title: Probability density estimation introduction tags: probability density, density estimation grammar_cjkRuby: true grammar_flow: true grammar_sequence: true
When learning probability theory, often see all kinds of strange names, some of the book only describes how to solve, but never describes why so called, and what's the use, this article will introduce the probability density estimate of what is and is used to do , the main reference Jason BrownLee the god of blog post are introduced.
Original Address: A Gentle Introduction to Probability Density Estimation
Will be introduced later in the term in English abbreviated form, are summarized as follows:
- The probability density (probability dense, PD)
- The probability density function (probability dense function, PDF)
- Probability density estimation (probability dense estimation, PDE)
The relationship between PD & PDF & PDE
The probability density is summarized in one sentence:
The probability density is the relationship between the observed value and its probability
A result of a random variable may be a very low probability, while others may result probability will be higher.
The overall shape of the probability density is referred to as a probability distribution (Probability Distribution) , the probability of a particular result of the random variable is calculated by the probability density function to complete, simply referred to as PDF (Probability Function the Dense) .
Then the probability density function of what use is it? Very useful! For example, we can determine the level of credibility of a sample by PDF, and then determine whether the samples are outliers. Sometimes we need to enter additional data required to obey a distribution also need to use PDF.
But usually we do not know is a random variable PDF, and we continue to approach this process is the PDF of the probability density estimation .
graph LR
A[概率密度函数] -->|描述| B(概率密度)
C[概率密度估计] -->|估计| A(概率密度函数)
