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$negemo_full_m, na.rm = T)
## [1] 1.015365
mean(dataset$negemo_full_m, na.rm = T)
## [1] 2.672167
sd(dataset$posemo_full_m, na.rm = T)
## [1] 0.9332975
mean(dataset$posemo_full_m, na.rm = T)
## [1] 2.429311
sd(dataset$neuro_t, na.rm = T)
## [1] 1.178334
mean(dataset$neuro_t, na.rm = T)
## [1] 3.281894
qplot(dataset$negemo_full_, binwidth = .1)
qplot(dataset$posemo_full_, binwidth = .1)
dataset$Acens <- case_when(dataset$negemo_full_m == 1 ~ "left",
dataset$negemo_full_m == 5 ~ "right",
TRUE ~ "none")
table(dataset$Acens)
##
## left none right
## 143 2904 44
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
## 350 2724 17
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"))
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: 3091)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 112)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.73 0.05 0.64 0.84 1.00 1940 3916
## sd(sigma_Intercept) 0.38 0.03 0.32 0.44 1.00 5020 8930
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.86 0.21 1.44 2.28 1.00 1250 2158
## sigma_Intercept -0.41 0.11 -0.64 -0.19 1.00 3613 7123
## neuro_t 0.24 0.06 0.12 0.37 1.00 1368 2139
## sigma_neuro_t 0.01 0.03 -0.05 0.08 1.00 3472 7176
##
## 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, 2.7, 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.
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: 3091)
## Draws: 4 chains, each with iter = 6000; warmup = 2000; thin = 1;
## total post-warmup draws = 16000
##
## Group-Level Effects:
## ~person_id (Number of levels: 112)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.72 0.05 0.63 0.83 1.00 1883 3031
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.87 0.21 1.47 2.28 1.00 1332 2403
## neuro_t 0.24 0.06 0.13 0.36 1.00 1381 2608
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.76 0.01 0.74 0.78 1.00 18165 11553
##
## 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$file, ".xlsx"))
kable(loo)
| modelB |
0.0000 |
0.00000 |
-3281.150 |
44.64588 |
200.8145 |
8.590109 |
6562.301 |
89.29176 |
Dataset 2 public.csv |
| modelA |
-282.0869 |
25.93122 |
-3563.237 |
44.70980 |
108.6799 |
3.166631 |
7126.474 |
89.41960 |
Dataset 2 public.csv |
censoring vs. no censoring
Kn_model_neuro4 <- brm(bf(negemo_full_m ~ neuro_t + (1|person_id),
sigma ~ neuro_t+ (1|person_id)), data = dataset,
iter = 7000, warmup = 2000, chains = 4,
control = list(adapt_delta = .9999), init = 0,
file = paste("models/", params$file, "Kn_model_neuro4"))
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: 3091)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 112)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.68 0.05 0.60 0.78 1.00 2712 6146
## sd(sigma_Intercept) 0.36 0.03 0.31 0.42 1.00 5524 9496
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.93 0.20 1.55 2.31 1.00 1959 4150
## sigma_Intercept -0.46 0.11 -0.68 -0.25 1.00 4352 7900
## neuro_t 0.23 0.06 0.12 0.34 1.00 1901 3642
## sigma_neuro_t 0.01 0.03 -0.05 0.07 1.00 4410 8193
##
## 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"))
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: 3091)
## Draws: 4 chains, each with iter = 5000; warmup = 2000; thin = 1;
## total post-warmup draws = 12000
##
## Group-Level Effects:
## ~person_id (Number of levels: 112)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept:neuro_Q[1.00,2.67)) 0.63 0.09 0.48 0.84 1.00 1680 3463
## sd(Intercept:neuro_Q[2.67,3.67)) 0.61 0.10 0.45 0.84 1.00 1901 3743
## sd(Intercept:neuro_Q[3.67,4.67)) 0.77 0.09 0.61 0.98 1.00 1223 2836
## sd(Intercept:neuro_Q[4.67,5.00]) 1.07 0.20 0.76 1.54 1.00 1195 2812
## sd(sigma_Intercept) 0.38 0.03 0.32 0.45 1.00 2730 5188
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.87 0.19 1.49 2.25 1.00 935 1953
## sigma_Intercept -0.41 0.12 -0.64 -0.19 1.00 1733 3333
## neuro_t 0.24 0.06 0.13 0.36 1.00 755 1858
## sigma_neuro_t 0.01 0.03 -0.05 0.08 1.00 1730 3602
##
## 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$file, ".xlsx"))
kable(loo_c)
| modelC |
0.0000000 |
0.0000000 |
-3280.787 |
44.51284 |
199.8632 |
8.407642 |
6561.574 |
89.02567 |
Dataset 2 public.csv |
| modelB |
-0.3634481 |
0.8202955 |
-3281.150 |
44.64588 |
200.8145 |
8.590109 |
6562.301 |
89.29176 |
Dataset 2 public.csv |
control for gender
dataset$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.
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: 3091)
## Draws: 8 chains, each with iter = 9000; warmup = 2000; thin = 1;
## total post-warmup draws = 56000
##
## Group-Level Effects:
## ~person_id (Number of levels: 112)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.72 0.05 0.63 0.84 1.00 6721 12734
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.86 0.25 1.36 2.34 1.00 3782 7825
## sigma_Intercept -0.29 0.05 -0.38 -0.19 1.00 50402 41449
## neuro_t 0.24 0.06 0.12 0.36 1.00 3761 8245
## gender1 0.03 0.15 -0.25 0.33 1.00 3506 7078
## sigma_neuro_t 0.02 0.01 -0.00 0.04 1.00 57423 44147
## sigma_gender1 -0.11 0.03 -0.17 -0.06 1.00 56582 42365
##
## 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.
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: 3091)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 112)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.65 0.05 0.56 0.75 1.00 4375 8363
## sd(sigma_Intercept) 0.35 0.03 0.30 0.41 1.00 6985 11124
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 3.43 0.19 3.07 3.79 1.00 2818 5721
## sigma_Intercept -0.34 0.11 -0.55 -0.13 1.00 6743 10303
## neuro_t -0.33 0.05 -0.43 -0.22 1.00 3106 6092
## sigma_neuro_t 0.01 0.03 -0.05 0.07 1.00 6972 10963
##
## 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, 2.3, 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.
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: 3091)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 112)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.63 0.05 0.55 0.73 1.00 4112 7199
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 3.41 0.18 3.05 3.77 1.00 2775 5342
## neuro_t -0.32 0.05 -0.42 -0.21 1.00 2882 5129
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.79 0.01 0.77 0.81 1.00 38139 14036
##
## 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$file, ".xlsx"))
kable(looP)
| modelBp |
0.0000 |
0.00000 |
-3370.868 |
42.08365 |
190.6272 |
6.872366 |
6741.736 |
84.16731 |
Dataset 2 public.csv |
| modelAp |
-218.5871 |
20.83619 |
-3589.455 |
41.60138 |
106.8277 |
2.929685 |
7178.910 |
83.20275 |
Dataset 2 public.csv |
censoring vs. no censoring
Kp_model_neuro4 <- brm(bf(posemo_full_m ~ neuro_t + (1|person_id),
sigma ~ neuro_t + (1|person_id)), data = dataset,
chains = 4,
control = list(adapt_delta = .9999), inits = 0,
iter = 7000, warmup = 2000,
file = paste("models/", params$file, "Kp_model_neuro4"))
## Warning: Argument 'inits' is deprecated. Please use argument 'init' instead.
print(Kp_model_neuro4)
## Warning: Parts of the model have not converged (some Rhats are > 1.05). Be careful when analysing the results! We recommend running more iterations and/or
## setting stronger priors.
## Warning: There were 231 divergent transitions after warmup. Increasing adapt_delta above 0.9999 may help. See
## http://mc-stan.org/misc/warnings.html#divergent-transitions-after-warmup
## 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: 3091)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 112)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.64 0.06 0.56 0.72 3.14 4 14
## sd(sigma_Intercept) 1.15 0.18 0.94 1.37 3.09 4 14
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 3.30 0.06 3.20 3.37 3.19 4 14
## sigma_Intercept -0.25 0.17 -0.46 -0.01 3.21 4 11
## neuro_t -0.27 0.01 -0.29 -0.25 3.02 5 14
## sigma_neuro_t -0.10 0.06 -0.18 -0.03 3.32 4 12
##
## 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"))
print(Kp_model_neuro_jinxed)
## Warning: Parts of the model have not converged (some Rhats are > 1.05). Be careful when analysing the results! We recommend running more iterations and/or
## setting stronger priors.
## Warning: There were 11 divergent transitions after warmup. Increasing adapt_delta above 0.99 may help. See
## http://mc-stan.org/misc/warnings.html#divergent-transitions-after-warmup
## 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: 3091)
## Draws: 4 chains, each with iter = 5000; warmup = 2000; thin = 1;
## total post-warmup draws = 12000
##
## Group-Level Effects:
## ~person_id (Number of levels: 112)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept:neuro_Q[1.00,2.67)) 0.61 0.15 0.46 0.82 3.29 4 12
## sd(Intercept:neuro_Q[2.67,3.67)) 0.61 0.11 0.48 0.79 3.09 5 24
## sd(Intercept:neuro_Q[3.67,4.67)) 0.53 0.05 0.49 0.60 3.12 5 13
## sd(Intercept:neuro_Q[4.67,5.00]) 0.65 0.09 0.54 0.77 3.69 4 13
## sd(sigma_Intercept) 0.97 0.06 0.88 1.04 2.01 5 24
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 3.04 0.13 2.88 3.22 3.16 4 23
## sigma_Intercept 0.07 0.10 -0.11 0.16 2.63 5 11
## neuro_t -0.20 0.03 -0.25 -0.17 2.89 5 14
## sigma_neuro_t -0.17 0.03 -0.20 -0.13 3.66 4 11
##
## 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)
| modelB |
0.000 |
0.0000 |
-3370.868 |
42.08365 |
190.6272 |
6.872366 |
6741.736 |
84.16731 |
Dataset 2 public.csv |
| modelC |
-335.531 |
143.0443 |
-3706.399 |
142.84474 |
1197.0931 |
192.237605 |
7412.798 |
285.68947 |
Dataset 2 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$RSD_NA, na.rm = T)
## [1] 0.1150273 0.8354141
mean(data_w$RSD_NA, na.rm = T)
## [1] 0.3772377
sd(data_w$RSD_NA, na.rm = T)
## [1] 0.1271634
data_w$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$file, "Kn_model_logrsd_uw"))
print(m_rvi_na)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_n ~ neuro_t
## Data: data_w (Number of observations: 112)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.03 0.10 -1.23 -0.83 1.00 3816 2637
## neuro_t -0.00 0.03 -0.06 0.06 1.00 3788 2572
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.36 0.02 0.31 0.41 1.00 3744 3009
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[4,3] <- extract_param(m_rvi_na, "b_neuro_t")
data_w$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)
}
## Warning in checkOutput(M, MIN, MAX): NaN returned. Data has a mean equal the minimum
range(data_w$RSD_PA)
## [1] NaN NaN
data_w$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"))
## Warning: Rows containing NAs were excluded from the model.
print(m_rvi_pa)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_p ~ neuro_t
## Data: data_w (Number of observations: 111)
## 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 -1.06 0.09 -1.25 -0.89 1.00 3484 2894
## neuro_t 0.02 0.03 -0.03 0.07 1.00 3482 2688
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.32 0.02 0.29 0.37 1.00 3749 2663
##
## 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] 2.677738
sd(data_w$mean_NA)
## [1] 0.7273519
data_w$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$mean_PA)
## [1] 2.437363
sd(data_w$mean_PA)
## [1] 0.6191169
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] 3.399467
sd(data_w$weight_NA)
## [1] 0.8044433
range(data_w$weight_NA)
## [1] 0.137931 4.173913
m_rvi_na_w <- brm(logrsd_n| weights(weight_NA) ~ neuro_t, data= data_w,
file = paste("models/", params$file, "Kn_model_logrsd"))
print(m_rvi_na_w)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_n | weights(weight_NA) ~ neuro_t
## Data: data_w (Number of observations: 112)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.11 0.05 -1.21 -1.00 1.00 3850 2876
## neuro_t 0.02 0.02 -0.01 0.05 1.00 4221 2927
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.35 0.01 0.32 0.37 1.00 3888 2879
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[5,3] <- extract_param(m_rvi_na_w, "b_neuro_t")
data_w$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$file, "Kp_model_logrsd"))
## Warning: Rows containing NAs were excluded from the model.
print(m_rvi_pa_w)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_p | weights(weight_PA) ~ neuro_t
## Data: data_w (Number of observations: 111)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.05 0.05 -1.15 -0.96 1.00 5156 2573
## neuro_t 0.01 0.01 -0.02 0.04 1.00 4621 3056
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.32 0.01 0.29 0.34 1.00 3830 3190
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[5,6] <- extract_param(m_rvi_pa_w, "b_neuro_t")
SD
data_w$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] 0.6844775
mean(data_w$sd_PA)
## [1] 0.6847533
data_w$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: 112)
## 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 -0.47 0.11 -0.69 -0.25 1.00 4076 3055
## neuro_t 0.01 0.03 -0.06 0.07 1.00 4112 2893
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.39 0.03 0.34 0.45 1.00 3832 3067
##
## 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$file, "Kp_model_logsd"))
## Warning: Rows containing NAs were excluded from the model.
m_sd_pa
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logsd_PA ~ neuro_t
## Data: data_w (Number of observations: 111)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -0.29 0.10 -0.49 -0.09 1.00 3785 2883
## neuro_t -0.04 0.03 -0.09 0.02 1.00 3654 2561
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.34 0.02 0.30 0.39 1.00 4355 2991
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[6,6] <- extract_param(m_sd_pa, "b_neuro_t")
library("writexl")
write_xlsx(results_K,paste0("", params$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")
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: 3091)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 112)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.78 0.06 0.68 0.90 1.00 1599 2971
## sd(sigma_Intercept) 0.38 0.03 0.32 0.44 1.00 4663 8628
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 2.66 0.08 2.51 2.80 1.01 924 2110
## sigma_Intercept -0.37 0.04 -0.45 -0.30 1.00 2764 5531
##
## 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] 112
nrow(rans_i)
## [1] 112
nrow(data_w)
## [1] 112
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
## -2.37545 -0.77272 0.07309 0.81984 2.75704
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.7703 0.3794 4.667 8.76e-06 ***
## Est.SD 0.5682 0.3145 1.807 0.0736 .
## Est.M 0.6455 0.1445 4.468 1.94e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.096 on 109 degrees of freedom
## Multiple R-squared: 0.156, Adjusted R-squared: 0.1405
## F-statistic: 10.07 on 2 and 109 DF, p-value: 9.697e-05
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
## -2.3493 -0.8991 0.1921 0.8066 2.4416
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.7776 0.3832 4.639 9.73e-06 ***
## Est.M 0.5635 0.1386 4.067 8.99e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.107 on 110 degrees of freedom
## Multiple R-squared: 0.1307, Adjusted R-squared: 0.1228
## F-statistic: 16.54 on 1 and 110 DF, p-value: 8.991e-05
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)
## 1 110 134.82
## 2 109 130.90 1 3.9192 3.2635 0.0736 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
summary(fit1)$r.squared-summary(fit1.2)$r.squared
## [1] 0.02527091
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"))