A two-stage model for multiple time series data of counts

We propose a two-stage model for time series data of counts from multiple locations. This method fits first-stage model(s) using the technique of iteratively weighted filtered least squares (IWFLS) to obtain location-specific intercepts and slopes, with possible lagged effects via polynomial distributed lag modeling. These slopes and/or intercepts are then taken to a second-stage mixed-effects meta-regression model in order to stabilize results from various locations. The representation of the models from the stages into a combined mixed-effects model, issues of inference and choices of the parameters in modeling the lag structure are discussed. We illustrate this proposed model via detailed analysis on the effect of air pollution on school absenteeism based on data from the Southern California Children's Health Study.     

Development of a versatile computer integrated control system for bioprocess controls

A general approach is described for the implementation of a networked multi-unit computer integrated control system. The use of data acquisition hardware and graphical programming tools alleviates tedious programming and maintains potency and flexibility. One application of the control system, the control of a mammalian cell perfusion culture based on a key nutrient glucose concentration, was demonstrated. The control system offers customized user interface for all process control parameters and allows the flexibility for continued improvement and implementation of new tailored functions. The temperature, pH, dissolved oxygen and glucose level were accurately controlled. This revised version was published online in June 2006 with corrections to the Cover Date.     

Fingerprint analysis of Psoralea corylifolia L. by HPLC and LC-MS

High-performance liquid chromatography (HPLC) was developed for fingerprint analysis of Psoralea corylifolia. Liquid chromatography-electrospray ionization-tandem mass spectrometry (LC-ESI-MSn) technique was first employed to identify the components of the fingerprint. The samples were separated with an Alltima C18 column (250 mm x 4.6 mm, 5 microm) by linear gradient elution using water-acetic acid (A; 100:0.1, v/v) and acetonitrile (B; 0 min, 40%; 15 min, 50%; 35 min, 60%; 45 min, 70%; 55 min, 80%; and maintained for 5 min) as mobile phase at a flow rate of 1.0 ml/min and detector wavelength at 245 nm. A standard procedure was developed for HPLC fingerprint analysis. Average chromatogram of 10 batches of P. corylifolia L. from Sichuan and Henan Provinces, PR China, which has been considered as the original and genuine herbal medicine for a long time, was first established as the characteristic fingerprint. There are 12 common peaks in this fingerprint. Ten of these common peaks were identified by MS data. This profile was then used to identify and assess the differences among the herb grown in various areas of China. The HPLC fingerprint analysis is specific and may serve for quality identification and comprehensive evaluation of P. corylifolia.     

A simple local sensitivity analysis tool for nonignorable coarsening: application to dependent censoring

Right- and interval-censored data are common special cases of coarsened data (Heitjan and Rubin, 1991, Annals of Statistics19, 2244-2253). As with missing data, standard statistical methods that ignore the random nature of the coarsening mechanism may lead to incorrect inferences. We extend a simple sensitivity analysis tool, the index of local sensitivity to nonignorability (Troxel, Ma, and Heitjan, 2004, Statistica Sinica14, 1221-1237), to the evaluation of nonignorability of the coarsening process in the general coarse-data model. By converting this index into a simple graphical display one can easily assess the sensitivity of key inferences to nonignorable coarsening. We illustrate the validity of the method with a simulated example, and apply it to right-censored data from an observational study of cardiac transplantation and to interval-censored data on time to detectable viral load from a clinical trial in HIV disease.     

生态系统服务供给量的确定——最小数据法在黑河流域中游的应用

确定生态系统服务供给量与付费标准是进行生态系统服务付费研究的关键问题。最小数据方法是一个推导生态系统服务供给曲线的数学模型,该模型通过分析土地利用收益的空间分布,计算出生态系统服务机会成本的空间分布,从而推导出生态系统服务供给曲线。介绍了最小数据方法,然后以黑河流域张掖市甘州区为例,以植被蒸散发量的减少表征生态系统服务,通过调查获得机会成本的空间分布,利用最小数据方法推导了水资源服务供给曲线。结果表明:随着补偿价格的提高,农业部门提供的水资源服务逐渐增加。当补偿价格从0.067元m-3(农业用水价格)提高到3元m-3(建筑用水水价),农业部门提供的水资源服务由2.08×106m3a-1增加到2.7×108m3a-1。这表明,采用生态系统服务付费政策可以有效减少农业用水量,同时这也为补偿标准的制定提供一种新的思路。     

Testing for common structures in a panel of threshold models

We consider the problem of examining the extent of (partial) similarity in the dynamics of a panel of independent threshold autoregressive processes. We develop some tests for common structure via Wald's approach and by checking whether the parameter estimates of the unconstrained threshold models satisfy the constraints defining the common structure. One test concerns the equality of independent ratios of normal means, which is shown to have nonstandard asymptotic null distribution. These tests are illustrated with a modern panel of Canadian lynx data; our analysis suggests that the lynx data over Canada share similar dynamics in the decrease phase, but they appear to be different in the increase phase.     

神农架川金丝猴栖息地优势乔木树种遥感识别及其分布特征

针对神农架川金丝猴生境基础研究中乔木树种大范围分布数据难以获取问题,尝试利用多源多时相遥感数据结合专家知识分层次实现树种识别。首先采用冬季Landsat8/OLI数据根据物侯特性分层提取常绿、落叶林的地域范围;进而依据夏季Worldview-2高分遥感影像的实地乔木样本的光谱特征分层次完成常绿树种(巴山冷杉、华山松、青$、刺叶栎)和落叶树种(红桦、日本落叶松、米心水青冈、漆树、锐齿槲栎、椅杨)的识别;并通过实地植被样方及专家知识通过高程数据完成分类结果的修正;最后结合GIS对主要优势树种的地形及地域分布特征进行了空间分析。实验精度表明常绿林中巴山冷杉、华山松、刺叶栎、虫害华山松整体精度较高,落叶林中红桦、漆树等识别精度相对较高,部分树种如椅杨、锐齿槲栎识别精度较低;总体上常绿树种的精度要优于落叶树种。从植物地理学、遥感、GIS三者相结合的角度,将多源、多时相遥感数据与物种物候特性、专家知识进行有效整合,提出了一种乔木树种识别的方法(1)提供了复杂山地环境的主要乔木优势种识别途径,且具有通用性;(2)完成了物种物候特性与遥感数据特性的整合利用,有效降低数据成本费用;(3)配合地面样方及专家知识修正结果,避免了过分依赖光谱特征引起的误判。这将为神农架川金丝猴栖息地保护与恢复提供更精确的数据依据。