minor

Examples/DSGE/Bayesian/CKmcmc_cn.log

@@ -0,0 +1,75 @@
+Dynare version: 0.9.12
+2024-05-27T11:03:33.318: Starting @dynare CKmcmc_cn.mod
+["CKmcmc_cn.mod", "language=julia", "json=compute"]
+Dynare preprocessor version: 6.4.0+0
+2024-05-27T11:03:33.369: End of preprocessing
+2024-05-27T11:03:33.427: Start parse_statements!
+ * Status: success
+
+ * Candidate solution
+    Final objective value:     -1.230593e+03
+
+ * Found with
+    Algorithm:     BFGS
+
+ * Convergence measures
+    |x - x'|               = 1.14e-02 ≰ 0.0e+00
+    |x - x'|/|x'|          = 4.10e-03 ≰ 0.0e+00
+    |f(x) - f(x')|         = 7.68e-04 ≰ 0.0e+00
+    |f(x) - f(x')|/|f(x')| = 6.24e-07 ≤ 1.0e-05
+    |g(x)|                 = 3.48e-01 ≰ 1.0e-08
+
+ * Work counters
+    Seconds run:   0  (vs limit Inf)
+    Iterations:    16
+    f(x) calls:    54
+    ∇f(x) calls:   54
+
+  Posterior mode
+
+───────────┬──────────────────────────────────────────────────────────
+ Parameter │ Estimated value  Standard error  80% confidence interval
+──────────────────────────────────────────────────────────────────────
+     betta │          0.9923          0.0022         0.9894 .. 0.9952
+       gam │          1.8895          0.2858         1.5237 .. 2.2554
+      rho1 │          0.9075          0.0368         0.8604 .. 0.9547
+    sigma1 │          0.0089          0.0032          0.0048 .. 0.013
+      rho2 │          0.6908          0.0367         0.6438 .. 0.7377
+    sigma2 │            0.02          0.0014         0.0182 .. 0.0219
+       nss │          0.3313          0.0017         0.3291 .. 0.3335
+───────────┴──────────────────────────────────────────────────────────
+
+Chains MCMC chain (20000×8×1 Array{Float64, 3}):
+
+Iterations        = 1:1:20000
+Number of chains  = 1
+Samples per chain = 20000
+parameters        = betta, gam, rho1, sigma1, rho2, sigma2, nss
+internals         = lp
+
+Summary Statistics
+  parameters      mean       std      mcse   ess_bulk   ess_tail      rhat   ess_per_sec
+      Symbol   Float64   Float64   Float64    Float64    Float64   Float64       Missing
+
+       betta    0.9922    0.0001    0.0000    43.0958    52.6142    1.1303       missing
+         gam    1.9438    0.1844    0.0127   212.9630   531.2424    1.0051       missing
+        rho1    0.9134    0.0121    0.0012   106.6110   189.5468    1.0012       missing
+      sigma1    0.0087    0.0002    0.0000    47.5387    60.8079    1.0289       missing
+        rho2    0.6930    0.0308    0.0028   121.1247   172.7737    1.0456       missing
+      sigma2    0.0192    0.0006    0.0001    42.2265    53.5604    1.5697       missing
+         nss    0.3319    0.0010    0.0001    44.1977    60.1431    1.0207       missing
+
+Quantiles
+  parameters      2.5%     25.0%     50.0%     75.0%     97.5%
+      Symbol   Float64   Float64   Float64   Float64   Float64
+
+       betta    0.9919    0.9922    0.9923    0.9923    0.9925
+         gam    1.6043    1.8146    1.9333    2.0667    2.3280
+        rho1    0.8911    0.9049    0.9136    0.9217    0.9362
+      sigma1    0.0081    0.0085    0.0087    0.0089    0.0090
+        rho2    0.6302    0.6726    0.6946    0.7136    0.7519
+      sigma2    0.0179    0.0188    0.0191    0.0196    0.0203
+         nss    0.3299    0.3313    0.3320    0.3326    0.3337
+
+2024-05-27T11:04:18.646: End parse_statements!
+2024-05-27T11:04:18.646: End parser

Examples/DSGE/Bayesian/CKmcmc_cn.mod

@@ -56,11 +56,6 @@ z1 = 0;
 z2 = 0;
 end;
 
-steady;
-
-stoch_simul(order=1);
-
-
 estimated_params;
 // start values for the optimization 
 // the numbers after the comment are the true 
@@ -77,6 +72,6 @@ end;
 varobs c n;  // experiment choosing one or two from y c n r w
 
 // Does a single fairly short chain 
-estimation(order=1, datafile='dsgedata.csv', mh_replic=20000, mh_jscale=2.) ;
+estimation(order=1, datafile='dsgedata.csv', mh_replic=20000, mh_nblocks=4, mh_jscale=2.) ;
 
 

Examples/DSGE/ML/CKml/model/julia/DynamicParamsDerivs.jl → Examples/DSGE/Bayesian/CKmcmc_cn/model/julia/DynamicParamsDerivs.jl

@@ -1,5 +1,5 @@
 # NB: this file was automatically generated by Dynare
-#     from CKml.mod
+#     from CKmcmc_cn.mod
 #
 function dynamic_params_derivs(y, x, params, steady_state, it_,ss_param_deriv, ss_param_2nd_deriv)
 @inbounds begin

Examples/DSGE/ML/CKml/model/julia/StaticParamsDerivs.jl → Examples/DSGE/Bayesian/CKmcmc_cn/model/julia/StaticParamsDerivs.jl

@@ -1,5 +1,5 @@
 # NB: this file was automatically generated by Dynare
-#     from CKml.mod
+#     from CKmcmc_cn.mod
 #
 function static_params_derivs(y, x, params)
 @inbounds begin

Examples/DSGE/ML/CKml/model/julia/SteadyState2.jl → Examples/DSGE/Bayesian/CKmcmc_cn/model/julia/SteadyState2.jl

@@ -1,5 +1,5 @@
 # NB: this file was automatically generated by Dynare
-#     from CKml.mod
+#     from CKmcmc_cn.mod
 #
 function steady_state!(ys_::Vector{<: Real}, exo_::Vector{<: Real}, params::Vector{<: Real})
 @inbounds begin

Examples/DSGE/Bayesian/Estimate.jl

@@ -0,0 +1,6 @@
+using Dynare
+
+context = @dynare "CKmcmc_cn.mod"
+
+results = context.results.model_results[1]
+results.estimation.posterior_mode

Examples/DSGE/BayesianGMM/DoMCMC.jl

@@ -1,13 +1,13 @@
 ##
 cd(@__DIR__)
-using Econometrics, LinearAlgebra, Statistics, DelimitedFiles, SolveDSGE, MCMCChains, Plots, Distributions
+using Econometrics, LinearAlgebra, Statistics, CSV, SolveDSGE, MCMCChains, Plots, Distributions
 include("DSGEmoments.jl")
 include("DSGEmodel.jl") # defines prior and log-likelihood
 include("CKlib.jl")
 
 function main()
     cd(@__DIR__)
-    data = readdlm("dsgedata.txt")
+    data = CSV.File("dsgedata.csv") |> CSV.Tables.matrix
     lb, ub = PriorSupport()
     θtrue = TrueParameters()
     # start values from GMM

Examples/DSGE/BayesianGMM/dsgedata.csv

@@ -0,0 +1 @@
+../GenData/dsgedata.csv

Examples/DSGE/GMM/DoGMM.jl

@@ -1,7 +1,7 @@
 # this computes the GMM estimator by SA minimization, for
 # one of the 1000 data sets. Can be parallelized using
 # threads.
-using Econometrics, SolveDSGE, DelimitedFiles, Statistics, LinearAlgebra, ForwardDiff
+using Econometrics, SolveDSGE, CSV, Statistics, LinearAlgebra, ForwardDiff
 cd(@__DIR__)
 include("DSGEmoments.jl")  # computes errors
 include("CKlib.jl")
@@ -11,7 +11,7 @@ global const dsge = retrieve_processed_model("../GenData/CK_processed.txt")
 function main(defaultdata = true)
 cd(@__DIR__)
 # call program as main() for the default data, as main(false) for new random data
-defaultdata ? data = readdlm("dsgedata.txt") : data = dgp(TrueParameters(), dsge, 1, rand(1:Int64(1e10)))[1]
+defaultdata ? data = CSV.File("dsgedata.csv") |> CSV.Tables.matrix : data = dgp(TrueParameters(), dsge, 1, rand(1:Int64(1e10)))[1]
 
 # define CUE GMM criterion
 include("parameters.jl") # load true parameter values

Examples/DSGE/GMM/dsgedata.csv

@@ -0,0 +1 @@
+../GenData/dsgedata.csv