Group C- Conjoint Analysis

Conjoint Analysis is a technique used to assess the relative importance individuals place on different features of a given product. A conjoint study usually involves showing respondents a set of features and asking them to indicate how much they like or prefer the different attributes of that feature.

In a conjoint analysis, the respondent may be asked to arrange a list of combinations of product attributes in decreasing order of preference. Once this ranking is obtained, a computer is used to find the utilities of different values of each attribute that would result in the respondent's order of preference. This method is efficient in the sense that the survey does not need to be conducted using every possible combination of attributes. The utilities can be determined using a subset of possible attribute combinations.

From these results one can predict the desirability of the combinations that were not tested.

Steps in Developing a Conjoint Analysis

Developing a conjoint analysis involves the following steps:

1. Choose product attributes, for example, appearance, size, or price.

2. Choose the values or options for each attribute. For example, for the attribute of size, one may choose the levels of 5", 10", or 20". The higher the number of options used for each attribute, the more burden that is placed on the respondents.

3. Define products as a combination of attribute options. The set of combinations of attributes that will be used will be a subset of the possible universe of products.

4. Choose the form in which the combinations of attributes are to be presented to the respondents. Options include verbal presentation, paragraph description, and pictorial presentation.

5. Decide how responses will be aggregated. There are three choices – use individual responses, pool all responses into a single utility function, or define segments of respondents who have similar preferences.

6. Select the technique to be used to analyze the collected data. The part-worth model is one of the simpler models used to express the utilities of the various attributes. There also are vector (linear) models and ideal-point (quadratic) models.

The data is processed by statistical software written specifically for conjoint analysis.

Example of Syntax for Conjoint Analysis:

conjoint plan = 'C:\Users\ABC\Desktop\Conjoint\Plan.sav'

/data = 'C:\Users\ABC\Desktop\Conjoint\Data.sav'

/rank = card_1 to card_8

/subject = Name

/factors = CompanyType Industry Salary Growth Satisfaction WLBalance Security

/plot all.

Sample Output:

Subject 1: ABC

                                                 Utilities

		Utility Estimate	Std. Error
CompanyType	National	-1.000	.
	MNC	1.000	.
Industry	Service	.750	.
	Mfg	-.750	.
Salary	Above Avg	-1.250	.
	Below Avg	1.250	.
Growth	Fast	-.750	.
	Medium	.750	.
Satisfaction	High	.000	.
	Moderate	.000	.
WLBalance	Yes	.000	.
	No	.000	.
Security	Yes	-1.250	.
	No	1.250	.
(Constant)		4.500	.

 

 

 

 

 

 

 

              Importance Values

CompanyType	20.000
Industry	15.000
Salary	25.000
Growth	15.000
Satisfaction	.000
WLBalance	.000
Security	25.000

For Subject1 from conjoint analysis we find that most important attribute are Salary and Security.

Fig: Attributewise importance for the whole set of respondents.

 

From the figure above we find that Salary is the most important attribute.

Posted By:

S M Murshid Azam

Roll No -14104

Group C

Group A - Conjoint Analysis & Utilities

Conjoint analysis is a statistical technique used in market research to determine how people value
different features that make up an individual product or service.
The objective of conjoint analysis is to determine what combination of a limited number of
attributes is most influential on respondent choice or decision making. A controlled set of potential
products or services is shown to respondents and by analyzing how they make preferences
between these products, the implicit valuation of the individual elements making up the product or
service can be determined. These implicit valuations (utilities or part-worths) can be used to
create market models that estimate market share, revenue and even profitability of new designs.

As for the example taken up in the class, regarding purchase of a laptop, what are the factors
that affect the buying decision.

• Price
• Battery Life
• Weight

What are the different levels of the factors?

• Price 
• 15000
• 20000
• Battery Life
• 2hrs
• 4hrs
• Weight
• 3kg
• 5kg

That leaves us with the total combination of  8
Rank them from 1-8, from least preferred to most preferred

File-New-Data
Data-Orthogonal Design-Generate

8 combinations are generated
Orthogonal Design helps reduce number of combinations

Utility was calculated to ascertain the most important factors to least important factors for a subject.

This would help the marketers to understand which type of laptop would suit which group of people.

Another example taken up was that of Choice of  Job, what you want most in a job?
Following factors were identified by the class:

• Industry
• Company
• Salary
• Satisfaction
• Growth
• Work Life Balance
• Job Security

Based on several levels, the total number of combinations came out to be 2304, further reducing
the levels and using orthogonal design, the number of combinations finally came down to be 128.
 

Based on the ranking, the utility value was computed and percentage was calculated.
 

Final summary was computed for the class as a whole - Importance Summary
 

Importance summary generated several graphs for individual subjects and the class as a whole for individual factors.
This summarized information would help us in knowing what kind of a job offer will be most interesting for a subject.

Supriya Suman

14171, Operations

BA Session 21 & 22 | Group F

By Piyush Upmanyu
HR
11020841093
Group F

Session 21 & 22

Conjoint analysis is 

• A statistical technique used in market research  
• Identifies how individuals value different features that make up an individual product or service. 
• Determines the combination of a finite number of attributes that is most influential on respondent choice or decision making.  
• The implicit valuations (utilities or part-worths) can be used to create market models that estimate market share, sales, profitability, etc  
• Also referred to as multi-attribute compositional modeling, discrete choice modeling, or stated preference research 
• Is part of a broader set of trade-off analysis tools used for systematic analysis of decisions.

Using conjoint analysis, we can calculate which factor has a high utility value. Utility can be defined as a number which represents the value that consumers place on an attribute. In other words, it represents the relative worth of the attribute.

The importance of an attribute can be calculated by examining the range of utilities (that is, the difference between the lowest and highest utilities) across all levels of the attribute. These ranges tell us the relative importance of each attribute.

For Example : We analysed the preferences of students of our class while selecting a job. The attributes were Satisfaction, Work Life Balance, Salary, Industry, etc. 

Syntax :

Result Generated after Run Command

The higher importance value means that the particular attribute is more influential while selecting the job by the candidate.

BA_Lecture21-22_GroupB

Conjoint analysis is typically used to identify the most desirable combination of features to be offered in a new product or services (e.g. what features should be offered in a new public transportation system?). In such studies, respondents are told about the various combinations of features under consideration and are asked to indicate the combination they most prefer, to indicate the combination that is their third preference, and so on. Conjoint analysis uses such preference data to identify the most desirable combination of features to be included in the new product or service.

A conjoint analysis applies a complex form of analysis of variance to the preference data obtained from each respondent. This analysis calculates a value (or utility) for each feature. Features with the highest values are judged the most important to respondents. Conjoint analysis is applied to categorical variables, which reflect different features or characteristics of the product or service under consideration.

Conjoint Analysis Identifies Interdependencies among variables: Conjoint analysis differs from cross tabulation, regression, LDA, and AID in that it is not concerned primarily with a single dependent variable. Rather, conjoint analysis is like cluster and factor analysis in the sense that these methods try to identify the interdependencies which exist between number of variables. In the example involving a new public transportation system, the variables are the features and characteristics that can be designed into the new system and conjoint analysis tries to measure the relative importance of various combinations of those features and characteristics.

Strengths of Traditional Conjoint:

•          Good for both product design and pricing issues

•          Can be administered on paper, computer/internet

•          Shows products in full-profile, which many argue mimics real-world

•          Can be used even with very small sample sizes

Weaknesses of Traditional Full-Profile Conjoint:

•          Limited ability to study many attributes (more than about six)

•          Limited ability to measure interactions and other higher-order effects (cross-effects)

Rajendra Kumar Das

Operations – Group B

11020841156

Group C_ Conjoint analysis process and example

Conjoint analysis: process and examples for implementation

Conjoint analysis helps organizations understand which factors drive decisions. Analysts determine factor preferences by presenting multiple combinations of factors and asking respondents to rank them. Market researchers often use conjoint analysis to determine which product features are most critical to purchase decisions.

Conjoint analysis must currently be run using syntax. Unlike most procedures in SPSS for Windows, conjoint analysis requires the user to invoke two files:

1.Plan File:The plan file contains the combinations that will be presented to the participants.

2. Data File:The data file contains the participants' responses.

The syntax includes the full location of the plan file, but uses an asterisk to alert SPSS to use the file in the data editor as the data file. 

You can also save utilities—the values assigned to each factor from the conjoint—using the utility command. Make sure to include the utility command at the end of the syntax run and indicate where to save the file. You can use this to segment customers based on their preference patterns.

Step 1: Generating the Plan file:
Open SPSS ->Data > Orthogonal Design-> Generate 

Define factors :

Example : In a Hi-Tech hotel survey, IMNU students defined LAPTOP_CARRY, INT_CONNECT_VIDEO_DEMAND,VIDEO_CONF_VOIP, PRICE_PREMIUM as different factors.
They got 9 profiles by orthogonal design.

Step 2: Data -> Orthogonal Design->Display 

This will give you profiles (Multiple combination of factors).Go to your subject and find out their ranking for the given profiles.

Step 3: Generate the data file
This file is generated on basis of ranking provided to different preferences.

Step 4: Run a conjoint Analysis:CONJOINT PLAN='C:\Documents and Settings\Administrator\Desktop\VXLPLAN.SAV'
/DATA=*
/SUBJECT=ID
/FACTORS=LAPTOP_CARRY INT_CONNECT_VIDEO_DEMAND 
VIDEO_CONF_VOIP PRICE_PREMIUM
/RANK=PREF1 TO PREF9
/UTILITY='C:\Documents and Settings\Administrator\Desktop\OUTPUT.SAV'
/PLOT=SUMMARY
/PRINT=SUMMARYONLY.

Step 5: Analyze the output

Examples :-

Conjoint analysis can be used for many cases; some of them could be to study the factors that influence customers, purchasing decisions. Products possess attributes such as price, color, ingredients, guarantee, environmental impact, predicted reliability and so on. Conjoint analysis is based on a main effects analysis-of-variance model. Subjects provide data about their preferences for hypothetical products defined by attribute combinations. Conjoint analysis decomposes the judgment data into components, based on qualitative attributes of the products. A numerical part-worth utility value is computed for each level of each attribute. Large part-worth utilities are assigned to the most preferred levels, and small part-worth utilities are assigned to the least preferred levels. The attributes with the largest part-worth utility range are considered the most important in predicting preference. Conjoint analysis is a statistical model with an error term and a loss function.

Amar Kumar

14067

Operations, Group C

Source: -  http://www.surveyanalytics.com