Common Features in Vector Nonlinear Time Series Models

This thesis consists of four manuscripts in the area of nonlinear time series econometrics on topics of testing, modeling and forecasting nonlinear common features. The aim of this thesis is to develop new econometric contributions for hypothesis testing and forecasting in these area. Both stationary and nonstationary time series are concerned. A definition of common features is proposed in an appropriate way to each class. Based on the definition, a vector nonlinear time series model with common features is set up for testing for common features. The proposed models are available for forecasting as well after being well specified. The first paper addresses a testing procedure on nonstationary time series. A class of nonlinear cointegration, smooth-transition (ST) cointegration, is examined. The ST cointegration nests the previously developed linear and threshold cointegration. An Ftypetest for examining the ST cointegration is derived when stationary transition variables are imposed rather than nonstationary variables. Later ones drive the test standard, while the former ones make the test nonstandard. This has important implications for empirical work. It is crucial to distinguish between the cases with stationary and nonstationary transition variables so that the correct test can be used. The second and the fourth papers develop testing approaches for stationary time series. In particular, the vector ST autoregressive (VSTAR) model is extended to allow for common nonlinear features (CNFs). These two papers propose a modeling procedure and derive tests for the presence of CNFs. Including model specification using the testing contributions above, the third paper considers forecasting with vector nonlinear time series models and extends the procedures available for univariate nonlinear models. The VSTAR model with CNFs and the ST cointegration model in the previous papers are exemplified in detail,and thereafter illustrated within two corresponding macroeconomic data sets.

Stochastic simulation of time-series models combined with geostatistics to predict water-table scenarios in a Guarani Aquifer System outcrop area, Brazil

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Study of charge transport in blends of natural rubber and poly(o-methoxyaniline) based on a resistor network statistical model

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

A time series sequestration and storage model of atmospheric carbon dioxide

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Stochastic simulation of time-series models combined with geostatistics to predict water-table scenarios in a Guarani Aquifer System outcrop area, Brazil

Stochastic methods based on time-series modeling combined with geostatistics can be useful tools to describe the variability of water-table levels in time and space and to account for uncertainty. Monitoring water-level networks can give information about the dynamic of the aquifer domain in both dimensions. Time-series modeling is an elegant way to treat monitoring data without the complexity of physical mechanistic models. Time-series model predictions can be interpolated spatially, with the spatial differences in water-table dynamics determined by the spatial variation in the system properties and the temporal variation driven by the dynamics of the inputs into the system. An integration of stochastic methods is presented, based on time-series modeling and geostatistics as a framework to predict water levels for decision making in groundwater management and land-use planning. The methodology is applied in a case study in a Guarani Aquifer System (GAS) outcrop area located in the southeastern part of Brazil. Communication of results in a clear and understandable form, via simulated scenarios, is discussed as an alternative, when translating scientific knowledge into applications of stochastic hydrogeology in large aquifers with limited monitoring network coverage like the GAS.

Changes in the use of broad-spectrum antibiotics after cefepime shortage: a time series analysis

The original cefepime product was withdrawn from the Swiss market in January 2007 and replaced by a generic 10 months later. The goals of the study were to assess the impact of this cefepime shortage on the use and costs of alternative broad-spectrum antibiotics, on antibiotic policy, and on resistance of Pseudomonas aeruginosa toward carbapenems, ceftazidime, and piperacillin-tazobactam. A generalized regression-based interrupted time series model assessed how much the shortage changed the monthly use and costs of cefepime and of selected alternative broad-spectrum antibiotics (ceftazidime, imipenem-cilastatin, meropenem, piperacillin-tazobactam) in 15 Swiss acute care hospitals from January 2005 to December 2008. Resistance of P. aeruginosa was compared before and after the cefepime shortage. There was a statistically significant increase in the consumption of piperacillin-tazobactam in hospitals with definitive interruption of cefepime supply and of meropenem in hospitals with transient interruption of cefepime supply. Consumption of each alternative antibiotic tended to increase during the cefepime shortage and to decrease when the cefepime generic was released. These shifts were associated with significantly higher overall costs. There was no significant change in hospitals with uninterrupted cefepime supply. The alternative antibiotics for which an increase in consumption showed the strongest association with a progression of resistance were the carbapenems. The use of alternative antibiotics after cefepime withdrawal was associated with a significant increase in piperacillin-tazobactam and meropenem use and in overall costs and with a decrease in susceptibility of P. aeruginosa in hospitals. This warrants caution with regard to shortages and withdrawals of antibiotics.

A Diagnostic Test for the Mixing Distribution in a Generalised Linear Mixed Model

We introduce a diagnostic test for the mixing distribution in a generalised linear mixed model. The test is based on the difference between the marginal maximum likelihood and conditional maximum likelihood estimates of a subset of the fixed effects in the model. We derive the asymptotic variance of this difference, and propose a test statistic that has a limiting chi-square distribution under the null hypothesis that the mixing distribution is correctly specified. For the important special case of the logistic regression model with random intercepts, we evaluate via simulation the power of the test in finite samples under several alternative distributional forms for the mixing distribution. We illustrate the method by applying it to data from a clinical trial investigating the effects of hormonal contraceptives in women.

TIME SERIES ANALYSIS AS INPUT FOR PREDICTIVE MODELING: PREDICTING CARDIAC ARREST IN A PEDIATRIC INTENSIVE CARE UNIT

The first manuscript, entitled "Time-Series Analysis as Input for Clinical Predictive Modeling: Modeling Cardiac Arrest in a Pediatric ICU" lays out the theoretical background for the project. There are several core concepts presented in this paper. First, traditional multivariate models (where each variable is represented by only one value) provide single point-in-time snapshots of patient status: they are incapable of characterizing deterioration. Since deterioration is consistently identified as a precursor to cardiac arrests, we maintain that the traditional multivariate paradigm is insufficient for predicting arrests. We identify time series analysis as a method capable of characterizing deterioration in an objective, mathematical fashion, and describe how to build a general foundation for predictive modeling using time series analysis results as latent variables. Building a solid foundation for any given modeling task involves addressing a number of issues during the design phase. These include selecting the proper candidate features on which to base the model, and selecting the most appropriate tool to measure them. We also identified several unique design issues that are introduced when time series data elements are added to the set of candidate features. One such issue is in defining the duration and resolution of time series elements required to sufficiently characterize the time series phenomena being considered as candidate features for the predictive model. Once the duration and resolution are established, there must also be explicit mathematical or statistical operations that produce the time series analysis result to be used as a latent candidate feature. In synthesizing the comprehensive framework for building a predictive model based on time series data elements, we identified at least four classes of data that can be used in the model design. The first two classes are shared with traditional multivariate models: multivariate data and clinical latent features. Multivariate data is represented by the standard one value per variable paradigm and is widely employed in a host of clinical models and tools. These are often represented by a number present in a given cell of a table. Clinical latent features derived, rather than directly measured, data elements that more accurately represent a particular clinical phenomenon than any of the directly measured data elements in isolation. The second two classes are unique to the time series data elements. The first of these is the raw data elements. These are represented by multiple values per variable, and constitute the measured observations that are typically available to end users when they review time series data. These are often represented as dots on a graph. The final class of data results from performing time series analysis. This class of data represents the fundamental concept on which our hypothesis is based. The specific statistical or mathematical operations are up to the modeler to determine, but we generally recommend that a variety of analyses be performed in order to maximize the likelihood that a representation of the time series data elements is produced that is able to distinguish between two or more classes of outcomes. The second manuscript, entitled "Building Clinical Prediction Models Using Time Series Data: Modeling Cardiac Arrest in a Pediatric ICU" provides a detailed description, start to finish, of the methods required to prepare the data, build, and validate a predictive model that uses the time series data elements determined in the first paper. One of the fundamental tenets of the second paper is that manual implementations of time series based models are unfeasible due to the relatively large number of data elements and the complexity of preprocessing that must occur before data can be presented to the model. Each of the seventeen steps is analyzed from the perspective of how it may be automated, when necessary. We identify the general objectives and available strategies of each of the steps, and we present our rationale for choosing a specific strategy for each step in the case of predicting cardiac arrest in a pediatric intensive care unit. Another issue brought to light by the second paper is that the individual steps required to use time series data for predictive modeling are more numerous and more complex than those used for modeling with traditional multivariate data. Even after complexities attributable to the design phase (addressed in our first paper) have been accounted for, the management and manipulation of the time series elements (the preprocessing steps in particular) are issues that are not present in a traditional multivariate modeling paradigm. In our methods, we present the issues that arise from the time series data elements: defining a reference time; imputing and reducing time series data in order to conform to a predefined structure that was specified during the design phase; and normalizing variable families rather than individual variable instances. The final manuscript, entitled: "Using Time-Series Analysis to Predict Cardiac Arrest in a Pediatric Intensive Care Unit" presents the results that were obtained by applying the theoretical construct and its associated methods (detailed in the first two papers) to the case of cardiac arrest prediction in a pediatric intensive care unit. Our results showed that utilizing the trend analysis from the time series data elements reduced the number of classification errors by 73%. The area under the Receiver Operating Characteristic curve increased from a baseline of 87% to 98% by including the trend analysis. In addition to the performance measures, we were also able to demonstrate that adding raw time series data elements without their associated trend analyses improved classification accuracy as compared to the baseline multivariate model, but diminished classification accuracy as compared to when just the trend analysis features were added (ie, without adding the raw time series data elements). We believe this phenomenon was largely attributable to overfitting, which is known to increase as the ratio of candidate features to class examples rises. Furthermore, although we employed several feature reduction strategies to counteract the overfitting problem, they failed to improve the performance beyond that which was achieved by exclusion of the raw time series elements. Finally, our data demonstrated that pulse oximetry and systolic blood pressure readings tend to start diminishing about 10-20 minutes before an arrest, whereas heart rates tend to diminish rapidly less than 5 minutes before an arrest.

The Hurst exponent as an indicator of the behaviour of a model monopile in an ocean wave testing basin

With the importance of renewable energy well-established worldwide, and targets of such energy quantified in many cases, there exists a considerable interest in the assessment of wind and wave devices. While the individual components of these devices are often relatively well understood and the aspects of energy generation well researched, there seems to be a gap in the understanding of these devices as a whole and especially in the field of their dynamic responses under operational conditions. The mathematical modelling and estimation of their dynamic responses are more evolved but research directed towards testing of these devices still requires significant attention. Model-free indicators of the dynamic responses of these devices are important since it reflects the as-deployed behaviour of the devices when the exposure conditions are scaled reasonably correctly, along with the structural dimensions. This paper demonstrates how the Hurst exponent of the dynamic responses of a monopile exposed to different exposure conditions in an ocean wave basin can be used as a model-free indicator of various responses. The scaled model is exposed to Froude scaled waves and tested under different exposure conditions. The analysis and interpretation is carried out in a model-free and output-only environment, with only some preliminary ideas regarding the input of the system. The analysis indicates how the Hurst exponent can be an interesting descriptor to compare and contrast various scenarios of dynamic response conditions.

Stochastic simulation of time-series models combined with geostatistics to predict water-table scenarios in a Guarani Aquifer System outcrop area, Brazil

Stochastic methods based on time-series modeling combined with geostatistics can be useful tools to describe the variability of water-table levels in time and space and to account for uncertainty. Monitoring water-level networks can give information about the dynamic of the aquifer domain in both dimensions. Time-series modeling is an elegant way to treat monitoring data without the complexity of physical mechanistic models. Time-series model predictions can be interpolated spatially, with the spatial differences in water-table dynamics determined by the spatial variation in the system properties and the temporal variation driven by the dynamics of the inputs into the system. An integration of stochastic methods is presented, based on time-series modeling and geostatistics as a framework to predict water levels for decision making in groundwater management and land-use planning. The methodology is applied in a case study in a Guarani Aquifer System (GAS) outcrop area located in the southeastern part of Brazil. Communication of results in a clear and understandable form, via simulated scenarios, is discussed as an alternative, when translating scientific knowledge into applications of stochastic hydrogeology in large aquifers with limited monitoring network coverage like the GAS.

Coleman-Weinberg mechanism in a three-dimensional supersymmetric Chern-Simons-matter model

Using the superfield formalism, we study the dynamical breaking of gauge symmetry and super-conformal invariance in the N = 1 three-dimensional supersymmetric Chern-Simons model, coupled to a complex scalar superfield with a quartic self-coupling. This is an analogue of the conformally invariant Coleman-Weinberg model in four spacetime dimensions. We show that a mass for the gauge and matter superfields are dynamically generated after two-loop corrections to the effective superpotential. We also discuss the N = 2 extension of our work, showing that the Coleman-Weinberg mechanism in such model is not feasible, because it is incompatible with perturbation theory.

THE IMPORTANCE OF DISAGREEING: CONTRARIANS AND EXTREMISM IN THE CODA MODEL

In this paper, we study the effects of introducing contrarians in a model of Opinion Dynamics where the agents have internal continuous opinions, but exchange information only about a binary choice that is a function of their continuous opinion, the CODA model. We observe that the hung election scenario that arises when contrarians are introduced in discrete opinion models still happens. However, it is weaker and it should not be expected in every election. Finally, we also show that the introduction of contrarians make the tendency towards extremism of the original model weaker, indicating that the existence of agents that prefer to disagree might be an important aspect and help society to diminish extremist opinions.

Increased class A scavenger receptor and glomerular lipid precede mesangial matrix expansion in the bGH mouse model

Objective: Elevated neutral lipid content and mRNA expression of class A scavenger receptor (SRA) have been found in the renal cortex of the bovine growth hormone (bGH) mouse model of progressive glomerulosclerosis (GS). We hypothesize that the increased expression of SRA precedes glomerular scarring in this model. Design: Real time RT-PCR and immunofluorescence were employed to measure SRA and collagen types I and IV in the bGH transgenic and control mice at 5 and 12 weeks (wk) of age to determine the chronology of change in SRA expression in relation to glomerular scarring. Alternative mechanisms for increasing glomerular lipid were assessed by measuring mRNA expression levels of low-density lipoprotein receptor (LDL-r), 3-hydroxy-3-methylglutaryl coenzyme A reductase (HMGR), and ATP-binding cassette transporter A1 (ABCA1). In addition, the involvement of macrophages in early GS was assessed by CD68 mRNA expression in kidney cortex. Results: Both mRNA and protein levels of SRA were significantly increased in 5-wk bGH compared with control mice, whereas the expression of collagen I and IV was unaltered. Unchanged levels of LDL-r and HMGR mRNA indicate that neither regulated cholesterol uptake via LDL-r nor the cholesterol synthetic pathway played a role in the early lipid increase. The finding of increased ABCA1 expression was an indicator of excess intracellular lipid in the renal cortex of bGH mice at 5 wk. CD68 expression in bGH did not differ significantly from that of controls at 5 wk suggesting that cortical macrophage infiltration was not increased in bGH mice at this time point. Conclusion: An early increase in SRA mRNA and protein expression in the bGH kidney precedes glomerular scarring and is independent of macrophage influx. Published by Elsevier Ltd. on behalf of Growth Hormone Research Society.

Paste Residence Time in a Spouted Bed Dryer. IV: Effect of the Inert Particle Size Distribution

The residence time distribution and mean residence time of a 10% sodium bicarbonate solution that is dried in a conventional spouted bed with inert bodies were measured with the stimulus-response method. Methylene blue was used as a chemical tracer, and the effects of the paste feed mode, size distribution of the inert bodies, and mean particle size on the residence times and dried powder properties were investigated. The results showed that the residence time distributions could be best reproduced with the perfect mixing cell model or N = 1 for the continuous stirred tank reactor in a series model. The mean residence times ranged from 6.04 to 12.90 min and were significantly affected by the factors studied. Analysis of variance on the experimental data showed that mean residence times were affected by the mean diameter of the inert bodies at a significance level of 1% and by the size distribution at a level of 5%. Moreover, altering the paste feed from dripping to pneumatic atomization affected mean residence time at a 5% significance level. The dried powder characteristics proved to be adequate for further industrial manipulation, as demonstrated by the low moisture content, narrow range of particle size, and good flow properties. The results of this research are significant in the study of the drying of heat-sensitive materials because it shows that by simultaneously changing the size distribution and average size of the inert bodies, the mean residence times of a paste can be reduced by half, thus decreasing losses due to degradation.

Anti-inflammatory effects of Lafoensia pacari and ellagic acid in a murine model of asthma

We have shown that the ethanolic extract of Lafoensia pacari inhibits eosinophilic inflammation induced by Toxocara canis infection, and that ellagic acid is the secondary metabolite responsible for the anti-eosinophilic activity seen in a model of beta-glucan peritonitis. In the present study, we investigated the preventive and curative effects of L. pacari extract and ellagic acid on allergic lung inflammation using a murine model of ovalbumin-induced asthma. In bronchoalveolar lavage fluid, preventive (22-day) treatment with L. pacari (200 mg/kg) and ellagic acid (10 mg/kg) inhibited neutrophil counts (by 75% and 57%) and eosinophil counts (by 78% and 68%). L. pacari reduced IL-4 and IL-13 levels (by 67% and 73%), whereas ellagic acid reduced IL-4, IL-5 and IL-13 (by 67%, 88% and 85%). To investigate curative anti-inflammatory effects, we treated mice daily with ellagic acid (0.1, 1, or 10 mg/kg), also treating selected mice with L. pacari (200 mg/kg) from day 18 to day 22. The highest ellagic acid dose reduced neutrophil and eosinophil numbers (by 59% and 82%), inhibited IL-4, IL-5, and IL-13 (by 62%,61%, and 49%). Neither L. pacari nor ellagic acid suppressed ovalbumin-induced airway hyperresponsiveness or cysteinyl leukotriene synthesis in lung homogenates. In mice treated with ellagic acid (10 mg/kg) or L. pacari (200 mg/kg) at 10 min after the second ovalbumin challenge, eosinophil numbers were 53% and 69% lower, respectively. Cytokine levels were unaffected by this treatment. L. pacari and ellagic acid are effective eosinophilic inflammation suppressors, suggesting a potential for treating allergies. (c) 2007 Elsevier B.V All rights reserved.