new an introduction to conjoint analysis · 2020. 6. 19. · an introduction to conjoint analysis...

© Sawtooth Software, Inc. | www.sawtoothsoftware.com

An Introduction to Conjoint Analysis

SoftwareSawtoothThe survey software of choice

1


Presentation 1



How Do You Make Choices?

SECTION 1

2



How many choicesdo you make during a typical day?

3



Some choices are trivial…

4



Wansink, B., & Sobal, J. (2007). Mindless Eating: The 200 Daily Food Decisions We Overlook. Environment and Behavior, 39(1), 106-123.

Some choices are trivial…

5



Others are far more complex …

6



Others are far more complex …

7



And some choices are laden with emotion.

8


An Introduction to Conjoint Analysis 9

We need to understand how people make choices so we can create better alternativesand try to predict their choices



Many choices are composed of multiple attributes or features



✓ Likelihood of success✓ Risks ✓ Pain factors ✓ Side effects ✓ Life disruption

Cancer treatment:



Learning how people value the components of an alternative helps us

design more desirable offerings



We also prefer high-likelihood alternatives that are inexpensive



What Is Conjoint Analysis?

SECTION 2

16



Click play button to launch a five-minute video from http://youtu.be/Su2qIrTmv1c

What Can Conjoint Analysis Do for You?

17



Traditionally, researchers have written surveys that ask people about their preferences

18



Which brand do you prefer?

vs.

19



What interest rate would you like?

vs.

20



How much risk are you willing to take?

vs.

21



Answers are often trivial or unenlightening

22



How important is it that you get the …

✓ Brand

✓ Interest rate

✓ Annual fee

✓ Credit limit

…that you want?

23



7.5

8.1

7.2

6.7

0 5 10

Credit Limit

Annual Fee

Interest Rate

Brand

Average Importance Ratings

24



You can’t have the highest fuel efficiency and the most performance

26



Conjoint analysis mimics the real world and doesn’t allow people to say everything is important

Trade-off: a balance achieved between two desirable but incompatible features; a compromise.

27



12%

No Fee

$5000 limit

9.5%

No Fee

$3000 limit

7.5%

$75

$9000 limit

11.5%

$50

$7500 limit

28



http://www.sawtoothsoftware.com/baseball

29

http://www.sawtoothsoftware.com/surveys/baseball/login.html

http://www.sawtoothsoftware.com/baseball



What Outputs Can You Get

From Conjoint?

SECTION 3

30



Three conjoint analysis outputs

Utilities Importancescores

Market simulations



Utilities (part worths)

Numeric values that reflect the desirability of different features

2.5 1.8

5.3 3.2 1.4



Importance scores

Measure how much influence each attribute has on someone’s choice

2.5

1.8

0.7

5.3

1.4

3.9

0.7+ 3.9

4.6

0.74.6

15.2%=3.94.6

84.8%=

Importances are directly affected by the range of levels you choose for each attribute!



Market simulations

Competitive market scenarios to predict which products respondents would choose



Market simulations


Vanilla (2.5) + 35¢ (3.2) = 5.7Chocolate (1.8) + 25¢ (5.3) = 7.1



Market simulations




Market Simulation

Assumptions

SECTION 4

37



All attributes that affect buyer choices in the real world have

been accounted for

38



Each product has equal availability (distribution)

39



Respondents are aware of all products

40



The products reach long-range equilibrium

41



Equal effectiveness of sales force

42



No out-of-stockconditions

43



Shares of preference don’t always match real world market shares



Conjoint simulator assumptions usually don’t hold true in the real world



Conjoint simulators predict respondents’ interest in products or services



Conjoint simulators help managers design alternatives that achieve higher choice likelihood



Conjoint SimulatorExamples

SECTION 5

50



Lets you play “what-if” games to investigate the value of modificationsto an existing product or alternative

51



Lets you predict which healthcare treatment options respondents or segments of the population will choose

52



Lets you estimate how to design new products to maximize buyer interest at low manufacturing cost

53



Lets you investigate product line extensions

54



Lets you estimate demand curves

55



Choice-Based Conjoint

Adaptive Choice-Based Conjoint

57



Paul E. GreenWharton School–

University of Pennsylvania

Daniel L. McFaddenUniversity of

California–Berkeley, MIT, University of

Southern California

Jordan J. LouviereUniversity of Technology–

Sydney, University of South Australia

58

http://www.google.com/url?sa=i&rct=j&q=&esrc=s&source=images&cd=&cad=rja&uact=8&docid=YIMBHdIG2rpoIM&tbnid=iPVkIUXLQlDqTM:&ved=0CAUQjRw&url=http://www.marketingclassicspress.com/authors/green_pe/&ei=ZK4QVLjQEZT_yQSR14HYBg&bvm=bv.74649129,d.aWw&psig=AFQjCNFZopKz2AZFipk2P74xIFnbo_0Mlw&ust=1410465759838445





SoftwareSawtoothThe survey software of choice

60

For more informationplease visit:

www.SawtoothSoftware.com

+1 801 477 4700

new an introduction to conjoint analysis · 2020. 6. 19. · an introduction to conjoint analysis...

Documents