ABSTRACT
Many concepts or constructs exist in social science, which cannot be measured directly. Consider, for example, alienation, anomie, social deprivation, intelligence, quality of life, fear of crime, business confidence, cost of living: in every case we understand what the term conveys but no natural measurement scale exists. Such variables are called latent variables. The list of latent variables in social science seems limitless, so much so that social science could be defined as the study of latent variables. In order to undertake research and analysis on these concepts a measurement scale has to be constructed from manifest variables, that is, from variables that provide some indication of the underlying latent variable but which can themselves be measured. In the case of intelligence, individuals can be given tests to gauge their ability at certain tasks or knowledge of particular subjects. In the case of social deprivation, data on the manifestations or indicators of social deprivation (poor housing, high unemployment, etc.) can be pooled to form an index.
