$m0a

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m1 ~ 1 + (1 | id), data = longDF, n.adapt = 5, 
    n.iter = 10, seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
                 Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m1B: (Intercept)    0  0    0     0          0     NaN    NaN
m1C: (Intercept)    0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m1_id[1,1]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m0b

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m2 ~ 1 + (1 | id), data = longDF, n.adapt = 5, 
    n.iter = 10, seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
                 Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m2B: (Intercept)    0  0    0     0          0     NaN    NaN
m2C: (Intercept)    0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m2_id[1,1]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m1a

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m1 ~ C1 + (1 | id), data = longDF, n.adapt = 5, 
    n.iter = 10, seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
                 Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m1B: (Intercept)    0  0    0     0          0     NaN    NaN
m1B: C1             0  0    0     0          0     NaN    NaN
m1C: (Intercept)    0  0    0     0          0     NaN    NaN
m1C: C1             0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m1_id[1,1]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m1b

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m2 ~ C1 + (1 | id), data = longDF, n.adapt = 5, 
    n.iter = 10, seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
                 Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m2B: (Intercept)    0  0    0     0          0     NaN    NaN
m2B: C1             0  0    0     0          0     NaN    NaN
m2C: (Intercept)    0  0    0     0          0     NaN    NaN
m2C: C1             0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m2_id[1,1]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m1c

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m1 ~ c1 + (1 | id), data = longDF, n.adapt = 5, 
    n.iter = 10, seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
                 Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m1B: (Intercept)    0  0    0     0          0     NaN    NaN
m1C: (Intercept)    0  0    0     0          0     NaN    NaN
m1B: c1             0  0    0     0          0     NaN    NaN
m1C: c1             0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m1_id[1,1]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m1d

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m2 ~ c1 + (1 | id), data = longDF, n.adapt = 5, 
    n.iter = 10, seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
                 Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m2B: (Intercept)    0  0    0     0          0     NaN    NaN
m2C: (Intercept)    0  0    0     0          0     NaN    NaN
m2B: c1             0  0    0     0          0     NaN    NaN
m2C: c1             0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m2_id[1,1]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m2a

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m1 ~ C2 + (1 | id), data = longDF, n.adapt = 5, 
    n.iter = 10, seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
                 Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m1B: (Intercept)    0  0    0     0          0     NaN    NaN
m1B: C2             0  0    0     0          0     NaN    NaN
m1C: (Intercept)    0  0    0     0          0     NaN    NaN
m1C: C2             0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m1_id[1,1]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m2b

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m2 ~ C2 + (1 | id), data = longDF, n.adapt = 5, 
    n.iter = 10, seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
                 Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m2B: (Intercept)    0  0    0     0          0     NaN    NaN
m2B: C2             0  0    0     0          0     NaN    NaN
m2C: (Intercept)    0  0    0     0          0     NaN    NaN
m2C: C2             0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m2_id[1,1]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m2c

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m1 ~ c2 + (1 | id), data = longDF, n.adapt = 5, 
    n.iter = 10, seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
                 Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m1B: (Intercept)    0  0    0     0          0     NaN    NaN
m1C: (Intercept)    0  0    0     0          0     NaN    NaN
m1B: c2             0  0    0     0          0     NaN    NaN
m1C: c2             0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m1_id[1,1]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m2d

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m2 ~ c2 + (1 | id), data = longDF, n.adapt = 5, 
    n.iter = 10, seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
                 Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m2B: (Intercept)    0  0    0     0          0     NaN    NaN
m2C: (Intercept)    0  0    0     0          0     NaN    NaN
m2B: c2             0  0    0     0          0     NaN    NaN
m2C: c2             0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m2_id[1,1]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m3a

Bayesian linear mixed model fitted with JointAI

Call:
lme_imp(fixed = c1 ~ m1 + (1 | id), data = longDF, n.adapt = 5, 
    n.iter = 10, seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
            Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
(Intercept)    0  0    0     0          0     NaN    NaN
m1B            0  0    0     0          0     NaN    NaN
m1C            0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_c1_id[1,1]    0  0    0     0                NaN    NaN

Posterior summary of residual std. deviation:
         Mean SD 2.5% 97.5% GR-crit MCE/SD
sigma_c1    0  0    0     0     NaN    NaN


MCMC settings:
Iterations = 1:10
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m3b

Bayesian linear mixed model fitted with JointAI

Call:
lme_imp(fixed = c1 ~ m2 + (1 | id), data = longDF, n.adapt = 5, 
    n.iter = 10, seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
            Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
(Intercept)    0  0    0     0          0     NaN    NaN
m2B            0  0    0     0          0     NaN    NaN
m2C            0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_c1_id[1,1]    0  0    0     0                NaN    NaN

Posterior summary of residual std. deviation:
         Mean SD 2.5% 97.5% GR-crit MCE/SD
sigma_c1    0  0    0     0     NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m4a

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m1 ~ M2 + m2 * abs(C1 - C2) + log(C1) + 
    (1 | id), data = longDF, n.adapt = 5, n.iter = 10, seed = 2020, 
    warn = FALSE, mess = FALSE)


Posterior summary:
                      Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m1B: (Intercept)         0  0    0     0          0     NaN    NaN
m1B: M22                 0  0    0     0          0     NaN    NaN
m1B: M23                 0  0    0     0          0     NaN    NaN
m1B: M24                 0  0    0     0          0     NaN    NaN
m1B: abs(C1 - C2)        0  0    0     0          0     NaN    NaN
m1B: log(C1)             0  0    0     0          0     NaN    NaN
m1C: (Intercept)         0  0    0     0          0     NaN    NaN
m1C: M22                 0  0    0     0          0     NaN    NaN
m1C: M23                 0  0    0     0          0     NaN    NaN
m1C: M24                 0  0    0     0          0     NaN    NaN
m1C: abs(C1 - C2)        0  0    0     0          0     NaN    NaN
m1C: log(C1)             0  0    0     0          0     NaN    NaN
m1B: m2B                 0  0    0     0          0     NaN    NaN
m1B: m2C                 0  0    0     0          0     NaN    NaN
m1B: m2B:abs(C1 - C2)    0  0    0     0          0     NaN    NaN
m1B: m2C:abs(C1 - C2)    0  0    0     0          0     NaN    NaN
m1C: m2B                 0  0    0     0          0     NaN    NaN
m1C: m2C                 0  0    0     0          0     NaN    NaN
m1C: m2B:abs(C1 - C2)    0  0    0     0          0     NaN    NaN
m1C: m2C:abs(C1 - C2)    0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m1_id[1,1]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m4b

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m1 ~ ifelse(as.numeric(m2) > as.numeric(M1), 
    1, 0) * abs(C1 - C2) + log(C1) + (1 | id), data = longDF, 
    n.adapt = 5, n.iter = 10, seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
                                                                Mean SD 2.5%
m1B: (Intercept)                                                   0  0    0
m1B: abs(C1 - C2)                                                  0  0    0
m1B: log(C1)                                                       0  0    0
m1C: (Intercept)                                                   0  0    0
m1C: abs(C1 - C2)                                                  0  0    0
m1C: log(C1)                                                       0  0    0
m1B: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0)                 0  0    0
m1B: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0):abs(C1 - C2)    0  0    0
m1C: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0)                 0  0    0
m1C: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0):abs(C1 - C2)    0  0    0
                                                                97.5%
m1B: (Intercept)                                                    0
m1B: abs(C1 - C2)                                                   0
m1B: log(C1)                                                        0
m1C: (Intercept)                                                    0
m1C: abs(C1 - C2)                                                   0
m1C: log(C1)                                                        0
m1B: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0)                  0
m1B: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0):abs(C1 - C2)     0
m1C: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0)                  0
m1C: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0):abs(C1 - C2)     0
                                                                tail-prob.
m1B: (Intercept)                                                         0
m1B: abs(C1 - C2)                                                        0
m1B: log(C1)                                                             0
m1C: (Intercept)                                                         0
m1C: abs(C1 - C2)                                                        0
m1C: log(C1)                                                             0
m1B: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0)                       0
m1B: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0):abs(C1 - C2)          0
m1C: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0)                       0
m1C: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0):abs(C1 - C2)          0
                                                                GR-crit MCE/SD
m1B: (Intercept)                                                    NaN    NaN
m1B: abs(C1 - C2)                                                   NaN    NaN
m1B: log(C1)                                                        NaN    NaN
m1C: (Intercept)                                                    NaN    NaN
m1C: abs(C1 - C2)                                                   NaN    NaN
m1C: log(C1)                                                        NaN    NaN
m1B: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0)                  NaN    NaN
m1B: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0):abs(C1 - C2)     NaN    NaN
m1C: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0)                  NaN    NaN
m1C: ifelse(as.numeric(m2) > as.numeric(M1), 1, 0):abs(C1 - C2)     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m1_id[1,1]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m4c

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m1 ~ time + c1 + C1 + B2 + (c1 * time | 
    id), data = longDF, n.adapt = 5, n.iter = 10, seed = 2020, 
    warn = FALSE, mess = FALSE)


Posterior summary:
                 Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m1B: (Intercept)    0  0    0     0          0     NaN    NaN
m1B: C1             0  0    0     0          0     NaN    NaN
m1B: B21            0  0    0     0          0     NaN    NaN
m1C: (Intercept)    0  0    0     0          0     NaN    NaN
m1C: C1             0  0    0     0          0     NaN    NaN
m1C: B21            0  0    0     0          0     NaN    NaN
m1B: time           0  0    0     0          0     NaN    NaN
m1B: c1             0  0    0     0          0     NaN    NaN
m1C: time           0  0    0     0          0     NaN    NaN
m1C: c1             0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m1_id[1,1]    0  0    0     0                NaN    NaN
D_m1_id[1,2]    0  0    0     0          0     NaN    NaN
D_m1_id[2,2]    0  0    0     0                NaN    NaN
D_m1_id[1,3]    0  0    0     0          0     NaN    NaN
D_m1_id[2,3]    0  0    0     0          0     NaN    NaN
D_m1_id[3,3]    0  0    0     0                NaN    NaN
D_m1_id[1,4]    0  0    0     0          0     NaN    NaN
D_m1_id[2,4]    0  0    0     0          0     NaN    NaN
D_m1_id[3,4]    0  0    0     0          0     NaN    NaN
D_m1_id[4,4]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m4d

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m1 ~ C1 * time + I(time^2) + b2 * c1, data = longDF, 
    random = ~time | id, n.adapt = 5, n.iter = 10, seed = 2020, 
    warn = FALSE, mess = FALSE)


Posterior summary:
                 Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m1B: (Intercept)    0  0    0     0          0     NaN    NaN
m1B: C1             0  0    0     0          0     NaN    NaN
m1C: (Intercept)    0  0    0     0          0     NaN    NaN
m1C: C1             0  0    0     0          0     NaN    NaN
m1B: time           0  0    0     0          0     NaN    NaN
m1B: I(time^2)      0  0    0     0          0     NaN    NaN
m1B: b21            0  0    0     0          0     NaN    NaN
m1B: c1             0  0    0     0          0     NaN    NaN
m1B: C1:time        0  0    0     0          0     NaN    NaN
m1B: b21:c1         0  0    0     0          0     NaN    NaN
m1C: time           0  0    0     0          0     NaN    NaN
m1C: I(time^2)      0  0    0     0          0     NaN    NaN
m1C: b21            0  0    0     0          0     NaN    NaN
m1C: c1             0  0    0     0          0     NaN    NaN
m1C: C1:time        0  0    0     0          0     NaN    NaN
m1C: b21:c1         0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m1_id[1,1]    0  0    0     0                NaN    NaN
D_m1_id[1,2]    0  0    0     0          0     NaN    NaN
D_m1_id[2,2]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

$m4e

Bayesian multinomial logit mixed model fitted with JointAI

Call:
mlogitmm_imp(fixed = m1 ~ C1 + log(time) + I(time^2) + p1, data = longDF, 
    random = ~1 | id, n.adapt = 5, n.iter = 10, shrinkage = "ridge", 
    seed = 2020, warn = FALSE, mess = FALSE)


Posterior summary:
                 Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
m1B: (Intercept)    0  0    0     0          0     NaN    NaN
m1B: C1             0  0    0     0          0     NaN    NaN
m1C: (Intercept)    0  0    0     0          0     NaN    NaN
m1C: C1             0  0    0     0          0     NaN    NaN
m1B: log(time)      0  0    0     0          0     NaN    NaN
m1B: I(time^2)      0  0    0     0          0     NaN    NaN
m1B: p1             0  0    0     0          0     NaN    NaN
m1C: log(time)      0  0    0     0          0     NaN    NaN
m1C: I(time^2)      0  0    0     0          0     NaN    NaN
m1C: p1             0  0    0     0          0     NaN    NaN

Posterior summary of random effects covariance matrix:
             Mean SD 2.5% 97.5% tail-prob. GR-crit MCE/SD
D_m1_id[1,1]    0  0    0     0                NaN    NaN


MCMC settings:
Iterations = 6:15
Sample size per chain = 10 
Thinning interval = 1 
Number of chains = 3 

Number of observations: 329 
Number of groups:
 - id: 100

