A Note on Variables and Observations in Factor Analysis

Peter Murrell , Journal of Development Economics 21(2) , 319-325 , May 1986.

Bumb (1982) has claimed that factor analysis estimates are spurious when the number of observations is less than the number of variables. It is shown that the distinction between observation and variables is not one that carries any theoretical force in factor analysis. One can treat variables and observations symmetrically, leading to two economic interpretations of any model used in factor analysis. Therefore, the relation between numbers of variables and numbers of observations is not relevant to the question of whether a factor analysis model can be estimated.

Links to Researchers