i got exactly same problem with this question Overall rank from multiple ranked lists but i didnt get any references and answer for that.
example :
object | case 1 | case 2 | case 3 | case 4
Item 1 | Ranked 1 | Ranked 1 | Ranked 2 | Ranked 1
Item 2 | Ranked 2 | Ranked 2 | Ranked 3 | Ranked 3
Item 3 | Ranked 3 | Ranked 3 | Ranked 1 | Ranked 2
visually we can say the final rank from all case is item 1 got first rank because got rank (1 1 2 1), item 3 got second rank (3 3 1 2), and item 2 got last rank (2 2 3 3).
Final rank :
object | final rank
Item 1 | Ranked 1
Item 2 | Ranked 3
Item 3 | Ranked 2
visually we can say that, but is there a statistical calculation to get the final result? I have read the reference about friedman test. but it only deals with hypotheses to conclude whether their final rankings are the same or not. I get a solution to averaging its rankings but I need a clear reference like a journal for that. is there anybody can give me journal link that discusses about this? or discusses about averaging its rangkings?
