In this paper , we give a kernel shape estimation of m ( x ) using variable bandwidth local linear refression approch , and discuss the asymptotic normality , the convergence rate of mean square and convergence rate with probability 本文对上述模型，利用变窗宽局部线性回归方法，给出了m ( x )的核形估计，并讨论了这一估计的渐近正态性、依概率收敛速度、和均方收敛速度。
Our research uses multifactor model combined with cross - section regression and econometrics and analyzes 157 listed companies in shanghai and shenzhen securities markets from june 1st , 2001 to may 31st , 2002 实证研究采用多因素模型的理论框架，结合横截面回归方法和计量经济学检验手段，对2001年6月1日- 2002年5月31日我国沪深两证券市场共计157家上市公司分行业进行了分析。
By means of the law of large number , repeated sampling method and nonlinear regression method , the direct component models are built up for bronze inscription system , seal script system , official script system and song dynasty regular script system 借助于大数定律、重复抽样方法和非线性回归方法，分别建立了金文、小篆、汉隶和宋楷几个具有代表性的、不同时代的汉字系统直接构件关系模型。
Partial least squares regression is a new high - dimension - project - based nonparametric analysis method , which is an extension of ordinal least squares ( ols ) to deal with some defects of ols much more efficiently . its basic ideals had been come forth in 1960s early 偏最小二乘( pls )回归是一种基于高维投影思想的新的非参数回归方法，是对一般最小二乘( ols )的改进，比较有效地克服了ols的部分缺点。
In this paper , we make use of method of data envelopment analysis ( dea ) to observe the capital market output efficiency in china , then estimate the production function using two stages dea - regression method , and this function responds to the definition of economics 摘要本文运用数据包络分析对我国资本市场的产出效率进行了考察，运用两阶段的dea -回归方法建立符合经济学定义的我国资本市场生产函数。
Firstly , the mathematical model of chemical tankers " primary dimension is established by statistical regression method . secondly , rbf neural network is introduced for mathematics modeling of ship and the difference of two methods is compared too 首先采用传统的统计回归方法建立了化学品船主尺度和主要要素的数学模型，然后进一步利用rbf神经网络建立船舶数学模型，且对两种方法的优劣进行了探讨。
On the other hand , the method of multivariate linear regression analysis is used to deduce the relevant matrix between element analysis and of industry analysis coal . then a new calculation model of boiler efficiency by use of industry analysis data is established 同时采用多元线性回归方法，建立了煤的元素分析成分与工业分析结果的关联矩阵方程，从而获得以工业分析为基础的锅炉效率计算的新模型。
Now , many machine learning methods , such as artificial neural network and multivariate regression analysis , are applied to quantitative structure - activity relationship . in this paper , support vector regression is applied to quantitative structure - activity relationship 本文在简介定量构效关系发展状况的基础上,介绍了几种定量构效关系的解决方法,其中重点介绍了多元线性回归方法和人工神经网络方法。
The author validate that precipitation is the source of juzhai valley by using of isotopic . changhai in the recharge area receives the precipitation and thawing water , which drains along the rupture towards rize valley and jiuzhai valley so changhai has the important effect on the whole area 运用回归方法得山位于补给区的长海之水来源于大气降水的冰雪融水，并沿断裂补给到日则沟和九寨沟，因此长海水量多寡来源直接到本区湖泊水体的稳定。
For the cloudy region , the pixel values were substituted by the image data of same period and close time after being calculated . the calculation was based on the correlation of clear sky image with cloudy . at last , clear - sky day - time - averaged lst image of guangxi were made 再对该原图进行云剔除，并选择与原图时相最接近的实况样本，用统计回归方法进行相幅间的数值补偿，由此剔除原图中的云区，最终制作生成广西全境白天千米空间尺度的lst平均图。
