Search

The focus of the paper is nonparametric detection of changes in the mean of $$m$$ -dependent stationary functional data via a cumulative sum (CUSUM) procedure. We consider a projection-based quasi-maximum likelihood CUSUM-procedure which relies on a Darling-Erdős-type limit theorem. Under mild moment assumptions we investigate the asymptotic properties under the null hypothesis and show consistency under the alternatives of either an abrupt or a gradual change in the mean. The finite sample behavior is illustrated in a small simulation study including an application to temperature data from Hohenpeißenberg (Bavaria, Germany). [ABSTRACT FROM AUTHOR]

Abstract: Hydrological time series increasingly exhibit non-stationarity, e.g., variables such as precipitation and streamflow values do not maintain a consistent mean over long periods, due to natural and anthropogenic changes. Detecting whether such shifts are gradual or abrupt is a growing concern for water resources planning and management. This paper shows that conventional trend and change-point tests do not adequately enable these two types of change to be distinguished. We propose a method for combining the rank correlations of the Mann–Kendall and Pettitt statistics to extract an indicator whose value determines whether a shift observed in a given time series is gradual or abrupt. This method allows the success rate to be independent of the length of record, and it is validated with Monte-Carlo experiments. The limitations caused by the short and noisy nature of hydroclimatic time series are discussed. As an application, the proposed method provides useful insights on changes in hydroclimatic variables in the United States during 1910–2009 using time series from 1217 stations in the United States Hydroclimatic Data Network (USHCN). [Copyright &y& Elsevier]

To increase efficiency in the search for resources, many animals rely on their spatial abilities. Specifically, primates have been reported to use mostly topological and rarely Euclidean maps when navigating in large-scale space. Here, we aimed to investigate if the navigation of wild common marmosets inhabiting a semiarid environment is consistent with a topological representation and how environmental factors affect navigation. We collected 497 h of direct behavioral and GPS information on a group of marmosets using a 2-min instantaneous focal animal sampling technique. We found that our study group reused not only long-route segments (mean of 1007 m) but entire daily routes, a pattern that is not commonly seen in primates. The most frequently reused route segments were the ones closer to feeding sites, distant to resting sites, and in areas sparse in tree vegetation. We also identified a total of 56 clustered direction change points indicating that the group modified their direction of travel. These changes in direction were influenced by their close proximity to resting and feeding sites. Despite our small sample size, the obtained results are important and consistent with the contention that common marmosets navigate using a topological map that seems to benefit these animals in response to the exploitation of clustered exudate trees. Based on our findings, we hypothesize that the Caatinga landscape imposes physical restrictions in our group's navigation such as gaps in vegetation, small trees and xerophytic plants. This study, based on preliminary evidence, raises the question of whether navigation patterns are an intrinsic characteristic of a species or are ecologically dependent and change according to the environment. [ABSTRACT FROM AUTHOR]

Many species orient towards specific locations to reach important resources using different cognitive mechanisms. Some of these, such as path integration, are now well understood, but the cognitive orientation mechanisms that underlie movements in non-human primates remain the subject of debate. To investigate whether movements of chacma baboons are more consistent with Euclidean or topological spatial awareness, we investigated whether baboons made repeated use of the same network of pathways and tested three predictions resulting from the hypothesized use of Euclidean and topological spatial awareness. We recorded ranging behaviour of a group of baboons during 234 full days and 137 partial days in the Soutpansberg Mountains, South Africa. Results show that our baboons travelled through a dense network of repeated routes. In navigating this route network, the baboons did not approach travel goals from all directions, but instead approached them from a small number of the same directions, supporting topological spatial awareness. When leaving travel goals, baboons' initial travel direction was significantly different from the direction to the next travel goal, again supporting topological spatial awareness. Although we found that our baboons travelled with similar linearity in the core area as in the periphery of their home range, this did not provide conclusive evidence for the existence of Euclidean spatial awareness, since the baboons could have accumulated a similar knowledge of the periphery as of the core area. Overall, our findings support the hypothesis that our baboons navigate using a topological map. [ABSTRACT FROM AUTHOR]

In the statistical inference for long range dependent time series the shape of the limit distribution typically depends on unknown parameters. Therefore, we propose to use subsampling. We show the validity of subsampling for general statistics and long range dependent subordinated Gaussian processes that satisfy mild regularity conditions. We apply our method to a self-normalized change-point test statistic so that we can test for structural breaks in long range dependent time series without having to estimate nuisance parameters. The finite sample properties are investigated in a simulation study. We analyze three data sets and compare our results to the conclusions of other authors. [ABSTRACT FROM AUTHOR]

We propose methods for detecting structural changes in time series with discrete-valued observations. The detector statistics come in familiar L2-type formulations incorporating the empirical probability generating function. Special emphasis is given to the popular models of integer autoregression and Poisson autoregression. For both models, we study mainly structural changes due to a change in distribution, but we also comment for the classical problem of parameter change. The asymptotic properties of the proposed test statistics are studied under the null hypothesis as well as under alternatives. A Monte Carlo power study on bootstrap versions of the new methods is also included along with a real data example. [ABSTRACT FROM AUTHOR]

We develop testing procedures which detect if the observed time series is a martingale difference sequence. Furthermore, tests are developed that detect change–points in the conditional expectation of the series given its past. The test statistics are formulated following the approach of Fourier–type conditional expectations first proposed by Bierens (1982) and have the advantage of computational simplicity. The limit behavior of the test statistics is investigated under the null hypothesis as well as under alternatives. Since the asymptotic null distribution contains unknown parameters, a bootstrap procedure is proposed in order to actually perform the test. The performance of the bootstrap version of the test is compared in finite samples with other methods for the same problem. A real–data application is also included. [ABSTRACT FROM AUTHOR]