You are here: CTSPedia>CTSpedia Web>ResearchTopics>DefReliability>SpearmanRank (02 Jan 2011, ErinEsp)EditAttach

The Spearman Rank Correlation Coefficient takes on values between -1 and 1. The coefficient will be exactly 1 when the ranks for X are identical to the ranks of Y. In this case there is perfect association between the two variables. It will be exactly -1 when the case with rank 1 for X has rank n for Y, the case with rank 2 for X has rank n-1 for Y, and so on. In this case there is perfect inverse association between the two variables. A Spearman Rank Correlation Coefficient of 0 indicates that there is very little association between X and Y. An advantage of Spearman's procedure over Pearson's is that Spearman's is robust to a departure in the assumption of a linear relationship between X and Y.

-- ErinEsp - 02 Jan 2011

Edit | Attach | Print version | History: r1 | Backlinks | Raw View | Raw edit | More topic actions

Topic revision: r1 - 02 Jan 2011 - 20:45:35 - ErinEsp

Copyright &© by the contributing authors. All material on this collaboration platform is the property of the contributing authors.

Ideas, requests, problems regarding CTSPedia? Send feedback

Ideas, requests, problems regarding CTSPedia? Send feedback