Home About us Contact
|
Home About us Contact | ||
|
|
||
Kernel Density Estimator (kernel + density_estimator)
Selected AbstractsThe Impact of Industrial Restructuring on Earnings Inequality: The Decline of Steel and Earnings in PittsburghGROWTH AND CHANGE, Issue 1 2004Patricia Beeson ABSTRACT Inter-industry employment shifts were largely responsible for changes in the income distribution in the Pittsburgh region during the 1980s. Kernel density estimators were used, together with decomposition techniques developed by DiNardo et al. (1996) to show that industry shifts were responsible for over 90 percent of the earnings reductions at some points on the earnings distribution. Most of the losses at the lower end of the distribution occurred in the early 1980s as the economy plunged into a deep recession. The recovery in the later part of the decade brought little improvement as earnings in the lower part of the distribution continued to fall with the increase in employment of part-time workers in the low-wage trade and service sectors. [source] Allowing for redundancy and environmental effects in estimates of home range utilization distributionsENVIRONMETRICS, Issue 1 2005W. G. S. Hines Abstract Real location data for radio tagged animals can be challenging to analyze. They can be somewhat redundant, since successive observations of an animal slowly wandering through its environment may well show very similar locations. The data set can possess trends over time or be irregularly timed, and they can report locations in environments with features that should be incorporated to some degree. Also, the periods of observation may be too short to provide reliable estimates of characteristics such as inter-observation correlation levels that can be used in conventional time-series analyses. Moreover, stationarity (in the sense of the data being generated by a source that provides observations of constant mean, variance and correlation structure) may not be present. This article considers an adaptation of the kernel density estimator for estimating home ranges, an adaptation which allows for these various complications and which works well in the absence of exact (or precise) information about correlation structure and parameters. Modifications to allow for irregularly timed observations, non-stationarity and heterogeneous environments are discussed and illustrated. Copyright © 2004 John Wiley & Sons, Ltd. [source] A Streamflow Forecasting Framework using Multiple Climate and Hydrological Models,JOURNAL OF THE AMERICAN WATER RESOURCES ASSOCIATION, Issue 4 2009Paul J. Block Abstract:, Water resources planning and management efficacy is subject to capturing inherent uncertainties stemming from climatic and hydrological inputs and models. Streamflow forecasts, critical in reservoir operation and water allocation decision making, fundamentally contain uncertainties arising from assumed initial conditions, model structure, and modeled processes. Accounting for these propagating uncertainties remains a formidable challenge. Recent enhancements in climate forecasting skill and hydrological modeling serve as an impetus for further pursuing models and model combinations capable of delivering improved streamflow forecasts. However, little consideration has been given to methodologies that include coupling both multiple climate and multiple hydrological models, increasing the pool of streamflow forecast ensemble members and accounting for cumulative sources of uncertainty. The framework presented here proposes integration and offline coupling of global climate models (GCMs), multiple regional climate models, and numerous water balance models to improve streamflow forecasting through generation of ensemble forecasts. For demonstration purposes, the framework is imposed on the Jaguaribe basin in northeastern Brazil for a hindcast of 1974-1996 monthly streamflow. The ECHAM 4.5 and the NCEP/MRF9 GCMs and regional models, including dynamical and statistical models, are integrated with the ABCD and Soil Moisture Accounting Procedure water balance models. Precipitation hindcasts from the GCMs are downscaled via the regional models and fed into the water balance models, producing streamflow hindcasts. Multi-model ensemble combination techniques include pooling, linear regression weighting, and a kernel density estimator to evaluate streamflow hindcasts; the latter technique exhibits superior skill compared with any single coupled model ensemble hindcast. [source] Minimum , -divergence estimation for arch modelsJOURNAL OF TIME SERIES ANALYSIS, Issue 1 2006S. Ajay Chandra Abstract., This paper considers a minimum , -divergence estimation for a class of ARCH(p) models. For these models with unknown volatility parameters, the exact form of the innovation density is supposed to be unknown in detail but is thought to be close to members of some parametric family. To approximate such a density, we first construct an estimator for the unknown volatility parameters using the conditional least squares estimator given by Tjřstheim [Stochastic processes and their applications (1986) Vol. 21, pp. 251,273]. Then, a nonparametric kernel density estimator is constructed for the innovation density based on the estimated residuals. Using techniques of the minimum Hellinger distance estimation for stochastic models and residual empirical process from an ARCH(p) model given by Beran [Annals of Statistics (1977) Vol. 5, pp. 445,463] and Lee and Taniguchi [Statistica Sinica (2005) Vol. 15, pp. 215,234] respectively, it is shown that the proposed estimator is consistent and asymptotically normal. Moreover, a robustness measure for the score of the estimator is introduced. The asymptotic efficiency and robustness of the estimator are illustrated by simulations. The proposed estimator is also applied to daily stock returns of Dell Corporation. [source] Home-range overlap and spatial organization as indicators for territoriality among male bushbuck (Tragelaphus scriptus)JOURNAL OF ZOOLOGY, Issue 3 2005Torsten Wronski Abstract Many studies have concluded that territoriality is absent in male bushbuck Tragelaphus scriptus but a minority has suggested that some exclusive mechanisms act between adult males. This study provides indirect evidence for the existence of territorial structures between adult male bushbuck by comparing home-range overlap between adult and sub-adult males. The spatial organization of individuals in relation to each other was established by using numerical classification. Location fixes of 52 males, each individual distinguished by a characteristic coat pattern, were taken over a period of 3 years. Home ranges were estimated using the fixed kernel density estimator. Two indices (coefficient of overlap, index of overlap) were applied to compare home-range overlap between the different male age classes. There was a strong home-range overlap up to the 30% home-range core between sub-adult as well as between adult and sub-adult males, while adult male home ranges overlapped up to the 50% home-range core only. It could be shown that home ranges of adult males overlapped significantly less than those of sub-adult males and those between sub-adult and adult males indicating an exclusive use of central core areas (home sites). Sub-adult males form bachelor pools without being permanently associated. With increasing age, sub-adult males challenge territory holders and replace them in order to take over their exclusive areas. These maturing sub-adult males (young adults), often focused on a particular territory holder denoting the young adults as prospects or candidates. [source] Multivariate Statistical Process Monitoring Using Kernel Density EstimationASIA-PACIFIC JOURNAL OF CHEMICAL ENGINEERING, Issue 1-2 2005J. Liang In this paper, a general kernel density estimator has been introduced and discussed for multivariate processes in order to provide enhanced real-time performance monitoring. The proposed approach is based upon the concept of kernel density function, which is more appropriate to the underlying probability distribution of industrial process data in the development of a real-time monitoring scheme, to overcome the limitations of the conventional approach of defining the normal operating region based upon the assumption of normality. An optimal bandwidth selection rule is given based on the so-called mean integrated squared error index, and that is the normal operating region of process calculated using the optimal kernel density estimator before new process data are projected onto the normal operating region. The results of a case study of an industrial reheating furnace clearly demonstrates the power and advantages (e.g. decreasing the number of false alarms, identifying abnormal behaviour earlier, and reducing data sparsity) of the kernel density estimator-based approach over the conventional approach under the assumption of normality, which is still widely used. [source] Impact of the timing of stocking on growth and allometric index in aquaculture-based fisheriesFISHERIES MANAGEMENT & ECOLOGY, Issue 2 2004A. L. Ibáńez Abstract The impact of tilapia stocking on fisheries production in Lake Metztitlán was determined through progression analysis of modes obtained from (Gaussian) kernel density estimators (KDEs) of size frequency distributions of juvenile tilapia stocked after a period of total desiccation. The relationship between the allometric index of four cohorts and water temperature and variation in the volume of the basin was analysed. The use of KDEs was found to be a useful technique for the recognition and progression analysis of modes. The reasons for the low yields from the tilapia fishery of Lake Metztitlán are poor growth rate, low water temperature, which is manifest in low allometric indices, and the use of small mesh size nets. Yields can be sustained by improving fishery management; otherwise it is necessary to continue stocking. [source] Variable kernel density estimationAUSTRALIAN & NEW ZEALAND JOURNAL OF STATISTICS, Issue 3 2003Martin L. Hazelton Summary This paper considers the problem of selecting optimal bandwidths for variable (sample-point adaptive) kernel density estimation. A data-driven variable bandwidth selector is proposed, based on the idea of approximating the log-bandwidth function by a cubic spline. This cubic spline is optimized with respect to a cross-validation criterion. The proposed method can be interpreted as a selector for either integrated squared error (ISE) or mean integrated squared error (MISE) optimal bandwidths. This leads to reflection upon some of the differences between ISE and MISE as error criteria for variable kernel estimation. Results from simulation studies indicate that the proposed method outperforms a fixed kernel estimator (in terms of ISE) when the target density has a combination of sharp modes and regions of smooth undulation. Moreover, some detailed data analyses suggest that the gains in ISE may understate the improvements in visual appeal obtained using the proposed variable kernel estimator. These numerical studies also show that the proposed estimator outperforms existing variable kernel density estimators implemented using piecewise constant bandwidth functions. [source] | ||||||||||