Factor analysis was used to verify the results of survey research related to determining various forms of economic power in supply chains. The purpose of factor analysis is to reduce the information contained in many variables to a small number of factors that replace them. Factor analysis has two main applications:
-
simplifying the data set by reducing the number of interdependent variables
-
identifying underlying common factors, i.e., the structure and dimensionality of the data.
A factor is simply a variable that is not directly observable but is determined from input variables.
A factor can also be viewed as an indicator grouping specific input variables.
There are essentially two approaches in factor analysis:
-
principal component analysis
-
common factor analysis.
In principal component analysis, the total variance in the data is considered. Principal component analysis is recommended when the goal is to determine the minimum number of factors that are calculated for maximum variance in the data, used subsequently in multivariate analysis. In contrast, in common factor analysis, factors are estimated only on common variance. This method is recommended when we want to identify underlying dimensions. This method is also known as principal axis factoring. For the studied sample of enterprises, varimax rotation with Kaiser normalization was applied using SPSS software to facilitate the interpretation of results. Varimax rotation seeks a set of factor loadings such that each factor has some loadings close to zero and some loadings close to -1 or +1. The logic is that interpretation is easiest when variable-factor correlations are either close to +1 or -1, clearly indicating the relationship between the variable and the factor, while those close to 0 indicate no connection.
From the factor selection performed, according to the Kaiser criterion, 5 explanatory variables were obtained.