Calculates Impulse Response Function for rolling VAR
res=rolirf(results,S,arg1, ,argn)
results = results tlist returned by VAR
S = scalar for number of periods in IRF
arg1, ,argn = optional arguments:
- 'mres=x' where x = chol1 (cholesky decomposition) x = chol2 (triangular factorisation) x = original (original residuals) (default = chol1)
- 'meth=x' where x = asym (asymptotic formula) x = mc1 (Monte-Carlo simulations using draws from the coefficients) (default = asym)
- 'niter=x' where x= # iterations for the Monte-Carlo simulations (if any; default=1000)
- 'size=x' where x = significance level for the confidence band (default =0.05)
res= a results tlist with
- res('meth') = 'rolling irf'
- res('rolling var results') = the rolling Var results tlist entered as input to rolrif
- res('mres') = decomposition method
- res('T') = # of periods represented
- res('IRF') = (nrolling x (S+1) x T) impulse response functions (with nrolling = # of rolling VAR estimated)
- res('IRF_LOW') = (nrolling x (S+1) x T) lower range of impulse response confidence band
- res('IRF_UPP') = (nrolling x (S+1) x T) upper range of impulse response confidence band
- res('PHI') = (nrolling x N*p x T) matrix of coefficients
- res('msg') = message inidicating the nature of the decomposition
- res('size') = size of the confidence band
- res('ans_var 1 to_shock 1') until res('ans_var n to_shock n') = a (nrolling x N*p x T) matrix collecting all irf of one variabel at a time to a shock at a time