The percentage bend correlation between two variables X and Y is computed as follows:

• Set m = (1-n) + 0.5. Round m down to the nearest integer.
  
• Let for i = 1, ..., n where Mx. is the median of X.
  
• Sort the Wi in ascending order.
  
• = W(m) (i. e., the mth order statistic). W(m) is the estimate of the (1-) quantile of W.
  
• Sort the X values. Compute the number of values of that are less than -1 and the number that are greater than +1 and store in i1 and i2 respectively. Then compute
  
  
  
  
  
• Repeat the above calculations on the Y variable. Store corresponding quantities in , , and Vi.
  
• Define the function
  
  
  
• Compute
  
  
  Ai = i (Ui)
  Bi = i (Vi)
  
• Compute the percentage bend correlation
  
  

The value of is selected between 0 and 0.5. Higher values of result in a higher breakdown point at the expense of lower efficiency.

若能收集到该词条相关资料的跟帖者给予奖励，根据收集资料的水平给予5～100不等的论坛币，当然也可以谈谈自己的看法、应用背景，相关软件知识，上传资料等等都可以。请大家尽量不要复制一些搜索引擎很容易收集到的资料。

     我每天都会发送不等数量的词条，所以诚邀不同统计背景的各路大侠给予评论。

     欢迎大家多多跟帖！要数量也要质量哟