|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Key Advantages of ASEMAP Compared to Other Conjoint Analysis Methods
1. Published research* shows that ASEMAP predicts customer choices ~35% better than ACA (Adaptive Conjoint Analysis) when number of attributes is greater than 10. ASEMAP estimated attribute importances predict ~20% better than MAXDIFF.**
2. Unlike commonly used conjoint methods ASEMAP does not bias individual utility functions towards the sample average, making it better suited for segmentation.
3. Unlike other conjoint methods ASEMAP does not suffer from the “number of levels effect” error (attributes with more levels receiving too high importance).
4. ASEMAP ensures utility functions to behave in a logical way during data collection itself, rather than forcing them during estimation.
5. ASEMAP’s adaptive questions minimize respondent fatigue. No wasted questions.
6. ASEMAP works well even with smaller sample sizes because of the improved accuracy of individual utility functions.
7. The ASEMAP importances and part-worths are immediately available as soon as the respondent takes the survey; in CBC/ACBC you need to wait to get all the data, do a hierarchical Bayes analysis (additional researcher time).
This has implications for connected surveys where you may, for example, wish to collect perception data on only the three most important attributes for that particular respondent.
*Journal of Marketing Research, February 2011
**2009 Sawtooth Software Conference Proceedings, p. 160 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| ASEMAP ver 2.0 Copyright © 2024 VSBC. All rights reserved. ASEMAP is a service mark of VSBC. |
|
|
|