Dynamic conditional correlation models for realized covariance matrices

New dynamic models for realized covariance matrices are proposed. The expected value of the realized covariance matrix is specified in two steps: one for each realized variance, and one for the realized correlation matrix. The realized correlation model is a scalar dynamic conditional correlation model. Estimation can be done in two steps as well, and a QML interpretation is given to each step, by assuming a Wishart conditional distribution. The model is applicable to large matrices since estimation can be done by the composite likelihood method.