• ## Copula in tedat | Python: estimation and visualization of frank, Clayton and Gumbel copula models

Time：2022-7-18

Original link:http://tecdat.cn/?p=23646  You may ask, why copulas? We are referring to mathematical concepts. Simply put, copulas is a joint distribution function with uniform margin. Most importantly, they allow you to study dependencies and margins separately. Sometimes you have more information about the margin than about the joint function of the dataset, and copulas allows you […]

• ## Summary! 14 commonly used statistical hypothesis testing methods

Time：2022-6-22

This paper shares 14 commonly used statistical hypothesis testing methods using spssau, which are divided into the following five parts: 1、 Normality test Normality is the basic premise of many analysis methods. If normality is not satisfied, other analysis methods should be selected. Therefore, normality test should be carried out before some analysis. If the […]

• ## Visual asymptotic normality and convergence of extended tecdat|r language: Law of large numbers, central limit theorem, empirical cumulative distribution function

Time：2022-6-18

Original link: http://tecdat.cn/?p=23777 In our mathematical statistics course, we have seen the law of large numbers (which has been proved in the probability course), proving that  Give a set of i.i.d. random variables, of which To visually see this convergence, we can use > for(i in 1:20)B\[,i\]=mean_samples(i*10) > boxplot(B) You can also visually see the boundary(used in the central […]

• ## R language – Analysis of variance and regression analysis

Time：2022-4-5

this article isLiu Qiang, Pei Yanbo, Zhang Beibei R language and modern statistical methodsThe reading record of a book has only rough operation steps. People without basic mathematical statistics and relevant mathematical knowledge should use this book and this article with caution. 1、 Return fit <- lm(formula, data=data) The formula part can be y […]

• ## Time series analysis from ARMA to Arima to SARIMA

Time：2022-1-21

[TOC] ARMA The combination of AR (P) and MA (q) is ARMA (P, q), autoregressive moving average. The formula is as follows: The formula represents: The value of the current time step is a constant plus the sum of autoregressive lag and its multiplier, plus the sum of moving average lag and its multiplier, plus […]

• ## Skills of making HTML mail that can be displayed normally in mainstream mailbox

Time：2022-1-16

Suggestions for sending HTML mail: write inline CSS in style; Use less pictures; Use table to realize left-right layout or more complex layout; Use the background element to set the background picture, etc.Almost every membership website needs to send e-mail to communicate with members through the background, such as registration confirmation and marketing promotion. These […]

• ## R language bootstrap based confidence interval estimation method for linear regression prediction

Time：2022-1-12

Original link:http://tecdat.cn/?p=21625  We know the calculation of the confidence interval of the parameters, which obey a certain distribution (t distribution, normal distribution), so multiply the corresponding T score or Z score before the standard error. But if we can’t find a suitable distribution, can’t we calculate the confidence interval? Fortunately, there is a method that […]

• ## Matlab uses copula model for Monte Carlo simulation and fitting stock return data analysis

Time：2021-12-15

Original link: http://tecdat.cn/?p=24535 Recently, Copula has become popular in simulation models. Copulas is a function that describes the dependencies between variables and provides a method to create distributions to model related multivariate data. Using copula, data analysts can construct multivariable distribution by specifying the marginal univariate distribution and selecting a specific copula to provide the […]

• ## Realization of Volatility Prediction in R language: arch model and har-rv model

Time：2021-10-30

Original text:http://tecdat.cn/?p=3832 Volatility is a key parameter in many pricing and risk models, such as BS pricing method or the calculation of value at risk. In this model, or in textbooks, the volatility in these models is usually regarded as a constant. However, this is not the case. According to academic research, volatility is a […]

• ## R language extreme value inference: generalized Pareto distribution GPD uses maximum likelihood estimation, contour likelihood estimation and delta method

Time：2021-9-29

Original link:http://tecdat.cn/?p=22566  This paper is the content of extreme value inference. We use the maximum likelihood method on the generalized Pareto distribution. maximum likelihood estimation In the context of parametric models, the standard technique is to consider the maximum likelihood (or log likelihood). Consider some technical assumptions, such as ，A neighborhood of, then amongRepresents Fisher […]

• ## Analysis of geyser eruption time data by R language finite mixture model (FMM)

Time：2021-9-16

Original link:http://tecdat.cn/?p=22609  abstract This paper provides a set of methods for analyzing various finite mixture models. It includes not only the traditional methods, such as the EM algorithm of univariate and multivariable normal mixture, but also some newly studied methods reflecting the finite mixture model. Many algorithms are EM algorithms or based on em like […]

• ## Drawing 3D Earth by webgl

Time：2021-7-28

It may be convenient to display the 3D model through three.js, but do you know how it works step by step from mesh construction to mapping to final rendering? Now we can implement it directly by using the underlying web GL and a little mathematical knowledge. The effect of this section:Webgl 3D Earth content syllabus […]