ForecastingF {NGSSMEL} | R Documentation |
The function ForecastingF computes the parameters the shape and scale (recursions) of the one-step-ahead forecast and filtering distributions of the latent states.
ForecastingF(StaPar,Yt,Xt=NULL,model="Poisson",a0=0.01,b0=0.01,distl="PRED")
StaPar |
is the static parameter vector |
Yt |
is the time series of interest |
Xt |
are the explanatory time series to be inserted in the model |
model |
is the chosen model for the observations |
a0 |
is the shape parameter of the initial Gamma distribution |
b0 |
is the scale parameter of the initial Gamma distribution |
distl |
is the latent states distribution to be returned |
If necessary, more details than the description above
att |
Description of 'att': 'att' is the shape parameter of the one-step-ahead forecast distribution of the states. |
btt |
Description of 'btt': 'btt' is the scale parameter of the one-step-ahead forecast distribution of the states. |
at |
Description of 'at': 'at' is the shape parameter of the filtering distribution of the states. It is necessary to specify this option in the argument 'distl'. |
bt |
Description of 'bt': 'bt' is the scale parameter of the filtering distribution of the states. It is necessary to specify this option in the argument 'distl'. |
Thiago Rezende dos Santos
Gamerman, D., Santos, T. R., and Franco, G. C. (2013). A Non-Gaussian Family of State-Space Models with Exact Marginal Likelihood. Journal of Time Series Analysis, 34(6), 625-645.
Harvey, A. C., and Fernandes, C. (1989). Time series models for count or qualitative observations. Journal of Business and Economic Statistics, 7(4), 407-417.
# Forecasting and Filtering for the states # ForFunc(StaPar,Yt,Xt="NULL",model="Poisson",a0=0.01,b0=0.01) Yt=c(1,2,1,4,3) Par=c(0.9) #w predpar=ForecastingF(Par,Yt,Xt=NULL,model="Poisson",a0=0.01,b0=0.01) predpar filpar=ForecastingF(Par,Yt,Xt=NULL,model="Poisson", a0=0.01,b0=0.01,distl="FILTER") filpar