I have done a counting analysis for my alternative-specific CBC and I have a question for interpretation.
For the case that a primary attribute level X2 has the conditional attribute Z with the following proportions (each choice task including 3 concepts and a "None" option)
attribute levels of (primary) X:
X1: 0.1 => 0.1/0.6 => 0.17
X2: 0.5 => 0.5/0.6 => 0.83
attribute levels of (conditional) Z:
Z1: 0.3 => 0.3/0.5 => 0.6
Z2: 0.2 => 0.2/0.5 => 0.4
(for making comparisons across the attributes I divide the proportions by the sum (giving a unit sum) - this is recommended in your manual - is that right?)
that is to say: the primary attribute level X2 was the most popular, having been selected 83 percent of the times it occurred (by respondents who have not selected the none-option).
and: under the condition that an alternative with X2 was selected, it had the level Z1 in 60 percent of cases.
Is that correct?
Thanks in advance