Most popular tags

cbc lighthouse-9 acbc ssi-web ssi-web-8 maxdiff cbc-hb javascript grid-question constructed-list unverified-perl ssi-web-7 free-format skip-logic alternative-specific-design willingness-to-pay select-question choice-simulator cbc-latent-class quota-control acbc-hb mbc conditional-pricing smrt pass-in-fields

Have an idea?

Visit Sawtooth Software Feedback to share your ideas on how we can improve our products.

Number of Levels bias (opt out - in or out?)

I was thinking about NoL bias and the opt out.

We have a CBC study in which all Attributes have 5 levels, including zeros.
Zeros only appear in the None option.
The number of levels appearing in the purchase options is equal (4) across all attributes.

Now consider including the zero level for one of the attributes in the purchase options.

Strictly, there is no change in the (equal) number of levels for all attributes, when the None is included in the consideration.
But there is now an imbalance in the number of levels of the attributes in the purchase options (5 vs 4).

So, do we think the change makes the study more vulnerable to NoL effect/ criticism?
If yes, might that be sufficient to add another level to the other Attributes - equalizing the number of levels within purchase options, imbalancing them overall.

Perhaps this depends on whether the zero levels in the None option are being processed as such by respondents.

Any thoughts....?

thanks
Dan
asked Jul 22, 2014 by dan r Bronze (4,025 points)

Your solution to the original question

Please only use this to answer the original question. Otherwise please use comments.
Your name to display (optional):
Privacy: Your email address will only be used for sending these notifications.
Anti-spam verification:

To avoid this verification in future, please log in or register.
Powered by Question2Answer
...