eLab 2.0

Understanding Your Air Travel Preferences

Required configuration for this Java applet to work

Software. In order to run the conjoint analysis applet, you will need a browser capable of supporting version 1.1 of Java.

Screen resolution. Your monitor must be set to a minimum resolution of 800x600, or else you will not have enough screen space to comfortably view the applet.

Understanding Your Air Travel Preferences with Conjoint Analysis

This exercise familiarizes you with all of the major phases of a conjoint analysis study: data collection using full-profile methodology, calculation of utilities, and calculation of relative importances of attributes.

What characteristics do you find most important when making air travel reservations? Conjoint analysis is one way of finding out. The following characteristics describe a hypothetical flight you may take from New York City (Kennedy Airport) to Los Angeles (LAX). Assume that you are paying for the ticket yourself, and that you are making the trip for personal, not business, reasons.

Airline. You may fly on either:

• American Airlines
• Delta Airlines
• Continental Airlines

Route. The flight may be either:

• Non-Stop
• Direct (stop for one hour in Chicago)
• Connecting (one hour to change planes in Chicago)

Price. Your advance purchase economy fair from JFK to LAX is either:

• $350 round trip
• $400 round trip
• $450 round trip

Frequent Flier Program Status. You are either: 

• Enrolled in the specified airline's frequent flier program
• Not enrolled in the airline's frequent flier program

Movie Status. There will be either: 

• Movie during flight
• No movie during flight

We will refer to Airline, Route, Price, Frequent Flier Program Status, and Movie Status as attributes, and the specific values of these attributes (i.e., "American," "Non-Stop," "$350 round trip," etc.) as levels of an attribute. 

Follow the instructions in this exercise. You will use conjoint analysis to answer the question - "What do I find important in air travel?" 

 
The Conjoint Analysis Task

Below you should see a list of 18 flights that are described by various combinations of the above five attributes.  (If you do not see the list of 18 theaters, please verify you have the required configuration for the Java applet to work.) 


Sort the following 18 flights from "most preferred flight" to "least preferred flight." by clicking on a flight and dragging it up or down in the list.  Keep the following in mind as you sort the flights: 

a. The flight is a round trip from New York City (Kennedy Airport) to Los Angeles (LAX). 
b. You are paying for the ticket yourself. 
c. You are making the trip for personal, not business, reasons.

After you have sorted the flights, click on the Calculate button.

• After the flights have been sorted based on your preferences they are assigned a score from 1 to 18. A score of 18 is used for the most preferred flight, 17 for the second most preferred flight, 16 for the third most preferred flight, and down to 1 for the least preferred flight.
  
  
• The average scores for each attribute level are computed as follows:  for each attribute level, the score for the corresponding flights are totaled and then averaged.
  
  
• The average scores are then converted into part worths.   To do this, the maximum and minimum average scores are found.  The part worths are then calculated using the formula:
  
  
part worth = (average score - minimum ) / (maximum - minimum)

For example, if your maximum average score is 4.2, your minimum average score is 1.2, and your average score for Delta Airlines is 3.0, then your part worth would be (3.0 - 1.2)/(4.2 - 1.2) = 0.6.


• The relative importance of each of the final attributes is computed.  For each attribute the difference between the maximum and minimum part worth forms the "raw importance" for the attribute.  For example, your part worth for American Airlines might be 0.8, for Delta 0.6, and for Continental 0.4.  The difference between the maximum and minimum for Airlines is then 0.8 - 0.4 = 0.4, which is your raw importance for Airlines.  Further, suppose you calculated these raw importances for all five attributes and you found:

 

Airline	0.4
Route	0.3
Price	0.5
Frequent Flier	0.2
Movie Status	0.1

• Adding up the five raw importances, you find that the total is equal to 1.5.  Then convert each raw importance to a relative importance by dividing the raw importance by the total, and multiplying by 100.  In this example, the relative importance for airline is (0.4/1.5)*100 = 27%; the relative importance for route is (0.3/1.5)*100 = 20%; etc.

a. Interpret your pattern of part worth, and your relative importances.  What does it tell you about your air travel preferences? 

b. How do you expect your results might have changed if the instructions indicated that the trip was a business trip paid for by your employer?  (If you are feeling particularly ambitious, you can actually redo the conjoint analysis under this scenario). 

c. How might a different selection of airlines (say, American, USAIR, Northwest) have affected your results?  A different range of prices ($350, $500, $650)? 

d.  How might a different number of levels of attributes have affected your results?  For example, using five price points instead of three. 

e. Can you identify any other attributes, other than the five used in this exercise, that are important considerations for you in selecting an air carrier?  How might the inclusion of these additional attributes have affected your results? 

f. Assume we have part worths and relative importances for all class members.  How can this information be used for market segmentation? For product development?

g. Please prepare a one page overhead showing the plots of your part worths and your relative importances. (You will need to print, and then cut/paste/reduce your output to fit). Bring this to class. I will call on class members for examples.