Dear Members,

I wish to perform a kmeans factor analysis on the database I briefly described here:

https://www.statalist.org/forums/for...rs-not-allowed

More precisely, I have 20 variables each indicating how a certain feature of electric cars is perceived as a barrier to their purchase for each survey respondent. These barriers entail features such as practicality, range anxiety, ... till driving pleasure. These very same 20 variables can take only the following values: 1, 2, 3, 4. With respect to the proposed statement, 1 indicates that the respondent completely disagrees with it, 2 that she partially disagrees, 3 that she partially agrees, and 4 that she totally agrees.

Beyond the aforementioned set of variables that capture the perceived obstacles to the purchase of an electric car, the database also includes for each respondent a set of socio-economic characteristics, such as gender, level of income, level of education, number of cars in the household, number of family members with licence in the household, average number of kilometers travelled per day and per year, and many more.

Differently from the request I formulated in the abovereported link on Statalist, when I was interested to perform a kmeans cluster analysis on individuals, I would like now to perform a cluster analysis on the 20 variables that capture the presence of barriers, i.e. I would like to check if it is possible to group the 20 variables into a smaller number.

I am a little bit confused on how to proceed since the command I used to perform the cluster analysis on the individuals is, for example, the following, if I wanted to have three clusters:

Code:
cluster kmeans practicality-driv_pleas, k(3) name(cluster0)
Beyond this forum and Google, I checked on Youtube if there was some help and I looked at what SPSS offers (a software I have not access to). I believe that the following link:

https://www.youtube.com/watch?v=yHEnXtdVd2k

provides two possible options, but this is just an example. I believe there could be different ways to aggregate the variables and I am open to suggestions.

Many thanks.

Marco