Bayesian Modeling

Weakly informative priors were specified to regularize parameter estimates while remaining permissive of theoretically plausible effects. Regression coefficients were assigned normal priors centered at zero with standard deviation 0.5, reflecting the expectation that most effects would be small to moderate in magnitude while discouraging implausibly large estimates. Intercepts were assigned Student-t priors with 3 degrees of freedom, centered at zero with scale 2.5, providing robust regularization with heavier tails. These priors were selected to improve estimation stability given the modest sample size and correlated predictors.

## Running /Library/Frameworks/R.framework/Resources/bin/R CMD SHLIB foo.c
## using C compiler: ‘Apple clang version 17.0.0 (clang-1700.0.13.5)’
## using SDK: ‘MacOSX15.5.sdk’
## clang -arch arm64 -I"/Library/Frameworks/R.framework/Resources/include" -DNDEBUG   -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/Rcpp/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/unsupported"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/BH/include" -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/src/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppParallel/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/rstan/include" -DEIGEN_NO_DEBUG  -DBOOST_DISABLE_ASSERTS  -DBOOST_PENDING_INTEGER_LOG2_HPP  -DSTAN_THREADS  -DUSE_STANC3 -DSTRICT_R_HEADERS  -DBOOST_PHOENIX_NO_VARIADIC_EXPRESSION  -D_HAS_AUTO_PTR_ETC=0  -include '/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/stan/math/prim/fun/Eigen.hpp'  -D_REENTRANT -DRCPP_PARALLEL_USE_TBB=1   -I/opt/R/arm64/include    -fPIC  -falign-functions=64 -Wall -g -O2  -c foo.c -o foo.o
## In file included from <built-in>:1:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/stan/math/prim/fun/Eigen.hpp:22:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/Dense:1:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/Core:19:
## /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/src/Core/util/Macros.h:679:10: fatal error: 'cmath' file not found
##   679 | #include <cmath>
##       |          ^~~~~~~
## 1 error generated.
## make: *** [foo.o] Error 1
## Running /Library/Frameworks/R.framework/Resources/bin/R CMD SHLIB foo.c
## using C compiler: ‘Apple clang version 17.0.0 (clang-1700.0.13.5)’
## using SDK: ‘MacOSX15.5.sdk’
## clang -arch arm64 -I"/Library/Frameworks/R.framework/Resources/include" -DNDEBUG   -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/Rcpp/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/unsupported"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/BH/include" -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/src/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppParallel/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/rstan/include" -DEIGEN_NO_DEBUG  -DBOOST_DISABLE_ASSERTS  -DBOOST_PENDING_INTEGER_LOG2_HPP  -DSTAN_THREADS  -DUSE_STANC3 -DSTRICT_R_HEADERS  -DBOOST_PHOENIX_NO_VARIADIC_EXPRESSION  -D_HAS_AUTO_PTR_ETC=0  -include '/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/stan/math/prim/fun/Eigen.hpp'  -D_REENTRANT -DRCPP_PARALLEL_USE_TBB=1   -I/opt/R/arm64/include    -fPIC  -falign-functions=64 -Wall -g -O2  -c foo.c -o foo.o
## In file included from <built-in>:1:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/stan/math/prim/fun/Eigen.hpp:22:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/Dense:1:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/Core:19:
## /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/src/Core/util/Macros.h:679:10: fatal error: 'cmath' file not found
##   679 | #include <cmath>
##       |          ^~~~~~~
## 1 error generated.
## make: *** [foo.o] Error 1
## / 4000 [ 80%]  (Sampling)
## Chain 4: Iteration: 3200 / 4000 [ 80%]  (Sampling)
## Chain 3: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 2: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 2: 
## Chain 2:  Elapsed Time: 0.023 seconds (Warm-up)
## Chain 2:                0.016 seconds (Sampling)
## Chain 2:                0.039 seconds (Total)
## Chain 2: 
## Chain 4: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 1: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 3: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 3: 
## Chain 3:  Elapsed Time: 0.024 seconds (Warm-up)
## Chain 3:                0.017 seconds (Sampling)
## Chain 3:                0.041 seconds (Total)
## Chain 3: 
## Chain 4: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 4: 
## Chain 4:  Elapsed Time: 0.02 seconds (Warm-up)
## Chain 4:                0.015 seconds (Sampling)
## Chain 4:                0.035 seconds (Total)
## Chain 4: 
## Chain 1: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 1: 
## Chain 1:  Elapsed Time: 0.022 seconds (Warm-up)
## Chain 1:                0.018 seconds (Sampling)
## Chain 1:                0.04 seconds (Total)
## Chain 1:
## TAN_THREADS  -DUSE_STANC3 -DSTRICT_R_HEADERS  -DBOOST_PHOENIX_NO_VARIADIC_EXPRESSION  -D_HAS_AUTO_PTR_ETC=0  -include '/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/stan/math/prim/fun/Eigen.hpp'  -D_REENTRANT -DRCPP_PARALLEL_USE_TBB=1   -I/opt/R/arm64/include    -fPIC  -falign-functions=64 -Wall -g -O2  -c foo.c -o foo.o
## In file included from <built-in>:1:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/stan/math/prim/fun/Eigen.hpp:22:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/Dense:1:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/Core:19:
## /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/src/Core/util/Macros.h:679:10: fatal error: 'cmath' file not found
##   679 | #include <cmath>
##       |          ^~~~~~~
## 1 error generated.
## make: *** [foo.o] Error 1
## 00 [ 80%]  (Sampling)
## Chain 2: Iteration: 3200 / 4000 [ 80%]  (Sampling)
## Chain 3: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 4: Iteration: 3200 / 4000 [ 80%]  (Sampling)
## Chain 1: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 3: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 3: 
## Chain 3:  Elapsed Time: 0.042 seconds (Warm-up)
## Chain 3:                0.035 seconds (Sampling)
## Chain 3:                0.077 seconds (Total)
## Chain 3: 
## Chain 2: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 4: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 1: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 1: 
## Chain 1:  Elapsed Time: 0.043 seconds (Warm-up)
## Chain 1:                0.038 seconds (Sampling)
## Chain 1:                0.081 seconds (Total)
## Chain 1: 
## Chain 2: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 2: 
## Chain 2:  Elapsed Time: 0.045 seconds (Warm-up)
## Chain 2:                0.04 seconds (Sampling)
## Chain 2:                0.085 seconds (Total)
## Chain 2: 
## Chain 4: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 4: 
## Chain 4:  Elapsed Time: 0.042 seconds (Warm-up)
## Chain 4:                0.04 seconds (Sampling)
## Chain 4:                0.082 seconds (Total)
## Chain 4:
## Output of model 'm1':
## 
## Computed from 8000 by 32 log-likelihood matrix.
## 
##          Estimate   SE
## elpd_loo    -47.2  5.5
## p_loo         5.3  2.2
## looic        94.4 11.1
## ------
## MCSE of elpd_loo is 0.1.
## MCSE and ESS estimates assume MCMC draws (r_eff in [0.6, 1.2]).
## 
## All Pareto k estimates are good (k < 0.7).
## See help('pareto-k-diagnostic') for details.
## 
## Output of model 'm2':
## 
## Computed from 8000 by 32 log-likelihood matrix.
## 
##          Estimate  SE
## elpd_loo    -42.8 4.8
## p_loo         6.5 1.7
## looic        85.6 9.6
## ------
## MCSE of elpd_loo is 0.1.
## MCSE and ESS estimates assume MCMC draws (r_eff in [0.5, 1.2]).
## 
## All Pareto k estimates are good (k < 0.7).
## See help('pareto-k-diagnostic') for details.
## 
## Output of model 'm3':
## 
## Computed from 8000 by 32 log-likelihood matrix.
## 
##          Estimate  SE
## elpd_loo    -44.4 3.9
## p_loo         8.9 1.7
## looic        88.8 7.8
## ------
## MCSE of elpd_loo is 0.1.
## MCSE and ESS estimates assume MCMC draws (r_eff in [0.5, 1.2]).
## 
## All Pareto k estimates are good (k < 0.7).
## See help('pareto-k-diagnostic') for details.
## 
## Model comparisons:
##    elpd_diff se_diff
## m2  0.0       0.0   
## m3 -1.6       2.0   
## m1 -4.4       4.4

Model comparison suggested that including CELF measures improved predictive performance relative to the cognitive measures-only model. Specifically, the model including CELF syntax variables (Model 2) demonstrated better out-of-sample predictive fit than the baseline cognitive model (Model 1; elpd_diff = -4.5, SE = 4.5). In contrast, adding LIWC language variables to the model (Model 3) produced comparatively little improvement in predictive performance relative to the CELF model alone (elpd_diff = -1.6, SE = 2.0), suggesting that discourse-level language measures did not substantially improve model generalizability beyond broader structural language ability.

These findings suggest that language ability, particularly syntactic and structural language skills, plays an important role in advanced ToM performance. At the same time, cognitive-process language features may still reflect meaningful manifestations of ToM-related reasoning, even if they do not substantially increase overall predictive accuracy when modeled alongside broader language ability.

## Running /Library/Frameworks/R.framework/Resources/bin/R CMD SHLIB foo.c
## using C compiler: ‘Apple clang version 17.0.0 (clang-1700.0.13.5)’
## using SDK: ‘MacOSX15.5.sdk’
## clang -arch arm64 -I"/Library/Frameworks/R.framework/Resources/include" -DNDEBUG   -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/Rcpp/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/unsupported"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/BH/include" -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/src/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppParallel/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/rstan/include" -DEIGEN_NO_DEBUG  -DBOOST_DISABLE_ASSERTS  -DBOOST_PENDING_INTEGER_LOG2_HPP  -DSTAN_THREADS  -DUSE_STANC3 -DSTRICT_R_HEADERS  -DBOOST_PHOENIX_NO_VARIADIC_EXPRESSION  -D_HAS_AUTO_PTR_ETC=0  -include '/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/stan/math/prim/fun/Eigen.hpp'  -D_REENTRANT -DRCPP_PARALLEL_USE_TBB=1   -I/opt/R/arm64/include    -fPIC  -falign-functions=64 -Wall -g -O2  -c foo.c -o foo.o
## In file included from <built-in>:1:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/stan/math/prim/fun/Eigen.hpp:22:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/Dense:1:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/Core:19:
## /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/src/Core/util/Macros.h:679:10: fatal error: 'cmath' file not found
##   679 | #include <cmath>
##       |          ^~~~~~~
## 1 error generated.
## make: *** [foo.o] Error 1
## Running /Library/Frameworks/R.framework/Resources/bin/R CMD SHLIB foo.c
## using C compiler: ‘Apple clang version 17.0.0 (clang-1700.0.13.5)’
## using SDK: ‘MacOSX15.5.sdk’
## clang -arch arm64 -I"/Library/Frameworks/R.framework/Resources/include" -DNDEBUG   -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/Rcpp/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/unsupported"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/BH/include" -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/src/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppParallel/include/"  -I"/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/rstan/include" -DEIGEN_NO_DEBUG  -DBOOST_DISABLE_ASSERTS  -DBOOST_PENDING_INTEGER_LOG2_HPP  -DSTAN_THREADS  -DUSE_STANC3 -DSTRICT_R_HEADERS  -DBOOST_PHOENIX_NO_VARIADIC_EXPRESSION  -D_HAS_AUTO_PTR_ETC=0  -include '/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/stan/math/prim/fun/Eigen.hpp'  -D_REENTRANT -DRCPP_PARALLEL_USE_TBB=1   -I/opt/R/arm64/include    -fPIC  -falign-functions=64 -Wall -g -O2  -c foo.c -o foo.o
## In file included from <built-in>:1:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/stan/math/prim/fun/Eigen.hpp:22:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/Dense:1:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/Core:19:
## /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/src/Core/util/Macros.h:679:10: fatal error: 'cmath' file not found
##   679 | #include <cmath>
##       |          ^~~~~~~
## 1 error generated.
## make: *** [foo.o] Error 1
## 00 [ 80%]  (Sampling)
## Chain 1: Iteration: 3200 / 4000 [ 80%]  (Sampling)
## Chain 4: Iteration: 3200 / 4000 [ 80%]  (Sampling)
## Chain 2: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 3: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 1: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 4: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 2: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 2: 
## Chain 2:  Elapsed Time: 0.047 seconds (Warm-up)
## Chain 2:                0.044 seconds (Sampling)
## Chain 2:                0.091 seconds (Total)
## Chain 2: 
## Chain 3: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 3: 
## Chain 3:  Elapsed Time: 0.049 seconds (Warm-up)
## Chain 3:                0.041 seconds (Sampling)
## Chain 3:                0.09 seconds (Total)
## Chain 3: 
## Chain 1: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 1: 
## Chain 1:  Elapsed Time: 0.051 seconds (Warm-up)
## Chain 1:                0.047 seconds (Sampling)
## Chain 1:                0.098 seconds (Total)
## Chain 1: 
## Chain 4: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 4: 
## Chain 4:  Elapsed Time: 0.048 seconds (Warm-up)
## Chain 4:                0.048 seconds (Sampling)
## Chain 4:                0.096 seconds (Total)
## Chain 4:
## TR_ETC=0  -include '/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/stan/math/prim/fun/Eigen.hpp'  -D_REENTRANT -DRCPP_PARALLEL_USE_TBB=1   -I/opt/R/arm64/include    -fPIC  -falign-functions=64 -Wall -g -O2  -c foo.c -o foo.o
## In file included from <built-in>:1:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/StanHeaders/include/stan/math/prim/fun/Eigen.hpp:22:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/Dense:1:
## In file included from /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/Core:19:
## /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/RcppEigen/include/Eigen/src/Core/util/Macros.h:679:10: fatal error: 'cmath' file not found
##   679 | #include <cmath>
##       |          ^~~~~~~
## 1 error generated.
## make: *** [foo.o] Error 1
## 4000 [ 80%]  (Sampling)
## Chain 4: Iteration: 3200 / 4000 [ 80%]  (Sampling)
## Chain 3: Iteration: 3200 / 4000 [ 80%]  (Sampling)
## Chain 1: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 1: 
## Chain 1:  Elapsed Time: 0.044 seconds (Warm-up)
## Chain 1:                0.039 seconds (Sampling)
## Chain 1:                0.083 seconds (Total)
## Chain 1: 
## Chain 2: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 4: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 3: Iteration: 3600 / 4000 [ 90%]  (Sampling)
## Chain 2: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 2: 
## Chain 2:  Elapsed Time: 0.046 seconds (Warm-up)
## Chain 2:                0.039 seconds (Sampling)
## Chain 2:                0.085 seconds (Total)
## Chain 2: 
## Chain 4: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 4: 
## Chain 4:  Elapsed Time: 0.045 seconds (Warm-up)
## Chain 4:                0.036 seconds (Sampling)
## Chain 4:                0.081 seconds (Total)
## Chain 4: 
## Chain 3: Iteration: 4000 / 4000 [100%]  (Sampling)
## Chain 3: 
## Chain 3:  Elapsed Time: 0.046 seconds (Warm-up)
## Chain 3:                0.043 seconds (Sampling)
## Chain 3:                0.089 seconds (Total)
## Chain 3:
## Output of model 'm2':
## 
## Computed from 8000 by 32 log-likelihood matrix.
## 
##          Estimate  SE
## elpd_loo    -42.8 4.8
## p_loo         6.5 1.7
## looic        85.6 9.6
## ------
## MCSE of elpd_loo is 0.1.
## MCSE and ESS estimates assume MCMC draws (r_eff in [0.5, 1.2]).
## 
## All Pareto k estimates are good (k < 0.7).
## See help('pareto-k-diagnostic') for details.
## 
## Output of model 'm_cp':
## 
## Computed from 8000 by 32 log-likelihood matrix.
## 
##          Estimate  SE
## elpd_loo    -42.2 4.4
## p_loo         7.1 1.7
## looic        84.3 8.8
## ------
## MCSE of elpd_loo is 0.1.
## MCSE and ESS estimates assume MCMC draws (r_eff in [0.5, 1.3]).
## 
## All Pareto k estimates are good (k < 0.7).
## See help('pareto-k-diagnostic') for details.
## 
## Output of model 'm_insight':
## 
## Computed from 8000 by 32 log-likelihood matrix.
## 
##          Estimate  SE
## elpd_loo    -43.9 4.7
## p_loo         7.2 1.7
## looic        87.7 9.3
## ------
## MCSE of elpd_loo is 0.1.
## MCSE and ESS estimates assume MCMC draws (r_eff in [0.5, 1.3]).
## 
## All Pareto k estimates are good (k < 0.7).
## See help('pareto-k-diagnostic') for details.
## 
## Output of model 'm_tent':
## 
## Computed from 8000 by 32 log-likelihood matrix.
## 
##          Estimate  SE
## elpd_loo    -41.7 4.4
## p_loo         6.8 1.6
## looic        83.4 8.8
## ------
## MCSE of elpd_loo is 0.1.
## MCSE and ESS estimates assume MCMC draws (r_eff in [0.5, 1.5]).
## 
## All Pareto k estimates are good (k < 0.7).
## See help('pareto-k-diagnostic') for details.
## 
## Model comparisons:
##           elpd_diff se_diff
## m_tent     0.0       0.0   
## m_cp      -0.4       1.1   
## m2        -1.1       1.2   
## m_insight -2.1       1.1

Follow-up targeted Bayesian models were conducted to examine whether LIWC language features improved prediction of ToM performance above and beyond CELF scores. Compared to the CELF-only model, models including LIWC Cognitive Processes and Tentative language variables demonstrated comparable or slightly improved out-of-sample predictive performance. In contrast, the model including Insight language performed somewhat more weakly.