I have two sets of data from two respondents ranking 13 variables in order of their importance in percentages. What tests can I run to compare the agreebiality of disagreemnet between these two respondents? Having many respondents how do I compare their responses?
Mr. Abdel-Raheem, what about if we have more than two datasets and more than two variables in each data sets, how can we compare these data set?
Lin's concordance correlation coefficient (CCC) or intra-class correlation (ICC) may be two possibilities - see links below
http://en.wikipedia.org/wiki/Concordance_correlation_coefficient
http://www.udc.gal/dep/mate/biometria2003/Archivos/ot76.pdf
A nonparametric way to compare the datasets, which only looks at ranks but not values, is the Kendall tau rank correlation:
http://en.wikipedia.org/wiki/Kendall_tau_rank_correlation_coefficient
You may use the compatibility index G that measures the compatibility (distance) between two normalized vectors, (This index was built especially for measuring similarity/ in weighted environments).
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS