apologize if this was already sent -- having a few technical
difficulties :-)
...
hi
we're looking for the appropriate statistical test for the following
example:
1000 survey respondents were shown 5 different package designs and
asked to rank order them from most
preferred to least preferred
we're using the following measure to analyze the data:
the percent of time each item was chosen as one of the 2 most
preferred designs -- so each design
has a proportion score using this definition (could be seen as a yes
vs. no measure or in the top 2 vs.
not in the top 2)
we're looking for the best statistical test to state whether the
design with the highest proportion is
higher than the second-highest and same between second and third best
scores and so on
thanks
dave taber
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Locked
