随笔分类 -  [13] 数学/数理统计

数学/高数/线性代数/概率论与数理统计/ Prob. Statistics 。离散数学 Discrete Mathematics 。
摘要:可决系数 可决系数(coefficient of determination) 如果样本回归线对样本观测值拟合程度越好,各样本观测点与回归线靠得越近,由样本回归做出解释的离差平方和与总离差平方和越相近;反之,拟合程度越差,相差越大。 可决系数的计算式: 可决系数可以作为综合度量回归模型对样本观测值拟合优度的度量指标。 可决系数是测定多个变量间相关关系密切程度的统计分析指标,它也是反映多个自变量对因... 阅读全文
posted @ 2011-06-20 23:07 emanlee 阅读(10224) 评论(0) 推荐(0) 编辑
摘要:《极大似然估计的 Bahadur 渐近有效性》,成平, 《数学学报》, 1980年06期 asymptotically efficient estimator 渐近有效估计量 asymptotically normal 渐近正态 asymptotic variance 渐近方差 -- 对数似然函数对估计量的二阶偏导,然后取负号,再对这个数(矩阵)求逆。 阅读全文
posted @ 2011-06-20 22:00 emanlee 阅读(5460) 评论(0) 推荐(0) 编辑
摘要:In probability theory, heavy-tailed distributions are probability distributions whose tails are not exponentially bounded: that is, they have heavier tails than the exponential distribution. In many applications it is the right tail of the distribution that is of interest, but a distribution may hav 阅读全文
posted @ 2011-06-19 20:07 emanlee 阅读(4347) 评论(0) 推荐(1) 编辑
摘要:The goodness of fit of a statistical model describes how well it fits a set of observations. Measures of goodness of fit typically summarize the discrepancy between observed values and the values expe... 阅读全文
posted @ 2011-06-19 15:16 emanlee 阅读(802) 评论(0) 推荐(0) 编辑
摘要:Multiple comparisons In statistics, the multiple comparisons or multiple testing problem occurs when one considers a set of statistical inferences simultaneously. Errors in inference, including confid... 阅读全文
posted @ 2011-06-19 09:31 emanlee 阅读(515) 评论(0) 推荐(0) 编辑
摘要:与Permutation Tests有关的英文书籍: Permutation Tests for Complex Data: Theory, Applications and Software (Wiley Series in Probability and Statistics) http://www.amazon.com/Permutation-Tests-Complex-Data-App... 阅读全文
posted @ 2011-06-18 22:31 emanlee 阅读(246) 评论(0) 推荐(0) 编辑
摘要:For most hypothesis tests, we start with the assumptions and work forward to derive the sampling distribution of the test statistic under the null hypothesis. For permutation tests we will reverse the procedure, since the sampling distribution involves the permutations which give the procedure its n 阅读全文
posted @ 2011-06-18 21:29 emanlee 阅读(792) 评论(0) 推荐(0) 编辑
摘要:Randomization Tests Constrained ordination methods such as CCA and RDA find the ' best possible' relationship (defined in a mathematical sense) between species composition and the environment. Therefo... 阅读全文
posted @ 2011-06-18 21:23 emanlee 阅读(563) 评论(0) 推荐(0) 编辑
摘要:Randomization Tests We will begin with randomization tests, because they are closer in intent to more traditional parametric tests than are bootstrapping procedures. Their primary goal is to test some... 阅读全文
posted @ 2011-06-18 21:03 emanlee 阅读(372) 评论(0) 推荐(0) 编辑
摘要:Randomization Tests (1 of 6) Most distribution-free tests are based on the principle of randomization. The best way to understand the principle of randomization is in terms of a specific example of a ... 阅读全文
posted @ 2011-06-18 20:48 emanlee 阅读(451) 评论(0) 推荐(0) 编辑
摘要:The Cauchy–Lorentz distribution, named after Augustin Cauchy and Hendrik Lorentz, is a continuous probability distribution. As a probability distribution, it is known as the Cauchy distribution, while... 阅读全文
posted @ 2011-06-17 11:31 emanlee 阅读(780) 评论(0) 推荐(0) 编辑
摘要:In probability theory, a log-normal distribution is a probability distribution of a random variable whose logarithm is normally distributed. If X is a 阅读全文
posted @ 2011-06-17 11:18 emanlee 阅读(5080) 评论(0) 推荐(0) 编辑
摘要:betarnd 贝塔分布的随机数生成器 binornd 二项分布的随机数生成器 chi2rnd 卡方分布的随机数生成器 exprnd 指数分布的随机数生成器 frnd F分布的随机数生成器 gamrnd 伽玛分布的随机数生成器 geornd 几何分布的随机数生成器 hygernd 超几何分布的随机数生成器 lognrnd 对数正态分布的随机数生成器 nbinrnd 负二项分布的随机数生成器 ncf... 阅读全文
posted @ 2011-06-16 21:19 emanlee 阅读(2726) 评论(0) 推荐(0) 编辑
摘要:Poisson分布 概率密度函数 poisspdf(x,lamda) 分布函数poisscdf(X,lamda) 逆概率分布函数poissinv(F,lamda) x=[0:15]'; y1=[]; y2=[]; lam1=[1,2,5,10]; for i=1:length(lam1) y1=[y1,poisspdf(x,lam1(i))]; y2=[y2,poisscdf(x,lam1(i... 阅读全文
posted @ 2011-06-16 20:20 emanlee 阅读(2116) 评论(0) 推荐(0) 编辑
摘要:假定a为某指标在10个样本中的值,5个一组,看以两组均值的差为例(统计量),随机置换检验程序 example: a: 230 -1350 -1580 -400 -760 970 110 -50 -190 -200 v1=sum(a(1:5))/5; v2=sum(a(6:10))/5; T=abs(v1-v2); x=perms(a); %矩阵a的全排列(随机全排列) v11=(x(:,1)+x(... 阅读全文
posted @ 2011-06-16 09:46 emanlee 阅读(5609) 评论(0) 推荐(0) 编辑
摘要:工欲善其事,必先利其器! 数据分析也好,统计分析也好,数据挖掘也好、商业智能也好都需要在学习的时候掌握各种分析手段和技能,特别是要掌握分析软件工具!在数据分析领域,都有哪些软件分析工具呢?如何选择呢?其实很多领域或者说分析方法都有相应的软件工具,只要你想找就应该能够找到! 这里把软件分成纵横四个层次的的象限图来表达! 第一维度:数据存储层——>数据报表层——>数据分析层——>数据展现层 第二维度:... 阅读全文
posted @ 2011-06-16 09:24 emanlee 阅读(769) 评论(0) 推荐(1) 编辑
摘要:Probability density function (PDF) 概率密度函数 In probability theory, a probability density function (pdf), or density of a continuous random variable is a function that describes the relative likelihood f... 阅读全文
posted @ 2011-06-15 11:05 emanlee 阅读(2561) 评论(0) 推荐(0) 编辑
摘要:广义帕雷托分布 广义Pareto分布 MATLAB中如何产生pareto分布 函数 X = gprnd(X,K,sigma,theta,[M,N,...]) 。当 sigma=theta 时,就可以生成通常的pareto分布。 X = gprnd(1/2,15,15,1,10^6),即尾部参数为 alpha=2, 位置参数为 k = 15。 function r = gprnd(k,sigma,... 阅读全文
posted @ 2011-06-15 11:04 emanlee 阅读(2291) 评论(0) 推荐(0) 编辑
摘要:注:下载需要注册并且支付Money。 Statistical Analysis of Extreme Values: with Applications to Insurance, Finance, http://bbs.jjxj.org/thread-55441-1-1.html Statistical Analysis of Network Data: Methods and Models (... 阅读全文
posted @ 2011-06-15 08:07 emanlee 阅读(2479) 评论(0) 推荐(0) 编辑
摘要:中文: 1.《序列极值理论导引》 谢盛荣1993 2.《实用极值统计方法》史道济 2006 外文: 1.《Extreme value theory : an introduction》Haan, Laurens De/ Ferreira, Ana 2006 2.《Extreme value distributions: theory and applications》Samuel Kotz,Sar... 阅读全文
posted @ 2011-06-15 07:35 emanlee 阅读(2956) 评论(0) 推荐(0) 编辑