method has proved feasible when compared to other methods of combining and when subjected to modeling of series with greater variability.

Economic agents often face situations, where there are multiple competing fore- casts available. Despite five decades of research on forecast combinations, most of the methods introduced so far fail to outperform the equal weights forecast combination in empirical applications. In this study, we gather a wide spectrum of forecast combination methods and reexamine these findings in two different classical economic times series forecasting applications. These include out-of- sample combining forecasts from the ECB Survey of Professional Forecasters and forecasts of the realized volatility of the U.S. Treasury futures log-returns. We asses the performance of artificial predictions markets, a class of machine learning methods, which has not yet been applied to the problem of combin- ing economic times series forecasts. Furthermore, we propose a new simple method called Market for Kernels, which is designed specifically for combining time series forecasts. We found that equal weights can be significantly out- performed by several forecast combinations, including Bates-Granger methods and artificial prediction markets in the ECB Survey of Professional Forecasters application and by almost all examined forecast combinations in the financial application. We also found that the Market for Kernels forecast...

[pt] Essa dissertação teve como objetivo propor dois novos métodos para detecção de viés na previsão de demanda. Os métodos consistem numa adaptação de duas técnicas de controle estatístico de processos, o gráfico de controle de EWMA e o algoritmo CUSUM, ao contexto de detecção de viés na previsão de demanda. O desempenho dos métodos foi analisado por simulação, para diversos casos de mudança na inclinação (tendência) da série de dados (mudança de modelo constante para modelo com tendência; alteração na tendência de série crescente; estabilização de série crescente em um patamar constante), e com diferentes parâmetros para os métodos. O estudo limitou-se a séries sem sazonalidade e aos métodos de previsão de amortecimento exponencial simples e de Holt. Os resultados mostraram a grande superioridade do gráfico de EWMA proposto e apontam questões para pesquisas futuras. / [en] The purpose of this dissertation is to propose two new methods for detection of biases in demand forecasting. These methods are adaptations of two statistical process control techniques, the EWMA control chart and the CUSUM control chart (or CUSUM algorithm), to the context of the detection of biases in demand forecasting. The performance of the proposed methods was analyzed by simulation, for several magnitudes of changes in the trend of the series (change from a level series to a series with a trend, changes in the trend parameter, and stabilization of a series with a trend in a constant average level) and with different parameters for all methods. The study was limited to non-seasonal models and to the methods of simple exponential smoothing and Holt’s Exponential Smoothing. The results have shown the superiority of the EWMA method proposed and indicate issues for future research.

Submitted by Lucienne Costa (lucienneferreira@ufcg.edu.br) on 2018-08-08T20:51:33Z No. of bitstreams: 1 LEYDSON GALVÍNCIO DANTAS – DISSERTAÇÃO (PPGMET) 2016.pdf: 2738181 bytes, checksum: db3cee5c7f083124e00eb4eb3220492c (MD5) / Made available in DSpace on 2018-08-08T20:51:33Z (GMT). No. of bitstreams: 1 LEYDSON GALVÍNCIO DANTAS – DISSERTAÇÃO (PPGMET) 2016.pdf: 2738181 bytes, checksum: db3cee5c7f083124e00eb4eb3220492c (MD5) Previous issue date: 2016-02-19 / CNPq / A variabilidade espacial e temporal das precipitações no estado da Paraíba, proporciona irregularidades na distribuição da mesma, como frequentemente observado nos eventos de secas prolongadas e excesso de precipitação em intervalos curtos de tempo, comprometendo em termos gerais a qualidade de vida da população. Neste trabalho é elaborado o preenchimento das falhas encontradas nas séries temporais em alguns municípios do Estado, obtendo deste modo, uma séria robusta o bastante, na qual tem a função de auxiliar, as análises dos resultados ao ser trabalhada com a metodologia de Box-Jenkins para séries temporais. Visando assim, a elaboração de prognósticos pluviométricos em algumas cidades do Estado por intermédio de modelos estocásticos, onde nota-se que a forma do modelo SARIMA(1,0,1)×(1,1,1) é o que melhor se ajusta pela análise dos critérios e resíduos, dentre os municípios onde as previsões chegaram a equivaler alguns dos valores observados nas estações pluviométricas. Os municípios localizados nas proximidades do Planalto da Borborema foram os que demonstraram a melhor acurácia em termos de previsibilidade ao ser comparado com os outros analisados neste estudo. / The spatial and temporal variability of rainfall in the state of Paraiba, provides irregularities in the distribution of the same, as often observed in prolonged droughts events and excess rainfall in short time intervals, affecting generally the quality of life of the population. This paper prepared filling the gaps found in the time series in some cities of the State, thereby obtaining a robust serious enough, which has a helper function, the analysis of the results to be crafted with the Box-Jenkins methodology for time series. Aiming thus the development of rainfall predictions in some cities of the State through stochastic models, where it is noted that the model shape SARIMA(1,0,1)×(1,1,1) is the best fit for analysis the criteria and waste from the municipalities where the predictions come to equate some of the values observed in the rainfall stations. The Cities located near of the Planalto of Borborema were the ones that showed the best accuracy in terms of predictability when compared to the other analyzed in this study.

[pt] O sistema de geração de energia elétrica do Brasil é hidrotérmico e de grande porte, com predominância de usinas hidrelétricas. O seu tamanho e características peculiares permitem considerá-lo único em todo o mundo. Conseqüentemente a coordenação de todo esse sistema é uma tarefa de extrema complexidade e, portanto, há a necessidade de um correto planejamento e operação para evitar ou amenizar problemas relacionados a segurança de suprimento. Neste contexto, esta dissertação estuda as condições que resultaram no racionamento de energia elétrica no ano de 2001 e no início de 2002, além dos seus efeitos no curto e médio prazo e posteriormente infere sobre um possível novo racionamento. Para isto foram realizadas previsões do consumo de energia, durante o período de crise e foi desenvolvida uma modelagem computacional para simular os seus efeitos. Para obter os indicativos do racionamento passado e inferir sobre um novo, foram realizadas simulações no Modelo Computacional de Otimização Hidrotérmica de Médio Prazo - NEWAVE, desenvolvido pelo CEPEL. / [en] The Brazilian electric energy generation system is a hydrothermal system of great size, with predominance hydroelectric plants. Its peculiar size and characteristics is the only one in the world. Consequently, its coordination is very complex and, therefore, it´s necessary the correct planning and operation to prevent or reduce problems related to supplement security. In this context, this work studies the conditions that resulted in the rationing of electric energy in 2001 and in the beginning of 2002, as well as the effect in the short term and the medium term and infers on a new rationing possible. For this, energy consumption estimations were done, during the period of crisis and was developed a computational modeling to simulate its effect. To get the indicative of the last rationing and to infer on a new one was done simulations in the Computational Model NEWAVE, developed by CEPEL.

O presente estudo propõe um modelo de projeção de preços de curto-prazo para os polietilenos no mercado petroquímico brasileiro. O modelo foi desenvolvido através de testes com o uso das técnicas de regressão múltipla e de redes neurais artificiais (RNA) como instrumentos de previsão, comparando-se os resultados das mesmas. A seleção das variáveis com capacidade explicativa deu-se através de revisão de literatura, opinião de experts e regressão múltipla. Ficou evidenciada a existência de correlações satisfatórias com as variáveis: preço do petróleo, preço das matérias-primas nafta e eteno no mercado doméstico e preços dos polietilenos no mercado internacional. A base de dados consiste em indicadores mensais relativos ao período de março de 2002 a dezembro de 2005, sendo que a aferição dos resultados foi realizada para o período de janeiro a junho de 2006. Os resultados obtidos pela aplicação da técnica de RNA mostraram um incremento na precisão frente à regressão. O erro relativo médio na aferição com o uso de RNA se situou na faixa de 2,9 a 13,4%, para previsão 6 meses a frente, o que sugere a adoção da mesma na implementação futura do modelo construído. / This study proposes a model for forecasting short-term polyethylene prices in the Brazilian petrochemical market. The model was developed by means of tests using multiple regression techniques and Neural Networks as forecasting instruments, and compared their results. The variables with explanatory capacity were selected by reviewing literature, the opinion of experts, and multiple regression. Satisfactory correlations were found to be existent in the following variables: price of petroleum, price of the raw materials naphtha and ethylene in the domestic market, and polyethylene prices in the international market. The database consists of monthly indicators related to the period of March 2002 to December 2005 and the measuring of the results was carried out from January to June of 2006. The results obtained by applying the Neural Networks technique saw an increase in the precision in comparison with the regression. The average relative error in the measurement when using Neural Networks fell in the range of 2.9 to 13.4% for a forecast of 6 months ahead, which suggests that this should be adopted in the future implementation of the model built.