attribute aggrigation

This forum is for posts that specifically focus on Ngene.

Moderators: Andrew Collins, Michiel Bliemer, johnr

attribute aggrigation

Postby Unisa » Fri Sep 01, 2017 11:44 am

I think the presentation of attributes needs to reflect the true thought process of participants?
in my travel mode survey I am presenting information on travel time.

I want to include walking time, and service frequency (where relevant) as separate attributes
but after discussing with my colleagues i believe the total travel time is more important in the decision making process then the in vehicle time.
can I keep the attribute in the design and infer the effect of in vehicle time if I provide the respondents with the total travel time as the sum?
as this is how I believe the information is processed in reality

Regards
Unisa
 
Posts: 11
Joined: Tue Jul 25, 2017 4:09 pm

Re: attribute aggrigation

Postby Michiel Bliemer » Fri Sep 01, 2017 2:17 pm

What you present to the respondents and what you in the end model may be different things.
You can include all separate time or cost components to the respondents, and still end up modelling them in an aggregated way in your model. But by at least separately showing them in your design you can still test different models. If you only show the total, you cannot break it up later again. You could assist the respondent by showing both the component as well as the sum.

I do not think that 1 hour travel time and 1 hour in-vehicle time are the same, since 1 hour walking costs energy, so I do not believe they are considered the same thing by respondent. But of course this is up to you.

Note that this is not an Ngene question, please use the other forum for more general stated choice experimental design questions in the future.

Michiel
Michiel Bliemer
 
Posts: 1705
Joined: Tue Mar 31, 2009 4:13 pm


Return to Choice experiments - Ngene

Who is online

Users browsing this forum: No registered users and 8 guests

cron