Data Preparation
dataset <- read.csv(file = params$file, header = T, sep = ",")
#run parallel cores
options(mc.cores = 8, brms.backend = "cmdstanr", brms.file_refit = "on_change")
#install.packages("loo")
#remotes::install_github("stan-dev/loo")
library(remotes)
library(loo)
library(psych)
library(relativeVariability)
library(brms)
library(cmdstanr)
library(data.table)
library(ggplot2)
library(dplyr)
library(haven)
#library(rstanarm)
library(knitr)
library(rstan)
library(shinystan)
Rescale Data
dataset$negemo_full_m <- (dataset$negemo_full_m -1)*(4/6)+1
dataset$posemo_full_m <- (dataset$posemo_full_m -1)*(4/6)+1
dataset$neuro_t <- (dataset$neuro_t -1)*(4/6)+1
hist(dataset$negemo_full_m)
Censoring Data
range(dataset$negemo_full_m, na.rm = T)
## [1] 1 5
range(dataset$posemo_full_m, na.rm = T)
## [1] 1 5
sd(dataset$negemo_full_m, na.rm = T)
## [1] 0.7813725
mean(dataset$negemo_full_m, na.rm = T)
## [1] 1.884241
sd(dataset$posemo_full_m, na.rm = T)
## [1] 0.816388
mean(dataset$posemo_full_m, na.rm = T)
## [1] 3.527882
sd(dataset$neuro_t, na.rm = T)
## [1] 0.7994541
mean(dataset$neuro_t, na.rm = T)
## [1] 2.962274
qplot(dataset$negemo_full_, binwidth = .1)
## Warning: Removed 5743 rows containing non-finite values (`stat_bin()`).
qplot(dataset$posemo_full_, binwidth = .1)
## Warning: Removed 5732 rows containing non-finite values (`stat_bin()`).
dataset$Acens <- case_when(dataset$negemo_full_m == 1 ~ "left",
dataset$negemo_full_m == 5 ~ "right",
TRUE ~ "none")
table(dataset$Acens)
##
## left none right
## 3439 31631 25
dataset$Acens_p <- case_when(dataset$posemo_full_m == 1 ~ "left",
dataset$posemo_full_m == 5 ~ "right",
TRUE ~ "none")
table(dataset$Acens_p)
##
## left none right
## 61 34074 960
BCLSM Negative Emotion
Kn_model_neuro3 <- brm(bf(negemo_full_m | cens(Acens) ~ neuro_t + (1|person_id),
sigma ~ neuro_t+ (1|person_id)), data = dataset,
iter = 7000, warmup = 2000, chains = 4,
control = list(adapt_delta = .99), init = 0.1,
file = paste("models/", params$file, "Kn_model_neuro3"))
## Warning: Rows containing NAs were excluded from the model.
print(Kn_model_neuro3)
## Family: gaussian
## Links: mu = identity; sigma = log
## Formula: negemo_full_m | cens(Acens) ~ neuro_t + (1 | person_id)
## sigma ~ neuro_t + (1 | person_id)
## Data: dataset (Number of observations: 29352)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 176)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.59 0.03 0.53 0.65 1.01 764 1970
## sd(sigma_Intercept) 0.40 0.02 0.36 0.45 1.00 1002 1593
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 0.88 0.17 0.55 1.21 1.02 364 1076
## sigma_Intercept -0.66 0.12 -0.89 -0.43 1.01 702 1298
## neuro_t 0.31 0.05 0.21 0.42 1.02 391 1173
## sigma_neuro_t 0.03 0.04 -0.04 0.10 1.01 681 1347
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
plot(Kn_model_neuro3)
pp_check(Kn_model_neuro3)
## Using 10 posterior draws for ppc type 'dens_overlay' by default.
## Warning: Censored responses are not shown in 'pp_check'.
prior_summary(Kn_model_neuro3)
## prior class coef group resp dpar nlpar lb ub source
## (flat) b default
## (flat) b neuro_t (vectorized)
## (flat) b sigma default
## (flat) b neuro_t sigma (vectorized)
## student_t(3, 1.7, 2.5) Intercept default
## student_t(3, 0, 2.5) Intercept sigma default
## student_t(3, 0, 2.5) sd 0 default
## student_t(3, 0, 2.5) sd sigma 0 default
## student_t(3, 0, 2.5) sd person_id 0 (vectorized)
## student_t(3, 0, 2.5) sd Intercept person_id 0 (vectorized)
## student_t(3, 0, 2.5) sd person_id sigma 0 (vectorized)
## student_t(3, 0, 2.5) sd Intercept person_id sigma 0 (vectorized)
Model comparison
scale vs. no scale parameter
Kn_model_neuro2 <- brm(negemo_full_m | cens(Acens) ~ neuro_t + (1|person_id), data = dataset,
iter = 6000, warmup = 2000, chains = 4,
control = list(adapt_delta = .98), inits = 0.1 ,
file = paste("models/", params$file, "Kn_model_neuro2"))
## Warning: Argument 'inits' is deprecated. Please use argument 'init' instead.
## Warning: Rows containing NAs were excluded from the model.
print(Kn_model_neuro2)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: negemo_full_m | cens(Acens) ~ neuro_t + (1 | person_id)
## Data: dataset (Number of observations: 29352)
## Draws: 4 chains, each with iter = 6000; warmup = 2000; thin = 1;
## total post-warmup draws = 16000
##
## Group-Level Effects:
## ~person_id (Number of levels: 176)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.57 0.03 0.51 0.63 1.02 385 1079
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 0.95 0.16 0.62 1.26 1.02 216 562
## neuro_t 0.30 0.05 0.20 0.41 1.01 264 568
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.62 0.00 0.62 0.63 1.00 14913 12160
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
modelA <- Kn_model_neuro2
modelB <- Kn_model_neuro3
modelA <- add_criterion(modelA, "loo")
modelB <- add_criterion(modelB, "loo")
loo <- loo_compare(modelA,modelB, criterion = "loo")
loo <- as.data.frame(loo)
loo$Dataset <- params$file
loo <- tibble::rownames_to_column(loo, "model")
library("writexl")
write_xlsx(loo,paste0("loo", params$file, ".xlsx"))
kable(loo)
| modelB |
0.000 |
0.0000 |
-24013.13 |
181.2845 |
516.5601 |
16.962017 |
48026.25 |
362.5689 |
Dataset 4 public.csv |
| modelA |
-3198.284 |
109.1869 |
-27211.41 |
185.7813 |
178.6113 |
2.427518 |
54422.82 |
371.5627 |
Dataset 4 public.csv |
censoring vs. no censoring
Kn_model_neuro4 <- brm(bf(negemo_full_m ~ neuro_t + (1|person_id),
sigma ~ neuro_t+ (1|person_id)), data = dataset,
iter = 7000, warmup = 2000, chains = 4,
control = list(adapt_delta = .9999), init = 0,
file = paste("models/", params$file, "Kn_model_neuro4"))
## Warning: Rows containing NAs were excluded from the model.
print(Kn_model_neuro4)
## Family: gaussian
## Links: mu = identity; sigma = log
## Formula: negemo_full_m ~ neuro_t + (1 | person_id)
## sigma ~ neuro_t + (1 | person_id)
## Data: dataset (Number of observations: 29352)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 176)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.50 0.03 0.45 0.56 1.00 667 1602
## sd(sigma_Intercept) 0.38 0.02 0.34 0.42 1.00 907 2391
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.11 0.15 0.81 1.41 1.01 371 742
## sigma_Intercept -0.98 0.11 -1.21 -0.76 1.00 534 1454
## neuro_t 0.26 0.05 0.16 0.36 1.01 383 700
## sigma_neuro_t 0.10 0.04 0.03 0.17 1.01 495 1340
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
extract_param <- function(model, parameter) {
ci <- posterior_summary(model, variable = parameter)
est <- sprintf("%.2f %.2f [%.2f;%.2f]", ci[,"Estimate"],ci[,"Est.Error"], ci[,"Q2.5"], ci[,"Q97.5"])
est
}
results_Cens <- data.frame(matrix(nrow = 2,
ncol = 6+1))
names(results_Cens) <- c("model", "negemo_b_neuro", "negemo_b_neuro_sigma", "negemo_sigma",
"posemo_b_neuro", "posemo_b_neuro_sigma", "posemo_sigma"
)
results_Cens$model <- c("modelCensoring", "modelnoCensoring")
#NA
results_Cens[1, "negemo_b_neuro"] <- extract_param(Kn_model_neuro3, "b_neuro_t")
results_Cens[1, "negemo_b_neuro_sigma"] <- extract_param(Kn_model_neuro3, "b_sigma_neuro_t")
results_Cens[1, "negemo_sigma"] <- extract_param(Kn_model_neuro3, "b_sigma_Intercept")
results_Cens[2, "negemo_b_neuro"] <- extract_param(Kn_model_neuro4, "b_neuro_t")
results_Cens[2, "negemo_b_neuro_sigma"] <- extract_param(Kn_model_neuro4, "b_sigma_neuro_t")
results_Cens[2, "negemo_sigma"] <- extract_param(Kn_model_neuro4, "b_sigma_Intercept")
BCLSM vs. model C (two-part model)
dataset <- dataset %>% left_join(dataset %>% distinct(person_id, neuro_t) %>% mutate(neuro_Q =Hmisc::cut2(neuro_t, g = 4)), by = c("person_id", "neuro_t"))
Kn_model_neuro_jinxed <- brm(bf(negemo_full_m | cens(Acens) ~ neuro_t + (1|gr(person_id, by = neuro_Q)),
sigma ~ neuro_t + (1|person_id)), data = dataset,
iter = 5000, warmup = 2000, chains = 4,
control = list(adapt_delta = .99), init = 0.1,
file = paste("models/", params$file, "Kn_model_neuro_jinxed"))
## Warning: Rows containing NAs were excluded from the model.
print(Kn_model_neuro_jinxed)
## Family: gaussian
## Links: mu = identity; sigma = log
## Formula: negemo_full_m | cens(Acens) ~ neuro_t + (1 | gr(person_id, by = neuro_Q))
## sigma ~ neuro_t + (1 | person_id)
## Data: dataset (Number of observations: 29352)
## Draws: 4 chains, each with iter = 5000; warmup = 2000; thin = 1;
## total post-warmup draws = 12000
##
## Group-Level Effects:
## ~person_id (Number of levels: 176)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept:neuro_Q[1.12,2.62)) 0.49 0.05 0.39 0.60 1.01 663 1292
## sd(Intercept:neuro_Q[2.62,3.12)) 0.66 0.08 0.52 0.83 1.00 387 900
## sd(Intercept:neuro_Q[3.12,3.62)) 0.50 0.06 0.40 0.63 1.00 657 1408
## sd(Intercept:neuro_Q[3.62,4.88]) 0.72 0.08 0.58 0.90 1.01 530 938
## sd(sigma_Intercept) 0.39 0.02 0.35 0.44 1.01 494 1117
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 0.88 0.16 0.57 1.20 1.04 202 407
## sigma_Intercept -0.67 0.12 -0.90 -0.44 1.01 362 738
## neuro_t 0.31 0.05 0.20 0.42 1.04 201 383
## sigma_neuro_t 0.04 0.04 -0.04 0.11 1.01 368 693
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
modelB <- Kn_model_neuro3
modelC <- Kn_model_neuro_jinxed
modelB <- add_criterion(modelB, "loo")
modelC <- add_criterion(modelC, "loo")
loo_c <- loo_compare(modelB,modelC, criterion = "loo")
loo_c <- as.data.frame(loo_c)
loo_c$Dataset <- params$file
loo_c <- tibble::rownames_to_column(loo_c, "model")
library("writexl")
write_xlsx(loo_c,paste0("loo_c", params$file, ".xlsx"))
kable(loo_c)
| modelB |
0.000000 |
0.0000000 |
-24013.13 |
181.2845 |
516.5601 |
16.96202 |
48026.25 |
362.5689 |
Dataset 4 public.csv |
| modelC |
-2.180118 |
0.6852423 |
-24015.31 |
181.3500 |
519.0583 |
17.09484 |
48030.61 |
362.7001 |
Dataset 4 public.csv |
control for gender
dataset$gender <- as.factor(dataset$gender)
Kn_model_sex <- brm(bf(negemo_full_m | cens(Acens) ~ neuro_t + gender + (1|person_id),
sigma ~ neuro_t + gender), data = dataset,
iter = 9000, warmup = 2000, chains = 8,
control = list(adapt_delta = .99), inits = 0.1,
file = paste("models/", params$file, "Kn_model_sex"))
## Warning: Argument 'inits' is deprecated. Please use argument 'init' instead.
## Warning: Rows containing NAs were excluded from the model.
print(Kn_model_sex)
## Family: gaussian
## Links: mu = identity; sigma = log
## Formula: negemo_full_m | cens(Acens) ~ neuro_t + gender + (1 | person_id)
## sigma ~ neuro_t + gender
## Data: dataset (Number of observations: 29190)
## Draws: 8 chains, each with iter = 9000; warmup = 2000; thin = 1;
## total post-warmup draws = 56000
##
## Group-Level Effects:
## ~person_id (Number of levels: 175)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.56 0.03 0.50 0.62 1.00 1592 3011
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 0.92 0.17 0.58 1.27 1.01 1021 2178
## sigma_Intercept -0.61 0.02 -0.65 -0.58 1.00 29426 34309
## neuro_t 0.31 0.05 0.20 0.41 1.01 1008 1909
## gender1 -0.00 0.09 -0.18 0.18 1.02 670 1837
## sigma_neuro_t 0.05 0.01 0.04 0.06 1.00 32130 35169
## sigma_gender1 -0.02 0.01 -0.03 0.00 1.00 30598 34136
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
pp_check(Kn_model_sex)
## Using 10 posterior draws for ppc type 'dens_overlay' by default.
## Warning: Censored responses are not shown in 'pp_check'.
plot(Kn_model_sex)
BCLSM Positive Emotion
Kp_model_neuro3 <- brm(bf(posemo_full_m | cens(Acens_p) ~ neuro_t + (1|person_id),
sigma ~ neuro_t + (1|person_id)), data = dataset,
chains = 4,
control = list(adapt_delta = .95), inits = 0.1,
iter = 7000, warmup = 2000,
file = paste("models/", params$file, "Kp_model_neuro3"))
## Warning: Argument 'inits' is deprecated. Please use argument 'init' instead.
## Warning: Rows containing NAs were excluded from the model.
print(Kp_model_neuro3)
## Family: gaussian
## Links: mu = identity; sigma = log
## Formula: posemo_full_m | cens(Acens_p) ~ neuro_t + (1 | person_id)
## sigma ~ neuro_t + (1 | person_id)
## Data: dataset (Number of observations: 29363)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 176)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.55 0.03 0.49 0.61 1.00 1197 2673
## sd(sigma_Intercept) 0.34 0.02 0.30 0.38 1.00 1689 3592
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 4.31 0.16 4.00 4.63 1.01 595 1224
## sigma_Intercept -0.62 0.10 -0.82 -0.43 1.00 1137 2010
## neuro_t -0.26 0.05 -0.36 -0.16 1.01 621 1299
## sigma_neuro_t 0.03 0.03 -0.04 0.09 1.00 1166 2022
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
pp_check(Kp_model_neuro3)
## Using 10 posterior draws for ppc type 'dens_overlay' by default.
## Warning: Censored responses are not shown in 'pp_check'.
plot(Kp_model_neuro3)
prior_summary(Kp_model_neuro3)
## prior class coef group resp dpar nlpar lb ub source
## (flat) b default
## (flat) b neuro_t (vectorized)
## (flat) b sigma default
## (flat) b neuro_t sigma (vectorized)
## student_t(3, 3.6, 2.5) Intercept default
## student_t(3, 0, 2.5) Intercept sigma default
## student_t(3, 0, 2.5) sd 0 default
## student_t(3, 0, 2.5) sd sigma 0 default
## student_t(3, 0, 2.5) sd person_id 0 (vectorized)
## student_t(3, 0, 2.5) sd Intercept person_id 0 (vectorized)
## student_t(3, 0, 2.5) sd person_id sigma 0 (vectorized)
## student_t(3, 0, 2.5) sd Intercept person_id sigma 0 (vectorized)
Model comparison
scale vs. no scale parameter
Kp_model_neuro2 <- brm(posemo_full_m | cens(Acens_p) ~ neuro_t + (1|person_id), data = dataset,
iter = 7000, warmup = 2000, chains = 4,
control = list(adapt_delta = .95), inits = 0.1,
file = paste("models/", params$file, "Kp_model_neuro2"))
## Warning: Argument 'inits' is deprecated. Please use argument 'init' instead.
## Warning: Rows containing NAs were excluded from the model.
print(Kp_model_neuro2)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: posemo_full_m | cens(Acens_p) ~ neuro_t + (1 | person_id)
## Data: dataset (Number of observations: 29363)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 176)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.53 0.03 0.48 0.59 1.01 734 1753
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 4.28 0.15 3.98 4.58 1.01 440 1142
## neuro_t -0.25 0.05 -0.35 -0.15 1.00 431 1140
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.64 0.00 0.63 0.64 1.00 19639 13522
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
modelAp <- Kp_model_neuro2
modelBp <- Kp_model_neuro3
modelAp <- add_criterion(modelAp, "loo")
modelBp <- add_criterion(modelBp, "loo")
looP <- loo_compare(modelAp,modelBp, criterion = "loo")
looP <- as.data.frame(looP)
looP$Dataset <- params$file
looP <- tibble::rownames_to_column(looP, "model")
library("writexl")
write_xlsx(looP,paste0("looP", params$file, ".xlsx"))
kable(looP)
| modelBp |
0.000 |
0.0000 |
-25708.47 |
169.6149 |
459.8899 |
16.318112 |
51416.93 |
339.2298 |
Dataset 4 public.csv |
| modelAp |
-2791.055 |
95.9131 |
-28499.52 |
170.9698 |
176.8593 |
2.117323 |
56999.04 |
341.9396 |
Dataset 4 public.csv |
censoring vs. no censoring
Kp_model_neuro4 <- brm(bf(posemo_full_m ~ neuro_t + (1|person_id),
sigma ~ neuro_t + (1|person_id)), data = dataset,
chains = 4,
control = list(adapt_delta = .9999), inits = 0,
iter = 7000, warmup = 2000,
file = paste("models/", params$file, "Kp_model_neuro4"))
## Warning: Argument 'inits' is deprecated. Please use argument 'init' instead.
## Warning: Rows containing NAs were excluded from the model.
print(Kp_model_neuro4)
## Family: gaussian
## Links: mu = identity; sigma = log
## Formula: posemo_full_m ~ neuro_t + (1 | person_id)
## sigma ~ neuro_t + (1 | person_id)
## Data: dataset (Number of observations: 29363)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 176)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.50 0.03 0.45 0.56 1.00 683 1424
## sd(sigma_Intercept) 0.32 0.02 0.28 0.35 1.00 1197 3130
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 4.25 0.14 3.98 4.52 1.01 462 998
## sigma_Intercept -0.72 0.09 -0.90 -0.54 1.00 842 1923
## neuro_t -0.24 0.05 -0.33 -0.16 1.00 488 1204
## sigma_neuro_t 0.05 0.03 -0.01 0.11 1.01 738 1786
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
#pa
results_Cens[1, "posemo_b_neuro"] <- extract_param(Kp_model_neuro3, "b_neuro_t")
results_Cens[1, "posemo_b_neuro_sigma"] <- extract_param(Kp_model_neuro3, "b_sigma_neuro_t")
results_Cens[1, "posemo_sigma"] <- extract_param(Kp_model_neuro3, "b_sigma_Intercept")
results_Cens[2, "posemo_b_neuro"] <- extract_param(Kp_model_neuro4, "b_neuro_t")
results_Cens[2, "posemo_b_neuro_sigma"] <- extract_param(Kp_model_neuro4, "b_sigma_neuro_t")
results_Cens[2, "posemo_sigma"] <- extract_param(Kp_model_neuro4, "b_sigma_Intercept")
BCLSM vs. model C (two-part model)
Kp_model_neuro_jinxed <- brm(bf(posemo_full_m | cens(Acens) ~ neuro_t + (1|gr(person_id, by = neuro_Q)),
sigma ~ neuro_t + (1|person_id)), data = dataset,
iter = 5000, warmup = 2000, chains = 4,
control = list(adapt_delta = .99), init = 0.1,
file = paste("models/", params$file, "Kp_model_neuro_jinxed"))
## Warning: Rows containing NAs were excluded from the model.
print(Kp_model_neuro_jinxed)
## Family: gaussian
## Links: mu = identity; sigma = log
## Formula: posemo_full_m | cens(Acens) ~ neuro_t + (1 | gr(person_id, by = neuro_Q))
## sigma ~ neuro_t + (1 | person_id)
## Data: dataset (Number of observations: 29363)
## Draws: 4 chains, each with iter = 5000; warmup = 2000; thin = 1;
## total post-warmup draws = 12000
##
## Group-Level Effects:
## ~person_id (Number of levels: 176)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept:neuro_Q[1.12,2.62)) 0.42 0.04 0.34 0.51 1.01 620 1373
## sd(Intercept:neuro_Q[2.62,3.12)) 0.47 0.05 0.38 0.59 1.00 640 1449
## sd(Intercept:neuro_Q[3.12,3.62)) 0.45 0.06 0.36 0.58 1.01 850 1430
## sd(Intercept:neuro_Q[3.62,4.88]) 0.55 0.06 0.45 0.69 1.01 696 1328
## sd(sigma_Intercept) 0.31 0.02 0.28 0.35 1.00 813 1538
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 3.99 0.13 3.74 4.26 1.00 310 580
## sigma_Intercept -0.66 0.10 -0.84 -0.47 1.01 439 1010
## neuro_t -0.20 0.05 -0.29 -0.11 1.01 277 602
## sigma_neuro_t 0.03 0.03 -0.03 0.09 1.01 441 1065
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
modelB <- Kp_model_neuro3
modelC <- Kp_model_neuro_jinxed
modelB <- add_criterion(modelB, "loo")
modelC <- add_criterion(modelC, "loo")
loo_cP <- loo_compare(modelB,modelC, criterion = "loo")
## Warning: Not all models have the same y variable. ('yhash' attributes do not match)
loo_cP <- as.data.frame(loo_cP)
loo_cP$Dataset <- params$file
#loo_cP <- tibble::rownames_to_column(loo_c, "model")
library("writexl")
write_xlsx(loo_cP,paste0("loo_cP", params$file, ".xlsx"))
kable(loo_cP)
| modelC |
0.000 |
0.00000 |
-22958.28 |
160.8128 |
442.2849 |
18.32649 |
45916.56 |
321.6255 |
Dataset 4 public.csv |
| modelB |
-2750.183 |
78.01855 |
-25708.47 |
169.6149 |
459.8899 |
16.31811 |
51416.93 |
339.2298 |
Dataset 4 public.csv |
extract_param <- function(model, parameter) {
ci <- posterior_summary(model, variable = parameter)
est <- sprintf("%.2f %.2f [%.2f;%.2f]", ci[,"Estimate"],ci[,"Est.Error"], ci[,"Q2.5"], ci[,"Q97.5"])
est
}
results_K <- data.frame(matrix(nrow = 7,
ncol = 8+1))
names(results_K) <- c("model", "negemo_b_neuro", "negemo_b_neuro_sigma", "negemo_sigma", "b_neg_sigma_sex",
"posemo_b_neuro", "posemo_b_neuro_sigma", "posemo_sigma", "b_pos_sigma_sex"
)
results_K$model <- c("model1", "model2", "model3",
"RSD", "RSD_weight", "SD", "gender")
#NA
results_K[2, "negemo_b_neuro"] <- extract_param(Kn_model_neuro2, "b_neuro_t")
results_K[2, "negemo_sigma"] <- extract_param(Kn_model_neuro2, "sigma")
results_K[3, "negemo_b_neuro"] <- extract_param(Kn_model_neuro3, "b_neuro_t")
results_K[3, "negemo_b_neuro_sigma"] <- extract_param(Kn_model_neuro3, "b_sigma_neuro_t")
results_K[3, "negemo_sigma"] <- extract_param(Kn_model_neuro3, "b_sigma_Intercept")
#gender
results_K[7, "negemo_b_neuro"] <- extract_param(Kn_model_sex, "b_neuro_t")
results_K[7, "negemo_b_neuro_sigma"] <- extract_param(Kn_model_sex, "b_sigma_neuro_t")
results_K[7, "negemo_sigma"] <- extract_param(Kn_model_sex, "b_sigma_Intercept")
results_K[7, "b_neg_sigma_sex"] <- extract_param(Kn_model_sex, "b_sigma_gender1")
#pa
results_K[2, "posemo_b_neuro"] <- extract_param(Kp_model_neuro2, "b_neuro_t")
results_K[2, "posemo_sigma"] <- extract_param(Kp_model_neuro2, "sigma")
results_K[3, "posemo_b_neuro"] <- extract_param(Kp_model_neuro3, "b_neuro_t")
results_K[3, "posemo_b_neuro_sigma"] <- extract_param(Kp_model_neuro3, "b_sigma_neuro_t")
results_K[3, "posemo_sigma"] <- extract_param(Kp_model_neuro3, "b_sigma_Intercept")
RVI (Relative Variability Index)
data_w <- unique(dataset[,2:5])
Unweighted RVI
data_w$RSD_NA <- NA
for (i in 1:nrow(data_w)) {
data_w$RSD_NA[i] <- relativeSD(dataset$negemo_full_m[dataset$person_id == data_w$person_id[i]],
1, 5)
}
range(data_w$RSD_NA, na.rm = T)
## [1] 0.1220675 0.6996578
mean(data_w$RSD_NA, na.rm = T)
## [1] 0.359781
sd(data_w$RSD_NA, na.rm = T)
## [1] 0.1194503
data_w$logrsd_n <- log(data_w$RSD_NA)
#plot(data_w$logrsd_n)
m_rvi_na <- brm(logrsd_n ~ neuro_t, data= data_w,
file = paste("models/", params$file, "Kn_model_logrsd_uw"))
print(m_rvi_na)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_n ~ neuro_t
## Data: data_w (Number of observations: 176)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.01 0.10 -1.20 -0.82 1.00 4458 3209
## neuro_t -0.02 0.03 -0.09 0.04 1.00 4361 3402
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.35 0.02 0.31 0.39 1.00 4415 2944
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[4,3] <- extract_param(m_rvi_na, "b_neuro_t")
data_w$RSD_PA <- NA
for (i in 1:nrow(data_w)) {
data_w$RSD_PA[i] <- relativeSD(dataset$posemo_full_m[dataset$person_id == data_w$person_id[i]],
1, 5)
}
range(data_w$RSD_PA)
## [1] 0.1168063 0.6621192
data_w$logrsd_p <- log(data_w$RSD_PA)
m_rvi_pa <- brm(logrsd_p ~ neuro_t, data= data_w,
file = paste("models/", params$file, "Kp_model_logrsd_uw"))
print(m_rvi_pa)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_p ~ neuro_t
## Data: data_w (Number of observations: 176)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.17 0.10 -1.37 -0.96 1.00 3842 2834
## neuro_t -0.00 0.03 -0.07 0.06 1.00 3643 3037
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.35 0.02 0.31 0.39 1.00 3782 2908
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[4,6] <- extract_param(m_rvi_pa, "b_neuro_t")
Weighted RVI
data_w$mean_NA <- NA
for (i in 1:nrow(data_w)) {
data_w$mean_NA[i] <- mean(dataset$negemo_full_m[dataset$person_id == data_w$person_id[i]],
na.rm = T)
}
mean(data_w$mean_NA)
## [1] 1.886241
sd(data_w$mean_NA)
## [1] 0.5395514
data_w$mean_PA <- NA
for (i in 1:nrow(data_w)) {
data_w$mean_PA[i] <- mean(dataset$posemo_full_m[dataset$person_id == data_w$person_id[i]],
na.rm = T)
}
mean(data_w$mean_PA)
## [1] 3.523999
sd(data_w$mean_PA)
## [1] 0.5316833
data_w$weight_NA <- NA
for (i in 1:nrow(data_w)) {
if (!is.na(data_w$mean_NA[i])) {
data_w$weight_NA[i] <- maximumSD(data_w$mean_NA[i], # Mittelwert
1, # Minimum
5, # Maximum
sum(!is.na(dataset$negemo_full_m[dataset$person_id == data_w$person_id[i]]))
)
# W as reported in paper
data_w$weight_NA[i] <- data_w$weight_NA[i]^2
}
}
mean(data_w$weight_NA)
## [1] 2.468617
sd(data_w$weight_NA)
## [1] 1.030032
range(data_w$weight_NA)
## [1] 0.1501318 4.0170929
m_rvi_na_w <- brm(logrsd_n| weights(weight_NA) ~ neuro_t, data= data_w,
file = paste("models/", params$file, "Kn_model_logrsd"))
print(m_rvi_na_w)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_n | weights(weight_NA) ~ neuro_t
## Data: data_w (Number of observations: 176)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.15 0.07 -1.28 -1.01 1.00 3301 2892
## neuro_t 0.01 0.02 -0.03 0.05 1.00 3663 2690
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.34 0.01 0.32 0.36 1.00 3930 2917
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[5,3] <- extract_param(m_rvi_na_w, "b_neuro_t")
data_w$weight_PA <- NA
for (i in 1:nrow(data_w)) {
if (!is.na(data_w$mean_PA[i])) {
data_w$weight_PA[i] <- maximumSD(data_w$mean_PA[i], # Mittelwert
1, # Minimum
5, # Maximum
sum(!is.na(dataset$posemo_full_m[dataset$person_id == data_w$person_id[i]]))
)
# W as reported in paper
data_w$weight_PA[i] <- data_w$weight_PA[i]^2
}
}
m_rvi_pa_w <- brm(logrsd_p| weights(weight_PA) ~ neuro_t, data= data_w,
file = paste("models/", params$file, "Kp_model_logrsd"))
print(m_rvi_pa_w)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_p | weights(weight_PA) ~ neuro_t
## Data: data_w (Number of observations: 176)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.26 0.05 -1.36 -1.14 1.00 3825 2827
## neuro_t 0.02 0.02 -0.02 0.05 1.00 4104 3027
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.34 0.01 0.32 0.36 1.00 5076 2752
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[5,6] <- extract_param(m_rvi_pa_w, "b_neuro_t")
SD
data_w$sd_NA <- NA
for (i in 1:nrow(data_w)) {
data_w$sd_NA[i] <- sd(dataset$negemo_full_m[dataset$person_id == data_w$person_id[i]],
na.rm = T)
}
data_w$sd_PA <- NA
for (i in 1:nrow(data_w)) {
data_w$sd_PA[i] <- sd(dataset$posemo_full_m[dataset$person_id == data_w$person_id[i]],
na.rm = T)
}
mean(data_w$sd_NA)
## [1] 0.5358045
mean(data_w$sd_PA)
## [1] 0.5920927
data_w$sd_PA[data_w$sd_PA == 0] <- NA
data_w$sd_NA[data_w$sd_NA == 0] <- NA
data_w$logsd_NA <- log(data_w$sd_NA)
data_w$logsd_PA <- log(data_w$sd_PA)
m_sd_na <- brm(logsd_NA ~ neuro_t, data= data_w,
file = paste("models/", params$file, "Kn_model_logsd"))
m_sd_na
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logsd_NA ~ neuro_t
## Data: data_w (Number of observations: 176)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -0.98 0.11 -1.20 -0.76 1.00 3518 2502
## neuro_t 0.10 0.04 0.03 0.17 1.00 3821 2288
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.38 0.02 0.34 0.43 1.00 3632 2837
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[6,3] <- extract_param(m_sd_na, "b_neuro_t")
m_sd_pa <- brm(logsd_PA ~ neuro_t, data= data_w,
file = paste("models/", params$file, "Kp_model_logsd"))
m_sd_pa
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logsd_PA ~ neuro_t
## Data: data_w (Number of observations: 176)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -0.72 0.09 -0.90 -0.54 1.00 3948 2984
## neuro_t 0.05 0.03 -0.01 0.11 1.00 3883 2882
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.32 0.02 0.29 0.36 1.00 3684 2806
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[6,6] <- extract_param(m_sd_pa, "b_neuro_t")
library("writexl")
write_xlsx(results_K,paste0("", params$file, ".xlsx"))
Incremental Validity of SD
na_noneurot <- brm(bf(negemo_full_m | cens(Acens) ~ (1|person_id),
sigma ~ (1|person_id)), data = dataset,
iter = 7000, warmup = 2000,chains = 4,
control = list(adapt_delta = .99), init = 0.1,
file = "na_noneurot")
## Warning: Rows containing NAs were excluded from the model.
print(na_noneurot)
## Family: gaussian
## Links: mu = identity; sigma = log
## Formula: negemo_full_m | cens(Acens) ~ (1 | person_id)
## sigma ~ (1 | person_id)
## Data: dataset (Number of observations: 29352)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 176)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.64 0.04 0.57 0.71 1.01 830 1655
## sd(sigma_Intercept) 0.40 0.02 0.36 0.44 1.00 1357 2811
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.81 0.05 1.71 1.90 1.02 277 580
## sigma_Intercept -0.57 0.03 -0.63 -0.51 1.01 561 1352
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
rans <- coef(na_noneurot, summary = T)
rans_i <- as.data.frame(rans$person_id[,,"Intercept"]) %>% tibble::rownames_to_column("person_id")
rans_s <- as.data.frame(rans$person_id[,,"sigma_Intercept"]) %>% tibble::rownames_to_column("person_id")
nrow(rans_s)
## [1] 176
nrow(rans_i)
## [1] 176
nrow(data_w)
## [1] 176
dat <- merge(rans_s, rans_i, all = T, by= "person_id")
dat <- merge(dat, data_w, all = T, by= "person_id")
names(dat)[2] <- "Est.SD"
names(dat)[6] <- "Est.M"
fit1 <- lm(neuro_t ~ Est.SD + Est.M , data=dat)
summary(fit1)
##
## Call:
## lm(formula = neuro_t ~ Est.SD + Est.M, data = dat)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.52203 -0.52534 0.08667 0.49341 1.91113
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.15189 0.18397 11.697 < 2e-16 ***
## Est.SD 0.19742 0.14428 1.368 0.173
## Est.M 0.50787 0.08883 5.717 4.66e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7391 on 173 degrees of freedom
## Multiple R-squared: 0.1625, Adjusted R-squared: 0.1529
## F-statistic: 16.79 on 2 and 173 DF, p-value: 2.169e-07
fit1.2 <- lm(neuro_t ~ Est.M , data=dat)
summary(fit1.2)
##
## Call:
## lm(formula = neuro_t ~ Est.M, data = dat)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.53258 -0.55315 0.06906 0.54782 1.95216
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.05573 0.17045 12.061 < 2e-16 ***
## Est.M 0.49882 0.08881 5.617 7.58e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7409 on 174 degrees of freedom
## Multiple R-squared: 0.1535, Adjusted R-squared: 0.1486
## F-statistic: 31.55 on 1 and 174 DF, p-value: 7.581e-08
aov <- anova(fit1.2, fit1)
aov
## Analysis of Variance Table
##
## Model 1: neuro_t ~ Est.M
## Model 2: neuro_t ~ Est.SD + Est.M
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 174 95.527
## 2 173 94.504 1 1.0228 1.8724 0.173
summary(fit1)$r.squared-summary(fit1.2)$r.squared
## [1] 0.009063684
results_SDin <- data.frame(matrix(nrow = 1, ncol = 9))
names(results_SDin) <- c("Dataset","b_SD","Err.SD","p(b_SD)","b_M","Err.M","p(b_M)","ΔR²", "p")
results_SDin$Dataset <- params$file
results_SDin$`ΔR²` <- summary(fit1)$r.squared-summary(fit1.2)$r.squared
results_SDin$`p` <- aov$`Pr(>F)`[2]
results_SDin$Err.SD <- summary(fit1)$coefficients[2,2]
results_SDin$b_SD <- fit1$coefficients[2]
results_SDin$`p(b_SD)` <- summary(fit1)$coefficients[2,4]
results_SDin$b_M <- fit1$coefficients[3]
results_SDin$`p(b_M)` <- summary(fit1)$coefficients[3,4]
results_SDin$Err.M <- summary(fit1)$coefficients[3,2]
library("writexl")
write_xlsx(results_SDin,paste0("SD", params$file, ".xlsx"))