This function implements one step of the sequential importance sampling method for fading channels.
SISstep.fading(mm, xx, logww, yyy, par, xdim2, ydim)the Monte Carlo sample size m.
the sample in the last iteration.
the log weight in the last iteration.
the observations with T columns and ydim rows.
a list of parameter values. HH is the state coefficient model, WW*t(WW) is the state innovation covariance matrix,
VV*t(VV) is the covariance of the observation noise, GG is the observation model.
the dimension of the state variable x_t.
the dimension of the observation y_t.
The function returns a list with the following components:
the new sample.
the log weights.
Tsay, R. and Chen, R. (2018). Nonlinear Time Series Analysis. John Wiley & Sons, New Jersey.