Traffic data prediction is a critical aspect of Advanced Traffic Management System (ATMS). The utility of the traffic data is in providing information on the evolution of traffic process that can be passed on to the various users (commuters, Regional Traffic Management Centers (RTMCs), Department of Transportation (DoT), ... etc) for user-specific objectives. This information can be extracted from the data collected by various traffic sensors. Loop detectors collect traffic data in the form of flow, occupancy, and speed throughout the nation. Freeway traffic data from I-4 loop detectors has been collected and stored in a data warehouse called the Central Florida Data Warehouse (CFDW[trademark symbol]) by the University of Central Florida for the periods between 1993-1994 and 2000 - 2003. This data is raw, in the form of time stamped 30-second aggregated data collected from about 69 stations over a 36 mile stretch on I-4 from Lake Mary in the east to Disney-World in the west. This data has to be processed to extract information that can be disseminated to various users. Usually, most statistical procedures assume that each individual data point in the sample is independent of other data points. This is not true to traffic data as they are correlated across space and time. Therefore, the concept of time sequence and the layout of data collection devices in space, introduces autocorrelations in a single variable and cross correlations across multiple variables. Significant autocorrelations prove that past values of a variable can be used to predict future values of the same variable. Furthermore, significant cross-correlations between variables prove that past values of one variable can be used to predict future values of another variable. The traditional techniques in traffic prediction use univariate time series models that account for autocorrelations but not cross-correlations. These models have neglected the cross correlations between variables that are present in freeway traffic data, due to the way the data are collected. There is a need for statistical techniques that incorporate the effect of these multivariate cross-correlations to predict future values of traffic data. The emphasis in this dissertation is on the multivariate prediction of traffic variables. Unlike traditional statistical techniques that have relied on univariate models, this dissertation explored the cross-correlation between multivariate traffic variables and variables collected across adjoining spatial locations (such as loop detector stations). The analysis in this dissertation proved that there were significant cross correlations among different traffic variables collected across very close locations at different time scales. The nature of cross-correlations showed that there was feedback among the variables, and therefore past values can be used to predict future values. Multivariate time series analysis is appropriate for modeling the effect of different variables on each other. In the past, upstream data has been accounted for in time series analysis. However, these did not account for feedback effects. Vector Auto Regressive (VAR) models are more appropriate for such data. Although VAR models have been applied to forecast economic time series models, they have not been used to model freeway data. Vector Auto Regressive models were estimated for speeds and volumes at a sample of two locations, using 5-minute data. Different specifications were fit--estimation of speeds from surrounding speeds; estimation of volumes from surrounding volumes; estimation of speeds from volumes and occupancies from the same location; estimation of speeds from volumes from surrounding locations (and vice versa). These specifications were compared to univariate models for the respective variables at three levels of data aggregation (5-minutes, 10 minutes, and 15 minutes) in this dissertation. For data aggregation levels of [less than]15 minutes, the VAR models outperform the univariate models. At data aggregation level of 15 minutes, VAR models did not outperform univariate models. Since VAR models were used for all traffic variables reported by the loop detectors, this made the application of VAR a true multivariate procedure for dynamic prediction of the multivariate traffic variables--flow, speed and occupancy. Also, VAR models are generally deemed more complex than univariate models due to the estimation of multiple covariance matrices. However, a VAR model for k variables must be compared to k univariate models and VAR models compare well with AutoRegressive Integrated Moving Average (ARIMA) models. The added complexity helps model the effect of upstream and downstream variables on the future values of the response variable. This could be useful for ATMS situations, where the effect of traffic redistribution and redirection is not known beforehand with prediction models. The VAR models were tested against more traditional models and their performances were compared against each other under different traffic conditions. These models significantly enhance the understanding of the freeway traffic processes and phenomena as well as identifying potential knowledge relating to traffic prediction. Further refinements in the models can result in better improvements for forecasts under multiple conditions.

In many areas of the agriculture, biological, physical and social sciences, spatial lattice data are becoming increasingly common. In addition, a large amount of lattice data shows not only visible spatial pattern but also temporal pattern (see, Zhu et al. 2005). An interesting problem is to develop a model to systematically model the relationship between the response variable and possible explanatory variable, while accounting for space and time effect simultaneously. Spatial-temporal linear model and the corresponding likelihood-based statistical inference are important tools for the analysis of spatial-temporal lattice data. We propose a general asymptotic framework for spatial-temporal linear models and investigate the property of maximum likelihood estimates under such framework. Mild regularity conditions on the spatial-temporal weight matrices will be put in order to derive the asymptotic properties (consistency and asymptotic normality) of maximum likelihood estimates. A simulation study is conducted to examine the finite-sample properties of the maximum likelihood estimates. For spatial data, aside from traditional likelihood-based method, a variety of literature has discussed Bayesian approach to estimate the correlation (auto-covariance function) among spatial data, especially Zheng et al. (2010) proposed a nonparametric Bayesian approach to estimate a spectral density. We will also discuss nonparametric Bayesian approach in analyzing spatial data. We will propose a general procedure for constructing a multivariate Feller prior and establish its theoretical property as a nonparametric prior. A blocked Gibbs sampling algorithm is also proposed for computation since the posterior distribution is analytically manageable.

Submitted by Marilene Donadel (marilene.donadel@unioeste.br) on 2019-03-22T22:55:03Z No. of bitstreams: 1 Daniel_Centuriao_2018.pdf: 4691006 bytes, checksum: dfa8ad2e90bc4e251943d5f57fc3dbb5 (MD5) / Made available in DSpace on 2019-03-22T22:55:03Z (GMT). No. of bitstreams: 1 Daniel_Centuriao_2018.pdf: 4691006 bytes, checksum: dfa8ad2e90bc4e251943d5f57fc3dbb5 (MD5) Previous issue date: 2018-03-02 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / This study seeks to make some contributions to the debate on Brazilian deindustrialization, with a specific look at the determinants of changes in value added and employment in industry, and the structural factors that influenced these variations and the value of industrial production, for the period of 1990 to 2014. In order to contribute empirically, we used an analysis from the VEC (Vector Errors Correction) econometric model and an application of the input-output analysis with the SDA (Structural Decomposition Analysis) technique, in addition to a vast empirical review and theoretical history, in order to connect the results to the historical facts verified. In general, a period with a vast literature, with great changes of a political character, changes in the conduct of economic policy and, above all, in the connection of the Brazilian productive structure with the rest of the world. A major limitation was the availability of continuous data sets for key variables of the desired analysis. In addition to the data, the great volume and speed of events of the period that generate a certain limitation in the empirical evidence, since it is not always possible to construct suitable models to capture such effects. The results showed that industrial employment is significantly determined by productivity and by remuneration and value added by three groups of variables, one of macroeconomic character, one of foreign trade and another one related to the variations of value added of the other sectors of the economy. It was also found that structural changes, mainly in the direct coefficients of employed and value-added personnel, in technology and in demand, were decisive for the structural variations in occupation and added volume of industry in the period.. / Este estudo busca dar algumas contribuições ao debate sobre a desindustrialização brasileira, com um olhar específico para os determinantes das variações do valor adicionado e do emprego na indústria, e dos fatores estruturais que influenciaram estas variações e do valor da produção industrial, para o período de 1990 a 2014. Com o intuito de contribuir de forma empírica foram utilizados uma análise a partir do modelo econométrico VEC (Vector Erros Correction) e uma aplicação da análise de insumo-produto com a técnica SDA (Structural Decomposition Analysis), além de uma vasta revisão empírica e histórico teórica, a fim de conectar os resultados aos fatos históricos verificados. De modo geral se constitui um período com vasta literatura, com grandes mudanças de caráter político, de mudanças na condução da política econômica e principalmente de conexão da estrutura produtiva brasileira com o restante do mundo. Uma grande limitação verificada foi a disponibilidade de séries contínuas de dados para variáveis chave da análise desejada. Para além dos dados o grande volume e velocidade de acontecimentos do período que geram certa limitação na evidência empírica, pois nem sempre é possível construir modelos aptos captar tais efeitos. Os resultados demosntraram que o emprego industrial é significativamente determiando pela produtividade e pela remuneração e o valor adicionado por três grupos de variáveis, um de caráter macroeconômico, um de comércio exterior e outro referente as variações do valor adicionado dos demais setores da economia. Constatou-se também que modificações estruturais, principalemnet nos coefeicientes diretos do pessoal ocupado e do valor adicionado, na tecnologia e na demanda foram determinantes para as variações estruturais da ocupação e do vlor adicionado da indústria no período.

This thesis aims to produce short-term forecasts for the economic activity in Turkey. As a proxy for the economic activity, industrial production index is used. Univariate autoregressive distributed lag (ADL) models, vector autoregressive (VAR) models and combination forecasts method are utilized in a pseudo out-of-sample forecasting framework to obtain one-month ahead forecasts. To evaluate the models&rsquo / forecasting performances, the relative root mean square forecast error (RRMSFE) is calculated. Overall, results indicate that combining the VAR models with four endogenous variables yields the most substantial improvement in forecasting performance, relative to benchmark autoregressive (AR) model.

The dissertation is mainly made up of three empirical theses on the Optimum Currency Area theory, business cycle synchronization, and intra-industry trade. The second chapter conducts an empirical test into the theory of Optimum Currency Area. I investigate the feasibility of creating a currency union in East Asia by examining the dominance and symmetry of macroeconomic shocks. Relying on a series of structural Vector Autoregressive models with long-run and block exogeneity restrictions, I identify a variety of macroeconomic disturbances in eleven East Asian economies. To examine the nature of the disturbances, I look into the forecast error variance decomposition, correlation of disturbances, size of shocks, and speed of adjustments. Based on both statistical analysis and economic comparison, it is found that two groups of economies are subject to dominant and symmetrical domestic supply shocks, and that the two groups respond quickly to moderate-sized shocks. Therefore, it is economically feasible for the two groups of economies to foster common currency zones. The third chapter investigates the different effects of intra- and inter-industry trade on business cycle synchronization, controlling for financial market linkage and monetary policy making. The chapter is the first attempt to use intra- and inter-industry trade simultaneously in Instrument Variable estimations. The evidence in my paper is supportive that intra-industry trade increases business cycle synchronization, while inter-industry trade brings about divergence of cycles. The findings imply that country pairs with higher intra-industry trade intensity are more likely to experience synchronized business cycles and are more feasible to join a monetary union. My results also show that financial integration and monetary policy coordination provide no explanation for synchronization when industry-level trade are accounted for. The fourth chapter extends the third chapter and explores how the characteristics of global trade network influence intra-industry trade. Borrowing the concept of structural equivalence, the similarity of two countries’ aggregate trade relations with other countries, from the social network analysis, this study incorporates this measure of trade network to the augmented gravity model of intra-industry trade. I build up two fixed effects models to analyze intra-industry trade in the raw material and final product sectors among 182 countries from 1962 through 2000. Structural equivalence promotes intra-industry trade flows in the final product sector, but it does not influence intra-industry trade in the crude material sector. Moreover, structural equivalence has been increasingly important in boosting intra-industry trade over time. / Graduate / 0508

This paper proposes for the purposes of freight generation a spatial autoregressive model framework, combined with non-linear semi-parametric techniques. We demonstrate the capabilities of the model in a series of Monte Carlo studies. Moreover, evidence is provided for non-linearities in freight generation, through an applied analysis of European NUTS-2 regions. We provide evidence for significant spatial dependence and for significant non-linearities related to employment rates in manufacturing and infrastructure capabilities in regions. The non-linear impacts are the most significant in the agricultural freight generation sector.

No description available.

Investing in real estate carries inherent risks due to fluctuations in economic activity, changes in population dynamics, and shifts in market demand. While traditional approaches to scenario analysis, grounded in market expertise and keen intuition, have stood the test of time, they are also subjective and prone to human error and external influences. Therefore, an objective approach based on statistical inference was sought to serve as a supplementary instrument for real estate industry professionals. With efficacy and practical functionality in consideration, this thesis explores various solutions and determines autoregressive processes as a prime candidate for such an instrument. An instructive procedure is developed and applied to two data sets of historical Stockholm office rents and yields respectively. Starting with data typically available to real estate investors and advisors, this procedure implements locally weighted scatterplot smoothing, polynomial regression, autoregressive integrated moving average processes and matrix transformations to derive forecast intervals which may be applied to prescribe probability to precise ranges or points of the users variable of choice, several quarters into the future. The results demonstrate limitations in the distance of forecasting using this procedure but display satisfactory performance in the short to medium term. Additionally, the practical applicability of the procedure is reflected upon. / Investering i fastigheter medför inneboende risker på grund av fluktuationer i ekonomisk aktivitet, förändringar i befolkningsdynamik och efterfrågan på marknaden. Medan traditionella tillvägagångssätt för scenarioanalys, grundade på marknadsexpertis och skarp intuition, har bestått tidens tand, är de också subjektiva och medför risk för mänskliga fel och externa faktorer. Därav eftertraktades en objektiv metod baserad på statistiska processer för att fungera som ett kompletterande verktyg i fastighetsbranschen. Med hänsyn till effektivitet och praktisk funktionalitet fastställs autoregressiva processer som en primär kandidat som ett sådant verktyg i denna studie. En instruktiv procedur utvecklas och tillämpas på två dataset av historiska hyror respektive avkastning för kontorslokaler i Stockholm. Med utgångspunkt i data vanligt tillgänglig för fastighetsinvesterare och rådgivare implementerar denna procedur lokalt viktad spridningsdiagramsutjämning, polynomregression, autoregressiva integrerade glidande medelvärdesprocesser och matristransformationer för att härleda prognosintervall som kan användas för att föreskriva sannolikheter till exakta intervall eller punkter för variabeln i fråga, flera kvartal in i framtiden. Resultaten visar begränsningar i avståndet för prognoser med denna procedur men tillfredsställande prestanda på kort- till medellång sikt. Dessutom görs reflektioner kring den praktiska användbarheten av proceduren.

Orientador: Samuel da Silva / Resumo: O principal objetivo deste trabalho é usar métodos de extrapolação em coeficientes de modelos autorregressivos (AR), para fornecer informações futuras de condições de estruturas na existência de mecanismo de danos pré-definidos. Os modelos AR são estimados considerando a predição de um passo à frente, verificados e validados a partir de dados de vibração de uma estrutura na condição não danificada. Os erros de predição são usados para extrair um indicador para classificar a condição do sistema. Então, um novo modelo é identificado se qualquer variação de índices de dano ocorrer, e seus coeficientes são comparados com os do modelo de referência. A extrapolação dos coeficientes de AR é realizada através das splines cúbicas por partes que evitam possíveis instabilidades e alterações indesejáveis dos polinômios, obtendo aproximações adequadas através de polinômios de baixa ordem. Uma curva de tendência para o indicador capaz de predizer o comportamento futuro pode ser obtida a partir da extrapolação direta dos coeficientes. Uma estrutura de três andares com um para-choque e uma coluna de alumínio colocada no centro do último andar são analisados com diferentes cenários de dano para ilustrar a abordagem. Os resultados indicam a possibilidade de estimar a condição futura do sistema a partir dos dados de vibração nas condições de danos iniciais. / Abstract: The main purpose of this work is to apply extrapolation methods upon coefficients of autoregressive models (AR), to provide future condition information of structures in the existence of predefined damage mechanism. The AR models are estimated considering one-step-ahead prediction, verified and validated from vibration data of a structure in the undamaged condition. The prediction errors are used to extract an indicator to classify the system state condition. Then, a new model is identified if any variation of damage indices occurs, and its coefficients are compared to the ones from the reference model. The extrapolation of the AR coefficients is performed through the piecewise cubic splines that avoid possible instabilities and undesirable changes of the polynomials, obtaining suitable approximations through low-order polynomials. A trending curve for the indicator capable of predicting future behavior can be obtained from direct coefficient extrapolation. A benchmark of a three-story building structure with a bumper and an aluminum column placed on the center of the top floor is analyzed with different damage scenarios to illustrate the approach. The results indicate the feasibility of estimating the future system state from the vibration data in the initial damage conditions. / Mestre

No description available.