A Note on Change Point Detection Using Weighted Least Square

This paper is concerned with the application of weighted least square method in change point analysis. Testing shift in the mean normal observations with time varying variances as well as of a GARCH time series are considered. For both cases, the weighted estimators are given and their asymptotic behaviors are studied. It is also described that how the resampling methods like Monte Carlo and bootstrap may be applied to compute the finite sample behavior of estimators.

Terrestrial flux in sediments from the Okinawa Trough estimated using geochemical compositional data and its response to climate changes over the past 35000 a

Terrestrial supply to marginal seas is a function of interaction between land and ocean in response to climate changes.Terrestrial flux in sediments,therefore,is potential not only to reflect the paleoceanographic evolution of sedimentary basin,but also to reveal the paleoclimatic changes in source regions.Sediments from the Okinawa Trough were quantitatively partitioned into terrestrial,volcanic and biogenitic end members using constrained least-squares technique for geochemical compositional data.Combined with the density of bulk sediments and sedimentation rate,the terrestrial flux in sediments from the Okinawa Trough since the last 35 000 a was estimated.Based on surface seawater temperature（SST） and sea level changes over the past 35 000 a,the response of terrestrial flux to the climate changes was discussed.It is demonstrated that the terrestrial supply to the Okinawa Trough mainly derived from Chinese landmass via the Changjiang（Yangtze） River and controlled by sea level changes.During the post-glaciation,the terrestrial flux was the lowest in response to the highest sea level stand.During the last glacial maximum（LGM）,the terrestrial flux was not so high as previously expected,indicating the arid climatic condition in source region was responsible for lowering the Changjiang River＇s runoff during that time.During the deglaciation,the terrestrial flux increased in response to a quick rising of the sea level,probably implicating occurrence of down-slope transport.The four events characterized by slight increase in terrestrial flux exactly correspond to the LGM,Heinrich events（H1,H2,H3）,respectively.

Monthly Changes in the Influence of the Arctic Oscillation on Surface Air Temperature over China

Partial Least Squares Regression （PLSR） is used to study monthly changes in the influence of the Arctic Oscillation （AO） on spring, summer and autumn air temperature over China with the January 500 hPa geopotential height data from 1951 to 2004 and monthly temperature data from January to November at 160 stations in China. Several AO indices have been defined with the 500-hPa geopotential data and the index defined as the first principal component of the normalized geopotential data is best to be used to study the influence of the AO on SAT （surface air temperature） in China. There are three modes through which the AO in winter influences SAT in China. The influence of the AO on SAT in China changes monthly and is stronger in spring and summer than in autumn. The main influenced regions are Northeast China and the Changjiang River drainage area.

Influence of climatic conditions,topography and soil attributes on the spatial distribution of site productivity index of the species rich forests of Jalisco,Mexico

This paper presents an approach based on field data to model the spatial distribution of the site productivity index （SPI） of the diverse forest types in Jalisco, Mexico and the response in SPI to site and cli-matic conditions. A linear regression model was constructed to test the hypothesis that site and climate variables can be used to predict the SPI of the major forest types in Jalisco. SPI varied significantly with topog-raphy （elevation, aspect and slope）, soil attributes （pH, sand and silt）, climate （temperature and precipitation zones） and forest type. The most important variable in the model was forest type, which accounted for 35% of the variability in SPI. Temperature and precipitation accounted for 8 to 9% of the variability in SPI while the soil attributes accounted for less than 4% of the variability observed in SPI. No significant differences were detected between the observed and predicted SPI for the individual forest types. The linear regression model was used to develop maps of the spatial variability in predicted SPI for the individual forest types in the state. The spatial site productivity models developed in this study provides a basis for understanding the complex relationship that exists between forest productivity and site and climatic conditions in the state. Findings of this study will assist resource managers in making cost-effective decisions about the management of individual forest types in the state of Jalisco, Mexico.

利用均方误差相对变化规律确定正则化参数及其在PolInSAR测量反演中的应用

正则化方法是大地测量解算病态问题的常用方法,而正则化参数是影响正则化方法解算结果的关键参数。以均方误差最小为准则选取正则化参数,具有较充分的理论依据,可有效实现模型参数估值精度的提升。但是,均方误差计算过程中需要未知参数的真值,在实际情形中只能通过参数估值替代真值估算均方误差,难以获得可靠准确的均方误差值,限制了正则化参数的有效性。鉴于此,本文分析了正则化参数变化引起的方差与偏差变化规律,提出了一种均方误差相对变化值确定方法。依据不同正则化参数下模型参数真值不变原则,计算不同正则化参数下的方差与偏差相对变化量,从而消除参数真值对均方误差估计的影响。本文首先利用不同正则化参数计算两相邻正则化参数间的方差与标准差相对变化量;然后计算两正则化参数间模型参数估值变化量,通过差分运算分析得到两相邻正则化参数下的偏差相对变化量;最后综合标准差变化与偏差变化关系,得到均方误差最大降幅的正则化参数。通过PolInSAR植被高测量试验对本文方法的可行性进行了验证。试验表明,本文方法可有效改善正则化法模型参数估计精度。两个PolInSAR测量试验模型参数反演精度均得到了提高,合理验证了本文方法的可行性与有效性。

Measuring Spatio-temporal Characteristics of City Expansion and Its Driving Forces in Shanghai from 1990 to 2015

Urbanization has both direct and indirect impacts on land use change, and analyzing spatio-temporal characteristics of land use change is essential for understanding these impacts. By comparing Landsat TM images, this paper examines the changes of land use structure and landscape patterns in Shanghai from 1990 to 2015. It finds that the city doubled in size, with the growth of isolated construction land being most significant among eight land use types. A land use change matrix was established and landscape indices were selected to evaluate the change of spatial structure in Shanghai. In order to identify the main driving forces of city expansion in Shanghai, this research ran partial least square regression models to assess the impact of 10 social-economic factors on land use change of Shanghai from 1990 to 2015. It then conducted bivariate correlation analysis to explore the drivers of change of various land use types: urban settlement, rural settlement and isolated construction land. Besides quantitative analysis, this paper analyzes the influence of policy-dimensional factors in land use change. It concludes with future potential research topics on land use change in a rapidly urbanizing context.

Climate change characteristics of Amur River

Unusually severe weather is occurring more frequently due to global climate change. Heat waves, rainstorms, snowstorms, and droughts are becoming increasingly common all over the world, threatening human lives and property. Both temperature and precipitation are representative variables usually used to directly reflect and forecast the influences of climate change. In this study, daily data （from 1953 to 1995） and monthly data （from 1950 to 2010） of temperature and precipitation in five regions of the Amur River were examined. The significance of changes in temperature and precipitation was tested using the Mann-Kendall test method. The amplitudes were computed using the linear least-squares regression model, and the extreme temperature and precipitation were analyzed using hydrological statistical methods. The results show the following： the mean annual temperature increased significantly from 1950 to 2010 in the five regions, mainly due to the warming in spring and winter; the annual precipitation changed significantly from 1950 to 2010 only in the lower mainstream of the Amur River; the frequency of extremely low temperature events decreased from 1953 to 1995 in the mainstream of the Amur River; the frequency of high temperature events increased from 1953 to 1995 in the mainstream of the Amur River; and the frequency of extreme precipitation events did not change significantly from 1953 to 1995 in the mainstream of the Amur River. This study provides a valuable theoretical basis for settling disputes between China and Russia on sustainable development and utilization of water resources of the Amur River.

Statistical Procedures for Estimating and Detecting Climate Changes

This paper provides a concise description of the philosophy, mathematics, and algorithms for estimating, detecting, and attributing climate changes. The estimation follows the spectral method by using empirical orthogonal functions, also called the method of reduced space optimal averaging. The detection follows the linear regression method, which can be found in most textbooks about multivariate statistical techniques. The detection algorithms are described by using the space-time approach to avoid the non-stationarity problem. The paper includes （1） the optimal averaging method for minimizing the uncertainties of the global change estimate, （2） the weighted least square detection of both single and multiple signals, （3） numerical examples, and （4） the limitations of the linear optimal averaging and detection methods.

Trends of Shoreline Position: An Approach to Future Prediction for Balasore Shoreline, Odisha, India

The present study aims to analyze the shift in shoreline due to coastal processes and formulate available for best estimate of future shoreline positions based on precedent shorelines. Information on rates and trends of shoreline change can be used to improve the understanding of the underlying causes and potential effects of coastal erosion which can support informed coastal management decisions. In this paper, researchers go over the changes in the recent positions of the shoreline of the Balasore coast for the 38 years from 1975 through 2013. The study area includes the Balasore coastal region from Rasalpur to Udaypur together with Chandipur, Choumukh, Chandrabali as well as Bichitrapur. Transects wise shoreline data base were developed for approximately 67 kilometers of shoreline and erosional/accretional scenario has also been analysed by delineating the shoreline from Landsat imageries of 1975, 1980, 1990, 1995, 2000, 2005, 2010 and 2013. A simple Linear Regression Model and End Point Rate (EPR) have been adopted to take out the rate of change of shoreline and its future positions, based on empirical observations at 67 transects along the Balasore coast. It is found that the north eastern part of Balasore coast in the vicinity of Subarnarekha estuary and Chandrabali beach undergo high rates of shore line shift. The shoreline data were integrated for long- (about 17 years) and short-term (about 7 years) shift rates analysis to comprehend the shoreline change and prediction. For the prediction of future shoreline, the model has been validated with the present shoreline position (2013). The rate of shoreline movement calculated from the fixed base line to shoreline position of 1975, 1980, 1990, 1995, 2000, 2005 and 2010 and based on this, the estimated shoreline of 2013 was calculated. The estimated shoreline was compared with the actual shoreline delineated from satellite imagery of 2013. The model error or positional shift at each sample point is observed. The positional error varies from??4.82 m to 212.41 m. It has been found that model prediction error is higher in the left hand side of river Subarnarekha. The overall error for the entire predicted shoreline was found to be 41.88 m by Root Mean Square Error (RMSE). In addition, it was tested by means difference between actual and predicted shoreline positions using “t” test and it has been found that predicted shore line is not significantly different from actual shoreline position at (t132 = 0.278) p < 0.01.

RATE OF CONVERGENCE FOR MULTIPLE CHANGEPOINTS ESTIMATION OF MOVING-AVERAGE PROCESSES

In this paper, the least square estimator in the problem of multiple change points estimation is studied. Here, the moving-average processes of ALNQD sequence in the mean shifts are discussed. When the number of change points is known, the rate of convergence of change-points estimation is derived. The result is also true for p-mixing, φ-mixing, a-mixing, associated and negatively associated sequences under suitable conditions.

Spatio-temporal variation of Fraction of Photosynthetically Active Radiation absorbed by vegetation in the Hengduan Mountains, China

The Fraction of Absorbed Photosynthetically Active Radiation(FPAR) is an important indicator of the primary productivity of vegetation. FPAR is often used to estimate the assimilation of carbon dioxide in vegetation. Based on MOD15 A2 H/FPAR data product, the temporal and spatial variation characteristics and variation trend of FPAR in different vegetation types in 2001 to 2018 were analyzed in the Hengduan Mountains. The response of FPAR to climate change was investigated by using Pearson correlation analytical method and partial least squares regression analysis. Results showed that the FPAR in Hengduan Mountains presented an increasing trend with time. Spatially, it was high in the south and low in the north, and it also showed obvious vertical zonality by elevation gradient.The vegetation FPAR was found to be positively correlated with air temperature and sunshine duration but negatively correlated with precipitation. Partial least squares regression analysis showed that the influence of sunshine duration on vegetation FPAR in Hengduan Mountains was stronger than that of air temperature and precipitation.

Change-Point Analysis of Survival Data with Application in Clinical Trials

Effects of many medical procedures appear after a time lag, when a significant change occurs in subjects’ failure rate. This paper focuses on the detection and estimation of such changes which is important for the evaluation and comparison of treatments and prediction of their effects. Unlike the classical change-point model, measurements may still be identically distributed, and the change point is a parameter of their common survival function. Some of the classical change-point detection techniques can still be used but the results are different. Contrary to the classical model, the maximum likelihood estimator of a change point appears consistent, even in presence of nuisance parameters. However, a more efficient procedure can be derived from Kaplan-Meier estimation of the survival function followed by the least-squares estimation of the change point. Strong consistency of these estimation schemes is proved. The finite-sample properties are examined by a Monte Carlo study. Proposed methods are applied to a recent clinical trial of the treatment program for strong drug dependence.

基于2DPCA的矩阵时间序列统计监控及推断

在多元统计过程控制的研究中,越来越多的学者开始关注到矩阵数据的在线监控问题。矩阵数据通常可被拉直为向量数据再进行监控,但拉直操作破坏了矩阵数据的原有结构信息。而2DPCA方法直接对矩阵数据进行特征提取,可保留矩阵的结构特征。因此,利用2DPCA方法研究矩阵值时间序列的统计监控及推断是有意义的。首先基于2DPCA方法对矩阵数据进行正交投影获取特征,通过融合这些特征构造监控统计量;其次证明了该监控统计量的极限分布为卡方分布,并利用该分布进行统计推断。模拟实验表明:该方法理论正确;当样本容量较大时,该方法相对于同类方法表现更优。

近50a浙江省气候变化特征分析

用 1 95 1～ 1 999年资料详细研究了浙江省 4个观测站的年、季、月降水与气温的气候变化特征。提出了用蒙特卡洛 ( Monte Carlo)模拟方法对气象要素的长期变化进行统计检验。指出 ,气候变化也可以出现在气象要素的变率上 。

不同延时条件下基于激光诱导击穿光谱的烧结混合料定量检测

烧结混合料是烧结工艺中极为重要的一环,其成分检测的准确性直接影响烧结过程,激光诱导击穿光谱技术通过激光光谱分析烧结混合料中的元素成分和含量,实时性好,但定量检测效果相比于其他实验室方法仍有差距。研发了一套遥测激光诱导击穿光谱装置,并应用于烧结混合料成分检测,采用PLSR与PCA相结合的方法对烧结混合料中TFe,CaO,SiO_(2),MgO进行定量检测。通过对1.28μs和5μs不同延时的光谱数据计算发现,不同物质在不同探测延时条件下R_(2)有着明显差异,对于SiO_(2)和MgO这两种浓度相对较低的物质,采用较小的1.28μs探测延时,R_(2)分别达到了0.937和0.985,而浓度相对较高的TFe,CaO则采用更大的5μs探测延时效果更好,较采用1.28μs延时,TFe定量结果的R^(2)从0.903提高到0.987,CaO的R^(2)也从0.816提高到0.980。针对不同物质采用不同探测延时的方法显著提高了检测准确性,简化了检测流程,对烧结工艺起到指导作用。

基于FSA-LSSVR模型的安徽省耕地变化预测

针对耕地变化内部规律及其外部驱动因子的特点,利用鱼群算法优化最小二乘支持向量机回归(FSA-LSSVR)模型,探讨耕地变化预测模型,为耕地保护政策制定提供参考依据。结果表明:鱼群算法的全局搜索能力能使支持向量机算法有效地收敛到参数γ和σ的全局最优解;FSA-LSSVR模型的预测精度指标远高于多元线性、GM(1,1)和BP神经网络模型,且优于FSA-SVM,求解速度明显优于SVM。FSA-LSSVR模型可以解决SVM内部参数难以确定的问题,适用于多因素参与的高维非线性的耕地变化预测,而且速度快、精度高,具有推广价值。

GRACE卫星重力场同震变化的经验正交函数分解：以日本MW9.0地震为例

2011年3月11日日本东海发生MW9.0地震,造成日本岛整体东移、下沉并伴随巨大的质量重新分布。对于海底地震的震中区域,空间观测的GRACE卫星重力数据很好地弥补了GPS、InSAR等形变资料的缺失。利用GRACE卫星月重力场数据计算了地面0.5°×0.5°网格点上的重力变化时间序列,采用最小二乘拟合、经验正交函数(EOF)2种方法,提取了同震重力变化,结果显示震中两侧区域的重力变化呈两极分布,其中弧后区域重力下降,最大降幅约6μgal,海沟区域重力增加,最大增幅约3μgal。EOF方法避免了最小二乘拟合方法所需的地震发生时刻等先验信息,但卫星重力信号是由多种地球物理过程引起的重力变化的叠加,EOF结果的可靠性及其反映的真实物理来源往往随着事件的规模、观测时间的长短等而改变。文中第2,3,4主成分主要反映了非构造因素的影响,通过第1主成分空间一致性提取的同震重力变化与位错理论模型计算结果较为接近,因此较真实地反映了地震引起的重力变化特征。

长记忆时间序列的均值单变点估计

文章采用拟极大似然法估计了一类长记忆时间序列模型的单均值变点,在变点大小固定和变点收缩两种情形下分析了估计量的渐近性质。研究发现,变点大小与长记忆性之间存在一种权衡关系。具体而言,当变点大小固定时,变点估计量是不相合的,而变分点估计量是T-相合的;当变点收缩时,变点估计量的收敛速度依赖于记忆参数d,估计量的极限分布得以推导。最后,蒙特卡洛实验和实证分析验证了所提理论结果的有限样本表现。

新阶段、新特点、新思路——加入WTO与我国对外开放的新发展

加入WTO ,我国的对外开放进入全新的发展阶段 ,新世纪的开放在开放的路径、开放的内容、开放的方略上都与传统的开放模式有质的不同。这一时期我国的对外开放呈现出自主性开放为主向非自主性开放为主 ,政策性开放为主向体制性开放为主 ,“引进来”开放为主向“走出去”开放为主转变等新特点。为使我国经济更快地融入世界经济中 ,国内各项体制的改革必须尽快到位 ,政府必须切实转变管理方式 。

具有变点的AR-ARCH模型的估计

文章提出了可以利用稀疏组Lasso方法对AR-ARCH模型中的变点进行估计。讨论了SGL方法的良好性质,并通过一个模拟分析,说明了在有变点的情况下,与前后向无窗估计方法相比得到更好结果的最小二乘方法对数据进行了更高阶的估计。有效的做法是先将数据的变点估计出来,通过一个Dirichlet过程对数据进行分类确定变点数,再利用SGL方法得到变点估计,这一做法是有效且精确的。