Spearman’s Rank Correlation Coefficient To see if a correlation is statistically significant
The Spearman’s rank test gives you a number between -1 and 1. -1 = a perfect negative correlation 1 = a perfect positive correlation 0 = no correlation The graph in the middle will have a value close to -1
Difference between an observation’s ranking for the two variables you are investigating It will make sense In a minute Spearman’s rank correlation coefficient Number of observations
Is there a correlation between height and weight of a person? H0 – There is no correlation between height and weight of a person
Data Collected
The shortest height so gets a rank of 1 The heaviest weight gets a rank of 10 These two people weigh the same. If you get a tie, average the rankings between the two. They are both 4th and 5th so they both get 4.5
Add up the values of d2 = 50.5
Number of observations 0.694 What does this tell you about the correlation? (Larger than or equal to, you can reject the null) Number of observations The critical value is 0.648
0.694 is greater than 0.648 ....so the correlation is significant at the 0.05 level We can reject our null hypothesis!!!!!!
Is there a significant correlation between height and hand area?
Person Height Height ranking Hand area Hand area ranking d d2 1 2 3 4 5 6 7 8 9 10 11 12 13 14