An influence method for outlier detection applied to time series traffic data

The work of Chernick et al. (1982) is extended to form a quantitative outlier detection statistic for use with time series data. The statistic is formed from the squared elements of the influence function matrix, where each element of the matrix gives the influence on the theoretical autocorrelation function at lag k (pk) of a pair of obser vations at time lag k. The approximate first four moments for the statistic are derived and, by fitting Johnson curves to these theoretical moments, critical points are also produced. The statistic is also used to form the basis of an adjustment procedure to treat outliers or estimate missing values in the time series. The nuclear power data of Chernick et al. and the traffic count data of the Department of Transport are used for practical illustration.     

Combining Bayesian method and Kalman smoother for detection additive outlier patches in autoregressive time series

ABSTRACT

This article proposes a development of detecting patches of additive outliers in autoregressive time series models. The procedure improves the existing detection methods via Gibbs sampling. We combine the Bayesian method and the Kalman smoother to present some candidate models of outlier patches and the best model with the minimum Bayesian information criterion (BIC) is selected among them. We propose that this combined Bayesian and Kalman method (CBK) can reduce the masking and swamping effects about detecting patches of additive outliers. The correctness of the method is illustrated by simulated data and then by analyzing a real set of observations.     

Bias correction for outlier estimation in time series

The problem of outlier estimation in time series is addressed. The least squares estimators of additive and innovation outliers in the framework of linear stationary and non-stationary models are considered and their bias is evaluated. As a result, simple alternative nearly unbiased estimators are proposed both for the additive and the innovation outlier types. A simulation study confirms the theoretical results and suggests that the proposed estimators are effective in reducing the bias also for short series.     

Bootstrap methods for stationary functional time series

Bootstrap methods for estimating the long-run covariance of stationary functional time series are considered. We introduce a versatile bootstrap method that relies on functional principal component analysis, where principal component scores can be bootstrapped by maximum entropy. Two other bootstrap methods resample error functions, after the dependence structure being modeled linearly by a sieve method or nonlinearly by a functional kernel regression. Through a series of Monte-Carlo simulation, we evaluate and compare the finite-sample performances of these three bootstrap methods for estimating the long-run covariance in a functional time series. Using the intraday particulate matter (\(\hbox {PM}_{10}\)) dataset in Graz, the proposed bootstrap methods provide a way of constructing the distribution of estimated long-run covariance for functional time series.     

Portmanteau tests for linearity of stationary time series

This article considers the problem of testing for linearity of stationary time series. Portmanteau tests are discussed which are based on generalized correlations of residuals from a linear model (that is, autocorrelations and cross-correlations of different powers of the residuals). The finite-sample properties of the tests are assessed by means of Monte Carlo experiments. The tests are applied to 100 time series of stock returns.     

Projected polynomial autoregression for prediction of stationary time series

Polynomial autoregressions are usually considered to be unrealistic models for time series. However, this paper shows that they can successfully be used when the purpose of the time series study is to provide forecasts. A projection scheme inspired from projection pursuit regression and feedforward artificial neural networks is used in order to avoid an explosion of the number of parameters when considering a large number of lags. The estimation of the parameters of the projected polynomial autoregressions is a non-linear least-squares problem. A consistency result is proved. A simulation study shows that the naive use of the common final prediction error criterion is inappropriate to identify the best projected polynomial autoregression. An explanation of this phenomenon is given and a correction to the criterion is proposed. An important feature of the polynomial predictors introduced in this paper is their simple implementation, which allows for automatic use. This is illustrated with real data for the three-month US Treasury Bill.     

A simulation method for finite non-stationary time series

In this paper, we propose a novel simulation method which enables us to obtain a large number of simulated time series cheaply. The developed method can be applied to any non-stationary time series of finite length and it guarantees that not only the marginal distributions but also the autocorrelation structures of observed and simulated time series are the same. Extensive simulation studies have been conducted to check the performance of our method and to assess if the overall dynamics of the observed time series is preserved by the simulated realizations. The developed simulation method has also been applied to the real size data of cocoon filament, which can be reeled from a cocoon produced by a silkworm. Very good results have been achieved in all the cases considered in the paper.     

Bhattacharyya distance based linear discriminant function for stationary time series

The problem of classifying a covariance stationary normal time series is considered. Under certain regularity conditions, a compact form of the linear discriminant function in the sense of maximizing the Bhattacharyya distance is obtained.     

Spectral estimation for locally stationary time series with missing observations

Time series arising in practice often have an inherently irregular sampling structure or missing values, that can arise for example due to a faulty measuring device or complex time-dependent nature. Spectral decomposition of time series is a traditionally useful tool for data variability analysis. However, existing methods for spectral estimation often assume a regularly-sampled time series, or require modifications to cope with irregular or ‘gappy’ data. Additionally, many techniques also assume that the time series are stationary, which in the majority of cases is demonstrably not appropriate. This article addresses the topic of spectral estimation of a non-stationary time series sampled with missing data. The time series is modelled as a locally stationary wavelet process in the sense introduced by Nason et al. (J. R. Stat. Soc. B 62(2):271–292, 2000) and its realization is assumed to feature missing observations. Our work proposes an estimator (the periodogram) for the process wavelet spectrum, which copes with the missing data whilst relaxing the strong assumption of stationarity. At the centre of our construction are second generation wavelets built by means of the lifting scheme (Sweldens, Wavelet Applications in Signal and Image Processing III, Proc. SPIE, vol. 2569, pp. 68–79, 1995), designed to cope with irregular data. We investigate the theoretical properties of our proposed periodogram, and show that it can be smoothed to produce a bias-corrected spectral estimate by adopting a penalized least squares criterion. We demonstrate our method with real data and simulated examples.     

Posterior consistency for the spectral density of non-Gaussian stationary time series

Various nonparametric approaches for Bayesian spectral density estimation of stationary time series have been suggested in the literature, mostly based on the Whittle likelihood approximation. A generalization of this approximation involving a nonparametric correction of a parametric likelihood has been proposed in the literature with a proof of posterior consistency for spectral density estimation in combination with the Bernstein–Dirichlet process prior for Gaussian time series. In this article, we will extend the posterior consistency result to non-Gaussian time series by employing a general consistency theorem for dependent data and misspecified models. As a special case, posterior consistency for the spectral density under the Whittle likelihood is also extended to non-Gaussian time series. Small sample properties of this approach are illustrated with several examples of non-Gaussian time series.     

Methods for calculating stationary distribution in linear models of time series

The article deals with methods for computing the stationary marginal distribution in linear models of time series. Two approaches are described. First, an algorithm based on approximation of solution of the corresponding integral equation is briefly reviewed. Then, we study the limit behaviour of the partial sums c ₁ η₁+c ₂ η₂+···+c _n η _n where η _i are i.i.d. random variables and c _i real constants. We generalize procedure of Haiman (1998) [Haiman, G., 1998, Upper and lower bounds for the tail of the invariant distribution of some AR(1) processes. Asymptotic Methods in Probability and Statistics, 45, 723–730.] to an arbitrary causal linear process and relax the assumptions of his result significantly. This is achieved by investigating the properties of convolution of densities.     

A robust functional time series forecasting method

Univariate time series often take the form of a collection of curves observed sequentially over time. Examples of these include hourly ground-level ozone concentration curves. These curves can be viewed as a time series of functions observed at equally spaced intervals over a dense grid. Since functional time series may contain various types of outliers, we introduce a robust functional time series forecasting method to down-weigh the influence of outliers in forecasting. Through a robust principal component analysis based on projection pursuit, a time series of functions can be decomposed into a set of robust dynamic functional principal components and their associated scores. Conditioning on the estimated functional principal components, the crux of the curve-forecasting problem lies in modelling and forecasting principal component scores, through a robust vector autoregressive forecasting method. Via a simulation study and an empirical study on forecasting ground-level ozone concentration, the robust method demonstrates the superior forecast accuracy that dynamic functional principal component regression entails. The robust method also shows the superior estimation accuracy of the parameters in the vector autoregressive models for modelling and forecasting principal component scores, and thus improves curve forecast accuracy.     

Estimation of long-range dependence in gappy Gaussian time series

Statistics and Computing - Knowledge of the long-range dependence (LRD) parameter is critical to studies of self-similar behavior. However, statistical estimation of the LRD parameter becomes...     

A novel spatial outlier detection technique

Spatial outliers are spatially referenced objects whose non spatial attribute values are significantly different from the corresponding values in their spatial neighborhoods. In other words, a spatial outlier is a local instability or an extreme observation that deviates significantly in its spatial neighborhood, but possibly not be in the entire dataset. In this article, we have proposed a novel spatial outlier detection algorithm, location quotient (LQ) for multiple attributes spatial datasets, and compared its performance with the well-known mean and median algorithms for multiple attributes spatial datasets, in the literature. In particular, we have applied the mean, median, and LQ algorithms on a real dataset and on simulated spatial datasets of 13 different sizes to compare their performances. In addition, we have calculated area under the curve values in all the cases, which shows that our proposed algorithm is more powerful than the mean and median algorithms in almost all the considered cases and also plotted receiver operating characteristic curves in some cases.     

Multivariate analysis with a stationary time series covariance structure

When a covariance matrix has a pattern associated with a stationary time series on the errors, it is shown how certain hypothesis testing problems In multivariate analysis can be transformed into a product of two similar multivariate problems that each involve unpatterned covariance matrices.     

Multiresolution anomaly detection method for fractional Gaussian noise

Driven by network intrusion detection, we propose a MultiResolution Anomaly Detection (MRAD) method, which effectively utilizes the multiscale properties of Internet features and network anomalies. In this paper, several theoretical properties of the MRAD method are explored. A major new result is the mathematical formulation of the notion that a two-scaled MRAD method has larger power than the average power of the detection method based on the given two scales. Test threshold is also developed. Comparisons between MRAD method and other classical outlier detectors in time series are reported as well.     

Nonparametric change point detection for periodic time series

We consider detection of multiple changes in the distribution of periodic and autocorrelated data with known period. To account for periodicity we transform the sequence of vector observations by arranging them in matrices and thereby producing a sequence of independently and identically distributed matrix observations. We propose methods of testing the equality of matrix distributions and present methods that can be applied to matrix observations using the E-divisive algorithm. We show that periodicity and autocorrelation degrade existing change detection methods because they blur the changes that these procedures aim to discover. Methods that ignore the periodicity have low power to detect changes in the mean and the variance of periodic time series when the periodic effects overwhelm the true changes, while the proposed methods detect such changes with high power. We illustrate the proposed methods by detecting changes in the water quality of Lake Kasumigaura in Japan. The Canadian Journal of Statistics 48: 518–534; 2020 © 2020 Statistical Society of Canada