Home About us Contact
|
Home About us Contact | ||
|
|
||
Time-series Models (time-sery + models)
Selected AbstractsClimatic effects on the phenology of lake processesGLOBAL CHANGE BIOLOGY, Issue 11 2004Monika Winder Abstract Populations living in seasonal environments are exposed to systematic changes in physical conditions that restrict the growth and reproduction of many species to only a short time window of the annual cycle. Several studies have shown that climate changes over the latter part of the 20th century affected the phenology and population dynamics of single species. However, the key limitation to forecasting the effects of changing climate on ecosystems lies in understanding how it will affect interactions among species. We investigated the effects of climatic and biotic drivers on physical and biological lake processes, using a historical dataset of 40 years from Lake Washington, USA, and dynamic time-series models to explain changes in the phenological patterns among physical and biological components of pelagic ecosystems. Long-term climate warming and variability because of large-scale climatic patterns like Pacific decadal oscillation (PDO) and El Niño,southern oscillation (ENSO) extended the duration of the stratification period by 25 days over the last 40 years. This change was due mainly to earlier spring stratification (16 days) and less to later stratification termination in fall (9 days). The phytoplankton spring bloom advanced roughly in parallel to stratification onset and in 2002 it occurred about 19 days earlier than it did in 1962, indicating the tight connection of spring phytoplankton growth to turbulent conditions. In contrast, the timing of the clear-water phase showed high variability and was mainly driven by biotic factors. Among the zooplankton species, the timing of spring peaks in the rotifer Keratella advanced strongly, whereas Leptodiaptomus and Daphnia showed slight or no changes. These changes have generated a growing time lag between the spring phytoplankton peak and zooplankton peak, which can be especially critical for the cladoceran Daphnia. Water temperature, PDO, and food availability affected the timing of the spring peak in zooplankton. Overall, the impact of PDO on the phenological processes were stronger compared with ENSO. Our results highlight that climate affects physical and biological processes differently, which can interrupt energy flow among trophic levels, making ecosystem responses to climate change difficult to forecast. [source] Neural network volatility forecastsINTELLIGENT SYSTEMS IN ACCOUNTING, FINANCE & MANAGEMENT, Issue 3-4 2007José R. Aragonés We analyse whether the use of neural networks can improve ,traditional' volatility forecasts from time-series models, as well as implied volatilities obtained from options on futures on the Spanish stock market index, the IBEX-35. One of our main contributions is to explore the predictive ability of neural networks that incorporate both implied volatility information and historical time-series information. Our results show that the general regression neural network forecasts improve the information content of implied volatilities and enhance the predictive ability of the models. Our analysis is also consistent with the results from prior research studies showing that implied volatility is an unbiased forecast of future volatility and that time-series models have lower explanatory power than implied volatility. Copyright © 2008 John Wiley & Sons, Ltd. [source] Numerical fluctuations in the northern short-tailed shrew: evidence of non-linear feedback signatures on population dynamics and demographyJOURNAL OF ANIMAL ECOLOGY, Issue 2 2002Mauricio Lima Summary 1,We studied a fluctuating population of the northern short-tailed shrew (Blarina brevicauda) in the Appalachian Plateau Province of Pennsylvania, USA, spanning 21 years of monitoring. We analysed the pattern of annual temporal variation fitting both time-series models and capture,mark,recapture (CMR) statistical models for survival and recruitment rates. 2,We determined that non-linear first-order models explain almost 80% of the variation in annual per capita population growth rates. In particular, a non-linear self-excited threshold autoregressive (SETAR) model describes the time-series data well. Average snowfall showed positive and non-linear effects on population dynamics. 3,The CMR statistical models showed that a non-linear threshold model with strong effects of population density was the best one to describe temporal variation in survival rates. On the other hand, population density or climatic variables did not explain temporal variation in recruitment rates. Survival rates were high during the study period. Weekly changes in population size attributable to new recruits entering in the population fluctuate between 21% and 0%, while the changes in population size related to survival fluctuate between 79% and 100%. 4,Two important results arise from this study. First, non-linear models with first-order feedback appear to capture the essential features of northern short-tailed shrew dynamics and demography. Secondly, climate effects represented by snowfall appear to be small and non-linear on this insectivore. The population dynamics of this shrew in the Appalachian Plateau are determined apparently by a strong non-linear first-order feedback process, which is related to survival rates. 5,This study links population dynamics and demography by detecting the underlying demographic mechanisms driving population dynamics. The feedback structure of this shrew suggests the existence of population dynamics dominated by intraspecific competitive interactions, such as aggression, solitary nesting, non-overlapping home ranges and territoriality. [source] General-to-Specific Modelling Using PcGetsJOURNAL OF ECONOMIC SURVEYS, Issue 4 2003P. Dorian Owen Abstract., This review examines the facilities provided by PcGets version 1.0, an OxMetrics module designed to implement automated general-to-specific model selection in the context of cross-section or dynamic time-series models that are linear in the parameters. A cross-section empirical example is used to illustrate the steps involved, the output produced and the options available for modellers. [source] Factor forecasts for the UKJOURNAL OF FORECASTING, Issue 4 2005Michael J. Artis Abstract Data are now readily available for a very large number of macroeconomic variables that are potentially useful when forecasting. We argue that recent developments in the theory of dynamic factor models enable such large data sets to be summarized by relatively few estimated factors, which can then be used to improve forecast accuracy. In this paper we construct a large macroeconomic data set for the UK, with about 80 variables, model it using a dynamic factor model, and compare the resulting forecasts with those from a set of standard time-series models. We find that just six factors are sufficient to explain 50% of the variability of all the variables in the data set. These factors, which can be shown to be related to key variables in the economy, and their use leads to considerable improvements upon standard time-series benchmarks in terms of forecasting performance. Copyright © 2005 John Wiley & Sons, Ltd. [source] Evaluating Specification Tests for Markov-Switching Time-Series ModelsJOURNAL OF TIME SERIES ANALYSIS, Issue 4 2008Daniel R. Smith C12; C15; C22 Abstract., We evaluate the performance of several specification tests for Markov regime-switching time-series models. We consider the Lagrange multiplier (LM) and dynamic specification tests of Hamilton (1996) and Ljung,Box tests based on both the generalized residual and a standard-normal residual constructed using the Rosenblatt transformation. The size and power of the tests are studied using Monte Carlo experiments. We find that the LM tests have the best size and power properties. The Ljung,Box tests exhibit slight size distortions, though tests based on the Rosenblatt transformation perform better than the generalized residual-based tests. The tests exhibit impressive power to detect both autocorrelation and autoregressive conditional heteroscedasticity (ARCH). The tests are illustrated with a Markov-switching generalized ARCH (GARCH) model fitted to the US dollar,British pound exchange rate, with the finding that both autocorrelation and GARCH effects are needed to adequately fit the data. [source] Robust Estimation For Periodic Autoregressive Time SeriesJOURNAL OF TIME SERIES ANALYSIS, Issue 2 2008Q. Shao Abstract., A robust estimation procedure for periodic autoregressive (PAR) time series is introduced. The asymptotic properties and the asymptotic relative efficiency are discussed by the estimating equation approach. The performance of the robust estimators for PAR time-series models with order one is illustrated by a simulation study. The technique is applied to a real data analysis. [source] The effect of observations on Bayesian choice of an autoregressive modelJOURNAL OF TIME SERIES ANALYSIS, Issue 1 2006K. D. S. Young Abstract., We consider the effect, on a Bayes factor, of omitting observations in time-series models. In particular, we study a Bayes factor for deciding between autoregressive models of different orders. Throughout we use Gibbs sampling to estimate the parameters of the models and the marginal densities. We illustrate the methods using data generated from an autoregressive model and some data on bag snatching in the Hyde Park area of Chicago. [source] The Effect of the Estimation on Goodness-of-Fit Tests in Time Series ModelsJOURNAL OF TIME SERIES ANALYSIS, Issue 4 2005Yue Fang Abstract., We analyze, by simulation, the finite-sample properties of goodness-of-fit tests based on residual autocorrelation coefficients (simple and partial) obtained using different estimators frequently used in the analysis of autoregressive moving-average time-series models. The estimators considered are unconditional least squares, maximum likelihood and conditional least squares. The results suggest that although the tests based on these estimators are asymptotically equivalent for particular models and parameter values, their sampling properties for samples of the size commonly found in economic applications can differ substantially, because of differences in both finite-sample estimation efficiencies and residual regeneration methods. [source] FORECASTING QUARTERLY AGGREGATE CRIME SERIES,THE MANCHESTER SCHOOL, Issue 6 2005MICHAEL P. CLEMENTS In this paper we assess the forecasting performance of quarterly economic models of aggregate property and personal crime. We show that models that include long-run relationships between crime and its economic determinants tend to generate inaccurate forecasts, and attribute this to structural change. The forecast performance of the economic models is compared with that of time-series models, and forecast encompassing tests are reported. [source] Modelling financial time series with threshold nonlinearity in returns and trading volumeAPPLIED STOCHASTIC MODELS IN BUSINESS AND INDUSTRY, Issue 4 2007Mike K. P. So Abstract This paper investigates the effect of past returns and trading volumes on the temporal behaviour of international market returns. We propose a class of nonlinear threshold time-series models with generalized autoregressive conditional heteroscedastic disturbances. Using Bayesian approach, an implementation of Markov chain Monte Carlo procedure is used to obtain estimates of unknown parameters. The proposed family of models incorporates changes in log of volumes in the sense of regime changes and asymmetric effects on the volatility functions. The results show that when differences of log volumes are involved in the system of log return and volatility models, an optimum selection can be achieved. In all the five markets considered, both mean and variance equations involve volumes in the best models selected. Our best models produce higher posterior-odds ratios than that in Gerlach et al.'s (Phys. A Statist. Mech. Appl. 2006; 360:422,444) models, indicating that our return,volume partition of regimes can offer extra gain in explaining return-volatility term structure. Copyright © 2007 John Wiley & Sons, Ltd. [source] | ||||||||||||||||