学习网站资源:
黃冠華老師 video/notes:
所用教材:Introduction to Linear Regression Analysis, 5ed(2012) Montgomery, D.C., Peck, E.A., Vining, G.G.
Lab: build model using R
教学视频链接: http://ocw.nctu.edu.tw/course_detail-c.php?bgid=1&gid=4&nid=528&pid=831
The goals of this course are to introduce regression analysis for continuous and discrete data. Topics include simple and multiple linear regressions, inferences for regression coefficients, confounding and interaction, regression diagnostics, logistic regressions, Poisson regressions, and generalized linear models.(这个课程的目标是介绍连续和离散数据的回归分析。主题包括简单和多元线性回归、回归系数的推断、混杂和相互作用、回归诊断、逻辑回归、泊松回归和广义线性模型。)
最近正好学习线性回归这块知识,偶然间看到这个资源,所以想跟大家分享,并且将自己学习到的知识写下来记录一下,先回顾一下基本的统计学概念。
一、parameters、sample statistics and sampling distribution
参数、样本统计和样本分布
二、sample space,random variable and probability function
sample space (the set of all possible outcomes)ya'na'ben,举个列子就是掷骰子,有六种情况,因为一共有六个面,这六个面就是sample space;
random variable(numerical quantity that takes outcomes with specific values)随机变数,这个就是把sample space 的六种情况用值表示出来。{1,2,3,4,5,6}.
probability function(a mathematical fun. that assigns to random variable the prob.)几率函数,含义就是把random variable的概率表示出来,同样也是掷骰子,那么:
三、Probability distribution
Probability distribution:relationship between random variable and probability function.
四、Characteristics of sampling distributions
如果数据点服从常态分布normal distribution ,sample means from samples of sizes follow a normal distribution
五、评估Estimate
1、点估计(point estimate)和interval estimate
2、hypothesis testing