A hypothesis test using bias-adjusted AR estimators for classifying time series in small samples

A new test of hypothesis for classifying stationary time series based on the bias-adjusted estimators of the fitted autoregressive model is proposed. It is shown theoretically that the proposed test has desirable properties. Simulation results show that when time series are short, the size and power estimates of the proposed test are reasonably good, and thus this test is reliable in discriminating between short-length time series. As the length of the time series increases, the performance of the proposed test improves, but the benefit of bias-adjustment reduces. The proposed hypothesis test is applied to two real data sets: the annual real GDP per capita of six European countries, and quarterly real GDP per capita of five European countries. The application results demonstrate that the proposed test displays reasonably good performance in classifying relatively short time series.

Polarization of forecast densities : a new approach to time series classification

Time series classification has been extensively explored in many fields of study. Most methods are based on the historical or current information extracted from data. However, if interest is in a specific future time period, methods that directly relate to forecasts of time series are much more appropriate. An approach to time series classification is proposed based on a polarization measure of forecast densities of time series. By fitting autoregressive models, forecast replicates of each time series are obtained via the bias-corrected bootstrap, and a stationarity correction is considered when necessary. Kernel estimators are then employed to approximate forecast densities, and discrepancies of forecast densities of pairs of time series are estimated by a polarization measure, which evaluates the extent to which two densities overlap. Following the distributional properties of the polarization measure, a discriminant rule and a clustering method are proposed to conduct the supervised and unsupervised classification, respectively. The proposed methodology is applied to both simulated and real data sets, and the results show desirable properties.

Effect of the increase in "alcopops" tax on alcohol-related harms in young people : a controlled interrupted time series

Objective: To measure alcohol-related harms to the health of young people presenting to emergency departments (EDs) of Gold Coast public hospitals before and after the increase in the federal government "alcopops" tax in 2008. Design, setting and participants: Interrupted time series analysis over 5 years (28 April 2005 to 27 April 2010) of 15-29-year-olds presenting to EDs with alcohol-related harms compared with presentations of selected control groups. Main outcome measures: Proportion of 15-29-year-olds presenting to EDs with alcohol-related harms compared with (i) 30-49-year-olds with alcohol-related harms, (ii)15-29-year-olds with asthma or appendicitis, and (iii) 15-29-yearolds with any non-alcohol and non-injury related ED presentation. Results: Over a third of 15-29-year-olds presented to ED with alcohol-related conditions, as opposed to around a quarter for all other age groups. There was no significant decrease in alcohol-related ED presentations of 15-29-year-olds compared with any of the control groups after the increase in the tax. We found similar results for males and females, narrow and broad definitions of alcoholrelated harms, under-19s, and visitors to and residents of the Gold Coast. Conclusions: The increase in the tax on al copops was not associated with any reduction in alcohol-related harms in this population in a unique tourist and holiday region. A more comprehensive approach to reducing alcohol harms in young people is needed.

Simulation-based density estimation for time series using covariate data

This paper proposes a simulation-based density estimation technique for time series that exploits information found in covariate data. The method can be paired with a large range of parametric models used in time series estimation. We derive asymptotic properties of the estimator and illustrate attractive finite sample properties for a range of well-known econometric and financial applications.

Development of health risk-based metrics for defining a heatwave : a time series study in Brisbane, Australia

Background: This study attempted to develop health risk-based metrics for defining a heatwave in Brisbane, Australia. Methods: Poisson generalised additive model was performed to assess the impact of heatwaves on mortality and emergency hospital admissions (EHAs) in Brisbane. Results: In general, the higher the intensity and the longer the duration of a heatwave, the greater the health impacts. There was no apparent difference in EHAs risk during different periods of a warm season. However, there was a greater risk of mortality in the second half of a warm season than that in the first half. While elderly (>75 years)were particularly vulnerable to both the EHA and mortality effects of a heatwave, the risk for EHAs also significantly increased for two other age groups (0-64 years and 65-74 years) during severe heatwaves. Different patterns between cardiorespiratory mortality and EHAs were observed. Based on these findings, we propose the use of a teiered heat warning system based on the health risk of heatwave. Conclusions: Health risk-based metrics are a useful tool for the development of local heatwave definitions. thsi tool may have significant implications for the assessment of heatwave-related health consequences and development of heatwave response plans and implementation strategies.

Efficient use of correlation entropy for analysing time series data

The correlation dimension D 2 and correlation entropy K 2 are both important quantifiers in nonlinear time series analysis. However, use of D 2 has been more common compared to K 2 as a discriminating measure. One reason for this is that D 2 is a static measure and can be easily evaluated from a time series. However, in many cases, especially those involving coloured noise, K 2 is regarded as a more useful measure. Here we present an efficient algorithmic scheme to compute K 2 directly from a time series data and show that K 2 can be used as a more effective measure compared to D 2 for analysing practical time series involving coloured noise.

A Comparison of Machine Learning Techniques for Modeling River Flow Time Series: The Case of Upper Cauvery River Basin

Models of river flow time series are essential in efficient management of a river basin. It helps policy makers in developing efficient water utilization strategies to maximize the utility of scarce water resource. Time series analysis has been used extensively for modeling river flow data. The use of machine learning techniques such as support-vector regression and neural network models is gaining increasing popularity. In this paper we compare the performance of these techniques by applying it to a long-term time-series data of the inflows into the Krishnaraja Sagar reservoir (KRS) from three tributaries of the river Cauvery. In this study flow data over a period of 30 years from three different observation points established in upper Cauvery river sub-basin is analyzed to estimate their contribution to KRS. Specifically, ANN model uses a multi-layer feed forward network trained with a back-propagation algorithm and support vector regression with epsilon intensive-loss function is used. Auto-regressive moving average models are also applied to the same data. The performance of different techniques is compared using performance metrics such as root mean squared error (RMSE), correlation, normalized root mean squared error (NRMSE) and Nash-Sutcliffe Efficiency (NSE).

Contributions to time series data mining departing from the problem of road travel time modeling

194 p.

Modeling Financial Time Series with Artificial Neural Networks

Financial time series convey the decisions and actions of a population of human actors over time. Econometric and regressive models have been developed in the past decades for analyzing these time series. More recently, biologically inspired artificial neural network models have been shown to overcome some of the main challenges of traditional techniques by better exploiting the non-linear, non-stationary, and oscillatory nature of noisy, chaotic human interactions. This review paper explores the options, benefits, and weaknesses of the various forms of artificial neural networks as compared with regression techniques in the field of financial time series analysis.

Income ineqaulity from 1960-2012: a brief time-series history of capital and labour

This commentary examines two principal forms of inequality and their evolution since the 1960s: the division of national income between capital and labour, and the share of total income held by the top 1 per cent of earners. Trends are linked to current discussions of inequality drivers such as financialisation, and a brief time-series analysis of the effects of trade and financial sector growth on top incomes is presented.

Measuring time series predictability using support vector regression

Most studies involving statistical time series analysis rely on assumptions of linearity, which by its simplicity facilitates parameter interpretation and estimation. However, the linearity assumption may be too restrictive for many practical applications. The implementation of nonlinear models in time series analysis involves the estimation of a large set of parameters, frequently leading to overfitting problems. In this article, a predictability coefficient is estimated using a combination of nonlinear autoregressive models and the use of support vector regression in this model is explored. We illustrate the usefulness and interpretability of results by using electroencephalographic records of an epileptic patient.

Space-time cluster analysis of American visceral leishmaniasis in Bauru, Sao Paulo State, Brazil

A space-time analysis of American visceral leishmaniasis (AVL) in humans in the city of Bauru, Sao Paulo State, Brazil was carried out based on 239 cases diagnosed between June 2003 and October 2008. Spatial analysis of the disease showed that cases occurred especially in the city's urban areas. AVL annual incidence rates were calculated, demonstrating that the highest rate occurred in 2006 (19.55/100,000 inhabitants). This finding was confirmed by the time series analysis, which also showed a positive tendency over the period analyzed. The present study allows us to conclude that the disease was clustered in the Southwest side of the city in 2006, suggesting that this area may require special attention with regard to control and prevention measures.

Space-time cluster analysis of American visceral leishmaniasis in Bauru, São Paulo State, Brazil

A space-time analysis of American visceral leishmaniasis (AVL) in humans in the city of Bauru, São Paulo State, Brazil was carried out based on 239 cases diagnosed between June 2003 and October 2008. Spatial analysis of the disease showed that cases occurred especially in the city's urban areas. AVL annual incidence rates were calculated, demonstrating that the highest rate occurred in 2006 (19.55/100,000 inhabitants). This finding was confirmed by the time series analysis, which also showed a positive tendency over the period analyzed. The present study allows us to conclude that the disease was clustered in the Southwest side of the city in 2006, suggesting that this area may require special attention with regard to control and prevention measures.

Local Trigonometric Methods for Time Series Smoothing.

The thesis is concerned with local trigonometric regression methods. The aim was to develop a method for extraction of cyclical components in time series. The main results of the thesis are the following. First, a generalization of the filter proposed by Christiano and Fitzgerald is furnished for the smoothing of ARIMA(p,d,q) process. Second, a local trigonometric filter is built, with its statistical properties. Third, they are discussed the convergence properties of trigonometric estimators, and the problem of choosing the order of the model. A large scale simulation experiment has been designed in order to assess the performance of the proposed models and methods. The results show that local trigonometric regression may be a useful tool for periodic time series analysis.

Time series forecasting and prediction : a bibliography with abstracts.

Includes indexes.