The dynamic factor analysis model (Molenaar, 1985) which is one of the
generalizations of the p-technique factor analysis model, can explain
the lagged covariance structure among observed variables. Hershberger
, Corneal, and Molenaar (1994) showed that the dynamic factor model ca
n be easily evaluated within a structural equation modeling (SEM) prog
ram such as LISREL. In this paper, an alternative time series model co
ntaining the latent factors which are generated by the autoregression
and moving average (ARMA) process is proposed. This model, which has b
een named the time series factor analysis model, can also be easily ev
aluated with a SEM program. The application of this model to the leadi
ng index, the coincident index and the lagging index of the Japanese e
conomy revealed a latent common factor series generated by considerabl
e autoregression.