An TruthPrior object encapsulates the prior information for the short-term discrepancies of the shared discrepancy of the ensemble model.
dA numeric giving the number of variables of interest in the ensemble model.
initial_meanA numeric giving the standard deviation of the normal prior on the initial mean value of the random walk. This is the same standard deviation for each variable of interest.
initial_varA list of length 2 containing the shape and scale parameters (respectively) for the gamma priors on the variance of the initial value of the truth.
rw_covarianceA list of length 2 containing the inverse-Wishart parameters for the covariance of the random walk of the truth.
The truth \(\mathbf{y}^{(t)}\) is modelled as a random walk such that $$\mathbf{y}^{(t+1)} \sim N(\mathbf{y}^{(t)}, \Lambda_y).$$ The covariance matrix \(\Lambda_y\) is parameterised by an inverse Wishart distribution (contained in the rw_covariance slot) and the initial value is modelled as drawn from a normal distribution.