st: Regarding Kendall Coefficient of Concordance

[Urvashi Rathod <urvashi.srathod@gmail.com>]

The study in question is with multi-level rank order:

Three levels of hierarchy were identified based on the findings of
extensive exploration as given below:
Category
          Area
                 Factors

In confirmatory survey, practitioners were asked to rank 5 categories
within themselves (level 1 rank order). Then they were supposed to
rank the areas within each category (level 2 rank order). For example:

Category 1
       Category 2
       Rank
              Rank
              Area11
                    Area21
              Area12				 Area22
              Area13            			 Area23
              Area14
                   Area24
              Area15
                   Area25
              Area16
 And so on…
Within each area, factors were asked to be ranked (level 3 rank
order). All identified items were theoretically orthogonal and no rank
order had more than 7 items. We applied Kendall’s W at every level
separately.

Statistically, can it be objectionable? Is there any other rank order
test suitable to given scenario?

Thanks!

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/