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$negemo_full_m, na.rm = T)
## [1] 0.5315914
mean(dataset$negemo_full_m, na.rm = T)
## [1] 1.568377
sd(dataset$posemo_full_m, na.rm = T)
## [1] 0.7771591
mean(dataset$posemo_full_m, na.rm = T)
## [1] 3.276679
sd(dataset$neuro_t, na.rm = T)
## [1] 0.8803423
mean(dataset$neuro_t, na.rm = T)
## [1] 2.515274
qplot(dataset$negemo_full_, binwidth = .1)
## Warning: Removed 1805 rows containing non-finite values (`stat_bin()`).
qplot(dataset$posemo_full_, binwidth = .1)
## Warning: Removed 1805 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
## 1046 13050 2
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
## 23 13984 91
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: 12293)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 200)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.34 0.02 0.30 0.37 1.00 1616 3365
## sd(sigma_Intercept) 0.42 0.02 0.38 0.47 1.00 2227 4472
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.13 0.08 0.98 1.28 1.00 528 1020
## sigma_Intercept -1.34 0.09 -1.52 -1.16 1.01 1256 2732
## neuro_t 0.16 0.03 0.11 0.22 1.00 621 1095
## sigma_neuro_t 0.15 0.03 0.08 0.22 1.01 1301 3076
##
## 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, 1.4, 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: 12293)
## Draws: 4 chains, each with iter = 6000; warmup = 2000; thin = 1;
## total post-warmup draws = 16000
##
## Group-Level Effects:
## ~person_id (Number of levels: 200)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.34 0.02 0.31 0.38 1.00 1491 3011
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.13 0.07 0.98 1.27 1.00 718 1578
## neuro_t 0.17 0.03 0.11 0.22 1.00 831 1629
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.44 0.00 0.44 0.45 1.00 22246 10847
##
## 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$file, ".xlsx"))
kable(loo)
| modelB |
0.000 |
0.00000 |
-6046.185 |
146.9383 |
667.6368 |
39.433285 |
12092.37 |
293.8765 |
Dataset 5 public.csv |
| modelA |
-1651.279 |
93.64047 |
-7697.464 |
146.1187 |
200.4692 |
5.157393 |
15394.93 |
292.2373 |
Dataset 5 public.csv |
censoring vs. no censoring
Kn_model_neuro4 <- brm(bf(negemo_full_m ~ neuro_t + (1|person_id),
sigma ~ neuro_t+ (1|person_id)), data = dataset,
iter = 7000, warmup = 2000, chains = 4,
control = list(adapt_delta = .9999), init = 0,
file = paste("models/", params$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: 12293)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 200)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.30 0.02 0.27 0.33 1.00 1961 3847
## sd(sigma_Intercept) 0.43 0.02 0.39 0.48 1.00 2583 4778
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.19 0.07 1.06 1.32 1.01 751 1906
## sigma_Intercept -1.53 0.10 -1.72 -1.34 1.00 1513 3339
## neuro_t 0.15 0.02 0.10 0.20 1.00 899 1985
## sigma_neuro_t 0.19 0.04 0.12 0.26 1.00 1555 3430
##
## 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: 12293)
## Draws: 4 chains, each with iter = 5000; warmup = 2000; thin = 1;
## total post-warmup draws = 12000
##
## Group-Level Effects:
## ~person_id (Number of levels: 200)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept:neuro_Q[1.00,2.33)) 0.32 0.03 0.27 0.38 1.00 1711 3094
## sd(Intercept:neuro_Q2.33) 0.34 0.05 0.26 0.46 1.00 1889 3880
## sd(Intercept:neuro_Q[2.67,3.33)) 0.30 0.03 0.24 0.37 1.00 1559 2930
## sd(Intercept:neuro_Q[3.33,5.00]) 0.42 0.05 0.34 0.53 1.00 1853 3610
## sd(sigma_Intercept) 0.42 0.02 0.38 0.47 1.00 1763 3272
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.14 0.08 0.99 1.29 1.01 731 1272
## sigma_Intercept -1.34 0.09 -1.52 -1.16 1.00 1286 2908
## neuro_t 0.16 0.03 0.10 0.22 1.00 784 1456
## sigma_neuro_t 0.15 0.03 0.08 0.22 1.00 1278 2790
##
## 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$file, ".xlsx"))
kable(loo_c)
| modelC |
0.000000 |
0.000000 |
-6043.229 |
146.5852 |
664.8074 |
38.80593 |
12086.46 |
293.1703 |
Dataset 5 public.csv |
| modelB |
-2.955212 |
1.835703 |
-6046.185 |
146.9383 |
667.6368 |
39.43328 |
12092.37 |
293.8765 |
Dataset 5 public.csv |
control for gender
dataset$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: 12293)
## Draws: 8 chains, each with iter = 9000; warmup = 2000; thin = 1;
## total post-warmup draws = 56000
##
## Group-Level Effects:
## ~person_id (Number of levels: 200)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.33 0.02 0.30 0.37 1.00 3738 8662
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.00 0.09 0.83 1.18 1.00 1952 4212
## sigma_Intercept -1.21 0.03 -1.25 -1.16 1.00 39120 39935
## neuro_t 0.19 0.03 0.13 0.25 1.00 2401 5287
## gender1 0.13 0.05 0.04 0.24 1.01 1704 3927
## sigma_neuro_t 0.13 0.01 0.12 0.15 1.00 44925 42169
## sigma_gender1 0.09 0.02 0.06 0.12 1.00 43965 41037
##
## 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: 12293)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 200)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.37 0.02 0.34 0.41 1.00 3315 6810
## sd(sigma_Intercept) 0.28 0.02 0.25 0.32 1.00 5980 10164
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 3.66 0.08 3.50 3.81 1.00 2447 4985
## sigma_Intercept -0.62 0.06 -0.74 -0.49 1.00 4789 8372
## neuro_t -0.15 0.03 -0.21 -0.09 1.00 2670 5533
## sigma_neuro_t 0.06 0.02 0.02 0.11 1.00 4918 8279
##
## 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, 3.3, 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: 12293)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 200)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.37 0.02 0.34 0.41 1.00 3288 6250
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 3.65 0.08 3.49 3.81 1.00 2292 4102
## neuro_t -0.15 0.03 -0.21 -0.09 1.00 2413 4604
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.68 0.00 0.67 0.69 1.00 48019 14190
##
## 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$file, ".xlsx"))
kable(looP)
| modelBp |
0.0000 |
0.00000 |
-11999.92 |
90.49436 |
384.8770 |
9.689442 |
23999.84 |
180.9887 |
Dataset 5 public.csv |
| modelAp |
-830.9498 |
44.34006 |
-12830.87 |
90.70633 |
191.9368 |
2.812391 |
25661.74 |
181.4127 |
Dataset 5 public.csv |
censoring vs. no censoring
Kp_model_neuro4 <- brm(bf(posemo_full_m ~ neuro_t + (1|person_id),
sigma ~ neuro_t + (1|person_id)), data = dataset,
chains = 4,
control = list(adapt_delta = .9999), inits = 0,
iter = 7000, warmup = 2000,
file = paste("models/", params$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: 12293)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 200)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.37 0.02 0.33 0.41 1.00 1696 3546
## sd(sigma_Intercept) 0.27 0.02 0.24 0.30 1.00 3603 6691
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 3.66 0.08 3.50 3.82 1.00 922 2430
## sigma_Intercept -0.63 0.06 -0.75 -0.51 1.00 1914 4170
## neuro_t -0.15 0.03 -0.21 -0.09 1.00 1054 2305
## sigma_neuro_t 0.07 0.02 0.02 0.11 1.00 1943 4057
##
## 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$file, "Kp_model_neuro_jinxed"))
## Warning: Rows containing NAs were excluded from the model.
print(Kp_model_neuro_jinxed)
## Family: gaussian
## Links: mu = identity; sigma = log
## Formula: posemo_full_m | cens(Acens) ~ neuro_t + (1 | gr(person_id, by = neuro_Q))
## sigma ~ neuro_t + (1 | person_id)
## Data: dataset (Number of observations: 12293)
## Draws: 4 chains, each with iter = 5000; warmup = 2000; thin = 1;
## total post-warmup draws = 12000
##
## Group-Level Effects:
## ~person_id (Number of levels: 200)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept:neuro_Q[1.00,2.33)) 0.39 0.03 0.32 0.46 1.00 1327 2722
## sd(Intercept:neuro_Q2.33) 0.41 0.06 0.31 0.54 1.00 1281 2989
## sd(Intercept:neuro_Q[2.67,3.33)) 0.38 0.04 0.30 0.47 1.00 1465 3211
## sd(Intercept:neuro_Q[3.33,5.00]) 0.47 0.06 0.37 0.59 1.00 1475 3278
## sd(sigma_Intercept) 0.27 0.02 0.24 0.30 1.00 2111 4768
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 3.45 0.10 3.26 3.63 1.01 709 1423
## sigma_Intercept -0.61 0.06 -0.73 -0.48 1.00 1532 2875
## neuro_t -0.10 0.04 -0.17 -0.02 1.01 656 1311
## sigma_neuro_t 0.06 0.02 0.02 0.11 1.00 1511 3184
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
modelB <- Kp_model_neuro3
modelC <- Kp_model_neuro_jinxed
modelB <- add_criterion(modelB, "loo")
modelC <- add_criterion(modelC, "loo")
loo_cP <- loo_compare(modelB,modelC, criterion = "loo")
## Warning: Not all models have the same y variable. ('yhash' attributes do not match)
loo_cP <- as.data.frame(loo_cP)
loo_cP$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 |
-11325.59 |
87.25254 |
370.6448 |
9.181566 |
22651.18 |
174.5051 |
Dataset 5 public.csv |
| modelB |
-674.332 |
40.82591 |
-11999.92 |
90.49436 |
384.8770 |
9.689442 |
23999.84 |
180.9887 |
Dataset 5 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$RSD_NA, na.rm = T)
## [1] 0.0820998 0.6206965
mean(data_w$RSD_NA, na.rm = T)
## [1] 0.2922219
sd(data_w$RSD_NA, na.rm = T)
## [1] 0.09764044
data_w$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$file, "Kn_model_logrsd_uw"))
print(m_rvi_na)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_n ~ neuro_t
## Data: data_w (Number of observations: 200)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.45 0.07 -1.59 -1.30 1.00 3712 2597
## neuro_t 0.06 0.03 0.01 0.12 1.00 3598 2580
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.34 0.02 0.31 0.38 1.00 3752 2729
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[4,3] <- extract_param(m_rvi_na, "b_neuro_t")
data_w$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$RSD_PA)
## [1] 0.1303542 0.6296357
data_w$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: 200)
## 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 -1.29 0.06 -1.42 -1.18 1.00 4703 3139
## neuro_t 0.06 0.02 0.02 0.11 1.00 4877 2780
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.28 0.01 0.26 0.31 1.00 4523 2848
##
## 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] 1.572504
sd(data_w$mean_NA)
## [1] 0.3376875
data_w$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$mean_PA)
## [1] 3.274851
sd(data_w$mean_PA)
## [1] 0.3990785
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] 1.836377
sd(data_w$weight_NA)
## [1] 0.8652708
range(data_w$weight_NA)
## [1] 0.03938462 4.01779631
m_rvi_na_w <- brm(logrsd_n| weights(weight_NA) ~ neuro_t, data= data_w,
file = paste("models/", params$file, "Kn_model_logrsd"))
print(m_rvi_na_w)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_n | weights(weight_NA) ~ neuro_t
## Data: data_w (Number of observations: 200)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.47 0.05 -1.57 -1.37 1.00 3528 2955
## neuro_t 0.07 0.02 0.04 0.11 1.00 3889 3029
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.33 0.01 0.31 0.35 1.00 3738 3289
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[5,3] <- extract_param(m_rvi_na_w, "b_neuro_t")
data_w$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$file, "Kp_model_logrsd"))
print(m_rvi_pa_w)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_p | weights(weight_PA) ~ neuro_t
## Data: data_w (Number of observations: 200)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.29 0.03 -1.35 -1.23 1.00 3817 2582
## neuro_t 0.06 0.01 0.04 0.09 1.00 3820 2701
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.28 0.01 0.27 0.30 1.00 3496 2838
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[5,6] <- extract_param(m_rvi_pa_w, "b_neuro_t")
SD
data_w$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] 0.3841716
mean(data_w$sd_PA)
## [1] 0.6507666
data_w$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: 200)
## 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 -1.54 0.10 -1.72 -1.35 1.00 3851 2564
## neuro_t 0.19 0.04 0.12 0.26 1.00 3925 2710
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.44 0.02 0.40 0.48 1.00 3542 2757
##
## 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$file, "Kp_model_logsd"))
m_sd_pa
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logsd_PA ~ neuro_t
## Data: data_w (Number of observations: 200)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -0.63 0.06 -0.75 -0.51 1.00 3964 2991
## neuro_t 0.06 0.02 0.02 0.11 1.00 3827 3037
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.29 0.01 0.26 0.32 1.00 3626 3167
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[6,6] <- extract_param(m_sd_pa, "b_neuro_t")
library("writexl")
write_xlsx(results_K,paste0("", params$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: 12293)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 200)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.37 0.02 0.33 0.41 1.01 1078 2394
## sd(sigma_Intercept) 0.44 0.02 0.40 0.49 1.00 1656 3833
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.54 0.03 1.49 1.59 1.01 422 888
## sigma_Intercept -0.96 0.03 -1.03 -0.90 1.01 1047 2016
##
## 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] 200
nrow(rans_i)
## [1] 200
nrow(data_w)
## [1] 200
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
## -2.0708 -0.5950 -0.0799 0.5067 2.2655
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.5887 0.3505 4.533 1.01e-05 ***
## Est.SD 0.3331 0.1450 2.298 0.0226 *
## Est.M 0.8109 0.1730 4.688 5.14e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8053 on 197 degrees of freedom
## Multiple R-squared: 0.1762, Adjusted R-squared: 0.1679
## F-statistic: 21.07 on 2 and 197 DF, p-value: 5.101e-09
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
## -1.95439 -0.60496 -0.08031 0.47560 2.34873
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.0278 0.2542 4.044 7.53e-05 ***
## Est.M 0.9664 0.1609 6.007 8.92e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8139 on 198 degrees of freedom
## Multiple R-squared: 0.1541, Adjusted R-squared: 0.1499
## F-statistic: 36.08 on 1 and 198 DF, p-value: 8.921e-09
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)
## 1 198 131.16
## 2 197 127.74 1 3.4231 5.279 0.02263 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
summary(fit1)$r.squared-summary(fit1.2)$r.squared
## [1] 0.02207494
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"))