Adaptively varying-coefficient spatiotemporal models

Summary.  We propose an adaptive varying-coefficient spatiotemporal model for data that are observed irregularly over space and regularly in time. The model is capable of catching possible non-linearity (both in space and in time) and non-stationarity (in space) by allowing the auto-regressive coefficients to vary with both spatial location and an unknown index variable. We suggest a two-step procedure to estimate both the coefficient functions and the index variable, which is readily implemented and can be computed even for large spatiotemporal data sets. Our theoretical results indicate that, in the presence of the so-called nugget effect, the errors in the estimation may be reduced via the spatial smoothing—the second step in the estimation procedure proposed. The simulation results reinforce this finding. As an illustration, we apply the methodology to a data set of sea level pressure in the North Sea.     

A spatiotemporal auto-regressive moving average model for solar radiation

Summary.  To investigate the variability in energy output from a network of photovoltaic cells, solar radiation was recorded at 10 sites every 10 min in the Pentland Hills to the south of Edinburgh. We identify spatiotemporal auto-regressive moving average models as the most appropriate to address this problem. Although previously considered computationally prohibitive to work with, we show that by approximating using toroidal space and fitting by matching auto-correlations, calculations can be substantially reduced. We find that a first-order spatiotemporal auto-regressive (STAR(1)) process with a first-order neighbourhood structure and a Matern noise process provide an adequate fit to the data, and we demonstrate its use in simulating realizations of energy output.     

Efficient estimation of auto-regression parameters and innovation distributions for semiparametric integer-valued AR(p) models

Summary.  Integer-valued auto-regressive (INAR) processes have been introduced to model non-negative integer-valued phenomena that evolve over time. The distribution of an INAR( p ) process is essentially described by two parameters: a vector of auto-regression coefficients and a probability distribution on the non-negative integers, called an immigration or innovation distribution. Traditionally, parametric models are considered where the innovation distribution is assumed to belong to a parametric family. The paper instead considers a more realistic semiparametric INAR( p ) model where there are essentially no restrictions on the innovation distribution. We provide an (semiparametrically) efficient estimator of both the auto-regression parameters and the innovation distribution.     

Marginal distribution of Markov-switching VAR processes

We make available simple and accurate closed-form approximations to the marginal distribution of Markov-switching vector auto-regressive (MS VAR) processes. The approximation is built upon the property of MS VAR processes of being Gaussian conditionally on any semi-infinite sequence of the latent state. Truncating the semi-infinite sequence and averaging over all possible sequences of that finite length yields a mixture of normals that converges to the unknown marginal distribution as the sequence length increases. Numerical experiments confirm the viability of the approach which extends to the closely related class of MS state space models. Several applications are discussed.     

A hierarchical modelling approach to combining environmental data at different scales

Summary. Long-transported air pollution in Europe is monitored by a combination of a highly complex mathematical model and a limited number of measurement stations. The model predicts deposition on a 150 km × 150 km square grid covering the whole of the continent. These predictions can be regarded as spatial averages, with some spatially correlated model error. The measurement stations give a limited number of point estimates, regarded as error free. We combine these two sources of data by assuming that both are observations of an underlying true process. This true deposition is made up of a smooth deterministic trend, due to gradual changes in emissions over space and time, and two stochastic components. One is non- stationary and correlated over long distances; the other describes variation within a grid square. Our approach is through hierarchical modelling with predictions and measurements being independent conditioned on the underlying non-stationary true deposition. We assume Gaussian processes and calculate maximum likelihood estimates through numerical optimization. We find that the variation within a grid square is by far the largest component of the variation in the true deposition. We assume that the mathematical model produces estimates of the mean over an area that is approximately equal to a grid square, and we find that it has an error that is similar to the long-range stochastic component of the true deposition, in addition to a large bias.     

Temporal Aggregation of Stationary and Non-stationary Continuous-Time Processes

Abstract.  We study the autocorrelation structure of aggregates from a continuous-time process. The underlying continuous-time process or some of its higher derivative is assumed to be a stationary continuous-time auto-regressive fractionally integrated moving-average (CARFIMA) process with Hurst parameter H . We derive closed-form expressions for the limiting autocorrelation function and the normalized spectral density of the aggregates, as the extent of aggregation increases to infinity. The limiting model of the aggregates, after appropriate number of differencing, is shown to be some functional of the standard fractional Brownian motion with the same Hurst parameter of the continuous-time process from which the aggregates are measured. These results are then used to assess the loss of forecasting efficiency due to aggregation.     

Dynamic model-based clustering for spatio-temporal data

In many research fields, scientific questions are investigated by analyzing data collected over space and time, usually at fixed spatial locations and time steps and resulting in geo-referenced time series. In this context, it is of interest to identify potential partitions of the space and study their evolution over time. A finite space-time mixture model is proposed to identify level-based clusters in spatio-temporal data and study their temporal evolution along the time frame. We anticipate space-time dependence by introducing spatio-temporally varying mixing weights to allocate observations at nearby locations and consecutive time points with similar cluster’s membership probabilities. As a result, a clustering varying over time and space is accomplished. Conditionally on the cluster’s membership, a state-space model is deployed to describe the temporal evolution of the sites belonging to each group. Fully posterior inference is provided under a Bayesian framework through Monte Carlo Markov chain algorithms. Also, a strategy to select the suitable number of clusters based upon the posterior temporal patterns of the clusters is offered. We evaluate our approach through simulation experiments, and we illustrate using air quality data collected across Europe from 2001 to 2012, showing the benefit of borrowing strength of information across space and time.     

Shrinkage Estimation of the Memory Parameter in Stationary Gaussian Processes

The correct and efficient estimation of memory parameters in a stationary Gaussian processes is an important issue, since otherwise, forecasts based on the resulting time series would be misleading. On the other hand, if the memory parameters are suspected to fall in a smaller subspace through some hypothesis restrictions, it becomes a hard decision whether to use estimators based on the restricted spaces or to use unrestricted estimators over the full parameter space. In this article, we propose James-Stein-type estimators of the memory parameters of a stationary Gaussian times series process, which can efficiently incorporate the hypothetical restrictions. We show theoretically that the proposed estimators are more efficient than the usual unrestricted maximum likelihood estimators over the entire parameter space.     

Bayesian model learning based on a parallel MCMC strategy

We introduce a novel Markov chain Monte Carlo algorithm for estimation of posterior probabilities over discrete model spaces. Our learning approach is applicable to families of models for which the marginal likelihood can be analytically calculated, either exactly or approximately, given any fixed structure. It is argued that for certain model neighborhood structures, the ordinary reversible Metropolis-Hastings algorithm does not yield an appropriate solution to the estimation problem. Therefore, we develop an alternative, non-reversible algorithm which can avoid the scaling effect of the neighborhood. To efficiently explore a model space, a finite number of interacting parallel stochastic processes is utilized. Our interaction scheme enables exploration of several local neighborhoods of a model space simultaneously, while it prevents the absorption of any particular process to a relatively inferior state. We illustrate the advantages of our method by an application to a classification model. In particular, we use an extensive bacterial database and compare our results with results obtained by different methods for the same data.     

CLASSIFICATION, DISTRIBUTIONS AND ADMISSIBILITY IN AUTOREGRESSIVE PROCESS

The problem considered here is to classify a unit into one of two populations based on a vector of measurements on the unit. The observation vector is assumed to follow an auto-regressive process. Samples from the process are used to construct classification rules. The distributions of some classification statistics are obtained. The admissibility of some classification rules is established.     

Application of Quasi-Least Squares to Analyse Replicated Autoregressive Time Series Regression Models

Time series regression models have been widely studied in the literature by several authors. However, statistical analysis of replicated time series regression models has received little attention. In this paper, we study the application of the quasi-least squares method to estimate the parameters in a replicated time series model with errors that follow an autoregressive process of order p. We also discuss two other established methods for estimating the parameters: maximum likelihood assuming normality and the Yule-Walker method. When the number of repeated measurements is bounded and the number of replications n goes to infinity, the regression and the autocorrelation parameters are consistent and asymptotically normal for all three methods of estimation. Basically, the three methods estimate the regression parameter efficiently and differ in how they estimate the autocorrelation. When p=2, for normal data we use simulations to show that the quasi-least squares estimate of the autocorrelation is undoubtedly better than the Yule-Walker estimate. And the former estimate is as good as the maximum likelihood estimate almost over the entire parameter space.     

Max-stable processes for modeling extremes observed in space and time

Max-stable processes have proved to be useful for the statistical modeling of spatial extremes. For statistical inference it is often assumed that there is no temporal dependence; i.e., that the observations at spatial locations are independent in time. In a first approach we construct max-stable space–time processes as limits of rescaled pointwise maxima of independent Gaussian processes, where the space–time covariance functions satisfy weak regularity conditions. This leads to so-called Brown–Resnick processes. In a second approach, we extend Smith’s storm profile model to a space–time setting. We provide explicit expressions for the bivariate distribution functions, which are equal under appropriate choice of the parameters. We also show how the space–time covariance function of the underlying Gaussian process can be interpreted in terms of the tail dependence function in the limiting max-stable space–time process.     

On nonlinear models for time series

The paper is a review of nonlinear processes used in time series analysis and presents some new original results about stationary distribution of a nonlinear autoregres-sive process of the first order. The following models are considered: nonlinear autoregessive processes, threshold AR processes, threshold MA processes, bilinear models, auto-regressive models with random parameters including double stochastic models, exponential AR models, generalized threshold models and smooth transition autoregressive models, Some tests for linearity of processes are also presented.     

Space‐time cluster identification in point processes

The authors propose a new type of scan statistic to test for the presence of space‐time clusters in point processes data, when the goal is to identify and evaluate the statistical significance of localized clusters. Their method is based only on point patterns for cases; it does not require any specific knowledge of the underlying population. The authors propose to scan the three‐dimensional space with a score test statistic under the null hypothesis that the underlying point process is an inhomogeneous Poisson point process with space and time separable intensity. The alternative is that there are one or more localized space‐time clusters. Their method has been implemented in a computationally efficient way so that it can be applied routinely. They illustrate their method with space‐time crime data from Belo Horizonte, a Brazilian city, in addition to presenting a Monte Carlo study to analyze the power of their new test.     

Dynamic Asymmetries in U.S. Unemployment

We examine dynamic asymmetries in U.S. unemployment using nonlinear time series models and Bayesian methods. We find strong statistical evidence in favor of a two-regime threshold auto-regressive model. Empirical results indicate that, once we take into account both parameter and model uncertainty, there are economically interesting asymmetries in the unemployment rate. One finding of particular interest is that shocks that lower the unemployment rate tend to have a smaller effect than shocks that raise the unemployment rate. This finding is consistent with unemployment rises being sudden and falls gradual.     

A randomly reinforced urn

We study an urn containing balls of two or more colors. The urn is sequentially sampled. Each time a ball is extracted from the urn it is reintroduced in it together with a random number of balls of the same color: the distribution of the number of added balls may depend on the color extracted. We prove asymptotic results for the process of colors generated by the urn and for the process of its compositions. Applications to sequential clinical trials are considered as well as connections with response-adaptive design of experiments in a Bayesian framework.     

High-dimensional VAR with low-rank transition

Statistics and Computing - We propose a vector auto-regressive model with a low-rank constraint on the transition matrix. This model is well suited to predict high-dimensional series that are...     

Modelling spatio-temporal air pollution data from a mobile monitoring station

ABSTRACT

Environmental data is typically indexed in space and time. This work deals with modelling spatio-temporal air quality data, when multiple measurements are available for each space-time point. Typically this situation arises when different measurements referring to several response variables are observed in each space-time point, for example, different pollutants or size resolved data on particular matter. Nonetheless, such a kind of data also arises when using a mobile monitoring station moving along a path for a certain period of time. In this case, each spatio-temporal point has a number of measurements referring to the response variable observed several times over different locations in a close neighbourhood of the space-time point. We deal with this type of data within a hierarchical Bayesian framework, in which observed measurements are modelled in the first stage of the hierarchy, while the unobserved spatio-temporal process is considered in the following stages. The final model is very flexible and includes autoregressive terms in time, different structures for the variance-covariance matrix of the errors, and can manage covariates available at different space-time resolutions. This approach is motivated by the availability of data on urban pollution dynamics: fast measures of gases and size resolved particulate matter have been collected using an Optical Particle Counter located on a cabin of a public conveyance that moves on a monorail on a line transect of a town. Urban microclimate information is also available and included in the model. Simulation studies are conducted to evaluate the performance of the proposed model over existing alternatives that do not model data over the first stage of the hierarchy.     

EXPONENTIAL SMOOTHING AND NON‐NEGATIVE DATA

The most common forecasting methods in business are based on exponential smoothing, and the most common time series in business are inherently non‐negative. Therefore it is of interest to consider the properties of the potential stochastic models underlying exponential smoothing when applied to non‐negative data. We explore exponential smoothing state space models for non‐negative data under various assumptions about the innovations, or error, process. We first demonstrate that prediction distributions from some commonly used state space models may have an infinite variance beyond a certain forecasting horizon. For multiplicative error models that do not have this flaw, we show that sample paths will converge almost surely to zero even when the error distribution is non‐Gaussian. We propose a new model with similar properties to exponential smoothing, but which does not have these problems, and we develop some distributional properties for our new model. We then explore the implications of our results for inference, and compare the short‐term forecasting performance of the various models using data on the weekly sales of over 300 items of costume jewelry. The main findings of the research are that the Gaussian approximation is adequate for estimation and one‐step‐ahead forecasting. However, as the forecasting horizon increases, the approximate prediction intervals become increasingly problematic. When the model is to be used for simulation purposes, a suitably specified scheme must be employed.