统计学中,似然函数是给定数据的统计模型的参数的函数。
变量值集合:θ,已知结果x的似然函数和这些观察已知变量值的观察结果的概率相等:

似然函数在离散概率分布和连续概率分布中不同:
离散概率分布:
假设X为一个随机变量,符合离散概率分布p,基于参数θ。则函数为:

被认为是θ的函数,称之为似然函数。
连续概率分布:
设X为符合基于变量θ,密度函数为f的绝对连续分布。则函数为:

Log-likelihood
对于很多应用,似然函数的自然对数,称为对数-似然(log-likelihood),很适合计算。因为对数是单调函数。
找到一个函数的最大值,通常涉及对函数的求导,并求解参数使函数最大化。并且通常对log-likelihood最大化简单于直接对原始函数求解。
- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

- L ( θ | x ) = f θ ( x ) , {\displaystyle {\mathcal {L}}(\theta |x)=f_{\theta }(x),\,}

likelihood function
原文:http://www.cnblogs.com/dalu610/p/6370918.html