Conjoint and cluster analysis
- 1. CONJOINT ANALYSIS By KIRUBAHARAN B.E., MBA., RESEARCH SCHOLAR ANNA UNIVERSITY CHENNAI
- 2. introduction • CONJOINT – combining things that involved • CONJOINT ANALYSIS : It is a multivariate technique developed specifically to understand how respondents develop preference for any type of products or services.
- 3. purpose • It is used to find how consumers provide their estimates of preference by judging products or services formed by combination of attributes. ( it means combining the separate amount of value provided to each attribute of product or service)
- 4. Questions faced by researcher: 1) What are the important attribute that could affect preference? 2) How will respondents know the meaning of each attributes? 3) What do the respondents actually evaluate? 4) How many profiles are evaluated?
- 5. Example HBAT IS TRYING TO DEVELOP A NEW INDUSTRIAL CLEANSER ATTRIBUTES 1 2 INGREDIETNS PHOSPHATE FREE PHOSPHATE BASED FORM LIQUID POWDER BRAND NAME HBAT GENERIC BRAND VALUES Here two three attributes are present with two values so there is a chance for creating 8 possible combinations that is called as profile.
- 6. PROFILE FORM INGREDIENTS BRAND REPONDENT1 RESPONDENT2 1 Liquid Phosphate free HBAT 1 1 2 Liquid Phosphate free Generic 2 2 3 Liquid Phosphate based HBAT 5 3 4 Liquid Phosphate based Generic 6 4 5 Powder Phosphate free HBAT 3 7 6 Powder Phosphate free Generic 4 5 7 Powder Phosphate based HBAT 7 8 8 Powder Phosphate based Generic 8 6 The eight profiles represent all combinations of the three attributes, each with two levels(2x2x2) The simplest model would represent the preference structure for the industrial cleanser as determined by adding the three factors UTILITY = BRAND EFFECT + INGREDIENT EFFECT + FORM
- 8. Introduction • Cluster analysis – it is the process of grouping observations in to similar kinds in to smaller group within the larger population • Purpose: it is used to segment the market for targeting the customers of brand
- 9. Questions faced by the researcher: 1) How do we measure similarity? 2) How do we form cluster? 3) How many groups do we form?
- 10. example VARIABLE A B C D E F G V1 3 4 4 2 6 7 6 V2 2 5 7 7 6 7 4 RESPONDENTS TO MEASAURE THE LOYALTY– V1( store loyalty) and V2( brand loyalty) were measured for each respondent on a 0-10 scale, the values of the seven respondents are shown.
- 11. Scatter plot A B CD E F G 0 1 2 3 4 5 6 7 8 0 1 2 3 4 5 6 7 8 V1 V2
- 12. EUCLIDEAN DISTANCES OBSERVATION A B C D E F G A _ B 3.162 _ C 5.099 2 _ D 5.099 2.828 2 _ E 5 2.236 2.236 4.123 _ F 6.403 3.606 3 5 1.414 _ G 3.606 2.236 3.606 5 2 3.162 _
- 13. AGGLOMERATIVE METHOD STEP MINIMUM DISTANCE OBSERVATION PAIR CLUSTER MEMBER NO. OF. CLUSTERS OVERALL SIMILARITY MEASURE 1 1.414 E-F (A) (B) (C) (D) (E-F) (G) 6 1.414 2 2 E-G (A) (B) (C) (D) (E-F-G) 5 2.192 3 2 C-D (A) (B) (C-D) (E-F-G) 4 2.144 4 2 B-C (A) (B-C-D) (E-F-G) 3 2.234 5 2.326 B-E (A) (B-C-D-E-F-G) 2 2.896 6 3.162 A-B (A-B-C-D-E-F-G) 1 3.420
- 15. EXAMPLE FOR 3 DIMENSION
- 16. THANK YOU