半参数模型统计诊断与粗差检验(英文)

This paper systematically studies the statistical diagnosis and hypothesis testing for the semiparametric linear regression model according to the theories and methods of the statistical diagnosis and hypothesis testing for parametric regression model.Several diagnostic measures and the methods for gross error testing are derived.Especially,the global and local influence analysis of the gross error on the parameter X and the nonparameter s are discussed in detail;at the same time,the paper proves that the d...     

基于直线感知增强的边缘提取算法

根据视觉识别边缘的感知特性,提出了一种基于直线感知增强的弱边缘的边缘提取算法。借鉴视觉的直线感知方式,针对弱边缘整体上呈直线分布的特点将其筛选出来,进行编组、连接和扩展。与Edison边缘提取算子的比较实验证明,本算法在对弱边缘的提取和虚假边缘的抑制上有显著增强。     

Dissolved organic carbon in the southern Baltic Sea: Quantification of factors affecting its distribution

During a cruise of r/v ‘Oceania’ in May 2006, seven vertical dissolved organic carbon (DOC) concentration profiles were produced against a background of CTD, chlorophyll a (chl a) and phaeopigment concentration profiles. The results indicate distinct vertical and spatial DOC fluctuations, ranging from 248 ± 7 μmol C dm⁻³ at 70 m depth at the westernmost station G/06 to 398 ± 5 μmol C dm⁻³ at 5 m depth at station A/06 in the western Gulf of Gdańsk. DOC concentrations were the highest at 10 m depth, where phytoplankton activity was relatively intensive, as reflected by the active chl a concentration distribution. DOC concentrations decreased towards the sea bottom.     

Econometric analysis to differentiate effects of various ship safety inspections

This article provides a refined technique to measure and interpret variables associated with the quality of an inspection—be it port state control or vetting inspections towards the probability of a very serious, serious or less serious casualty. It concentrates on filtering out the effect of variables such as detention, the port state control regime that inspected the vessel, time in-between inspections, deficiencies found during an inspection and the effect of vetting inspections. The consensus amongst policy makers in the shipping industry is that data cannot be combined to target vessels. While this article does demonstrate that the decrease in the probability of casualty is stronger for the South American Region, the Indian Ocean Region and Australia versus North Europe, North America or the Caribbean, it also demonstrates that the data can be combined to target vessels for inspections. Since the time in-between inspections and detention is mostly not significant towards decreasing the probability of casualty, these results reflect the lack of coordination amongst port state control regimes and industry inspections. Due to this lack of coordination and trust, a ship might be inspected in several regimes during a relative short time period where the benefit of an inspection can be easily saturated. Our recommendation on direct policy implication is to promote the harmonization of inspection databases across port state control regimes, preferably with the coordination of the development of the Global Integrated Ship Information System (GISIS) of the International Maritime Organization (IMO), to review the policy of a release of a vessel from detention and to increase cooperation amongst regimes with respect to the follow up of the rectification of deficiencies.     

Econometric analysis of the ship demolition market

The topic of ship recycling has obtained considerable attention during the last two decades for a variety of reasons with the likelihood of the adoption of a new international convention under the auspices of the International Maritime Organization (IMO). This study applies econometric modeling to a unique data set to provide insight into the dynamics of the ship recycling market. The data set contains information on 51,112 ships over 100 gt and includes 748,621 events over a period of 29 years. The analysis confirms a negative relationship of earnings and a positive relationship of scrap prices for all locations while Bangladesh seems to be more sensitive to changes in earnings than the other locations and more likely demolishes larger and older vessels. The results for flag and ownership vary across scrapping locations with Malta and Cyprus indicating potential importance from a registry perspective. The overall safety profile of a vessel seems to be less important towards the probability of a ship being scrapped. Possible implementation of the convention at EU level will mostly likely affect Turkey while non-ratification of one of the major flags will most likely affect China or Bangladesh.     

Evaluation of Inference Adequacy in Cumulative Logistic Regression Models: An Empirical Validation of ISWRidge Relationships

Internal solitary wave propagation over a submarine ridge results in energy dissipation, in which the hydrodynamic interaction between a wave and ridge affects marine environment. This study analyzes the effects of ridge height and potential energy during wave-ridge interaction with a binary and cumulative logistic regression model. In testing the Global Null Hypothesis, all values are p 〈0.001, with three statistical methods, such as Likelihood Ratio, Score, and Wald. While comparing with two kinds of models, tests values obtained by cumulative logistic regression models are better than those by binary logistic regression models. Although this study employed cumulative logistic regression model, three probability functions p^1, p^2 and p^3, are utilized for investigating the weighted influence of factors on wave reflection. Deviance and Pearson tests are applied to cheek the goodness-of-fit of the proposed model. The analytical results demonstrated that both ridge height （X1 ） and potential energy （X2 ） significantly impact （p 〈 0. 0001 ） the amplitude-based refleeted rate; the P-values for the deviance and Pearson are all 〉 0.05 （0.2839, 0.3438, respectively）. That is, the goodness-of-fit between ridge height （ X1 ） and potential energy （X2） can further predict parameters under the scenario of the best parsimonious model. Investigation of 6 predictive powers （ R2, Max-rescaled R^2, Sorners＇ D, Gamma, Tau-a, and c, respectively） indicate that these predictive estimates of the proposed model have better predictive ability than ridge height alone, and are very similar to the interaction of ridge height and potential energy. It can be concluded that the goodness-of-fit and prediction ability of the cumulative logistic regression model are better than that of the binary logistic regression model.     

Evaluation of Inference Adequacy in Cumulative Logistic Regression Models： An Empirical Validation of ISW-Ridge Relationships

Internal solitary wave propagation over a submarine ridge results in energy dissipation, in which the hydrodynamic interaction between a wave and ridge affects marine environment. This study analyzes the effects of ridge height and potential energy during wave-ridge interaction with a binary and cumulative logistic regression model. In testing the Global Null Hypothesis, all values are p<0.001, with three statistical methods, such as Likelihood Ratio, Score, and Wald. While comparing with two kinds of models, tests values obtained by cumulative logistic regression models are better than those by binary logistic regression models. Although this study employed cumulative logistic regression model, three probability functions p^1, p^2 and p^3, are utilized for investigating the weighted influence of factors on wave reflection. Deviance and Pearson tests are applied to check the goodness-of-fit of the proposed model. The analytical results demonstrated that both ridge height (X1) and potential energy (X2) significantly impact (p<0.0001) the amplitude-based reflected rate; the P-values for the deviance and Pearson are all >0.05 (0.2839, 0.3438, respectively). That is, the goodness-of-fit between ridge height (X1) and potential energy (X2) can further predict parameters under the scenario of the best parsimonious model.Investigation of 6 predictive powers (R2, Max-rescaled R2, Somers'D, Gamma, Tau-a, and c, respectively) indicate that these predictive estimates of the proposed model have better predictive ability than ridge height alone, and are very similar to the interaction of ridge height and potential energy. It can be concluded that the goodness-of-fit and prediction ability of the cumulative logistic regression model are better than that of the binary logistic regression model.     

Skeletal linear extension rates of the foliose scleractinian coral Merulina ampliata (Ellis & Solander, 1786) in a turbid environment

Skeletal linear extension rates of a foliaceous, IndoPacific, skiophilous, heterotrophic, scleractinian Merulina ampliata (Ellis & Solander 1786) were obtained along a sediment/nutrient load gradient at the southern islands of Singapore. Measurements were made during November 1999– November 2000 using the alizarin red‐S staining technique. Suspended particulate matter concentration (r²_adj = 0.76), turbidity (r²_adj = 0.59), the organic content of suspended sediments (r² = 0.50), and nitrite‐nitrate concentration (r²_adj = 0.50) were significant predictors of the skeletal linear extension rate of M. ampliata. Maximum linear extension growth rates of M. ampliata (mean ± SD: 1.43 ± 0.67–3.26 ± 0.59 cm·year^?1) were comparable to 15‐year‐old accounts at the same research sites, indicating adaptation to low‐light, high‐sediment waters.     

台风对海洋叶绿素a浓度影响的定量遥感初探

研究台风对海洋水色环境的影响,是目前海洋遥感技术又一应用领域。由于台风期间天气恶劣,遥感资料较少,国际上主要针对个别典型台风,研究其对海表温度、海洋叶绿素a浓度及初级生产力的影响,很少通过遥感资料系统地对这一影响进行定量分析和建模。自2000到2007年,过境中国近海以及西北太平洋海域台风近百次,作者通过系统地分析这期间MODIS,SeaWiFS的3A级叶绿素a浓度数据,结果发现:(1)台风促进了相应海域叶绿素a浓度的大幅增长,总体上平均增长约1.426倍,个别区域在5倍以上,同时,该增长一般延后3~6d,在7~10d后恢复到原来的水平;(2)进一步对这些数据进行一元统计线性回归,发现叶绿素a浓度增长比(R_chl-a)与台风影响因子(Tsub>w)满足如下关系:R_chl-a=0.0012Tsub>w+1.017,其相关系数达0.8;(3)台风期间叶绿素a浓度与无台风时叶绿素a浓度之间有很强的线性关系,其关系满足:C_chl-a=1.2367C_0chl-a+0.0636,且相关系数高达0.98。这一初步研究结果对进一步通过遥感手段深入研究台风对海洋水色环境的影响有借鉴意义。     

青藏高原北缘公格尔山地区地形梯度的剖析

本文以青藏高原北缘西昆仑山脉的公格尔山地区为试验区域,基于SRTM-DEM数据,采用线状地形剖面和带状地形剖面的研究方法,对试验区从公格尔山顶到塔里木盆地的地形梯度进行了研究,并探讨了地形梯度与隆升过程之间的关系。研究结果表明:(1)线状地形剖面清晰直观,操作简单;带状剖面法能较好地反映区域的地形起伏状况。若将两种方法联合起来共同进行区域地形研究,则会获得更好效果。(2)从塔里木盆地到公格尔山顶,地形抬升共分3个梯度:分别是从海拔高度2 000m左右上升到约4 500m,从约4 500m上升到将近6 000m,从将近6000m上升到约7500m。地形抬升的不同梯度可能对应着公格尔山晚新生代地貌形成过程的不同隆升过程;而每个抬升梯度的拐点,则对应着不同隆升过程形成海拔高度的分界点。