What is a Posterior Probability?

最新推荐文章于 2024-08-26 14:34:29 发布

转载最新推荐文章于 2024-08-26 14:34:29 发布 · 1.7k 阅读

机器学习专栏收录该内容

11 篇文章

订阅专栏

本文介绍了后验概率的概念及其计算方法，后验概率是指在已知某个相关事件发生的情况下，目标事件发生的可能性。它通过贝叶斯定理进行计算，并与先验概率形成对比。后验概率在金融、股票投资组合等领域有着广泛的应用。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Posterior probability measures the likelihood that an event will occur given that a related event has already occurred. It is a modification of the original probability or the probability without further information, which is called prior probability (先验概率，普通意义下的概率). Posterior probability is calculated using Bayes’ Theorem. Financial modeling of stock portfolios is a common application of posterior probability in finance. It is sometimes difficult to accurately assign probabilities to events, limiting posterior probability’s usefulness.

In order to calculate posterior probability, the conditional probability of two dependent events can be examined. Let A be the target event, then P(A) is the a priori probability. Let B be a second event that is dependent, or is related to the event A, with probability P(B) （A 先发生，B 后发生，B依赖于A）. Furthermore, let the likelihood of event B occurring, given that A occurs, be P(B|A).

Using Bayes’ Theorem, the posterior probability P(A|B) can be calculated. The theory states: $P(A|B) = \frac{P(B|A)*P(A)}{ P(B)}$ . Note that if events A and B are independent, then their joint probability is $P(A|B) = P(A)$ . This means that their posterior and prior probabilities are identical, since the event B has no effect on the event A.