In [[statistics]], '''latent variables''' (as opposed to [[observable variable]]s), are [[variableVariable (mathematics)|variables]]s that are not directly observed but are rather inferred (through a [[mathematical model]]) from other variables that are observed and directly measured. They are also sometimes known as '''hidden variables''', '''model parameters''', '''hypothetical variables''' or '''hypothetical constructs'''. The use of latent variables is common in [[social science]]s, [[robotics]], and to an extent [[economics]], but the exact definition of a latent variable varies in these fields. Examples of latent variables from the field of [[economics]] include [[quality of life]], business confidence, morale, happiness and conservatism: these are all variables which cannot be measured directly. However, given an economic model linking these latent variables to other, observable variables (such as [[Gross domestic product|GDP]]), the values of the latent variables can be inferred from measurements of the observable variables.
One advantage of using latent variables is that it [[Dimensionality reduction|reduces the dimensionality]] of data. A large number of observable variables can be aggregated in a model to represent an underlying concept, making it easier for humans to understand the data. In this sense, they serve the same function as theories in general do in science. At the same time, latent variables link observable ("sub-symbolic") data in the real world, to symbolic data in the modelled world.
