Multivariate Analysis
- or -
Post a project like this4516
£50(approx. $63)
- Posted:
- Proposals: 1
- Remote
- #105711
- Awarded
Description
Experience Level: Intermediate
I have collected data for six brands from 300 respondents via an online survey. For each brand respondents have stated a level of agreement (seven point Likert Scale) with regards to five brand-related assocations. For example, "For Brand A please state your level of agreement with the following: Brand A is cool, Brand A is boring, Brand A is inspiring, Brand A is conservative, Brand A is refreshing". The same question is asked for the other five brands.
I would like to develop a perceptual map that positions the six brands in relation to each other and in relation to the positioning attributes. This will enable me to determine 1)which brands occupy a similar psychological space in the samples' minds 2) in what way the brands are perceived as similar / unique based on the five brand associations. For example there could be a cluster of four brands that are perceived as cool and inspiring in one quadrant, another brand could be perceived as being boring and the final brand perceived as inspiring.
My journey initially started with Multidimensional Scaling (based on Hair et al's book). This would only allow me to map the brands along arbitrary axes. Too vague. Next I moved on to Multiple Correspondence Analysis as this allows the brands and positioning associations to be mapped. However, with so many respondents the perceptual map became too cluttered / impossible to interpret. When I looked to take averages for each positioning attribute for each brand I was warned this would affect the data integrity (for reasons I could not understand to be honest). I was then advised to use "Multiple" Factor Analysis but could not see how this would help and so have hit a bit of a brick wall.
I have a good understanding of multivariate techniques (factor analysis, confirmatory factor analysis, structural equation modelling and cluster analysis) but finding a solution to this challenge has eluded me.
I would like someone to conduct the analysis and provide details on how they did this.
I would like to develop a perceptual map that positions the six brands in relation to each other and in relation to the positioning attributes. This will enable me to determine 1)which brands occupy a similar psychological space in the samples' minds 2) in what way the brands are perceived as similar / unique based on the five brand associations. For example there could be a cluster of four brands that are perceived as cool and inspiring in one quadrant, another brand could be perceived as being boring and the final brand perceived as inspiring.
My journey initially started with Multidimensional Scaling (based on Hair et al's book). This would only allow me to map the brands along arbitrary axes. Too vague. Next I moved on to Multiple Correspondence Analysis as this allows the brands and positioning associations to be mapped. However, with so many respondents the perceptual map became too cluttered / impossible to interpret. When I looked to take averages for each positioning attribute for each brand I was warned this would affect the data integrity (for reasons I could not understand to be honest). I was then advised to use "Multiple" Factor Analysis but could not see how this would help and so have hit a bit of a brick wall.
I have a good understanding of multivariate techniques (factor analysis, confirmatory factor analysis, structural equation modelling and cluster analysis) but finding a solution to this challenge has eluded me.
I would like someone to conduct the analysis and provide details on how they did this.
Darren C.
100% (3)Projects Completed
6
Freelancers worked with
6
Projects awarded
10%
Last project
3 Dec 2020
United Kingdom
New Proposal
Login to your account and send a proposal now to get this project.
Log inClarification Board Ask a Question
-
There are no clarification messages.
We collect cookies to enable the proper functioning and security of our website, and to enhance your experience. By clicking on 'Accept All Cookies', you consent to the use of these cookies. You can change your 'Cookies Settings' at any time. For more information, please read ourCookie Policy
Cookie Settings
Accept All Cookies