Hi Allstaters,
I would be very grateful for any thoughts on my problem.
I have 8 questions that ask patients about a hypothetical situation, they
are then asked to pick one of three responses. The 8 questions are designed
to assess at what point a respondent will change their response. Because of
this there are patients who are asked only one question, or 2 questions, and
actually by design, no one will answer all 8 questions.
It was suggested to my colleague that a decision tree analysis would be
ideal to assess the decision process of different patients based on a number
of different variables like age, gender and comorbidity. However, now I am
looking into this further I have no idea how I would structure my data
because of these skip patterns and now I am wondering whether this is
actually the best way to analyze this data, if any one has some advice on
the best way to tackle such a problem I would really appreciate it as I am
now at bit of a loss.
Kind Regards,
Bellinda
|