检索结果-内蒙古大学图书馆

Nonparametric modeling of clustered customer survival data

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION 2017年第1期46卷 603-618页

作者： Gauran, Iris Ivy M. Barrios, Erniel B. Univ Philippines Diliman Sch Stat Stat BldgMagsaysay Ave Quezon City 1101 Philippines

We incorporate a random clustering effect into the nonparametric version of Cox Proportional Hazards model to characterize clustered survival data. The simulation studies provide evidence that clustered survival data can be better characterized through a nonparametric model. Predictive accuracy of the nonparametric model is affected by number of clusters and distribution of the random component accounting for clustering effect. As the functional form of the covariate departs from linearity, the nonparametric model is becoming more advantageous over the parametric counterpart. Finally, nonparametric is better than parametric model when data are highly heterogenous and/or there is misspecification error.

关键词： Backfitting algorithm Clustered data generalized additive models Nonparametric regression Random effects Survival analysis

来源：评论

学校读者我要写书评

暂无评论

Revealing topoclimatic heterogeneity using meteorological station data

引用

INTERNATIONAL JOURNAL OF CLIMATOLOGY 2017年第Sup1期37卷 544-556页

作者： Aalto, Juha Riihimaki, Henri Meineri, Eric Hylander, Kristoffer Luoto, Miska Univ Helsinki Dept Geosci & Geog POB 64Gustaf Hallstromin Katu 2a FIN-00014 Helsinki Finland Finnish Meteorol Inst Climate Serv Ctr Helsinki Finland Stockholm Univ Deparment Ecol Environm & Plant Sci Stockholm Sweden

Climate is a crucial driver of the distributions and activity of multiple biotic and abiotic processes, and thus high-quality and high-resolution climate data are often prerequisite in various environmental research. However, contemporary gridded climate products suffer critical problems mainly related to sub-optimal pixel size and lack of local topography-driven temperature heterogeneity. Here, by integrating meteorological station data, high-quality terrain information and multivariate modelling, we aim to explicitly demonstrate this deficiency. Monthly average temperatures (1981-2010) from Finland, Sweden and Norway were modelled using generalized additive modelling under (1) a conventional (i.e. considering geographical location, elevation and water cover) and (2) a topoclimatic framework (i.e. also accounting for solar radiation and cold-air pooling). The performance of the topoclimatic model was significantly higher than the conventional approach for most months, with bootstrapped mean R-2 for the topoclimatic model varying from 0.88 (January) to 0.95 (October). The estimated effect of solar radiation was evident during summer, while cold air pooling was identified to improve local temperature estimates in winter. The topoclimatic modelling exposed a substantial temperature heterogeneity within coarser landscape units (>5 degrees C/1 km(-2) in summer) thus unveiling a wide range of potential microclimatic conditions neglected by the conventional approach. Moreover, the topoclimatic model predictions revealed a pronounced asymmetry in average temperature conditions, causing isotherms during summer to differ several hundreds of metres in altitude between the equator and pole facing slopes. In contrast, cold-air pooling in sheltered landscapes lowered the winter temperatures ca. 1.1 degrees C/100m towards the local minimum altitude. Noteworthy, the analysis implies that conventional models produce biassed predictions of long-term average temperature conditions, w

关键词： topoclimate temperature heterogeneity asymmetry generalized additive models local climate

来源：评论

学校读者我要写书评

暂无评论

Analysis and out-year forecast of beetle, borer, and drought-induced tree mortality in California

引用

FOREST ECOLOGY AND MANAGEMENT 2017年 399卷 166-178页

作者： Preisler, Haiganoush K. Grulke, Nancy E. Heath, Zachary Smith, Sheri L. US Forest Serv USDA Pacific South West Res Stn 800 Buchanan St Albany CA 94710 USA US Forest Serv USDA Western Wildland Environm Threat Assessment Ctr 3160 NE 3rdSt Prineville OR 97754 USA US Forest Serv USDA State & Private Forestry 16400 Champ Way Sandy OR 97055 USA US Forest Serv USDA State & Private Forestry 2550 Riverside Dr Susanville CA 96130 USA

The level of tree mortality and drought observed over the past decade in North America has been described as 'unparalleled' in our modern history, in particular in the Sierra Nevada, California. Forest managers could use early warning of where and how much tree mortality to expect in the very near future to plan and prioritize hazard tree removal, pest suppression activities, infer location of funding needs and fuels reduction treatments as well as access for firefighting. To answer these needs, we developed an empirically-based forecast model for expected tree mortality for an upcoming year based on (1) previous years' tree mortality as observed in late summer;(2) previous years' hydrologic year precipitation levels;and (3) site characteristics including amount of available host. Using this approach, initial forecasts for the next growing season can be developed by late fall for the following late summer. We demonstrated the application of this model by developing a forecast for the state of California for 2017. The explanatory variables in the California model accounted for similar to 43% of the variability in tree mortality. Overall, the model missed forecasting high levels of mortality in approximately 5% of forested or woodland locations for the state of California. Locations with more mortality than expected in 2015 & 2016 were mostly associated with new outbreaks of insects;land use changes, and margins of prescribed- or wildfires not initially attributed. The forecasts may also be useful to natural resource and land managers in locating new outbreaks that may be attributed to novel behavior or exotic insects. Published by Elsevier B.V.

关键词： Bark beetle outbreak Drought Fuels reduction Forest planning generalized additive models Predictive tool

来源：评论

学校读者我要写书评

暂无评论

A Penalized Framework for Distributed Lag Non-Linear models

引用

BIOMETRICS 2017年第3期73卷 938-948页

作者： Gasparrini, Antonio Scheipl, Fabian Armstrong, Ben Kenward, Michael G. London Sch Hyg & Trop Med Dept Social & Environm Hlth Res 15-17 Tavistock Pl London WC1H 9SH England London Sch Hyg & Trop Med Dept Med Stat Keppel St London WC1E 7HT England Ludwig Maximilians Univ Munchen Dept Stat Munich Germany

Distributed lag non-linear models (DLNMs) are a modelling tool for describing potentially non-linear and delayed dependencies. Here, we illustrate an extension of the DLNM framework through the use of penalized splines within generalized additive models (GAM). This extension offers built-in model selection procedures and the possibility of accommodating assumptions on the shape of the lag structure through specific penalties. In addition, this framework includes, as special cases, simpler models previously proposed for linear relationships (DLMs). Alternative versions of penalized DLNMs are compared with each other and with the standard unpenalized version in a simulation study. Results show that this penalized extension to the DLNM class provides greater flexibility and improved inferential properties. The framework exploits recent theoretical developments of GAMs and is implemented using efficient routines within freely available software. Real-data applications are illustrated through two reproducible examples in time series and survival analysis.

关键词： Distributed lag Exposure-lag-response generalized additive models Latency Penalized splines

来源：评论

学校读者我要写书评

暂无评论

Assimilation of optical and radar remote sensing data in 3D mapping of soil properties over large areas

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2017年 579卷 1094-1110页

作者： Poggio, Laura Gimona, Alessandro James Hutton Inst Craigiebuckler Aberdeen AB15 8QH Scotland

Soil is very important for many land functions. To achieve sustainability it is important to understand how soils vary over space in the landscape. Remote sensing data can be instrumental in mapping and spatial modelling of soil properties, resources and their variability. The aims of this study were to compare satellite sensors (MODIS, Landsat, Sentinel-1 and Sentinel-2) with varying spatial, temporal and spectral resolutions for Digital Soil Mapping (DSM) of a set of soil properties in Scotland, evaluate the potential benefits of adding Sentinel-1 data to DSM models, select the most suited mix of sensors for DSM to map the considered set of soil properties and validate the results of topsoil (2D) and whole profile (3D) models. The results showed that the use of a mixture of sensors proved more effective to model and map soil properties than single sensors. The use of radar Sentinel-1 data proved useful for all soil properties, improving the prediction capability of models with only optical bands. The use of MODIS time series provided stronger relationships than the use of temporal snapshots. The results showed good validation statistics with a RMSE below 20% of the range for all considered soil properties. The RMSE improved from previous studies including only MODIS sensor and using a coarser prediction grid. The performance of the models was similar to previous studies at regional, national or continental scale. A mix of optical and radar data proved useful to map soil properties along the profile. The produced maps of soil properties describing both lateral and vertical variability, with associated uncertainty, are important for further modelling and management of soil resources and ecosystem services. Coupled with further data the soil properties maps could be used to assess soil functions and therefore conditions and suitability of soils for a range of purposes. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Sensors inter-comparison Probabilistic approach Uncertainty assessment generalized additive models GlobalSoilMap

来源：评论

学校读者我要写书评

暂无评论

Assessing and minimizing contamination in time of flight based validation data

引用

NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT 2017年 870卷 30-36页

作者： Lennox, Kristin P. Rosenfield, Paul Blair, Brenton Kaplan, Alan Ruz, Jaime Glenn, Andrew Wurtz, Ronald Lawrence Livermore Natl Lab Computat Engn Div Livermore CA 94550 USA Lawrence Livermore Natl Lab Phys Div Livermore CA USA

Time of flight experiments are the gold standard method for generating labeled training and testing data for the neutron/gamma pulse shape discrimination problem. As the popularity of supervised classification methods increases in this field, there will also be increasing reliance on time of flight data for algorithm development and evaluation. However, time of flight experiments are subject to various sources of contamination that lead to neutron and gamma pulses being mislabeled. Such labeling errors have a detrimental effect on classification algorithm training and testing, and should therefore be minimized. This paper presents a method for identifying minimally contaminated data sets from time of flight experiments and estimating the residual contamination rate. This method leverages statistical models describing neutron and gamma travel time distributions and is easily implemented using existing statistical software. The method produces a set of optimal intervals that balance the trade-off between interval size and nuisance particle contamination, and its use is demonstrated on a time of flight data set for Cf-252. The particular properties of the optimal intervals for the demonstration data are explored in detail. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Time of flight Pulse shape discrimination Poisson regression generalized additive models

来源：评论

学校读者我要写书评

暂无评论

Nonparametric hypothesis testing in clustered survival model

引用

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION 2017年第9期46卷 7485-7500页

作者： Eustaquio, John de Guzman Barrios, Erniel B. Univ Philippines Diliman Sch Stat Sch Stat BldgMagsaysay Ave Quezon City 1101 Philippines

A nonparametric test for the presence of clustering in survival data is proposed. Assuming a model that incorporates the clustering effect into the Cox Proportional Hazards model, simulation studies indicate that the procedure is correctly sized and powerful in a reasonably wide range of scenarios. The test for the presence of clustering over time is also robust to model misspecification. With large number of clusters, the test is powerful even if the data is highly heterogeneous.

关键词： Bootstrap confidence interval Backfitting algorithm Clustered data Survival analysis generalized additive models

来源：评论

学校读者我要写书评

暂无评论

Time Series Modeling of Pathogen-Specific Disease Probabilities with Subsampled Data

引用

BIOMETRICS 2017年第1期73卷 283-293页

作者： Fisher, Leigh Wakefield, Jon Bauer, Cici Self, Steve Univ Washington Dept Biostat Seattle WA 98195 USA Univ Washington Dept Stat Seattle WA 98195 USA Brown Univ Dept Biostat Providence RI 02912 USA Fred Hutchinson Canc Res Ctr Vaccine & Infect Dis Div 1124 Columbia St Seattle WA 98104 USA

Many diseases arise due to exposure to one of multiple possible pathogens. We consider the situation in which disease counts are available over time from a study region, along with a measure of clinical disease severity, for example, mild or severe. In addition, we suppose a subset of the cases are lab tested in order to determine the pathogen responsible for disease. In such a context, we focus interest on modeling the probabilities of disease incidence given pathogen type. The time course of these probabilities is of great interest as is the association with time-varying covariates such as meteorological variables. In this set up, a natural Bayesian approach would be based on imputation of the unsampled pathogen information using Markov Chain Monte Carlo but this is computationally challenging. We describe a practical approach to inference that is easy to implement. We use an empirical Bayes procedure in a first step to estimate summary statistics. We then treat these summary statistics as the observed data and develop a Bayesian generalized additive model. We analyze data on hand, foot, and mouth disease (HFMD) in China in which there are two pathogens of primary interest, enterovirus 71 (EV71) and Coxackie A16 (CA16). We find that both EV71 and CA16 are associated with temperature, relative humidity, and wind speed, with reasonably similar functional forms for both pathogens. The important issue of confounding by time is modeled using a penalized B-spline model with a random effects representation. The level of smoothing is addressed by a careful choice of the prior on the tuning variance.

关键词： Empirical Bayes generalized additive models Infectious disease modeling Subsampled data

来源：评论

学校读者我要写书评

暂无评论

Long-term changes in nutrients, chlorophyll a and their relationships in a semi-enclosed eutrophic ecosystem, Bohai Bay, China

引用

MARINE POLLUTION BULLETIN 2017年第1-2期117卷 222-228页

作者： Qiao, Yinhuan Feng, Jianfeng Cui, Shangfa Zhu, Lin Nankai Univ Coll Environm Sci & Engn Key Lab Pollut Proc & Environm Criteria Minist Educ Tianjin 300071 Peoples R China Nankai Univ Coll Environm Sci & Engn Tianjin Key Lab Environm Remediat & Pollut Contro Tianjin 300071 Peoples R China

As the representative semi-enclosed bay of China, Bohai Bay has experienced severe eutrophication in recent decades. Monitoring data from 1995 to 2013 were analysed by generalized additive models (GAMS) to explore the temporal variations in nutrients concentrations, nutrient ratios, chlorophyll a (Chl a) concentrations and the responses of Chl a to the changes in nutrients in the spring and summer. The results showed that dissolved inorganic nitrogen (DIN) decreased from 1995 to 2000 but increased after 2000 in both the spring and summer, and soluble reactive phosphorus (SRP) decreased while the molar nitrogen/phosphorus (N/P) ratios (DIN to SRP) increased over the last two decades. Generally, P-limited phytoplankton growth was observed in the spring and summer and DIN was identified as the main pollutant constituent in Bohai Bay. Furthermore, negative correlations were found between DIN and Chl a in summer in Bohai Bay. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Nitrogen Phosphorus Chlorophyll a Bohai Bay generalized additive models

来源：评论

学校读者我要写书评

暂无评论

Linking small pelagic fish and cetacean distribution to model suitable habitat for coastal dolphin species, Delphinus delphis and Tursiops truncatus, in the Greek Seas (Eastern Mediterranean)

引用

AQUATIC CONSERVATION-MARINE AND FRESHWATER ECOSYSTEMS 2017年第2期27卷 436-451页

作者： Giannoulaki, Marianna Markoglou, Evangelia Valavanis, Vasilis D. Alexiadou, Paraskevi Cucknell, Anna Frantzis, Alexandros Hellen Ctr Marine Res Inst Marine Biol Resources & Inland Waters Iraklion 71003 Crete Greece Mediterranean Agron Inst Chania Geoinformat Environm Management Hania Greece Pelagos Cetacean Res Inst Athens Greece Marine Conservat Res Int Kelvedon Essex England

1. A large- scale assessment of the summertime suitable habitat for Delphinus delphis ( short- beaked common dolphin) and Tursiops truncatus (common bottlenose dolphin) in Greek Seas (Eastern Mediterranean) was conducted using data from dedicated and opportunistic cetacean surveys and published data records. 2. Using a presence/absence approach, generalized additive models were applied to define a suite of environmental, bathymetric and biotic factors that best describe common and bottlenose dolphin spatial distribution, during early (May, June, July) and late (August, September) summer. 3. A geographic information system (GIS) was used to integrate sightings data with environmental characteristics, distance from the coast and sardine probability of presence. These variables were considered as good proxies for defining species-suitable habitat within the study area's coastal environment. 4. The final selected models were used to produce annual probability maps of the presence of the species in the entire Greek Seas, as a measure of habitat suitability. Based on the mean probability and standard deviation maps for the study period GIS techniques were subsequently used to determine the persistent (areas with high mean and low variation) and occasional (high mean and high variation) habitat of each species. 5. Results showed that there was a high probability of common dolphin presence in areas with a high probability of sardine presence. For bottlenose dolphin, higher probability of the presence of species occurred in areas closer to the shore, with a high probability of sardine presence and with high concentrations of chlorophyll-a. 6. In both seasons, the North Aegean Sea and the Inner Ionian Sea Archipelago were indicated as the most suitable areas for common dolphin distribution. Persistent habitat areas of the bottlenose dolphin included enclosed seas, continental shelf waters, and waters surrounding islands. The indicated suitable areas are discussed along with d

关键词： Habitat suitability modelling marine mammals small pelagics Delphinus delphis Tursiops truncatus generalized additive models Eastern Mediterranean

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：