class_0 <- sample(1:2^K, N, replace = L)
Alphas_0 <- matrix(0,N,K)
for(i in 1:N){
Alphas_0[i,] <- inv_bijectionvector(K,(class_0[i]-1))
}
thetas_true = rnorm(N)
lambdas_true = c(-1, 1.8, .277, .055)
Alphas <- sim_alphas(model="HO_sep",
lambdas=lambdas_true,
thetas=thetas_true,
Q_matrix=Q_matrix,
Design_array=Design_array)
table(rowSums(Alphas[,,5]) - rowSums(Alphas[,,1])) # used to see how much transition has taken place
#>
#> 0 1 2 3 4
#> 39 33 92 145 41
itempars_true <- matrix(runif(J*2,.1,.2), ncol=2)
Y_sim <- sim_hmcdm(model="DINA",Alphas,Q_matrix,Design_array,
itempars=itempars_true)
output_HMDCM = hmcdm(Y_sim,Q_matrix,"DINA_HO",Test_order = Test_order, Test_versions = Test_versions,
chain_length=100,burn_in=30,
theta_propose = 2,deltas_propose = c(.45,.35,.25,.06))
#> 0
output_HMDCM = hmcdm(Y_sim,Q_matrix,"DINA_HO",Design_array,
chain_length=100,burn_in=30,
theta_propose = 2,deltas_propose = c(.45,.35,.25,.06))
#> 0
output_HMDCM
#>
#> Model: DINA_HO
#>
#> Sample Size: 350
#> Number of Items:
#> Number of Time Points:
#>
#> Chain Length: 100, burn-in: 30
summary(output_HMDCM)
#>
#> Model: DINA_HO
#>
#> Item Parameters:
#> ss_EAP gs_EAP
#> 0.1017 0.13216
#> 0.2474 0.09055
#> 0.1806 0.03374
#> 0.1402 0.09625
#> 0.1357 0.11591
#> ... 45 more items
#>
#> Transition Parameters:
#> lambdas_EAP
#> λ0 -1.9439
#> λ1 2.1820
#> λ2 0.2850
#> λ3 0.1486
#>
#> Class Probabilities:
#> pis_EAP
#> 0000 0.1395
#> 0001 0.2157
#> 0010 0.1121
#> 0011 0.2642
#> 0100 0.1734
#> ... 11 more classes
#>
#> Deviance Information Criterion (DIC): 18811
#>
#> Posterior Predictive P-value (PPP):
#> M1: 0.526
#> M2: 0.49
#> total scores: 0.6311
a <- summary(output_HMDCM)
a$ss_EAP
#> [,1]
#> [1,] 0.10172587
#> [2,] 0.24736889
#> [3,] 0.18064153
#> [4,] 0.14019417
#> [5,] 0.13569675
#> [6,] 0.17756314
#> [7,] 0.12205056
#> [8,] 0.14291386
#> [9,] 0.19125192
#> [10,] 0.19646961
#> [11,] 0.12783460
#> [12,] 0.19636923
#> [13,] 0.21034413
#> [14,] 0.08478494
#> [15,] 0.09935250
#> [16,] 0.15771836
#> [17,] 0.19543967
#> [18,] 0.13813074
#> [19,] 0.09818522
#> [20,] 0.16384060
#> [21,] 0.12517765
#> [22,] 0.15973210
#> [23,] 0.19520807
#> [24,] 0.16738171
#> [25,] 0.19387789
#> [26,] 0.18170231
#> [27,] 0.19556135
#> [28,] 0.15851900
#> [29,] 0.16295966
#> [30,] 0.12945732
#> [31,] 0.15771180
#> [32,] 0.13328476
#> [33,] 0.15367361
#> [34,] 0.19155704
#> [35,] 0.12467063
#> [36,] 0.17624710
#> [37,] 0.18130316
#> [38,] 0.17155445
#> [39,] 0.15211197
#> [40,] 0.14977973
#> [41,] 0.20383130
#> [42,] 0.12534357
#> [43,] 0.15107714
#> [44,] 0.17519526
#> [45,] 0.20058653
#> [46,] 0.19203196
#> [47,] 0.15903400
#> [48,] 0.07334262
#> [49,] 0.25126079
#> [50,] 0.15015730
a$lambdas_EAP
#> [,1]
#> λ0 -1.9438625
#> λ1 2.1819750
#> λ2 0.2849638
#> λ3 0.1486371
mean(a$PPP_total_scores)
#> [1] 0.6304898
mean(upper.tri(a$PPP_item_ORs))
#> [1] 0.49
mean(a$PPP_item_means)
#> [1] 0.5154286
a$DIC
#> Transition Response_Time Response Joint Total
#> D_bar 2063.928 NA 14666.40 1277.324 18007.65
#> D(theta_bar) 1797.105 NA 14153.44 1253.772 17204.31
#> DIC 2330.752 NA 15179.37 1300.877 18811.00
head(a$PPP_total_scores)
#> [,1] [,2] [,3] [,4] [,5]
#> [1,] 0.4571429 0.21428571 0.1571429 0.1857143 0.8285714
#> [2,] 0.6571429 0.80000000 0.9285714 0.8000000 0.7857143
#> [3,] 0.8571429 0.00000000 0.1142857 0.5857143 0.2428571
#> [4,] 0.8285714 0.08571429 0.2142857 0.0000000 0.3714286
#> [5,] 0.1714286 0.60000000 0.8428571 0.8428571 0.4857143
#> [6,] 0.9428571 0.95714286 0.6000000 0.9000000 0.8142857
head(a$PPP_item_means)
#> [1] 0.5142857 0.4571429 0.4714286 0.5285714 0.5142857 0.5285714
head(a$PPP_item_ORs)
#> [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8]
#> [1,] NA 1 0.5571429 0.8714286 0.6285714 0.4428571 0.8142857 0.8000000
#> [2,] NA NA 0.9571429 0.8285714 0.8857143 0.9714286 0.8857143 0.8571429
#> [3,] NA NA NA 0.4857143 0.9571429 0.8428571 0.7714286 0.3857143
#> [4,] NA NA NA NA 0.9714286 0.7571429 0.9571429 0.2571429
#> [5,] NA NA NA NA NA 0.4142857 0.6285714 0.8285714
#> [6,] NA NA NA NA NA NA 0.1571429 0.3571429
#> [,9] [,10] [,11] [,12] [,13] [,14] [,15]
#> [1,] 0.1428571 0.9142857 0.5428571 0.32857143 0.7714286 0.1714286 0.9714286
#> [2,] 0.5428571 0.4285714 0.5571429 0.24285714 0.9714286 0.9428571 0.6000000
#> [3,] 0.8714286 0.8285714 0.2142857 0.24285714 0.8428571 0.9000000 0.9285714
#> [4,] 0.3571429 0.7571429 0.6285714 0.52857143 0.8000000 0.2285714 0.8000000
#> [5,] 0.4285714 0.8428571 0.2857143 0.04285714 0.7285714 0.3000000 0.7142857
#> [6,] 0.4142857 0.3571429 0.6714286 0.38571429 0.9571429 0.4428571 0.5714286
#> [,16] [,17] [,18] [,19] [,20] [,21] [,22]
#> [1,] 0.9000000 0.07142857 0.8428571 0.15714286 0.2142857 0.7714286 0.7000000
#> [2,] 0.9285714 0.17142857 0.9714286 0.50000000 1.0000000 0.5142857 0.9000000
#> [3,] 0.7142857 0.68571429 0.7285714 0.28571429 0.9000000 0.6714286 0.7000000
#> [4,] 0.8571429 0.82857143 0.5142857 0.10000000 0.7142857 0.5285714 0.9857143
#> [5,] 0.8000000 0.37142857 0.8714286 0.00000000 1.0000000 0.6714286 0.7571429
#> [6,] 0.4000000 0.12857143 0.7714286 0.02857143 0.8857143 0.6714286 0.7714286
#> [,23] [,24] [,25] [,26] [,27] [,28] [,29]
#> [1,] 0.5857143 0.04285714 0.4000000 0.15714286 0.8142857 0.6428571 0.6285714
#> [2,] 0.9428571 0.35714286 0.6571429 0.00000000 0.4857143 0.5714286 0.8857143
#> [3,] 0.7142857 0.10000000 1.0000000 0.44285714 0.6142857 0.9857143 0.8285714
#> [4,] 0.8285714 0.57142857 0.7000000 0.22857143 0.9428571 0.4000000 0.5142857
#> [5,] 0.9571429 0.37142857 0.3000000 0.44285714 0.7857143 0.8714286 0.4142857
#> [6,] 0.9714286 0.98571429 0.8142857 0.08571429 0.5571429 0.8142857 0.5000000
#> [,30] [,31] [,32] [,33] [,34] [,35] [,36]
#> [1,] 0.6142857 0.87142857 0.9714286 0.9285714 0.6285714 0.9285714 0.31428571
#> [2,] 0.5142857 0.02857143 0.7571429 0.8428571 0.8571429 0.7142857 0.68571429
#> [3,] 0.3857143 0.90000000 0.8000000 0.8142857 0.5714286 0.5714286 0.71428571
#> [4,] 0.2857143 0.15714286 0.4428571 0.5285714 0.5714286 0.3571429 0.15714286
#> [5,] 0.1714286 0.34285714 0.6428571 1.0000000 0.9714286 0.4714286 0.37142857
#> [6,] 0.7285714 0.04285714 0.5714286 0.3571429 0.7571429 0.2714286 0.04285714
#> [,37] [,38] [,39] [,40] [,41] [,42] [,43]
#> [1,] 0.9000000 0.61428571 0.6714286 0.7428571 0.60000000 0.2000000 0.8000000
#> [2,] 0.8000000 0.08571429 0.9142857 0.2142857 0.42857143 0.3857143 0.9571429
#> [3,] 0.5285714 1.00000000 0.5571429 0.7714286 0.41428571 0.9000000 0.7857143
#> [4,] 0.6571429 0.71428571 0.8428571 0.1714286 0.01428571 0.4428571 0.2285714
#> [5,] 0.7857143 0.51428571 0.9714286 0.7428571 0.70000000 0.5571429 0.9000000
#> [6,] 0.1857143 0.22857143 0.8571429 0.1714286 0.28571429 0.2571429 0.4285714
#> [,44] [,45] [,46] [,47] [,48] [,49] [,50]
#> [1,] 0.9714286 0.9142857 0.5428571 0.4142857 0.4000000 0.6285714 0.67142857
#> [2,] 0.1571429 0.7285714 0.9857143 0.9571429 0.8285714 0.5428571 0.88571429
#> [3,] 0.9714286 0.3285714 0.3428571 0.7428571 0.9428571 0.9000000 0.38571429
#> [4,] 0.9000000 0.2000000 0.1000000 0.1000000 0.4142857 0.7285714 0.01428571
#> [5,] 0.9571429 0.9571429 0.4714286 0.9142857 0.6714286 0.3428571 0.64285714
#> [6,] 0.2857143 0.6714286 0.4428571 0.7571429 0.6428571 0.1142857 0.08571429
library(bayesplot)
pp_check(output_HMDCM)
pp_check(output_HMDCM, plotfun="hist", type="item_OR")
#> `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Checking convergence of the two independent MCMC chains with
different initial values using coda
package.
# output_HMDCM1 = hmcdm(Y_sim, Q_matrix, "DINA_HO", Design_array,
# chain_length=100, burn_in=30,
# theta_propose = 2, deltas_propose = c(.45,.35,.25,.06))
# output_HMDCM2 = hmcdm(Y_sim, Q_matrix, "DINA_HO", Design_array,
# chain_length=100, burn_in=30,
# theta_propose = 2, deltas_propose = c(.45,.35,.25,.06))
#
# library(coda)
#
# x <- mcmc.list(mcmc(t(rbind(output_HMDCM1$ss, output_HMDCM1$gs, output_HMDCM1$lambdas))),
# mcmc(t(rbind(output_HMDCM2$ss, output_HMDCM2$gs, output_HMDCM2$lambdas))))
#
# gelman.diag(x, autoburnin=F)