The terminology multiplicative error model (MEM) has been introduced by Engle (2002b) for a general class of time series models for positive-valued random variables which are decomposed into the product of their conditional mean and a positive-valued error term. Such models might be alternatively classified as autoregressive conditional mean models where the conditional mean of a distribution is assumed to follow a stochastic process. The idea of a MEM is well known in financial econometrics and originates from the structure of the autoregressive conditional heteroscedasticity (ARCH) model introduced by Engle (1982) or the stochastic volatility (SV) model proposed by Taylor (1982) where the conditional variance is dynamically parameterized and multiplicatively interacts with an innovation term. In high-frequency econometrics, a MEM has been firstly introduced by Engle and Russell (1997, 1998) to model the dynamic behavior of the time between trades and was referred to as autoregressive conditional duration (ACD) model.
CITATION STYLE
Hautsch, N. (2012). Vector Multiplicative Error Models. In Econometrics of Financial High-Frequency Data (pp. 177–194). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-21925-2_7
Mendeley helps you to discover research relevant for your work.