Difference between revisions of "Histogram"

From Open Risk Manual
 
 
Line 20: Line 20:
  
 
[[Category:Visualization]]
 
[[Category:Visualization]]
 +
[[Category:Statistics]]

Latest revision as of 14:54, 18 October 2021

Definition

A Histogram is a numerical approximation (and associated visual depiction) of the observed (sampled) distribution of a continuous Random Variable after its range has been suitably decomposed into a numbef of bins. The bins are typically consecutive and non-overlapping intervals of a variable.

Formula

If X_j is the set of N observed values, k is the number of distinct bins, and B_i = [L_i, R_i] are the left and right boundaries of the i-th bin, then the histogram is the function that counts how many observations fall into each bin.


m_i = \sum_j^N  1_{\{X_j \in B_i\}}

Hence the sum


N = \sum_i^k m_i


See Also