Pearson Vrs Kendall's T Correlation

[jaivipin]

Question #5 of 69

A risk manager that wants to incorporate the effect of outliers into hr statistical correlation measures would most likely use:

A) Kendall's T correlation
B) Pearson correlation
C) Ordinal correlation
D) Spearman's rank correlation


Can someone please tell why the answer "A" is correct? I thought B is correct since Kendall and Spearman ignore outliers when calculating risk.

Thx

 

[David Harper CFA FRM]

@jaivipin Agreed, answer should be "Pearson's"; e.g., Kendall's and Spearman are both ordinal (rank) correlation measures, so even if the language's intent is misleading (e.g., it the meaning were somehow that she "wants to incorporate outliers without too much sensitivity [sic?]" , the preference of Kandall over Spearman lacks specific motivation. Even if the choice logic were cleared up, this is not an exam-worthy question, frankly, due to the loose setup. Modern exam problems have a better setup ... but it demonstrates, once again, that you can often learn from lazy questions

 

[jaivipin]

Thank you David.