Alternative-Specific Designs

(Advanced Design Module Only)

 

Top  Previous  Next

(The capabilities described in this section are only available if you own the CBC Advanced Design Module.)

 

Some CBC projects require more flexible designs than the standard approach used with our CBC system.  With standard CBC, if there are six attributes in the study, all six appear within each product concept.

 

Researchers have employed a specialized type of CBC design wherein some or all product alternatives have their own unique sets of attributes.  Conditional Pricing is one example of such a design, where each brand might have its own set of prices.  But, designs can be much more complex than that.  For example, consider modes of transportation: cars versus buses.  Each option has its own set of features (beyond just price) uniquely associated with that mode of transportation.

 

Consider the following attributes for cars and buses:

 

Car  

Parking fee $5.00/day

Parking fee $8.00/day

Parking fee $10.00/day        

 

Bus  

Picks up every 20 min.

Picks up every 15 min.

Picks up every 10 min.

Picks up every 5 min.  

 

25 cents per one-way trip

50 cents per one-way trip

75 cents per one-way trip

$1.00 per one-way trip

 

 

Assume we wanted to measure three other (constant) alternatives: walking, biking, or "I'd choose another way to get to work."

 

The CBC question might look like the following:

 

If you lived 1 mile away from your workplace in downtown New York and these were your choices for getting there, which would you choose?

 

Ride the bus

 

Picks up every 10 min.  

 

$1.00 per one-way trip        

 

Bike

Drive my car  

 

Parking fee $8.00/day        

 

Walk

I'd choose another way to get to work

 

 

To implement this design using CBC's Advanced Design Module, you define the attributes as follows:

 

Attribute 1:

Walk

Bike

Ride the bus

Drive my car

 

Attribute 2:

Picks up every 20 min.

Picks up every 15 min.

Picks up every 10 min.

Picks up every 5 min.

 

Attribute 3:

25 cents per one-way trip

50 cents per one-way trip

75 cents per one-way trip

$1.00 per one-way trip

 

Attribute 4:

Parking fee $5.00/day

Parking fee $8.00/day

Parking fee $10.00/day

 

Before proceeding, it is useful to introduce some terminology to describe the different roles attributes can play in alternative-specific designs.

 

Primary attribute: an attribute whose levels appear in every product concept and upon which conditional attributes (described below) depend.  In the example above, attribute 1 is the primary attribute.

 

Conditional attribute: attributes only displayed with a particular level or levels of the primary attribute.  Attributes 2 through 4 are conditional attributes.

 

Common attribute: attributes displayed with all levels of the primary attribute.  (The example above doesn't include a common attribute.)  In traditional CBC designs, all attributes are common.

 


Specifying an Alternative-Specific Design

 

Choose Compose | Write Questionnaire... and the select a CBC question within the desired CBC Exercise to edit.  This will bring up the CBC Exercise Settings dialog.  From that dialog, click the Design Tab and then check the Alternative-Specific CBC Design radio button.

 

To create the "None" alternative, select Traditional None Option under the Format tab and specify the text: "I'd choose another way to get to work."  Additional constant alternatives are defined as levels within the primary attribute.

 

To complete the design, set the following attribute level prohibitions (make sure to check "alternative-specific design" prior to setting these prohibitions):

 

Attribute 1, Level 1   with   Attributes 2 through 4 (all levels)

Attribute 1, Level 2   with   Attributes 2 through 4 (all levels)

Attribute 1, Level 3   with   Attribute 4 (all levels)

Attribute 1, Level 4   with   Attribute 2 (all levels)

Attribute 1, Level 4   with   Attribute 3 (all levels)

 


Additional Guidelines for Alternative-Specific Designs

 

For alternative-specific designs, we generally suggest the Complete Enumeration strategy (unless you have so many attributes that the design generation process is prohibitively slow).  If the time to generate the design is too long, then you might consider 1) generating fewer total designs (e.g. 20 instead of 300) or 2) the Shortcut design strategy.  In either case, use the Test Design procedure (estimated standard errors via logit and relative D-efficiency test) to determine the effect of one strategy versus the other.  

 

The "None" alternative is always displayed in the last concept position (or in the question's header or footer).  Other constant alternatives you define (with exhaustive prohibitions) within the primary attribute are positioned randomly within the task by default, but you can control their order of presentation on the Design tab of the CBC Exercise Settings dialog by selecting Concept Sorting.  Depending on how many concepts are displayed per task and the design method, it is possible that a constant alternative may not appear in some tasks.  If you want the constant alternatives to appear in every task, you should display at least as many concepts as levels in the primary attribute and then choose the Shortcut design strategy.

 

It is possible to have multiple primary attributes and multiple conditional "branches" in an alternative-specific design.  Conditional attributes can be shared (common) between two or more levels of the primary attribute.  You can choose to have those common attribute aligned in the same row within your choice task by checking Align Common Attributes on Same Row from the Design tab.

 

Fixed alternative-specific tasks (or entire designs) may be specified.

 

Primary attributes must appear in the attribute list before conditional attributes.

 

CBC's experimental designer programs do not formally support mixing standard prohibitions (where not all levels of a conditional attribute are prohibited from showing with a level or levels of a primary attribute) and alternative-specific design prohibitions.  Unexpected results may occur.  We strongly recommend you configure your attributes and levels so that only alternative-specific type prohibitions are used.


Design Efficiency and Alternative-Specific Designs

 

Alternative-specific designs usually require a complex set of prohibitions.  Therefore, we strongly encourage you to test the design to ensure acceptably stable estimation of the part-worths.  For such designs, we suggest you use the Test Design design procedure (estimated standard errors via logit and relative D-efficiency test).  

 

When testing the design, you should check is that it doesn't return the message: "WARNING - THE DESIGN IS DEFICIENT." You should pay particular attention to the standard errors of the part-worths.  Lack of convergence or very large standard errors are an indication that your design is deficient.  

 

Hint: One rule of thumb is to look for standard errors from logit for principal or common attributes no greater than about 0.05, and standard errors for alternative specific (conditional) attributes to be no greater than about 0.10.

 

If your design is like those described in our transportation example where prohibitions are between all levels of the conditional attribute(s) with a particular level (or levels) of the primary attribute, you will likely be on safe ground.  If you define additional prohibitions, you may encounter problems during analysis.

 

You can specify two-way interactions for alternative-specific designs, though in our example it doesn't make sense to specify two-way interactions between primary and conditional attributes, since the effects measured are already "specific" to the reference levels of the primary attribute.  However, for this example design, it is possible to study the interaction between the frequency of bus pick-up and the cost per bus trip, since there were no prohibitions between those two attributes.  If a common attribute were defined (applying to all levels of the primary attribute), it is possible to specify other interactions, such as between the primary and common attribute.

 

Analysis proceeds as with any other CBC study.  The only difference is that when specifying product concepts in the market simulator, you type "N/A" for conditional attributes that aren't applicable.

 

Logit, Latent Class, or HB estimation are possible with alternative-specific designs.

 

Page link: http://www.sawtoothsoftware.com/help/lighthouse-studio/manual/index.html?hid_web_cbc_designs_7.html