Ordinary Least Squares and Quantile Regression: An Inquiry-Based Learning Approach to a Comparison of Regression Methods

We present a short, inquiry-based learning course on concepts and methods underlying ordinary least squares (OLS), least absolute deviation (LAD), and quantile regression (QR). Students investigate squared, absolute, and weighted absolute distance functions (metrics) as location measures. Using differential calculus and properties of convex functions, students discover the sample mean, median, and pth quantile by minimizing sums of distances. Students use these metrics to define loss functions for OLS, LAD, and QR, and explore methods to minimize them. We discuss classroom experiences over two semesters. Classroom activities, Maple worksheets, and R demonstration code are available at a companion website.     

Student Hits in an Internet‐Supported Course: How Can Instructors Use Them and What Do They Mean?

The world of education is changing as Web‐based technology and courseware are increasingly used for delivery of course material. In this environment, instructors may need new measures for determining student involvement, and ultimately student performance. This study examines whether hits to a Web site have any value for predicting student performance in a traditional course supported by Web activities. Total Hits at the end of the semester was used as one measure. Hit Consistency, determined by assigning a 0 when no hits occurred between class meetings and by assigning a 1 when one or more hits occurred between class meetings, was another. Hit Consistency was significantly correlated with course average (r= .37, p < .001) for 108 students in two course sections. Hit Consistency started to show a significant relationship with course average by the third week (or class). Total Hits was not found to significantly correlate with course average (r= .08, p > .05) at the end of the semester or during any week. These results suggest that students who consistently access a Web site will perform better than those who do not. When Hit Consistency and Total Hits were entered as independent variables into a stepwise regression with course average as the dependent variable, the model was enhanced by the addition of Total Hits after Hit Consistency was entered (R= .43, p < .001) . Hierarchical regression analysis in which cumulative grade point average was entered as the first controlling variable suggested that online access may go beyond the predictive value of achievement alone for predicting course performance with Hit Consistency appearing to be the dominant causal variable.     

支持向量机在图像去噪处理中的初步研究

图像去噪是图像分割等操作的关键预处理环节,是从图像处理过度到图像分析和理解的重要手段之一,是图像处理中研究的重点内容.现有典型的一些图像去噪方法大多采用平滑滤波机理,在保护图像边缘信息等方面存在一定的局限性. 本文在对现有典型的图像去噪方法总结的基础上,提出了一种图像去噪的新方法--利用支持向量机(SVM)技术构建图像去噪滤波器,并在实现算法和实验仿真方面做了初步探讨.     

我国区域高等教育发展水平的统计分析

文章利用数理统计的方法，对我国31个省、市、自治区的高等教育发展水平进行排序和分类，并对影响高等教育发展的因素进行了相关分析与回归分析，以便从宏观上把握我国各地区高教发展的现状，为更好地指导和规划高等教育事业的健康发展提供一定的科学依据。     

研发操纵行为、融资约束与上市公司创新效率研究

文章研究了2008-2016年间上市公司的研发操纵行为和动机,及其对上市公司创新效率的影响。首先通过断点回归方法实证了上市公司研发操纵行为的存在性；其次文章分析了研发操纵行为及其融资约束动机之间的关系；最后检验了上市公司研发操纵行为以及融资约束对公司创新效率的影响。研究得出主要结论包括三点：第一,在3%的研发门槛附近存在显著的上市公司研发操纵现象；第二,研发操纵显著的帮助公司缓解融资约束；第三,在研发门槛之上的非研发操纵公司创新效率显著降低,研发操纵公司创新效率没有显著提高,这说明存在创新资源冗余现象。研究表明融资约束是研发操纵主要动机之一,此外政府对高新技术企业投入了过多的创新资源,研究发现有助于提升上市公司创新监管效率和促进创新资源配置优化。     

农田生态系统田间结构的优化配置——以辽河平原中部地区米麦间套作为例

连续2a采用4因子二次通用旋转组合设计，研究了辽河平原中部地区米麦间套作产量与田间结构因子中的玉米播期X1、玉米株距X2、玉米幅宽X3、和小麦幅宽X4关系。结果表明：作物产量Y与试验所设田间结构因子符合二次多项式回归方程；田间结构单因子，对产量作用大小依玉米幅宽、玉米播期、小麦幅宽对产量则呈极显著的正交互效应。玉米株距和幅宽〉玉米播期和小麦幅宽〉玉米播期和株距；利用频数分析法可分别确定米麦间套作不同产量水平田间结构的优化配置。指出了研究区域目前米麦间套作普遍存在的主要问题，根据该研究提出了解决问题的途径。     

岩体边坡中流体包裹体参数的逐步回归分析

以白鹤岭铁路隧道岩体边坡为例，在垂直边坡面的4条剖面上采集了不同变形和破坏状态岩石中的16个定向样品，测定了流体包裹体迹面（FluidInclusionPlane简称为FIP）特征参数（包括FIP的长度、形态、连通性、闭合性、粗糙度、交叉性质等参数）与包裹体热动力学参数（包括FIP中包裹体的均一温度、均一压力、包裹体流体密度、流体包裹体成分和氧逸度等参数）。同时，将样品中裂隙分布的分形维数作为描述岩石变形破坏状态的定量指标，采用反馈式逐步回归方法分析这些分形维数与所选7个FIP参数的定量关系。分析表明，影响岩体变形和破裂的主要微观参数包括两个FIP特征参数（即粗糙度系数和分布密度）和两个包裹体热力学参数（即水溶液包裹体均一温度和CO2-H2O包裹体均一温度）。由于岩体的变形和（或）破坏不仅可使FIP中包裹体成分泄漏、也会使FIP迹面特征参数和包裹体热动力学参数发生改变，因此，岩体边坡中流体包裹体参数的逐步回归分析结果对进一步研究岩体变形破坏过程与边坡稳定性将具有重要的参考价值。     

天然次生林多维空间格局的数量排序

本文通过对豫西和豫南天然次生的大量群落样地调查，以主分量分析（PCA)与回归分析（RA)相结合，定量地揭示了河南天然次生林群落的组成和分布在多维生态空间上梯度变化的宏观格局，建立了包括27个乔木建群种和6个主要环境因子在内的主分量模型和回归模型，为河南林业生产、林4天然次生林、数量排序、     

拒斥还是继续比较对话

面对"语境回归"对"比较对话"批评,指出拒斥"比较对话"的合法性是不现实的,分析了"比较对话"的必要性和可能性,并重申了"比较对话"的合法性。