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$negemo_full_m, na.rm = T)
## [1] 0.6183701
mean(dataset$negemo_full_m, na.rm = T)
## [1] 1.41108
sd(dataset$posemo_full_m, na.rm = T)
## [1] 0.6631019
mean(dataset$posemo_full_m, na.rm = T)
## [1] 2.950298
sd(dataset$neuro_t, na.rm = T)
## [1] 0.8655486
mean(dataset$neuro_t, na.rm = T)
## [1] 2.524973
qplot(dataset$negemo_full_, binwidth = .1)
## Warning: Removed 1092 rows containing non-finite values (`stat_bin()`).
qplot(dataset$posemo_full_, binwidth = .1)
## Warning: Removed 1085 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
## 1474 4656 8
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
## 16 6114 8
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: 4650)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 78)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.51 0.05 0.43 0.60 1.00 1670 3013
## sd(sigma_Intercept) 0.65 0.06 0.55 0.77 1.00 1895 3736
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 0.91 0.18 0.57 1.26 1.00 875 2075
## sigma_Intercept -1.28 0.23 -1.72 -0.82 1.00 1249 2482
## neuro_t 0.15 0.07 0.02 0.27 1.00 1014 2656
## sigma_neuro_t 0.13 0.09 -0.04 0.30 1.00 1290 2726
##
## 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, 1.1, 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: 4650)
## Draws: 4 chains, each with iter = 6000; warmup = 2000; thin = 1;
## total post-warmup draws = 16000
##
## Group-Level Effects:
## ~person_id (Number of levels: 78)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.54 0.05 0.46 0.64 1.00 935 1634
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 0.82 0.19 0.46 1.19 1.01 737 1681
## neuro_t 0.18 0.07 0.04 0.31 1.01 753 1594
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.54 0.01 0.53 0.56 1.00 12281 11072
##
## 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$file, ".xlsx"))
kable(loo)
| modelB |
0.00 |
0.00000 |
-2437.735 |
88.03844 |
252.72362 |
28.332715 |
4875.471 |
176.0769 |
Dataset 8 public.csv |
| modelA |
-1095.98 |
77.20871 |
-3533.716 |
83.72160 |
80.11214 |
3.362601 |
7067.431 |
167.4432 |
Dataset 8 public.csv |
censoring vs. no censoring
Kn_model_neuro4 <- brm(bf(negemo_full_m ~ neuro_t + (1|person_id),
sigma ~ neuro_t+ (1|person_id)), data = dataset,
iter = 7000, warmup = 2000, chains = 4,
control = list(adapt_delta = .9999), init = 0,
file = paste("models/", params$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: 4650)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 78)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.42 0.04 0.36 0.50 1.01 905 1610
## sd(sigma_Intercept) 0.69 0.06 0.59 0.81 1.00 838 2050
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.09 0.14 0.82 1.36 1.01 469 795
## sigma_Intercept -1.89 0.24 -2.37 -1.42 1.01 432 871
## neuro_t 0.12 0.05 0.02 0.23 1.01 554 1336
## sigma_neuro_t 0.24 0.09 0.07 0.42 1.00 452 905
##
## 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: 4650)
## Draws: 4 chains, each with iter = 5000; warmup = 2000; thin = 1;
## total post-warmup draws = 12000
##
## Group-Level Effects:
## ~person_id (Number of levels: 78)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept:neuro_Q[1.00,2.00)) 0.47 0.09 0.34 0.68 1.00 1712 2916
## sd(Intercept:neuro_Q[2.00,2.67)) 0.31 0.06 0.21 0.45 1.00 1642 3389
## sd(Intercept:neuro_Q[2.67,3.33)) 0.72 0.14 0.50 1.05 1.00 1083 2035
## sd(Intercept:neuro_Q[3.33,5.00]) 0.63 0.13 0.44 0.94 1.00 1858 3465
## sd(sigma_Intercept) 0.64 0.06 0.55 0.76 1.01 1145 1820
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 0.83 0.18 0.46 1.18 1.01 797 1426
## sigma_Intercept -1.29 0.23 -1.73 -0.85 1.00 943 1738
## neuro_t 0.15 0.08 0.01 0.30 1.00 713 1566
## sigma_neuro_t 0.13 0.08 -0.03 0.30 1.00 883 1756
##
## 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$file, ".xlsx"))
kable(loo_c)
| modelC |
0.000000 |
0.000000 |
-2436.469 |
87.90374 |
251.2105 |
27.98919 |
4872.938 |
175.8075 |
Dataset 8 public.csv |
| modelB |
-1.266533 |
1.952663 |
-2437.735 |
88.03844 |
252.7236 |
28.33271 |
4875.471 |
176.0769 |
Dataset 8 public.csv |
control for gender
dataset$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"))
print(Kn_model_sex)
pp_check(Kn_model_sex)
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: 4655)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 78)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.47 0.04 0.40 0.55 1.00 1211 2675
## sd(sigma_Intercept) 0.41 0.04 0.35 0.49 1.00 1890 3722
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 3.43 0.16 3.11 3.75 1.01 796 1677
## sigma_Intercept -1.04 0.15 -1.33 -0.74 1.00 1310 2452
## neuro_t -0.18 0.06 -0.30 -0.06 1.00 852 1485
## sigma_neuro_t 0.06 0.05 -0.05 0.17 1.00 1376 2543
##
## 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, 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: 4655)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 78)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.46 0.04 0.39 0.55 1.00 1102 2256
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 3.44 0.16 3.11 3.75 1.01 647 1323
## neuro_t -0.19 0.06 -0.30 -0.06 1.01 677 1228
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.47 0.00 0.46 0.48 1.00 13623 13369
##
## 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$file, ".xlsx"))
kable(looP)
| modelBp |
0.0000 |
0.00000 |
-2513.414 |
82.11583 |
213.22310 |
24.565637 |
5026.828 |
164.2317 |
Dataset 8 public.csv |
| modelAp |
-632.8817 |
57.16816 |
-3146.296 |
70.88340 |
79.57036 |
2.466759 |
6292.592 |
141.7668 |
Dataset 8 public.csv |
censoring vs. no censoring
Kp_model_neuro4 <- brm(bf(posemo_full_m ~ neuro_t + (1|person_id),
sigma ~ neuro_t + (1|person_id)), data = dataset,
chains = 4,
control = list(adapt_delta = .9999), inits = 0,
iter = 7000, warmup = 2000,
file = paste("models/", params$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: 4655)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 78)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.47 0.04 0.40 0.55 1.00 2071 4036
## sd(sigma_Intercept) 0.40 0.03 0.34 0.48 1.00 3073 4941
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 3.43 0.16 3.11 3.76 1.01 1177 2405
## sigma_Intercept -1.05 0.14 -1.34 -0.77 1.00 2017 4125
## neuro_t -0.18 0.06 -0.30 -0.06 1.01 1312 2823
## sigma_neuro_t 0.06 0.05 -0.05 0.16 1.00 2033 4329
##
## 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$file, "Kp_model_neuro_jinxed"))
## Warning: Rows containing NAs were excluded from the model.
print(Kp_model_neuro_jinxed)
## Family: gaussian
## Links: mu = identity; sigma = log
## Formula: posemo_full_m | cens(Acens) ~ neuro_t + (1 | gr(person_id, by = neuro_Q))
## sigma ~ neuro_t + (1 | person_id)
## Data: dataset (Number of observations: 4655)
## Draws: 4 chains, each with iter = 5000; warmup = 2000; thin = 1;
## total post-warmup draws = 12000
##
## Group-Level Effects:
## ~person_id (Number of levels: 78)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept:neuro_Q[1.00,2.00)) 0.37 0.07 0.26 0.53 1.00 1800 3601
## sd(Intercept:neuro_Q[2.00,2.67)) 0.52 0.09 0.37 0.72 1.00 1042 2455
## sd(Intercept:neuro_Q[2.67,3.33)) 0.39 0.08 0.27 0.57 1.00 1423 2877
## sd(Intercept:neuro_Q[3.33,5.00]) 0.61 0.12 0.43 0.89 1.00 1592 3567
## sd(sigma_Intercept) 0.42 0.04 0.36 0.50 1.00 1912 3473
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 3.11 0.15 2.81 3.41 1.00 913 1822
## sigma_Intercept -0.95 0.15 -1.25 -0.65 1.00 1127 2114
## neuro_t -0.12 0.06 -0.24 -0.00 1.01 881 1685
## sigma_neuro_t 0.04 0.06 -0.07 0.16 1.00 1136 2232
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
modelB <- Kp_model_neuro3
modelC <- Kp_model_neuro_jinxed
modelB <- add_criterion(modelB, "loo")
modelC <- add_criterion(modelC, "loo")
loo_cP <- loo_compare(modelB,modelC, criterion = "loo")
## Warning: Not all models have the same y variable. ('yhash' attributes do not match)
loo_cP <- as.data.frame(loo_cP)
loo_cP$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 |
0.0000 |
0.00000 |
-2328.892 |
59.51439 |
174.4699 |
11.20535 |
4657.785 |
119.0288 |
Dataset 8 public.csv |
| modelB |
-184.5219 |
56.00635 |
-2513.414 |
82.11583 |
213.2231 |
24.56564 |
5026.828 |
164.2317 |
Dataset 8 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$RSD_NA, na.rm = T)
## [1] 0.08121707 0.69932240
mean(data_w$RSD_NA, na.rm = T)
## [1] 0.3363936
sd(data_w$RSD_NA, na.rm = T)
## [1] 0.1406409
data_w$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$file, "Kn_model_logrsd_uw"))
print(m_rvi_na)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_n ~ neuro_t
## Data: data_w (Number of observations: 78)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.23 0.16 -1.54 -0.92 1.00 3786 2952
## neuro_t 0.03 0.06 -0.08 0.15 1.00 3874 3036
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.45 0.04 0.39 0.53 1.00 3817 2503
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[4,3] <- extract_param(m_rvi_na, "b_neuro_t")
data_w$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$RSD_PA)
## [1] 0.07800037 0.57423965
data_w$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: 78)
## 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 -1.75 0.15 -2.04 -1.45 1.00 4031 2881
## neuro_t 0.07 0.05 -0.04 0.18 1.00 4190 2688
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.41 0.03 0.35 0.48 1.00 4483 3136
##
## 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] 1.43376
sd(data_w$mean_NA)
## [1] 0.4758251
data_w$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$mean_PA)
## [1] 2.935263
sd(data_w$mean_PA)
## [1] 0.4851171
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] 1.299776
sd(data_w$weight_NA)
## [1] 1.150438
range(data_w$weight_NA)
## [1] 0.005664317 4.005961151
m_rvi_na_w <- brm(logrsd_n| weights(weight_NA) ~ neuro_t, data= data_w,
file = paste("models/", params$file, "Kn_model_logrsd"))
## Warning: Rows containing NAs were excluded from the model.
print(m_rvi_na_w)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_n | weights(weight_NA) ~ neuro_t
## Data: data_w (Number of observations: 78)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.45 0.17 -1.77 -1.12 1.00 2970 2287
## neuro_t 0.11 0.06 -0.00 0.22 1.00 3374 2861
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.49 0.03 0.43 0.57 1.00 3312 2924
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[5,3] <- extract_param(m_rvi_na_w, "b_neuro_t")
data_w$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$file, "Kp_model_logrsd"))
## Warning: Rows containing NAs were excluded from the model.
print(m_rvi_pa_w)
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logrsd_p | weights(weight_PA) ~ neuro_t
## Data: data_w (Number of observations: 78)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.74 0.07 -1.88 -1.60 1.00 3923 3058
## neuro_t 0.07 0.03 0.01 0.12 1.00 3823 2985
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.41 0.02 0.38 0.44 1.00 4973 3197
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[5,6] <- extract_param(m_rvi_pa_w, "b_neuro_t")
SD
data_w$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] 0.3452938
mean(data_w$sd_PA)
## [1] 0.4366325
data_w$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"))
## Warning: Rows containing NAs were excluded from the model.
m_sd_na
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logsd_NA ~ neuro_t
## Data: data_w (Number of observations: 78)
## 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 -1.88 0.24 -2.36 -1.40 1.00 4601 3241
## neuro_t 0.23 0.09 0.05 0.41 1.00 4694 3277
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.70 0.06 0.59 0.82 1.00 3814 3177
##
## 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$file, "Kp_model_logsd"))
## Warning: Rows containing NAs were excluded from the model.
m_sd_pa
## Family: gaussian
## Links: mu = identity; sigma = identity
## Formula: logsd_PA ~ neuro_t
## Data: data_w (Number of observations: 78)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept -1.05 0.14 -1.34 -0.77 1.00 3942 3013
## neuro_t 0.06 0.05 -0.05 0.16 1.00 4053 3046
##
## Family Specific Parameters:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sigma 0.41 0.03 0.35 0.49 1.00 3583 2877
##
## Draws were sampled using sample(hmc). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).
results_K[6,6] <- extract_param(m_sd_pa, "b_neuro_t")
library("writexl")
write_xlsx(results_K,paste0("", params$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: 5046)
## Draws: 4 chains, each with iter = 7000; warmup = 2000; thin = 1;
## total post-warmup draws = 20000
##
## Group-Level Effects:
## ~person_id (Number of levels: 85)
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept) 0.55 0.05 0.47 0.64 1.01 1500 3508
## sd(sigma_Intercept) 0.65 0.05 0.55 0.76 1.00 1873 3570
##
## Population-Level Effects:
## Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept 1.31 0.06 1.19 1.43 1.01 446 1035
## sigma_Intercept -0.96 0.07 -1.11 -0.82 1.00 798 1875
##
## 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] 85
nrow(rans_i)
## [1] 85
nrow(data_w)
## [1] 85
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
## -1.56872 -0.63540 -0.07836 0.47728 2.54748
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.2267 0.3406 6.537 6.75e-09 ***
## Est.SD 0.1756 0.1605 1.094 0.2774
## Est.M 0.3692 0.1980 1.865 0.0661 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8547 on 75 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.07438, Adjusted R-squared: 0.0497
## F-statistic: 3.014 on 2 and 75 DF, p-value: 0.0551
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
## -1.5759 -0.6392 -0.0664 0.4946 2.7480
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.9924 0.2652 7.513 9.37e-11 ***
## Est.M 0.4220 0.1922 2.195 0.0312 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8558 on 76 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.05961, Adjusted R-squared: 0.04724
## F-statistic: 4.817 on 1 and 76 DF, p-value: 0.03123
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 76 55.659
## 2 75 54.784 1 0.87447 1.1972 0.2774
summary(fit1)$r.squared-summary(fit1.2)$r.squared
## [1] 0.01477476
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"))