choice-metrics.com

I will try that as well, as after increasing the range of the attribute levels and relaxing some constrains I still cannot get a solution. Thank you!

1) Thank you very much Michiel! This is very helpful. I work on revising my ATTR. levels to allow for some flexibility.

- Indeed, I forgot to remove the constraints of type altx.mode = altx.mode that were there from my previous syntax, but are not necessary here.

- Yes, by ;reject altx.mode = 2 ...

Hello again,

1) For the "simplified" version of the syntax I get the same error as before:

Error: There were problems generating a fractional factorial of choice tasks. For the modified federov algorithm, increasing the number of candidates might assist.

Design
;alts = alt1*, alt2*, alt3 ...

It is my mistake, because I have in mind that I want to switch to alt. specific parameters eventually (keeping the code generic to be able to make the switch easily). But this will not work with this syntax. I am trying your suggestion now to see if I can get a first result. For alt. spec. params I ...

Thank you for the reply Michiel! I will take a look at it again. Initially I misunderstood and thought I would need to combine your proposed syntax with the "partial choice set design", but it is not the case. In your syntax though, I would still need to interact the mode.dummy with each attribute ...

Hello again,

I went through it once more and I think that the method of "partial choice set design" is probably not the best approach for my unlabeled design. I could indeed treat my design as (imitate) a labeled design and generate candidate sets, but I would end up with a huge complete set to ...

Thank you for the clarifications and the suggestions Michiel! I will try them out.

Best,
Eva

Hello,

I am developing an unlabeled mode choice experiment where the mode is treated as an attribute.

I have 12 potential modes. Only 5 alternatives will be offered to the respondent in each choice situation.
Given that I have an unlabeled design, I am trying to code this without an availability ...