• ## 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 […]

• ## The extended tecdat|r language uses metropolis hasting sampling algorithm for logical regression

Time：2022-7-11

Original link:http://tecdat.cn/?p=6761 Source of original text:Tuoduan data tribe official account In logistic regression, we take the binary dependent variable y\_ I regression to covariate x\_ I up. The following code uses metropolis sampling to explore beta\_ 1 and beta\_ The posterior Yi of 2 to the covariate Xi. Define exit and fractional logarithm linking functions […]

• ## Remember a lesson about the promise of cryptography

Time：2022-7-9

What does the security strength of 80bit mean? Generally speaking, the security strength of 80bit and 160bit is a concept in symmetric cryptography. It means to brutally crack or enumerate private keys. There are$$2^{80}$$The power is a possibility. So how many bits of security strength in a symmetric password corresponding to a 2048bit public key […]

• ## [course notes] information theory of China University of science and Technology (III)

Time：2022-7-5

Chain rule of entropy \begin{aligned} H(X, Y) &=\mathrm{E}\left[\log \frac{1}{p(X, Y)}\right] \\ &=\mathrm{E}\left[\log \frac{1}{p(X) p(Y \mid X)}\right] \\ &=\mathrm{E}\left[\log \frac{1}{p(X)}+\log \frac{1}{p(Y \mid X)}\right] \\ &=\mathrm{E}\left[\log \frac{1}{p(X)}\right]+\mathrm{E}\left[\log \frac{1}{p(Y \mid X)}\right] \\ &=H(X)+H(Y \mid X) \end{aligned} If the minus sign of entropy is written outside, it is easy to make mistakes Understand the chain rule of three […]

• ## R language meta analysis effect quantity

Time：2022-5-21

Original link: http://tecdat.cn/?p=23855 When conducting a meta-analysis, you will most likely have to use generic metrics to calculate or convert effect sizes to effect sizes. There are several tools available to do this. Calculate effect size R language covers most effect size calculation and conversion options, which can let you better understand. For example, get […]

• ## In Python, the long-term and short-term memory model LSTM is used for time series prediction analysis – predicting power load data

Time：2022-4-2

Original link:http://tecdat.cn/?p=6663 Original source:Tuo end data tribal official account In this example, the neural network is used to predict the power consumption of citizens’ offices using data from April 2011 to February 2013. Daily data is created by totaling the consumption of 15 minute intervals provided each day. Introduction to LSTM LSTM (or short-term memory […]

• ## Machine learning algorithm series (VII) – logarithmic probability regression algorithm (I) (logistic regression algorithm)

Time：2022-3-29

Background knowledge required for reading this article: linear regression, maximum likelihood estimation and yidui programming knowledge 1、 Introduction    in the previous sections, we studied standard linear regression, and then introduced three regularization methods – ridge regression, Lasso regression and elastic network regression. These linear models solve the problem of regression. At the beginning, it […]

• ## Machine learning algorithm series (VII) – logistic regression algorithm (I)

Time：2022-3-28

Background knowledge required for reading this article: linear regression, maximum likelihood estimation and yidui programming knowledge 1、 Introduction    in the previous sections, we studied standard linear regression, and then introduced three regularization methods – ridge regression, Lasso regression and elastic network regression. These linear models solve the problem of regression. At the beginning, it […]

• ## R language nonlinear mixed effect NLME model (fixed effect & random effect) study on the kinetics of theophylline, an anti asthma drug

Time：2022-3-18

Original link: http://tecdat.cn/?p=24074 brief introduction Theophylline data Theophylline data files report data from studies on the kinetics of theophylline, an antiasthmatic drug. Theophylline was administered orally to 12 subjects, and then serum concentrations were measured at 11 time points over the next 25 hours. head(thdat) Here, the time is the time (H) from the time […]

• ## Machine learning algorithm series (VIII) – logarithmic probability regression algorithm (II) (logistic regression algorithm)

Time：2022-3-15

Background knowledge required for reading this article: logarithmic probability regression algorithm (I), conjugate gradient method, and a little programming knowledge 1、 Introduction The last article is the logarithmic probability regression algorithm (I), which introduces two methods to optimize the cost function of logarithmic probability regression – gradient descent method and Newton’s method. However, when using […]

• ## Machine learning algorithm series (IX) – multiple logistic regression

Time：2022-3-4

Background knowledge required for reading this article: logarithmic probability regression algorithm and yidui programming knowledge 1、 Introduction    the logarithmic probability regression algorithm introduced earlier is called regression algorithm, but it is actually used to deal with classification problems. The data set is divided into two categories, represented by 0, 1 or – 1, 1. […]

• ## R language bugs sequence Monte Carlo SMC, Markov transformation random volatility SV model, particle filter, metropolis Hastings time series analysis

Time：2021-12-29

Original link: http://tecdat.cn/?p=24162 In this example, we consider Markov transformation stochastic volatility model. statistical model Let YT be the dependent variable and XT be the unobserved logarithmic volatility of YT. For t ≤ Tmax, the stochastic volatility model is defined as follows The state variable CT follows a two state Markov process with transition probability […]