1 Preparing for analysis

Required Packages:

library(tidyverse)
library(corrplot)
library(BayesFM)
library(hablar)
library(blavaan)

Read the data from our behavioral stability dataset, remove columns with session information, and transform integer variables into numeric variables (which is required by the BayesFM package). This also randomly removes 3 participants whose first session was prompt S to correct counterbalancing.

df <- read_csv("by_token_estimates.csv")

# Remove 3 participants for which session_no 1 was prompt S at random
set.seed(365)
rnd_subs <- filter(df, session_no == "1", prompt == "S") %>% 
  pull(participant) %>% factor() %>% levels() %>% 
  sample(3)

df <- df %>% filter(!(participant %in% rnd_subs))  %>%
  mutate(across(participant, factor))

# Check counterbalancing
count(df, session_no, prompt)
## # A tibble: 9 × 3
##   session_no prompt     n
##        <dbl> <chr>  <int>
## 1          1 A         10
## 2          1 G         10
## 3          1 S         10
## 4          2 A         10
## 5          2 G         10
## 6          2 S         10
## 7          3 A         10
## 8          3 G         10
## 9          3 S         10
df <- df %>% 
  select(-c(token, prompt, session_no, participant)) %>% 
  mutate(across(c(starts_with("n_"), starts_with("len_")), ~log(.+1)),
         across(starts_with("prop_"), brms::logit_scaled),
         across(where(is.numeric), ~scale(.)[,1])) 

Create a correlation matrix for the variables in the dataset: (very ugly and unreadable right now. Need to figure out how to adjust that)

cor_stability <- cor(df)
corrplot::corrplot.mixed(corr = cor_stability, 
                         upper = "ellipse", 
                         order = "hclust")

2 Split the sample for exploratory factor analysis and confirmatory factor analysis

We want 45 sessions for exploratory factor analysis. Then we will check the factor loadings, ensure that they make sense, and then confirm that the other half of the data has the same factor structure through confirmatory factor analysis.

n <- 2
list_dfs <- split(df, factor(sort(rank(row.names(df))%%n)))

df.efa <- list_dfs[[1]]
df.cfa <- list_dfs[[2]]

3 Set factor-indicator parameters

Select Nid (Minimum number of manifest variables dedicated to each latent factor for identification.) and Kmax (Maximum number of latent factors):

Nid <- 2
# Kmax <- trunc(x = ncol(df)/Nid); Kmax # This is the default formula for Kmax, but I am going to manually set it to 5 because that's what we believe should be the actual maximum number of factors for this data.
Kmax <- 5

4 Simulate prior distribution of factor correlation matrix

set.seed(823)  # this is a random number generator seed. Setting it to a given number makes results reproducible.
simul.R.prior_df.efa <- simul.R.prior(
  Kmax = Kmax,
  nu0 = Kmax + c(1, 2, 5, 7, 10)
)
## simulating prior for nu0 = 6 and S0 = 1 
## simulating prior for nu0 = 7 and S0 = 1 
## simulating prior for nu0 = 10 and S0 = 1 
## simulating prior for nu0 = 12 and S0 = 1 
## simulating prior for nu0 = 15 and S0 = 1
simul.R.prior_df.efa
## sample from prior distribution of factor correlation matrix
## 
## call:
##   simul.R.prior(Kmax = Kmax, nu0 = Kmax + c(1, 2, 5, 7, 10))
## 
## Kmax = 5 
## 
## parameter values:
##   nu0 = 6, S0 = 1
##   nu0 = 7, S0 = 1
##   nu0 = 10, S0 = 1
##   nu0 = 12, S0 = 1
##   nu0 = 15, S0 = 1
## 
## nrep = 1e+05 
## 
## use summary() and plot() functions to summarize and plot prior density
## of maximum correlation and/or of minimum eigenvalue

We review this output to look at possible maximum correlations for each randomly generated covariance matrix for each distribution for different nu0 values:

summary(object = simul.R.prior_df.efa)
## prior distribution of correlation matrix of latent factors
## 
## maximum correlation (in absolute value):
## 
##                     mean   median      sd     min     max
## nu0 = 6, S0 = 1    0.822    0.849   0.133   0.223   1.000
## nu0 = 7, S0 = 1    0.758    0.774   0.140   0.193   1.000
## nu0 = 10, S0 = 1   0.625    0.625   0.139   0.120   0.985
## nu0 = 12, S0 = 1   0.566    0.563   0.133   0.109   0.991
## nu0 = 15, S0 = 1   0.503    0.498   0.122   0.110   0.951
## 
##                       5%     10%     25%     75%     90%     95%
## nu0 = 6, S0 = 1    0.568   0.631   0.739   0.930   0.973   0.986
## nu0 = 7, S0 = 1    0.504   0.561   0.662   0.870   0.933   0.959
## nu0 = 10, S0 = 1   0.395   0.442   0.526   0.726   0.809   0.851
## nu0 = 12, S0 = 1   0.352   0.395   0.471   0.660   0.744   0.790
## nu0 = 15, S0 = 1   0.311   0.348   0.415   0.587   0.667   0.713
## 
## minimum eigenvalue of correlation matrix:
## 
##                     mean   median      sd     min     max
## nu0 = 6, S0 = 1    0.103    0.082   0.086   0.000   0.702
## nu0 = 7, S0 = 1    0.151    0.134   0.097   0.000   0.727
## nu0 = 10, S0 = 1   0.263    0.253   0.110   0.008   0.791
## nu0 = 12, S0 = 1   0.317    0.310   0.111   0.008   0.820
## nu0 = 15, S0 = 1   0.380    0.376   0.108   0.047   0.806
## 
##                       5%     10%     25%     75%     90%     95%
## nu0 = 6, S0 = 1    0.007   0.015   0.037   0.147   0.221   0.272
## nu0 = 7, S0 = 1    0.025   0.040   0.076   0.207   0.286   0.336
## nu0 = 10, S0 = 1   0.100   0.128   0.183   0.333   0.412   0.460
## nu0 = 12, S0 = 1   0.148   0.179   0.237   0.390   0.465   0.511
## nu0 = 15, S0 = 1   0.211   0.243   0.303   0.452   0.524   0.567

Plotting this lets us look at the distributions for maximum correlation and eigenvalues. If we don’t know what to expect, we want larger variance and a central tendency closer to the middle. (For the eigenvalue plots, shorter peaks mean greater variance.)

plot(x = simul.R.prior_df.efa)

5 Simulate prior distribution of number of latent factors

simul.nfac.prior_df.efa <- BayesFM::simul.nfac.prior(
  nvar = ncol(df.efa),
  Kmax = Kmax,
  Nid = Nid,
  kappa = c(.1, .2, .5, 1)
)
simul.nfac.prior_df.efa
## sample from prior distribution of number of latent factors
## 
## call:
##   BayesFM::simul.nfac.prior(nvar = ncol(df.efa), Kmax = Kmax, Nid = Nid, 
##     kappa = c(0.1, 0.2, 0.5, 1))
## 
## nvar = 20 
## Kmax  = 5 
## Nid   = 2 
## kappa = 0.1 0.2 0.5 1 
## nrep  = 1e+06 
## 
## use summary() and plot() functions to summarize and plot
## prior distribution of number of latent factors

This gives the likelihoods of the model choosing each number of factors (1 through 11 factors) given a kappa value:

summary(object = simul.nfac.prior_df.efa)
## prior probabilities of numbers of factors:
##                   1       2       3       4       5     acc
## kappa = 0.1   0.387   0.452   0.145   0.015   0.000   0.728
## kappa = 0.2   0.164   0.439   0.319   0.073   0.005   0.604
## kappa = 0.5   0.018   0.179   0.432   0.313   0.058   0.470
## kappa = 1     0.001   0.036   0.258   0.488   0.216   0.437

Plotting these likelihoods

plot(x = simul.nfac.prior_df.efa)

6 Select prior parameters by looking at the priors

Nid <- 2
Kmax <- 5 # selected from what we believe to be a reasonable amount of reduction for this data with 20 variables
nu0 <- 15  #chosen from the plotted values that looked "best" from line 31
kappa <- .5

simul.R.prior_df.efa <- BayesFM::simul.R.prior(
  Kmax = Kmax,
  nu0 = nu0
)
## simulating prior for nu0 = 15 and S0 = 1
simul.R.prior_df.efa
## sample from prior distribution of factor correlation matrix
## 
## call:
##   BayesFM::simul.R.prior(Kmax = Kmax, nu0 = nu0)
## 
## Kmax = 5 
## 
## parameter values:
##   nu0 = 15, S0 = 1
## 
## nrep = 1e+05 
## 
## use summary() and plot() functions to summarize and plot prior density
## of maximum correlation and/or of minimum eigenvalue

Plotting with just the selected parameters. This is what we assume to be the distribution prior to looking at the data:

plot(x = simul.R.prior_df.efa)

Prior probabilities for the number of factors:

simul.nfac.prior_df.efa <- BayesFM::simul.nfac.prior(
  nvar = ncol(df),
  Kmax = Kmax,
  Nid = Nid,
  kappa = kappa
)

#simul.nfac.prior_df

summary(object = simul.nfac.prior_df.efa)
## prior probabilities of numbers of factors:
##                   1       2       3       4       5    acc
## kappa = 0.5   0.018   0.179   0.433   0.313   0.057   0.47

7 Performing Bayesian Exploratory Factor Analysis (using selected priors from above analyses)

befa_stability <- BayesFM::befa(
  model = df.efa,
  burnin = 5000,
  iter = 50000,
  Nid = Nid,
  Kmax = Kmax,
  nu0 = nu0,
  kappa = kappa,
  kappa0 = 0.5,
  xi0 = 0.5
)
## starting MCMC sampling...
##     5%
## done with burn-in period
##    10%
##    15%
##    20%
##    25%
##    30%
##    35%
##    40%
##    45%
##    50%
##    55%
##    60%
##    65%
##    70%
##    75%
##    80%
##    85%
##    90%
##    95%
##   100%
## done with sampling!
befa_stability <- BayesFM::post.column.switch(
  mcmc = befa_stability
)

befa_stability <- BayesFM::post.sign.switch(
  mcmc = befa_stability
)

Summary and plot

summary(object = befa_stability)
## BEFA - Bayesian Exploratory Factor Analysis
## Summary of posterior results
## 
## Maximum number of factors (Kmax) = 5 
## Identification restriction (Nid) = 2 
## 
## MCMC iterations = 50000 
## burn-in period  = 5000 
## 
## Metropolis-Hastings acceptance rate = 0.897
## 
## Posterior frequency of number of latent factors:
##   K =  4     70.68%
##   K =  5     29.12%
## 
## -----------------------------------------------------------------
## Model parameters
## 
## Factor loadings:
## 
##                                                  dedic    prob     mean      sd
## alpha:n_major_block                                  1   0.897    0.562   0.253
## alpha:n_jumps                                        1   0.707    0.862   0.183
## alpha:n_edges                                        1   0.707    0.874   0.174
## alpha:n_sustained_reading                            1   0.958    0.621   0.115
## alpha:prop_edits_before_sentence                     2   0.698   -0.724   0.156
## alpha:prop_edits_before_word                         2   0.699   -0.881   0.113
## alpha:prop_edits_within_word                         2   0.699   -0.829   0.106
## alpha:prop_lookbacks_before_sentence                 3   0.701    0.769   0.131
## alpha:prop_lookbacks_before_word                     3   0.701    0.793   0.110
## alpha:prop_lookbacks_within_word                     3   0.701    0.730   0.116
## alpha:len_nonlookbacks                               3   0.701   -0.839   0.104
## alpha:len_prodseq                                    2   0.699    0.737   0.133
## alpha:lookback_duration                              0   0.910                 
## alpha:prob_long_lookback_duration                    4   0.357    0.519   0.188
## alpha:short_event_duration_before_sentence           4   0.419    0.523   0.185
## alpha:short_event_duration_before_word               4   0.698    0.891   0.170
## alpha:short_event_duration_within_word               4   0.699    0.900   0.170
## alpha:prob_long_event_duration_before_sentence       0   0.913                 
## alpha:prob_long_event_duration_before_word           0   0.808                 
## alpha:prob_long_event_duration_within_word           0   0.862                 
##                                                   [ 95%    hpd ]
## alpha:n_major_block                               0.231    0.992
## alpha:n_jumps                                     0.632    1.135
## alpha:n_edges                                     0.673    1.125
## alpha:n_sustained_reading                         0.398    0.846
## alpha:prop_edits_before_sentence                 -1.028   -0.416
## alpha:prop_edits_before_word                     -1.109   -0.673
## alpha:prop_edits_within_word                     -1.042   -0.631
## alpha:prop_lookbacks_before_sentence              0.520    1.035
## alpha:prop_lookbacks_before_word                  0.583    1.011
## alpha:prop_lookbacks_within_word                  0.506    0.959
## alpha:len_nonlookbacks                           -1.054   -0.650
## alpha:len_prodseq                                 0.477    0.999
## alpha:lookback_duration                                         
## alpha:prob_long_lookback_duration                 0.193    0.848
## alpha:short_event_duration_before_sentence        0.189    0.882
## alpha:short_event_duration_before_word            0.567    1.230
## alpha:short_event_duration_within_word            0.575    1.243
## alpha:prob_long_event_duration_before_sentence                  
## alpha:prob_long_event_duration_before_word                      
## alpha:prob_long_event_duration_within_word                      
## 
## Idiosyncratic variances:
## 
##                                                   mean      sd   [ 95%   hpd ]
## sigma:n_major_block                              0.830   0.231   0.425   1.331
## sigma:n_jumps                                    0.251   0.080   0.115   0.411
## sigma:n_edges                                    0.164   0.049   0.081   0.261
## sigma:n_sustained_reading                        0.293   0.099   0.101   0.469
## sigma:prop_edits_before_sentence                 0.728   0.165   0.444   1.061
## sigma:prop_edits_before_word                     0.154   0.043   0.080   0.240
## sigma:prop_edits_within_word                     0.138   0.037   0.074   0.211
## sigma:prop_lookbacks_before_sentence             0.401   0.093   0.239   0.590
## sigma:prop_lookbacks_before_word                 0.178   0.047   0.096   0.270
## sigma:prop_lookbacks_within_word                 0.267   0.065   0.150   0.394
## sigma:len_nonlookbacks                           0.106   0.028   0.059   0.161
## sigma:len_prodseq                                0.456   0.106   0.273   0.670
## sigma:lookback_duration                          0.636   0.133   0.409   0.907
## sigma:prob_long_lookback_duration                0.706   0.186   0.386   1.090
## sigma:short_event_duration_before_sentence       0.907   0.241   0.492   1.387
## sigma:short_event_duration_before_word           0.495   0.192   0.154   0.847
## sigma:short_event_duration_within_word           0.488   0.195   0.145   0.849
## sigma:prob_long_event_duration_before_sentence   0.913   0.194   0.576   1.301
## sigma:prob_long_event_duration_before_word       0.999   0.219   0.617   1.452
## sigma:prob_long_event_duration_within_word       1.143   0.244   0.724   1.642
## 
## Factor correlation matrix:
## 
##           mean      sd    [ 95%    hpd ]
## R:1:2   -0.363   0.211   -0.782   -0.031
## R:1:3    0.030   0.187   -0.361    0.360
## R:1:4    0.058   0.272   -0.570    0.499
## R:1:5    0.006   0.258   -0.495    0.506
## R:2:3    0.167   0.178   -0.165    0.516
## R:2:4    0.140   0.177   -0.202    0.472
## R:2:5   -0.007   0.262   -0.513    0.496
## R:3:4   -0.032   0.160   -0.340    0.280
## R:3:5    0.012   0.252   -0.462    0.493
## R:4:5    0.010   0.240   -0.480    0.477
plot(x = befa_stability)

## Press <Enter> to show next graph...

## Press <Enter> to show next graph...

## Press <Enter> to show next graph...

## Press <Enter> to show next graph...

8 Running Bayesian Exploratory Factor Analysis using all defaults

b1 <- befa(df.efa)
## starting MCMC sampling...
##     5%
## done with burn-in period
##    10%
##    15%
##    20%
##    25%
##    30%
##    35%
##    40%
##    45%
##    50%
##    55%
##    60%
##    65%
##    70%
##    75%
##    80%
##    85%
##    90%
##    95%
##   100%
## done with sampling!
b1 <- BayesFM::post.column.switch(
  mcmc = b1
)

b1 <- BayesFM::post.sign.switch(
  mcmc = b1
)

summary(object = b1)
## BEFA - Bayesian Exploratory Factor Analysis
## Summary of posterior results
## 
## Maximum number of factors (Kmax) = 6 
## Identification restriction (Nid) = 3 
## 
## MCMC iterations = 10000 
## burn-in period  = 1000 
## 
## Metropolis-Hastings acceptance rate = 0.523
## 
## Posterior frequency of number of latent factors:
##   K =  4     97.84%
## 
## -----------------------------------------------------------------
## Model parameters
## 
## Factor loadings:
## 
##                                                  dedic    prob     mean      sd
## alpha:n_major_block                                  1   0.723    0.559   0.196
## alpha:n_jumps                                        1   0.971    0.886   0.131
## alpha:n_edges                                        1   0.971    0.894   0.118
## alpha:n_sustained_reading                            1   0.982    0.605   0.117
## alpha:prop_edits_before_sentence                     2   0.966    0.736   0.159
## alpha:prop_edits_before_word                         2   0.970    0.895   0.115
## alpha:prop_edits_within_word                         2   0.970    0.842   0.110
## alpha:prop_lookbacks_before_sentence                 3   0.972    0.780   0.137
## alpha:prop_lookbacks_before_word                     3   0.972    0.801   0.114
## alpha:prop_lookbacks_within_word                     3   0.972    0.736   0.117
## alpha:len_nonlookbacks                               3   0.972   -0.850   0.109
## alpha:len_prodseq                                    2   0.970   -0.757   0.139
## alpha:lookback_duration                              0   0.952                 
## alpha:prob_long_lookback_duration                    4   0.705    0.539   0.157
## alpha:short_event_duration_before_sentence           4   0.580    0.526   0.169
## alpha:short_event_duration_before_word               4   0.963    0.888   0.175
## alpha:short_event_duration_within_word               4   0.963    0.905   0.170
## alpha:prob_long_event_duration_before_sentence       0   0.957                 
## alpha:prob_long_event_duration_before_word           0   0.900                 
## alpha:prob_long_event_duration_within_word           0   0.921                 
##                                                   [ 95%    hpd ]
## alpha:n_major_block                               0.227    0.917
## alpha:n_jumps                                     0.628    1.144
## alpha:n_edges                                     0.668    1.124
## alpha:n_sustained_reading                         0.383    0.840
## alpha:prop_edits_before_sentence                  0.456    1.078
## alpha:prop_edits_before_word                      0.694    1.139
## alpha:prop_edits_within_word                      0.633    1.056
## alpha:prop_lookbacks_before_sentence              0.537    1.071
## alpha:prop_lookbacks_before_word                  0.593    1.031
## alpha:prop_lookbacks_within_word                  0.518    0.973
## alpha:len_nonlookbacks                           -1.059   -0.640
## alpha:len_prodseq                                -1.046   -0.505
## alpha:lookback_duration                                         
## alpha:prob_long_lookback_duration                 0.243    0.855
## alpha:short_event_duration_before_sentence        0.182    0.834
## alpha:short_event_duration_before_word            0.546    1.233
## alpha:short_event_duration_within_word            0.564    1.222
## alpha:prob_long_event_duration_before_sentence                  
## alpha:prob_long_event_duration_before_word                      
## alpha:prob_long_event_duration_within_word                      
## 
## Idiosyncratic variances:
## 
##                                                   mean      sd   [ 95%   hpd ]
## sigma:n_major_block                              0.927   0.248   0.495   1.411
## sigma:n_jumps                                    0.261   0.078   0.128   0.422
## sigma:n_edges                                    0.164   0.048   0.081   0.259
## sigma:n_sustained_reading                        0.332   0.083   0.193   0.519
## sigma:prop_edits_before_sentence                 0.726   0.167   0.451   1.058
## sigma:prop_edits_before_word                     0.155   0.043   0.086   0.246
## sigma:prop_edits_within_word                     0.141   0.038   0.075   0.215
## sigma:prop_lookbacks_before_sentence             0.401   0.094   0.239   0.590
## sigma:prop_lookbacks_before_word                 0.179   0.047   0.093   0.268
## sigma:prop_lookbacks_within_word                 0.269   0.066   0.152   0.401
## sigma:len_nonlookbacks                           0.107   0.028   0.058   0.162
## sigma:len_prodseq                                0.455   0.105   0.267   0.658
## sigma:lookback_duration                          0.639   0.136   0.399   0.899
## sigma:prob_long_lookback_duration                0.689   0.187   0.367   1.082
## sigma:short_event_duration_before_sentence       0.912   0.238   0.517   1.410
## sigma:short_event_duration_before_word           0.526   0.216   0.148   0.956
## sigma:short_event_duration_within_word           0.511   0.219   0.147   0.916
## sigma:prob_long_event_duration_before_sentence   0.916   0.192   0.574   1.298
## sigma:prob_long_event_duration_before_word       1.012   0.217   0.640   1.443
## sigma:prob_long_event_duration_within_word       1.156   0.246   0.734   1.662
## 
## Factor correlation matrix:
## 
##           mean      sd    [ 95%   hpd ]
## R:1:2    0.355   0.156    0.059   0.660
## R:1:3    0.118   0.158   -0.198   0.408
## R:1:4    0.162   0.177   -0.193   0.499
## R:1:5   -0.004   0.399   -0.754   0.714
## R:1:6    0.000   0.399   -0.737   0.730
## R:2:3   -0.111   0.167   -0.421   0.216
## R:2:4   -0.237   0.167   -0.558   0.073
## R:2:5    0.005   0.410   -0.759   0.750
## R:2:6    0.008   0.407   -0.777   0.727
## R:3:4   -0.052   0.170   -0.380   0.299
## R:3:5    0.024   0.368   -0.729   0.702
## R:3:6    0.003   0.369   -0.697   0.716
## R:4:5   -0.011   0.389   -0.725   0.706
## R:4:6   -0.007   0.379   -0.740   0.690
## R:5:6   -0.008   0.460   -0.802   0.820

Plot using defaults

plot(x = b1)

## Press <Enter> to show next graph...

## Press <Enter> to show next graph...

## Press <Enter> to show next graph...

## Press <Enter> to show next graph...

Get the most popular factor allocation and loadings using defaults

summary(b1, hpd.prob = .95)$alpha %>% 
  round(2) %>% 
  rownames_to_column("measure") %>% 
  mutate(loading = paste0(mean," [",hpd.lo,", ",hpd.up,"]")
         , measure = str_remove(measure,"alpha:")) %>% 
  select(measure, "factor" = dedic, loading) %>% 
  arrange(factor) %>% 
  knitr::kable()
measure factor loading
lookback_duration 0 NA [NA, NA]
prob_long_event_duration_before_sentence 0 NA [NA, NA]
prob_long_event_duration_before_word 0 NA [NA, NA]
prob_long_event_duration_within_word 0 NA [NA, NA]
n_major_block 1 0.56 [0.23, 0.92]
n_jumps 1 0.89 [0.63, 1.14]
n_edges 1 0.89 [0.67, 1.12]
n_sustained_reading 1 0.6 [0.38, 0.84]
prop_edits_before_sentence 2 0.74 [0.46, 1.08]
prop_edits_before_word 2 0.9 [0.69, 1.14]
prop_edits_within_word 2 0.84 [0.63, 1.06]
len_prodseq 2 -0.76 [-1.05, -0.5]
prop_lookbacks_before_sentence 3 0.78 [0.54, 1.07]
prop_lookbacks_before_word 3 0.8 [0.59, 1.03]
prop_lookbacks_within_word 3 0.74 [0.52, 0.97]
len_nonlookbacks 3 -0.85 [-1.06, -0.64]
prob_long_lookback_duration 4 0.54 [0.24, 0.85]
short_event_duration_before_sentence 4 0.53 [0.18, 0.83]
short_event_duration_before_word 4 0.89 [0.55, 1.23]
short_event_duration_within_word 4 0.9 [0.56, 1.22]

Correlations among all factors using defaults

summary(b1)$R %>% 
  round(2) %>% 
  rownames_to_column("factors") %>% 
  mutate(correlation = paste0(mean," [",hpd.lo,", ",hpd.up,"]")
         , factors = str_remove(factors,"R:")) %>% 
  select(factors, correlation) %>% 
  knitr::kable()
factors correlation
1:2 0.35 [0.06, 0.66]
1:3 0.12 [-0.2, 0.41]
1:4 0.16 [-0.19, 0.5]
1:5 0 [-0.75, 0.71]
1:6 0 [-0.74, 0.73]
2:3 -0.11 [-0.42, 0.22]
2:4 -0.24 [-0.56, 0.07]
2:5 0 [-0.76, 0.75]
2:6 0.01 [-0.78, 0.73]
3:4 -0.05 [-0.38, 0.3]
3:5 0.02 [-0.73, 0.7]
3:6 0 [-0.7, 0.72]
4:5 -0.01 [-0.72, 0.71]
4:6 -0.01 [-0.74, 0.69]
5:6 -0.01 [-0.8, 0.82]

9 Performing Bayesian Confirmatory Factor Analysis

Above, we performed exploratory factor analysis on half of the data. That allowed us to identify factors as they emerged from the data. Now, we will check to confirm that these factors would fit the second half of the data.

path <- '
f1 =~ n_major_block + n_jumps + n_edges + n_sustained_reading
f2 =~ prop_edits_before_sentence + prop_edits_before_word + prop_edits_within_word + len_prodseq
f3 =~ prop_lookbacks_before_sentence + prop_lookbacks_before_word + prop_lookbacks_within_word + len_nonlookbacks
f4 =~ prob_long_lookback_duration + short_event_duration_before_sentence + short_event_duration_before_word + short_event_duration_within_word
'


# fit the model and output the results
cfamodel <- blavaan(path, data=df.cfa, auto.var=TRUE, auto.fix.first=TRUE, auto.cov.lv.x=TRUE)
## 
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 1).
## Chain 1: 
## Chain 1: Gradient evaluation took 0.001332 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 13.32 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1: 
## Chain 1: 
## Chain 1: Iteration:    1 / 1500 [  0%]  (Warmup)
## Chain 1: Iteration:  150 / 1500 [ 10%]  (Warmup)
## Chain 1: Iteration:  300 / 1500 [ 20%]  (Warmup)
## Chain 1: Iteration:  450 / 1500 [ 30%]  (Warmup)
## Chain 1: Iteration:  501 / 1500 [ 33%]  (Sampling)
## Chain 1: Iteration:  650 / 1500 [ 43%]  (Sampling)
## Chain 1: Iteration:  800 / 1500 [ 53%]  (Sampling)
## Chain 1: Iteration:  950 / 1500 [ 63%]  (Sampling)
## Chain 1: Iteration: 1100 / 1500 [ 73%]  (Sampling)
## Chain 1: Iteration: 1250 / 1500 [ 83%]  (Sampling)
## Chain 1: Iteration: 1400 / 1500 [ 93%]  (Sampling)
## Chain 1: Iteration: 1500 / 1500 [100%]  (Sampling)
## Chain 1: 
## Chain 1:  Elapsed Time: 53.724 seconds (Warm-up)
## Chain 1:                96.7796 seconds (Sampling)
## Chain 1:                150.504 seconds (Total)
## Chain 1: 
## 
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 2).
## Chain 2: 
## Chain 2: Gradient evaluation took 0.000593 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 5.93 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2: 
## Chain 2: 
## Chain 2: Iteration:    1 / 1500 [  0%]  (Warmup)
## Chain 2: Iteration:  150 / 1500 [ 10%]  (Warmup)
## Chain 2: Iteration:  300 / 1500 [ 20%]  (Warmup)
## Chain 2: Iteration:  450 / 1500 [ 30%]  (Warmup)
## Chain 2: Iteration:  501 / 1500 [ 33%]  (Sampling)
## Chain 2: Iteration:  650 / 1500 [ 43%]  (Sampling)
## Chain 2: Iteration:  800 / 1500 [ 53%]  (Sampling)
## Chain 2: Iteration:  950 / 1500 [ 63%]  (Sampling)
## Chain 2: Iteration: 1100 / 1500 [ 73%]  (Sampling)
## Chain 2: Iteration: 1250 / 1500 [ 83%]  (Sampling)
## Chain 2: Iteration: 1400 / 1500 [ 93%]  (Sampling)
## Chain 2: Iteration: 1500 / 1500 [100%]  (Sampling)
## Chain 2: 
## Chain 2:  Elapsed Time: 41.1072 seconds (Warm-up)
## Chain 2:                78.9646 seconds (Sampling)
## Chain 2:                120.072 seconds (Total)
## Chain 2: 
## 
## SAMPLING FOR MODEL 'stanmarg' NOW (CHAIN 3).
## Chain 3: 
## Chain 3: Gradient evaluation took 0.001119 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 11.19 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3: 
## Chain 3: 
## Chain 3: Iteration:    1 / 1500 [  0%]  (Warmup)
## Chain 3: Iteration:  150 / 1500 [ 10%]  (Warmup)
## Chain 3: Iteration:  300 / 1500 [ 20%]  (Warmup)
## Chain 3: Iteration:  450 / 1500 [ 30%]  (Warmup)
## Chain 3: Iteration:  501 / 1500 [ 33%]  (Sampling)
## Chain 3: Iteration:  650 / 1500 [ 43%]  (Sampling)
## Chain 3: Iteration:  800 / 1500 [ 53%]  (Sampling)
## Chain 3: Iteration:  950 / 1500 [ 63%]  (Sampling)
## Chain 3: Iteration: 1100 / 1500 [ 73%]  (Sampling)
## Chain 3: Iteration: 1250 / 1500 [ 83%]  (Sampling)
## Chain 3: Iteration: 1400 / 1500 [ 93%]  (Sampling)
## Chain 3: Iteration: 1500 / 1500 [100%]  (Sampling)
## Chain 3: 
## Chain 3:  Elapsed Time: 39.6377 seconds (Warm-up)
## Chain 3:                45.913 seconds (Sampling)
## Chain 3:                85.5508 seconds (Total)
## Chain 3: 
## Computing posterior predictives...
summary(cfamodel, fit.measures=TRUE)
## ** WARNING ** blavaan (0.4-3) did NOT converge after 500 adapt+burnin iterations
## ** WARNING ** Proceed with caution
## 
##   Number of observations                            45
## 
##   Number of missing patterns                         1
## 
##   Statistic                                 MargLogLik         PPP
##   Value                                       -936.178       0.000
## 
## Latent Variables:
##                    Estimate  Post.SD pi.lower pi.upper     Rhat    Prior       
##   f1 =~                                                                        
##     n_major_block     1.000                                                    
##     n_jumps           2.601    1.333    1.428    6.166    1.014    normal(0,10)
##     n_edges           2.646    1.343    1.449    6.419    1.013    normal(0,10)
##     n_sustand_rdng    1.759    0.992    0.732    4.453    1.012    normal(0,10)
##   f2 =~                                                                        
##     prp_dts_bfr_sn    1.000                                                    
##     prp_dts_bfr_wr    4.972    2.725    1.993   12.359    1.005    normal(0,10)
##     prp_dts_wthn_w    5.441    2.990    2.181   13.557    1.005    normal(0,10)
##     len_prodseq      -4.009    2.248  -10.185   -1.525    1.005    normal(0,10)
##   f3 =~                                                                        
##     prp_lkbcks_bf_    1.000                                                    
##     prp_lkbcks_bf_   -3.228    6.710  -17.988    1.643    3.426    normal(0,10)
##     prp_lkbcks_wt_   -3.256    6.759  -18.079    1.637    3.475    normal(0,10)
##     len_nonlokbcks    3.596    7.436   -1.760   19.883    3.497    normal(0,10)
##   f4 =~                                                                        
##     prb_lng_lkbck_    1.000                                                    
##     shrt_vnt_drt__    0.951    2.571   -3.896    6.588    1.000    normal(0,10)
##     shrt_vnt_drt__    8.051    3.967    2.250   17.169    1.001    normal(0,10)
##     shrt_vnt_drt__   10.051    4.794    2.902   21.091    1.002    normal(0,10)
## 
## Covariances:
##                    Estimate  Post.SD pi.lower pi.upper     Rhat    Prior       
##   f1 ~~                                                                        
##     f2                0.052    0.037    0.007    0.147    1.001     lkj_corr(1)
##     f3                0.053    0.072   -0.029    0.224    1.320     lkj_corr(1)
##     f4               -0.001    0.009   -0.019    0.017    1.000     lkj_corr(1)
##   f2 ~~                                                                        
##     f3                0.041    0.052   -0.018    0.174    1.394     lkj_corr(1)
##     f4               -0.011    0.010   -0.037   -0.002    1.000     lkj_corr(1)
##   f3 ~~                                                                        
##     f4                0.003    0.014   -0.023    0.035    1.014     lkj_corr(1)
## 
## Intercepts:
##                    Estimate  Post.SD pi.lower pi.upper     Rhat    Prior       
##    .n_major_block     0.000                                                    
##    .n_jumps           0.000                                                    
##    .n_edges           0.000                                                    
##    .n_sustand_rdng    0.000                                                    
##    .prp_dts_bfr_sn    0.000                                                    
##    .prp_dts_bfr_wr    0.000                                                    
##    .prp_dts_wthn_w    0.000                                                    
##    .len_prodseq       0.000                                                    
##    .prp_lkbcks_bf_    0.000                                                    
##    .prp_lkbcks_bf_    0.000                                                    
##    .prp_lkbcks_wt_    0.000                                                    
##    .len_nonlokbcks    0.000                                                    
##    .prb_lng_lkbck_    0.000                                                    
##    .shrt_vnt_drt__    0.000                                                    
##    .shrt_vnt_drt__    0.000                                                    
##    .shrt_vnt_drt__    0.000                                                    
##     f1                0.000                                                    
##     f2                0.000                                                    
##     f3                0.000                                                    
##     f4                0.000                                                    
## 
## Variances:
##                    Estimate  Post.SD pi.lower pi.upper     Rhat    Prior       
##    .n_major_block     0.595    0.137    0.377    0.918    1.003 gamma(1,.5)[sd]
##    .n_jumps           0.024    0.026    0.000    0.092    1.004 gamma(1,.5)[sd]
##    .n_edges           0.083    0.033    0.013    0.148    1.001 gamma(1,.5)[sd]
##    .n_sustand_rdng    0.953    0.215    0.620    1.439    1.000 gamma(1,.5)[sd]
##    .prp_dts_bfr_sn    0.673    0.154    0.438    1.026    1.000 gamma(1,.5)[sd]
##    .prp_dts_bfr_wr    0.116    0.034    0.054    0.192    1.000 gamma(1,.5)[sd]
##    .prp_dts_wthn_w    0.022    0.026    0.000    0.094    1.000 gamma(1,.5)[sd]
##    .len_prodseq       0.400    0.092    0.257    0.620    0.999 gamma(1,.5)[sd]
##    .prp_lkbcks_bf_    0.679    0.471    0.251    1.726    2.759 gamma(1,.5)[sd]
##    .prp_lkbcks_bf_    0.243    0.054    0.157    0.367    1.000 gamma(1,.5)[sd]
##    .prp_lkbcks_wt_    0.216    0.050    0.138    0.337    1.000 gamma(1,.5)[sd]
##    .len_nonlokbcks    0.006    0.008    0.000    0.031    1.002 gamma(1,.5)[sd]
##    .prb_lng_lkbck_    1.132    0.244    0.740    1.703    0.999 gamma(1,.5)[sd]
##    .shrt_vnt_drt__    0.980    0.219    0.645    1.510    0.999 gamma(1,.5)[sd]
##    .shrt_vnt_drt__    0.425    0.158    0.100    0.750    1.002 gamma(1,.5)[sd]
##    .shrt_vnt_drt__    0.223    0.168    0.002    0.592    1.003 gamma(1,.5)[sd]
##     f1                0.237    0.144    0.026    0.583    1.002 gamma(1,.5)[sd]
##     f2                0.084    0.076    0.007    0.285    1.000 gamma(1,.5)[sd]
##     f3                0.497    0.397    0.003    1.245    2.168 gamma(1,.5)[sd]
##     f4                0.012    0.017    0.001    0.061    1.000 gamma(1,.5)[sd]
coef(cfamodel)
##                                                                f1=~n_jumps 
##                                                                      2.601 
##                                                                f1=~n_edges 
##                                                                      2.646 
##                                                    f1=~n_sustained_reading 
##                                                                      1.759 
##                                                 f2=~prop_edits_before_word 
##                                                                      4.972 
##                                                 f2=~prop_edits_within_word 
##                                                                      5.441 
##                                                            f2=~len_prodseq 
##                                                                     -4.009 
##                                             f3=~prop_lookbacks_before_word 
##                                                                     -3.228 
##                                             f3=~prop_lookbacks_within_word 
##                                                                     -3.256 
##                                                       f3=~len_nonlookbacks 
##                                                                      3.596 
##                                   f4=~short_event_duration_before_sentence 
##                                                                      0.951 
##                                       f4=~short_event_duration_before_word 
##                                                                      8.051 
##                                       f4=~short_event_duration_within_word 
##                                                                     10.051 
##                                               n_major_block~~n_major_block 
##                                                                      0.595 
##                                                           n_jumps~~n_jumps 
##                                                                      0.024 
##                                                           n_edges~~n_edges 
##                                                                      0.083 
##                                   n_sustained_reading~~n_sustained_reading 
##                                                                      0.953 
##                     prop_edits_before_sentence~~prop_edits_before_sentence 
##                                                                      0.673 
##                             prop_edits_before_word~~prop_edits_before_word 
##                                                                      0.116 
##                             prop_edits_within_word~~prop_edits_within_word 
##                                                                      0.022 
##                                                   len_prodseq~~len_prodseq 
##                                                                      0.400 
##             prop_lookbacks_before_sentence~~prop_lookbacks_before_sentence 
##                                                                      0.679 
##                     prop_lookbacks_before_word~~prop_lookbacks_before_word 
##                                                                      0.243 
##                     prop_lookbacks_within_word~~prop_lookbacks_within_word 
##                                                                      0.216 
##                                         len_nonlookbacks~~len_nonlookbacks 
##                                                                      0.006 
##                   prob_long_lookback_duration~~prob_long_lookback_duration 
##                                                                      1.132 
## short_event_duration_before_sentence~~short_event_duration_before_sentence 
##                                                                      0.980 
##         short_event_duration_before_word~~short_event_duration_before_word 
##                                                                      0.425 
##         short_event_duration_within_word~~short_event_duration_within_word 
##                                                                      0.223 
##                                                                     f1~~f1 
##                                                                      0.237 
##                                                                     f2~~f2 
##                                                                      0.084 
##                                                                     f3~~f3 
##                                                                      0.497 
##                                                                     f4~~f4 
##                                                                      0.012 
##                                                                     f1~~f2 
##                                                                      0.052 
##                                                                     f1~~f3 
##                                                                      0.053 
##                                                                     f1~~f4 
##                                                                     -0.001 
##                                                                     f2~~f3 
##                                                                      0.041 
##                                                                     f2~~f4 
##                                                                     -0.011 
##                                                                     f3~~f4 
##                                                                      0.003