Answers are grounded in this paper and cite their sources.
Constructing an index out of several component variables is a common practice in social science research, and the use of composite indices in data analysis is likely to increase. In constructing such an index, a researcher must solve two problems: (1) how to evaluate the assumption that given variables meet the criterion of unidimensionality, or a one-factor (common) model; and (2) how to combine the indicator variables into a single scale in such a way
No takes yet. Share an insight, caveat, or question.
Kim et al. (1980) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: