DINA_HO_RT_sep

library(hmcdm)

Load the spatial rotation data

N = length(Test_versions)
J = nrow(Q_matrix)
K = ncol(Q_matrix)
L = nrow(Test_order)

(1) Simulate responses and response times based on the HMDCM model with response times (no covariance between speed and learning ability)

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,0,1)
tausd_true=0.5
taus_true = rnorm(N,0,tausd_true)
G_version = 3
phi_true = 0.8
lambdas_true <- c(-2, 1.6, .4, .055)       # empirical from Wang 2017
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 
#>  58  48  94 118  32
itempars_true <- matrix(runif(J*2,.1,.2), ncol=2)
RT_itempars_true <- matrix(NA, nrow=J, ncol=2)
RT_itempars_true[,2] <- rnorm(J,3.45,.5)
RT_itempars_true[,1] <- runif(J,1.5,2)

Y_sim <- sim_hmcdm(model="DINA",Alphas,Q_matrix,Design_array,
                   itempars=itempars_true)
L_sim <- sim_RT(Alphas,Q_matrix,Design_array,RT_itempars_true,taus_true,phi_true,G_version)

(2) Run the MCMC to sample parameters from the posterior distribution

output_HMDCM_RT_sep = hmcdm(Y_sim,Q_matrix,"DINA_HO_RT_sep",Design_array,
                            100, 30,
                            Latency_array = L_sim, G_version = G_version,
                            theta_propose = 2,deltas_propose = c(.45,.35,.25,.06))
#> 0
output_HMDCM_RT_sep
#> 
#> Model: DINA_HO_RT_sep 
#> 
#> Sample Size: 350
#> Number of Items: 
#> Number of Time Points: 
#> 
#> Chain Length: 100, burn-in: 50
summary(output_HMDCM_RT_sep)
#> 
#> Model: DINA_HO_RT_sep 
#> 
#> Item Parameters:
#>  ss_EAP gs_EAP
#>  0.1689 0.1990
#>  0.1956 0.1301
#>  0.2301 0.2492
#>  0.1918 0.2010
#>  0.1541 0.1024
#>    ... 45 more items
#> 
#> Transition Parameters:
#>    lambdas_EAP
#> λ0     -2.2152
#> λ1      2.7005
#> λ2      0.1436
#> λ3      0.2048
#> 
#> Class Probabilities:
#>      pis_EAP
#> 0000  0.1133
#> 0001  0.2259
#> 0010  0.1568
#> 0011  0.2376
#> 0100  0.1500
#>    ... 11 more classes
#> 
#> Deviance Information Criterion (DIC): 156396.6 
#> 
#> Posterior Predictive P-value (PPP):
#> M1: 0.5084
#> M2:  0.49
#> total scores:  0.6234
a <- summary(output_HMDCM_RT_sep)
head(a$ss_EAP)
#>           [,1]
#> [1,] 0.1688630
#> [2,] 0.1956231
#> [3,] 0.2300799
#> [4,] 0.1918051
#> [5,] 0.1540848
#> [6,] 0.1943653

(3) Check for parameter estimation accuracy

(cor_thetas <- cor(thetas_true,a$thetas_EAP))
#>           [,1]
#> [1,] 0.7847377
(cor_taus <- cor(taus_true,a$response_times_coefficients$taus_EAP))
#>           [,1]
#> [1,] 0.9870796

(cor_ss <- cor(as.vector(itempars_true[,1]),a$ss_EAP))
#>           [,1]
#> [1,] 0.6864551
(cor_gs <- cor(as.vector(itempars_true[,2]),a$gs_EAP))
#>           [,1]
#> [1,] 0.7291134

AAR_vec <- numeric(L)
for(t in 1:L){
  AAR_vec[t] <- mean(Alphas[,,t]==a$Alphas_est[,,t])
}
AAR_vec
#> [1] 0.9042857 0.9214286 0.9485714 0.9478571 0.9514286

PAR_vec <- numeric(L)
for(t in 1:L){
  PAR_vec[t] <- mean(rowSums((Alphas[,,t]-a$Alphas_est[,,t])^2)==0)
}
PAR_vec
#> [1] 0.6885714 0.7485714 0.8228571 0.8228571 0.8400000

(4) Evaluate the fit of the model to the observed response and response times data (here, Y_sim and R_sim)

a$DIC
#>              Transition Response_Time Response    Joint    Total
#> D_bar          1943.428      134775.4 15319.89 3204.199 155242.9
#> D(theta_bar)   1690.220      134340.2 14895.43 3163.330 154089.2
#> DIC            2196.636      135210.6 15744.35 3245.067 156396.6
head(a$PPP_total_scores)
#>      [,1] [,2] [,3] [,4] [,5]
#> [1,] 0.44 0.76 0.18 0.42 0.86
#> [2,] 0.70 0.40 0.86 0.66 0.22
#> [3,] 0.94 0.54 0.94 0.70 0.68
#> [4,] 0.90 0.04 0.06 0.20 0.04
#> [5,] 0.28 0.78 0.20 0.78 0.84
#> [6,] 0.66 0.68 0.78 0.88 0.66
head(a$PPP_item_means)
#> [1] 0.52 0.38 0.56 0.44 0.46 0.52
head(a$PPP_item_ORs)
#>      [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10] [,11] [,12] [,13] [,14]
#> [1,]   NA 0.76 0.56 0.62 0.76 0.60 0.48 0.98 0.14  0.92  0.82  0.62  0.72  0.12
#> [2,]   NA   NA 0.74 0.98 0.82 0.58 0.94 0.56 0.26  0.58  0.74  0.30  0.34  0.94
#> [3,]   NA   NA   NA 0.98 0.80 0.90 0.92 0.78 0.96  0.30  0.88  0.84  0.90  0.62
#> [4,]   NA   NA   NA   NA 0.92 0.22 0.80 0.68 0.92  0.66  0.62  0.98  0.28  0.48
#> [5,]   NA   NA   NA   NA   NA 0.80 0.46 0.74 0.46  0.78  0.98  0.76  0.24  0.42
#> [6,]   NA   NA   NA   NA   NA   NA 0.74 0.96 0.68  0.56  0.00  0.56  0.96  0.62
#>      [,15] [,16] [,17] [,18] [,19] [,20] [,21] [,22] [,23] [,24] [,25] [,26]
#> [1,]  0.16  0.76  0.54  0.88  0.62  0.26  0.80  0.12  0.84  0.24  0.62  0.64
#> [2,]  0.88  0.94  0.66  0.70  0.78  0.92  0.38  0.10  0.66  0.56  0.32  0.72
#> [3,]  0.46  0.84  0.34  0.48  0.70  0.84  0.80  0.88  0.94  0.50  0.28  0.52
#> [4,]  0.48  0.44  0.88  0.50  0.58  0.76  0.98  0.34  0.98  0.80  0.88  1.00
#> [5,]  0.70  0.94  0.36  0.60  0.74  0.54  0.92  0.46  0.74  0.52  0.58  1.00
#> [6,]  0.44  0.32  0.46  0.10  0.36  0.46  0.96  0.66  0.16  0.46  0.16  0.28
#>      [,27] [,28] [,29] [,30] [,31] [,32] [,33] [,34] [,35] [,36] [,37] [,38]
#> [1,]  0.02  0.40  0.40  0.94  0.44  0.60  0.42  0.32  0.76  1.00  0.72  0.98
#> [2,]  0.18  0.18  0.28  0.44  0.70  0.28  0.96  0.56  0.68  0.60  0.76  0.44
#> [3,]  0.76  0.64  0.52  0.52  0.32  0.26  0.76  0.82  0.24  0.60  0.54  0.66
#> [4,]  0.60  0.20  0.76  1.00  0.66  0.86  1.00  0.36  1.00  0.90  1.00  1.00
#> [5,]  0.32  0.64  0.46  1.00  0.62  0.14  0.26  0.54  0.82  0.88  0.78  0.80
#> [6,]  0.52  0.50  0.44  0.80  0.82  0.16  0.12  0.58  0.96  0.30  0.72  0.50
#>      [,39] [,40] [,41] [,42] [,43] [,44] [,45] [,46] [,47] [,48] [,49] [,50]
#> [1,]  0.98  0.86  0.94  0.82  0.08  0.72  0.94  0.64  0.80  0.80  0.06  0.76
#> [2,]  0.78  0.28  0.06  0.74  0.46  0.48  0.84  0.22  0.70  0.42  0.76  0.54
#> [3,]  0.42  0.58  0.76  0.70  0.68  0.04  0.80  0.72  0.30  0.80  0.14  0.76
#> [4,]  0.22  0.84  0.70  0.60  0.00  0.64  0.72  1.00  0.08  1.00  0.78  0.72
#> [5,]  0.32  0.24  0.52  1.00  0.78  0.92  1.00  0.94  0.62  1.00  0.78  1.00
#> [6,]  0.70  0.68  0.94  0.26  0.70  0.78  0.90  0.44  0.48  1.00  0.94  0.82
library(bayesplot)
#> This is bayesplot version 1.14.0
#> - Online documentation and vignettes at mc-stan.org/bayesplot
#> - bayesplot theme set to bayesplot::theme_default()
#>    * Does _not_ affect other ggplot2 plots
#>    * See ?bayesplot_theme_set for details on theme setting
pp_check(output_HMDCM_RT_sep, type="total_latency")