choice-metrics.com

Thank you Michiel,

Your assistance and guidance is appreciated as always. One final point of clarification:

1. Have you used (do you recommend) using a non-nested test to compare Mixed logit and MNL models. Or is it sufficient to compare across adjusted rho-squared?

Some researchers state that ...

Hi Michiel, John and Andrew,

I wanted to get your advice and confirm my understanding in relation to two issues in completing segmented consumer discrete choice studies.

In short – I have completed a segmented study on consumer preference to a new product. I segmented consumers based on their ...

Hi Michiel,

Apologies for posting in the wrong forum – my mistake.

Thank you for answering the questions. I greatly appreciate the assistance.

David

Hi Michiel,

Thank you for confirming that, very much appreciated!

I was also hoping to get your thoughts on a few follow up questions:

I was hoping to complete an efficient design, however my research team has requested an orthogonal design due to their past experiences with this design framework ...

Hi Ngene Team,

I was wondering if you can please assist in advising on the following issue experienced when developing a fractional factorial design. I am developing a fractional factorial design to test a MNL and Hybrid choice model.

When developing the following syntax, ngene is able to locate ...

Thank you Michiel for the response!

The only other question I have is:

- Are there any issues in including both two way interactions and the fold over condition in the design development. Example syntax would be:



Design
;alts = Base, Alt1*, Alt2*
;rows = 36
;orth = sim
;eff = (mnl,d)
;block = 9 ...

Hi Michiel, John and Andrew,

I am now developing a fractional factorial design as per the following syntax, but have a few questions:

1.As I want to include a reference alternative, should I just include it in the alternatives above and not in the utility function? As i understand, a reference ...

Hi John,

I agree that that would be an improvement. My concern is how to handle a greater number of attributes and a range of interactions (covariates, such as socio demographics), that may or may not be significant.

For example, say I had 5 attributes and wanted to include 3 potential socio ...

Thanks John!

At this stage I am going to go with a Bayesian efficient ‘main effects only’ design. Using the s-error as a minimum for sample size :D

My only reservation is not including the interactions (10+ demographics and two-way interactions) in the design, and including them in the estimation ...

Thanks John again for the feedback and discussion. It is certainly an interesting and thought provoking topic.

Following on from the points you raised, I have a few follow up questions.


1. Determination of sample size for orthogonal designs:

How do you think the literature has got away with ...