The statistical analysis was conducted using the SAS statistical software program. Frequency distribution analysis was primarily done to evaluate the characteristics of the respondents and summarising their profile. Then, more than 40 per cent product-related attribute's responses were analysed under exploratory factor analyses (EFA) with varimax rotation to reduce the items to a smaller, more parsimonious set of variables. Eigen value higher than 1.0, and factor loading scores were used to identify the number of factors to extract.

Kaiser-Meyer-Olkin (KMO) measure of sampling adequacy test was done to find whether factor analysis data was appropriate within the value that falls between the ranges of being great and appropriate of factor analysis data. KMO should be 0.60 or higher in order to proceed with factor analysis. Bartlett's test was done with the result, which indicates a highly significant result with P = 0.000 (P < 0.05) and therefore factor analysis is appropriate and accepted.

Reliability of the extracted factor was assessed to examine the internal consistency of the result measurements. The reliability test was conducted using Cronbach's alpha value of 0.91 and a significance level of 0.000. The tool can be used to assess the data on Likert scale only. Due to this limitation the factor related to socio-economic and demography could not be assessed, as many of these variables were numeric.

Also, a cluster analysis exercise was carried out to group respondents into clusters based on their responses. Respondents within a cluster have a high degree of similarity, while respondents between clusters are unique. This way, cluster analysis would help us know the differentiating factors between clusters. Additionally, significant differences were identified for the cluster based on Chi-square tests and t-tests.