F = jforecast(M,D,Range,...)
M
[ model ] - Solved model object.
D
[ struct ] - Input data from which the initial condition is taken.
Range
[ numeric ] - Forecast range.
F
[ struct ] - Output struct with the judgmentally adjusted forecast.'anticipate='
[ true
| false
] - If true, real future shocks are anticipated, imaginary are unanticipated; vice versa if false.
'currentOnly='
[ true
| false
] - If true
, MSE matrices will be computed only for the current-dated variables, not for their lags or leads.
'deviation='
[ true
| false
] - Treat input and output data as deviations from balanced-growth path.
'dtrends='
[ @auto
| true
| false
] - Measurement data contain deterministic trends.
'initCond='
[ 'data'
| 'fixed'
] - Use the MSE for the initial conditions if found in the input data or treat the initical conditions as fixed.
'meanOnly='
[ true
| false
] - Return only mean data, i.e. point estimates.
'plan='
[ plan ] - Simulation plan specifying the exogenised variables and endogenised shocks.
'vary='
[ struct | empty ] - Database with time-varying std deviations or cross-correlations of shocks.
When adjusting the mean and/or std devs of shocks, you can use real and imaginary numbers ot distinguish between anticipated and unanticipated shocks:
any shock entered as an imaginary number is treated as an anticipated change in the mean of the shock distribution;
any std dev of a shock entered as an imaginary number indicates that the shock will be treated as anticipated when conditioning the forecast on the reduced-form tunes.
the same shock or its std dev can have both the real and the imaginary part.