更改

=== Absolute mutual information ===<!-- This section is linked from [[Kolmogorov complexity]] -->

=== 绝对互信息 Absolute mutual information ===<!-- This section is linked from Kolmogorov complexity -->

 

 

Using the ideas of [[Kolmogorov complexity]], one can consider the mutual information of two sequences independent of any probability distribution:

Using the ideas of [[Kolmogorov complexity]], one can consider the mutual information of two sequences independent of any probability distribution:

=== For discrete data ===

=== 对于离散数据 For discrete data ===

 

 

 

 

 

 

When <math>X</math> and <math>Y</math>  are limited to be in a discrete number of states, observation data is summarized in a [[contingency table]], with row variable <math>X</math> (or <math>i</math>) and column variable <math>Y</math> (or <math>j</math>).  Mutual information is one of the measures of [[association (statistics)|association]] or [[correlation and dependence|correlation]] between the row and column variables.  Other measures of association include [[Pearson's chi-squared test]] statistics, [[G-test]] statistics, etc. In fact, mutual information is equal to [[G-test]] statistics divided by <math>2N</math>, where <math>N</math> is the sample size.

When <math>X</math> and <math>Y</math>  are limited to be in a discrete number of states, observation data is summarized in a [[contingency table]], with row variable <math>X</math> (or <math>i</math>) and column variable <math>Y</math> (or <math>j</math>).  Mutual information is one of the measures of [[association (statistics)|association]] or [[correlation and dependence|correlation]] between the row and column variables.  Other measures of association include [[Pearson's chi-squared test]] statistics, [[G-test]] statistics, etc. In fact, mutual information is equal to [[G-test]] statistics divided by <math>2N</math>, where <math>N</math> is the sample size.