回归的

What is the sampling distribution of a regression coefficient?

分别回答什么是回归系数，什么是回归系数的样本分布？

This thesis is composed of two sections in which we discuss generalized spectral density test of conditional autoregressive heteroscedasticity for threshold autoregressive model.

本文分两节对门限自回归模型中自回归条件异方差的广义谱密度检验进行了讨论。

The declining of confidence limit is the reason that makes the multiple-regression model not to fit for better precision any more.

而多元线性回归分析方法，在更高分辨率的空间插值中，由于测站数目相对减少，可能导致回归可信度下降而使该方法不再适用。

The unitary linear regression analysis showed that the b value of regression coefficient and the a value of constant term were relatively small in Shajinhong, Shanhuang apricot, Chuanzhihong, Apple apricot, and Lanzhou apricot by comparing them with the degree of cold resistance.

结果表明：经一元线性回归，用回归系数b值和常数项a值来对比分析抗寒性大小发现：沙金红、山黄杏、串枝红、苹果杏和兰州杏等品种的这两个数值相对较小。

Based on AFCT, a new adaptive staring principle is established using floating threshold which is calculated by system reference model based on extrapolation method and linear regression algorithm. The principle of "forecasting model on line identifier"and"forecasting model parameters'selftuner"are put forward. In the module of"adjustment mechanism", the forecasting method of break points is introduced to fulfill control functions to "forecasting model parameters'self tuner".

本文详细讨论了针对输电线路主保护的自适应预测模型的建立方法，应用时间序列法和自回归模型或动平均自回归模型建立了精确反映保护对象状态量的系统预测模型，以自回归模型为例给出了"预测模型在线辨识"环节和"模型参数自适应校正"环节的算法，应用"适应机构"实现其对"模型参数自适应校正"环节的控制作用，应用并行计算算法实现了在继电保护中的"预测模型在线辨识"环节，使系统状态预测模型自适应于变化的电力系统。

The study methods: Based on digital printing and offset printing technology principle, the basic parameters having effect on the ink-jet printing output quality were analyzed. And the mathematics models between the ink quantity and the solid density, and the relation between the gamma and printing contrast were established. The relation among the output dot area coverage, the original dot area coverage and the dot-gain percent was analyzed. And the mathematics models of printing characteristics curves and dot-gain curves were established. The factors influencing the dot-gain were analyzed, and then the dot-gain compensation function was acquired. All the models were verified by the method of regression analysis. And the precisions of the models were obtained by the correlation coefficient and multiple correlation coefficients.

研究方法：根据数码印刷以及胶版印刷的工艺原理，分析了影响喷墨印刷输出质量的基本参数，建立墨量与样张实地密度、γ与相对反差的数学模型；分析输出网点面积率、标定网点面积率以及网点扩大率三者之间的关系，建立网点扩大曲线和印刷阶调复制曲线的数学模型，并对网点扩大的影响因素进行了分析，导出了网点扩大补偿函数；运用回归分析方法分析模型，并用相关系数和复相关系数检验回归模型的显著性；使用灰平衡方程，结合回归法得出灰平衡控制曲线。

The gray balance curves were obtained by the gray balance function and regression analysis. The main works: The parameters in the mathematic models were ascertained, as well as all the regression functions. The models included the relation between the ink quantity and the solid density, the relation between the gamma and printing contrast, the printing reproduction curves, the dot-gain curves and the dot-gain compensation curves. The fitting accuracies of the regression models were checked out by the correlation coefficient or multiple correlation coefficients. The effect that the ink had on the solid density and the gamma on the printing contrast were analyzed. And the methods of choosing the ink and gamma were gained.

主要工作：确定了墨量与样张实地密度、γ与相对反差、阶调复制曲线、网点扩大曲线以及网点扩大补偿曲线各自数学模型中的参数，得到了回归表达式；得到了各个回归表达式的相关系数或复相关系数，检验了回归模型的拟合程度；分析了墨量对实地密度的影响以及γ对相对反差的影响，并提出了墨量和γ的选取方法；得到了喷墨印刷质量控制的灰平衡控制、网点扩大以及扩大补偿规律。

objective to study the correlation among psychosomatic health factors,depression,anxiety and sleep status in college students,to analyze influence factors in sleep status.methods with questionnaire opened in-vestigation,200college students were evaluated using cornell medical index,self-rating depression,self-rating anxiety scaleand pittsburgh sleep quality index.stepwise regression analysis was used.re-sults total score of sds was35.55±7.8,and sas was0.48±0.9.each score of cmi was higher than normal range,the highest was digestion system,next was respiration system,then,fatigue,eyes and ears,anxiety,sensitivity,tension,maladjustment in turn.total average score of psqi was6.32±3.6,ordinary sleep were115cases（57.5%）,good and bad sleep were42（21%）and43（21.5%）cases respectively.influence factors in total score of psqi were sas,cmi,respiration system,anxiety,past healthy,digestion system,fatigue,sensitivity,sds and malad-justment in turn,using stepwise regression analysis,total score of psqi as dependent variable,each factor score of cmi,total score of sds and sas as independent variables.conclusion problems of psychosomatic health,anxiety and depression could both lead to sleep disorder.

目的 研究在校大学生心身健康因素及抑郁焦虑等与睡眠状况的相关性，并对影响睡眠状况的有关因素进行分析。方法采用问卷式的开放性研究，对在校的200名大学生进行康奈尔心身健康问卷、自评抑郁量表、焦虑自评量表和匹兹堡睡眠质量量表的测定，采用逐步回归分析方法。结果 sds总分为35.55±7.8、sas总分为0.48±0.9，cmi评分：消化系统最为严重评分为2.52，其次为呼吸系统、疲劳感、眼和耳、焦虑、敏感、紧张、不适应等，评分均高于正常常模。psqi总均分为6.32±3.6，一般睡眠有115例占57.5%，睡眠质量较好42例占21.0%，睡眠质量较差43例占21.5%。评估对睡眠状况的影响程度，以psqi总分为因变量，选择cmi各因子分和sds、sas总分作为自变量，进行多因素逐步回归分析，进入方程的因素依据标准化偏回归系数，影响psqi总分的因素依次为sas总分、cmi总分、呼吸系统、焦虑、既往健康、消化系统、疲劳感、敏感、sds总分、不适应（f=226.8；p.01；r=0.73）。结论心身健康问题和焦虑抑郁可导致睡眠障碍。

The results from statistic data analysis using the statistic software SPSS15.0 for descriptive statistics, chi-square evaluation, laddered logistic regression, factors analysis, credibility analysis, variables analysis, and multiple comparison are as follows: I. An analysis of the prominently related variables with whether or not to receive cervical smear screen of tendency factors, enabling factors and needs factors by using the logistic regression model was performed.: 6 variables of tendency factors with predictive value as to whether a woman receive cervical smear screen or not include age, marital status, educational level, family structure, religion, and the knowledge of free smear examination offered by mandatory citizen health insurance; 4 variables with enabling factors with predictive value include average monthly income, district, whether receiving telephone or letter notices in the past year, and the degree of convenience of the examination location. One variable of needs factors with predictive value: is the suitability of the examination time notified. The accuracy rate of laddered logistic regression model built by this research was 74.1%.

利用统计软体SPSS15.0进行描述性统计、卡方检定、阶层式逻辑斯回归、因素分析、信度分析、变异数分析、多重比较等统计方法分析，根据统计资料分析结果：经卡方检定后，将倾向、能用、需要因素中具有显著相关变项与是否接受抹片检查，放入逻辑斯回归预测模型中，本研究结果发现：倾向因素中的六个变项：年龄、婚姻状况、教育程度、家庭结构、宗教信仰、是否知道健保提供免费抹片检查对受检与否具有预测力；能用因素中的四个变项：平均月收入、地区别、过去一年内是否接到电话或信函通知、收到通知的受检地点是否方便对受检与否具有预测力；需要因素中的一个变项：收到通知的受检时间是否合适对受检与否具有预测力；本研究所建立的阶层逻辑斯回归模型的整体预测正确率为74.1﹪。

4Some job stressors can predict job burnout, stresses form ecomocial-socail treatment, workload and school management entered emotional exhaustion regression equation, stresses form student factors entered depersonalization regression equation, stresses from workload and examination entered reduced personal accomplishment regression equation. It is clearly that stresses from ecomocial-socail treatment and school management have positive influence to turnover intention; also emotional exhaustion and reduced personal accomplishment have positive influence to turnover intention.

部分压力源对职业倦怠的三个维度有预测作用，来自经济社会待遇、工作负荷、学校管理的压力进入情感衰竭的回归方程，学生因素进入去个性化的回归方程，学校管理的压力和考试压力进入个人成就感降低的回归方程；学校管理、经济社会待遇的压力对离职倾向有显著的预测作用；情感衰竭和成就感降低对离职倾向有显著的预测作用。

This one mode pays close attention to network credence foundation of the businessman very much.

这一模式非常关注商人的网络信用基础。

Cell morphology of bacterial ghost of Pasteurella multocida was observed by scanning electron microscopy and inactivation ratio was estimated by CFU analysi.

扫描电镜观察多杀性巴氏杆菌细菌幽灵和菌落形成单位评价遗传灭活率。