Opt out as choice?

[mgj2]

Hi

Here is our current design

Design
;alts = alt1*, alt2*, OptOut
;rows = 36
;block = 3
;eff = (mnl,d)
;alg = swap(stop=noimprov(120 secs))
?;cond:
?if(alt1.maturation = 3 or alt1.maturation = 4, alt1.Yield <> 40),
?if(alt2.maturation = 3 or alt2.maturation = 4, alt2.Yield <> 40)

;model:
U(alt1) =
b1[-0.01] * Seedlings[0,10,20]
+ b2.effects[-0.1] * Labor[1,2]
+ b3.effects[0.1|0] * Maturation[3,4,6]
+ b4.effects[-0.1|0] * Yield[15,25,40]
+ b5[0.01] * Price[3,5,10,15,20,40]
/
U(alt2) =
b1 * Seedlings + b2 * Labor + b3 * Maturation + b4 * Yield + b5 * Price
/
U(OptOut) = None[-0.001]
$

We trying to decide whether to ask opt out as a choice or force a choice. The opt out is essentially to 'I do not want to plant'. If we force then we ask whether they want to plant or not after the choice. From the pre test we found that they really want and that opt out as a choice as in the current design. But we want the opt out to be the status quo or baseline. In other words if they choice alt 1 or 2 we know they have more utility for that choice than the opt out. I'm told then we need an attribute for the opt out. can you help specify a design so opt out is not a missing value. To use in mixed logit model.

Thanks

[johnr]

Hi mgj2

You need to distinguish between an opt out and a status quo alternative, which can be quite different. If I have a nothing in my cupboard and go to the supermarket, I might look at all the soups on the shelf and decide I like non of them. When I go home, I still have no soup. I have opted out of the market - no soup for me. Now consider a situation where I have a soup can in my cupboard, but think to myself, I might go to the supermarket and see if there is a soup I might prefer more than the one I currently have. If I go to the supermarket, look at all the soups on the shelf and decide I prefer the one I already have, then I have stuck with the status quo alternative - I eat the soup I have.

Whilst both scenarios result in a non-purchase decision, in one case I am assumed to have compared the attributes of alternatives on the shelf and decided I would rather go hungry, whilst in the other scenario, I am assumed to have compared the attributes of alternatives on the shelf, not just with those of the other alternatives on the shelf, but also with the attributes of the alternative I currently have in my possession (presumably I didn't take it to the supermarket though, otherwise I might be accused of stealing it as I lost the receipt). In the first case, I do not have a soup, hence the opt out alternative does not have any levels (not eating has no cost, no flavour, etc.). In the second status quo example, my current alternative does have attributes (it had a cost, it has some flavour presumably).

Thus the answer to your question about I do not want to plant having attribute levels is another question ... what does that mean?

John

[mgj2]

John,
Interesting analogies
I think the scenario one the analogy is not quite right as they may just not like either choice - doesn't mean they go hungry. But anyway how would you model the attributes in the second status quo example you describe.
Thanks, Mike

[johnr]

Hi Mike

In a situation involving a true no choice situation, the no choice alternative has no attribute levels. In that case, your sources may have misinformed you. Only in a case involving a status quo might the opt out alternative have actual actual levels.

Assuming you do want a no choice as opposed to a status quo, it is important to remember utility is relative, not absolute. By setting the utility of the no choice alternative, the utilities for the SP alternatives will be calculated relative to zero. This is perfectly fine. Consider the following outcome in terms of utility.

U(no) = 0
U(a) = -2
U(b) = 3

The zero for the no choice does not mean it has no utility. It simply means that compared to the utility for a (=-2), it has more utility, but less utility that b. Now consider the role constants play.

U(0) = 0
U(a) = asc1 = -2
U(b) = asc2 = 3

If we re-arrange the ASCs so that it goes into the no-choice, you will get

U(0) = asc1 = 2
U(a) = 0
U(b) = asc2 = 5

which will preserve the relative differences in utility. So you can place an ASC in the no-choice if you want, but it is just re-arranging the deck chairs (hopefully not on the Titanic).

You can place socio-demographics into the SQ alternative (though this is NOT a design question - it is an estimation one). For example

U(0) = theta*gender + ....
U(a) = asc1 + beta1*x1a ...
U(b) = asc2 + beta1*x1b ...

That will simply tell you whether people with different socio-demographic characteristics are either more likely or less likely to choose the no choice alternative (depends on the signs of the parameters).

But unless the no choice alternative has actual attributes that describe it, then something * 0 will in most cases I am aware of, be = 0.

So

U(0) = beta1*x10 ...
U(a) = asc1 + beta1*x1a ...
U(b) = asc2 + beta1*x1b ...

if x1. is price, then for the no-choice alternative, it = 0 unless there is a cost of not choosing, and by my calculations (proof not shown), beta1*0 = 0.

This may cover what you say, that is, they simply don't like a or b. The thing is that you are comparing a and b to nothing at all - they prefer b to having nothing, but prefer nothing to a. The question is what is nothing at all. You can do the above, and assume it is a status quo (I'm an economist, I can assume anything). The problem with this, is that if not choosing means respondents have a status quo alternative in reality and they are sticking wit that, and the levels of the status quo have some distribution over that population in terms of the levels associated with each, then by doing the above you are assuming a form of preference homogeniety for the no choice (it is 0 for everyone), when in fact utility for this alternative might have some distribution over the population, even if the preferences are fixed. That is

U(0) = beta* random variable

means U(0) varies randomly over the population, whereas

U(0) = 0

does not.

So now what if it is a status quo alternative and not a no choice? One form of this (there are others) is described in Section 8.3 of the manual.

John