# dlmBSample: Draw from the posterior distribution of the state vectors In dlm: Bayesian and Likelihood Analysis of Dynamic Linear Models

## Description

The function simulates one draw from the posterior distribution of the state vectors.

## Usage

 `1` ```dlmBSample(modFilt) ```

## Arguments

 `modFilt` a list, typically the ouptut from `dlmFilter`, with elements `m`, `U.C`, `D.C`, `a`, `U.R`, `D.R` (see the value returned by `dlmFilter`), and `mod` The latter is an object of class `"dlm"` or a list with elements `GG`, `W` and, optionally, `JGG`, `JW`, and `X`

## Details

The calculations are based on singular value decomposition.

## Value

The function returns a draw from the posterior distribution of the state vectors. If `m` is a time series then the returned value is a time series with the same `tsp`, otherwise it is a matrix or vector.

## Author(s)

Giovanni Petris [email protected]

## References

Giovanni Petris (2010), An R Package for Dynamic Linear Models. Journal of Statistical Software, 36(12), 1-16. http://www.jstatsoft.org/v36/i12/.
Petris, Petrone, and Campagnoli, Dynamic Linear Models with R, Springer (2009).
West and Harrison, Bayesian forecasting and dynamic models (2nd ed.), Springer (1997).

See also `dlmFilter`
 ```1 2 3 4 5 6 7 8``` ```nileMod <- dlmModPoly(1, dV = 15099.8, dW = 1468.4) nileFilt <- dlmFilter(Nile, nileMod) nileSmooth <- dlmSmooth(nileFilt) # estimated "true" level plot(cbind(Nile, nileSmooth\$s[-1]), plot.type = "s", col = c("black", "red"), ylab = "Level", main = "Nile river", lwd = c(2, 2)) for (i in 1:10) # 10 simulated "true" levels lines(dlmBSample(nileFilt[-1]), lty=2) ```