This paper consists of two parts : in the first part , we will discuss the prob - lem of the pth - mean , complete consistency for the estimators of a nonparamet - ric and linear model with l ~ p - mixingale errors ; in the second part , we will dis - cuss the problem of the rth - mean 、 complete consistency for the estimators of themodels above with weak stationary linear process errors and the uniformly mean consistency . to the nonparametric model y _ ni = g ( x _ ni ) + _ ni , 1 i n , let g _ n ( x ) = w _ ni ( x , w _ n1 , … ? xnn ) y _ ni estimate the unknown function g ( x ) . to the linear model y _ i - x _ i1 1 + … ? + x _ iq ? _ q , we use lse _ nj to estimate the unknown parametric _ j 本篇论文主要是由两大部分内容构成：一是关于误差是l ~ p ?混合序列的线性回归模型参数的最小二乘估计与非参数回归模型未知函数的权函数估计的p ~ -阶平均相合性和完全收敛性问题；另一部分是关于误差是弱平稳线性过程的线性模型参数的最小二乘估计与非参数回归模型未知函数的权函数估计的r ?阶平均相合性和完全收敛性以及权函数估计的一致平均相合性问题。
The error of the elongation is 2 . 3 % , by the multi - dimension linear regression model , the relative error are from ? 5 % to ? 15 % respectively . comparing the results , it can be found that the neural network overmatches the multi - dimension linear regression . so that , the model can be used in the production of the marine propeller aluminum bronze 计算结果表明，三项输出的预测值与实测数据接近，抗拉强度和屈服强度的相对误差在1的范围以内，延伸率的最大绝对误差为2 . 3 ，明显优于多元线性回归模型5 ? 15的误差，能较好地满足工程应用的要求，对高强度船用螺旋桨铝青铜的生产具有一定的指导意义。
It will analyze the following several respects especially : first , through setting up linear regression model , it reveals the linear relation between investment and increasing in gdp of real estate in chongqing , i . e . the real estate ’ s increasing of the investment of 100 million yuan each time , will pull gdp to increase by 504 million yuan ; the real estate ‘ s increasing by 1 % , will drive increasing in gdp by 0 . 39 % 重点从以下几个方面进行:第一,通过建立线性回归模型,揭示出重庆市房地产业投资与gdp增长之间的线性关系,即房地产业每增加1亿元的投资,将拉动gdp增加5 . 04亿元;房地产业增长1 % ,将带动gdp增长0 . 39 % 。
The paper makes use of linear regressive model , grey prediction model and combined forecasting methods to predict the quality cost of engineering project , analyses the superiority and inferiority of every method . due to the theoretical defect of grey prediction formula , the paper modifies the previous formula , proposes new formula , and improves the prediction accuracy at a certain degree . in addition , the paper introduces the other five steps in the quality cost management system and management scheme decision - making method that considers value deviation 本文运用线性回归模型、灰色系统模型及组合预测模型对工程项目质量成本进行预测，分析了各种方法的优劣，并就灰色gm ( 1 , 1 )预测模型存在的一些问题，对gm ( 1 , 1 )预测模型建模方法作了一定的改进，在一定程度上提高了预测精度。
The security market of china developed late in the 1990s , and the system was especial , so the capital structure of listed companies have different characters with foreign companies , the affecting factors are more complicated . the paper is based on the theories of capital structure which is learned and practiced from 1950 , s 本文以上世纪50年代以来被广为研究和运用的企业资本结构理论为基础进行资本结构影响因素分析,建立上市公司资本结构的线性回归模型,并在此基础上分析吉林省上市公司资本结构影响因素的相关关系。
The decrease in cultivated average farmland mainly and the farm capital substituting function on the workforce embody agricultural repel strength . the absorbing forces in rural and urban area use one liner regression model predicting the absorbing power of the secondary industry and the tertiary industry in rural region and the urban as a whole . the shifting frictional force shows as economic cost and psychological cost mainly 农业排斥力主要通过人均耕地面积的减少和农业资本对劳动力的替代作用来体现；城乡吸纳力主要运用一元线性回归模型分别预测了农村第二产业、第三产业和城镇总体对农业劳动力的吸纳能力；转移摩擦力主要表现为经济成本和心理成本。
( 5 ) at the last part , we use method of econometrics to conduct regression of various statistics of near years " consuming structure and build regression model to predict our provincial 2005 year to 2010 year ' s consuming structure changes . finally we analyze the result of prediction ( 5 )在本文的最后一部分，我们运用经济计量学的方法对我省近年来消费结构的各项数据进行回归，建立了线性回归模型，根据模型对2005 - 2010年我省消费结构的变化进行了预测，并对预测结果进行了分析。
Thirdly , i will analyse the chinese stock market . and all of these , i talk about the function of chinese stock market in detail . finally , i will empirically analyse the problem by using multiple regression analysis and draw a conclusion that the relation between the chinese stock market and the economic growth is positively correlated 在本文的最后一部分，借鉴国外先进的理论模型，采用逐步回归法，利用1998年? 2003年中国股票市场与宏观经济季度数据，对股票市场与经济增长的关系进行了回归分析，得出了多元线性回归模型，并对其结果进行了相关的分析，分析的结论是中国股票市场与经济增长具有显著的正相关性，也就是股票市场对经济增长确实有促进作用。
In chapter four , we investigate the complete convergence for weighted sums of - mixing sequences . we apply results to the least square estimations in linear regression models and weighted function estimates g in nonparametric regression . the results improve the results appeared in literature 第四章，讨论了-混合序列加权和的完全收敛性，并将此结果应用于线性回归模型参数的最小二乘估计及非参数回归模型g的权函数估计中，所得的结果改进了已有的相应的结果。
The main human driving forces are population growth , industrialization and urbanization , development of the tertiary industry , the mechanism of economic management , social behavior , etc . ( 3 ) quantitative analytical methods such as principal components " analysis , multi - linear regression model , and stepwise regression model etc can be used for analyzing the direction and speed of luc within certain period , and can connect luc with human driving forces very well 影响土地利用变化的主要人类驱动力因素主要有人口增长、工业化和城镇化、第三产业的发展、经济管理机制、社会行为等。 ( 3 )主成分分析法、多元线性回归模型、逐步回归法等定量分析方法可以较好地用来分析在一定时段内土地利用变化的方向和变化速度，能很好地将人类驱动力因素与土地利用变化有机地联系起重庆市不同经济区土地利用变化的人类驱动力研究来。
