Prior Inclusion Probabilities
Prior inclusion probabilities as required for stochastic search variable selection (SSVS) à la George et al. (2008) and Bayesian variable selection (BVS) à la Korobilis (2013).
inclusion_prior( object, prob = 0.5, exclude_deterministics = TRUE, minnesota_like = FALSE, kappa = c(0.8, 0.5, 0.5, 0.8) )
object |
an object of class |
prob |
a numeric specifying the prior inclusion probability of all model parameters. |
exclude_deterministics |
logical. If |
minnesota_like |
logical. If |
kappa |
a numeric vector of four elements containing the prior inclusion probabilities
of coefficients that correspond to own lags of endogenous variables, to endogenous variables,
which do not correspond to own lags, to exogenous variables and deterministic terms, respectively.
Only used if |
If minnesota_like = TRUE, prior inclusion probabilities \underline{π}_1
are calculated as
| \frac{κ_1}{r} | for own lags of endogenous variables, |
| \frac{κ_2}{r} | for other endogenous variables, |
| \frac{κ_3}{1 + r} | for exogenous variables, |
| κ_{4} | for deterministic variables, |
for lag r with κ_1, κ_2, κ_3, κ_4 as the first, second,
third and forth element in kappa, respectively.
For vector error correction models the function generates prior inclusion probabilities for differenced variables and unrestricted deterministc terms as described above. For variables in the error correction term prior inclusion probabilites are calculated as
| κ_1 | fow own levels of endogenous variables, |
| κ_2 | for levels of other endogenous variables, |
| κ_3 | for levels of exogenous variables, |
| κ_4 | for deterministic variables. |
A list containing a matrix of prior inclusion probabilities and an integer vector specifying the positions of variables, which should be included in the variable selction algorithm.
George, E. I., Sun, D., & Ni, S. (2008). Bayesian stochastic search for VAR model restrictions. Journal of Econometrics, 142(1), 553–580. doi: 10.1016/j.jeconom.2007.08.017
Korobilis, D. (2013). VAR forecasting using Bayesian variable selection. Journal of Applied Econometrics, 28(2), 204–230. doi: 10.1002/jae.1271
# Prepare data
data("e1")
# Generate model input
object <- gen_var(e1)
# Obtain inclusion prior
pi_prior <- inclusion_prior(object)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.