Package 'BPrinStratTTE' reference manual

Title:	Causal Effects in Principal Strata Defined by Antidrug Antibodies
Description:	Bayesian models to estimate causal effects of biological treatments on time-to-event endpoints in clinical trials with principal strata defined by the occurrence of antidrug antibodies. The methodology is based on Frangakis and Rubin (2002) <doi:10.1111/j.0006-341x.2002.00021.x> and Imbens and Rubin (1997) <doi:10.1214/aos/1034276631>, and here adapted to a specific time-to-event setting.
Authors:	Christian Stock [aut, cre] , Emma Torrini [aut], Boehringer Ingelheim Pharma GmbH & Co. KG [cph, fnd]
Maintainer:	Christian Stock <[email protected]>
License:	GPL (>= 3)
Version:	0.0.7
Built:	2025-01-24 04:27:46 UTC
Source:	https://github.com/boehringer-ingelheim/bprinstrattte

The 'BPrinStratTTE' package.

Description

Bayesian models to estimate causal effects of biological treatments on time-to-event endpoints in clinical trials with principal strata defined by the occurrence of antidrug antibodies. The methodology is based on Frangakis and Rubin (2002) doi:10.1111/j.0006-341x.2002.00021.x and Imbens and Rubin (1997) doi:10.1214/aos/1034276631, and intended to be applied to a specific time-to-event setting.#'

References

Stan Development Team (2022). RStan: the R interface to Stan. R package version 2.21.5. https://mc-stan.org

Fit multiple models to data from two-arm trials with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Description

Fit multiple models to data from two-arm trials with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Usage

fit_mult_exp_covar(dat_mult_trials, params, seed = 23)
fit_mult_exp_covar(dat_mult_trials, params, seed = 23)

Arguments

`dat_mult_trials`	List generated by `sim_dat_mult_trials_exp_covar`.
`params`	List of model parameters as supplied to `fit_single_exp_covar`.
`seed`	Numeric value, seed for reproducibility.

Value

A list of objects generated by fit_single_exp_covar.

Examples

d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 48*7,
  prop_cens = 0.15,         
  T0T_rate = 0.2,     
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
dat_mult_trials <- sim_dat_mult_trials_exp_covar(
  n_iter = 2,
  params = d_params_covar 
)
m_params_covar <- list(
  tg = 48,
  p = 2, 
  prior_delta = matrix(
    c(0, 5, 0, 5),
    nrow = 2, byrow = TRUE),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2,
  n_iter = 3000,
  warmup = 1500,
  cores = 2,
  open_progress = FALSE,
  show_messages = TRUE
)

fit_multiple <- fit_mult_exp_covar(
  dat_mult_trials = dat_mult_trials,
  params = m_params_covar,
  seed = 12
)
lapply(fit_multiple, dim)
head(fit_multiple[[1]])


d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 48*7,
  prop_cens = 0.15,         
  T0T_rate = 0.2,     
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
dat_mult_trials <- sim_dat_mult_trials_exp_covar(
  n_iter = 2,
  params = d_params_covar 
)
m_params_covar <- list(
  tg = 48,
  p = 2, 
  prior_delta = matrix(
    c(0, 5, 0, 5),
    nrow = 2, byrow = TRUE),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2,
  n_iter = 3000,
  warmup = 1500,
  cores = 2,
  open_progress = FALSE,
  show_messages = TRUE
)

fit_multiple <- fit_mult_exp_covar(
  dat_mult_trials = dat_mult_trials,
  params = m_params_covar,
  seed = 12
)
lapply(fit_multiple, dim)
head(fit_multiple[[1]])

Fit multiple models to data from two-arm trials with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Description

Fit multiple models to data from two-arm trials with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Usage

fit_mult_exp_nocovar(dat_mult_trials, params, seed = 23)
fit_mult_exp_nocovar(dat_mult_trials, params, seed = 23)

Arguments

`dat_mult_trials`	List generated by `sim_dat_mult_trials_exp_nocovar`.
`params`	List of model parameters as supplied to `fit_single_exp_nocovar`.
`seed`	Numeric value, seed for reproducibility.

Value

A list of objects generated by fit_single_exp_nocovar.

Examples

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  prop_cens = 0.15,  
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
dat_mult_trials <- sim_dat_mult_trials_exp_nocovar(
  n_iter = 2,
  params = d_params_nocovar 
)
m_params_nocovar <- list(
  tg = 48L,
  prior_piT = c(0.5, 0.5),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2L,
  n_iter = 3000L,
  warmup = 1500L,
  cores = 2L,
  open_progress = FALSE,
  show_messages = TRUE
)

fit_multiple <- fit_mult_exp_nocovar(
  dat_mult_trials = dat_mult_trials,
  params = m_params_nocovar,
  seed = 12
)
lapply(fit_multiple, dim)
head(fit_multiple[[1]])

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  prop_cens = 0.15,  
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
dat_mult_trials <- sim_dat_mult_trials_exp_nocovar(
  n_iter = 2,
  params = d_params_nocovar 
)
m_params_nocovar <- list(
  tg = 48L,
  prior_piT = c(0.5, 0.5),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2L,
  n_iter = 3000L,
  warmup = 1500L,
  cores = 2L,
  open_progress = FALSE,
  show_messages = TRUE
)

fit_multiple <- fit_mult_exp_nocovar(
  dat_mult_trials = dat_mult_trials,
  params = m_params_nocovar,
  seed = 12
)
lapply(fit_multiple, dim)
head(fit_multiple[[1]])

Fit single model to data from a two-arm trial with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Description

Fit single model to data from a two-arm trial with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Usage

fit_single_exp_covar(data, params, summarize_fit = TRUE)
fit_single_exp_covar(data, params, summarize_fit = TRUE)

Arguments

data

Data frame of a structure as generated by sim_dat_one_trial_exp_covar().

params

List, containing model parameters:

tg Positive integer value, number of intervals to calculate restricted mean survival time using the trapezoidal rule.
p Positive integer value, number of predictors of the intercurrent event of interest (i.e. the event that determines. the principal stratum membership).
prior_delta px2 matrix of positive numerical values, containing normal priors (mean and standard deviation) of the model parameter delta.
prior_0N Numeric vector of length 2, containing parameters (alpha, beta) of the gamma prior on lambda_0N.
prior_1N Numeric vector of length 2, containing parameters (alpha, beta) of the gamma prior on lambda_1N.
prior_0T Numeric vector of length 2, containing parameters (alpha, beta) of the gamma prior on lambda_0T.
prior_1T Numeric vector of length 2, containing parameters (alpha, beta) of the gamma prior on lambda_1T.
t_grid Numeric vector of length tg, containing time points defining the time grid (in months) to calculate restricted mean survival time using the trapezoidal rule.
chains Positive integer value, specifying the number of Markov chains.
n_iter Positive integer value, specifying the number of iterations for each chain (including warmup).
warmup Positive integer value, specifying the number of warmup (aka burnin) iterations per chain.
cores Positive integer value, specifying the number of cores to use when executing the chains in parallel.
open_progress Logical value, indicating whether the progress of the chains will be redirected to a file that is automatically opened for inspection.
show_messages Logical value, indicating whether to print the summary of informational messages.

summarize_fit

Logical, if TRUE (default), the output is restricted to a summary of results on key parameters over all chains, if FALSE, the complete stanfit object is returned.

Details

The data supplied as params are used either as priors (prior_delta, prior_0N, prior_1N, prior_1T), to inform the model setup (tg, p, t_grid), or as parameters to rstan::sampling() which is invoked internally (chains, n_iter, warmup, cores, open_progress, show_messages).

Value

tibble() containing a summary of results on key parameters, or a stanfit object (S4 class), depending on summarize_fit.

Examples

d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 48*7,       
  T0T_rate = 0.2,     
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
dat_single_trial <- sim_dat_one_trial_exp_covar(
  n = d_params_covar[["n"]], 
  nt = d_params_covar[["nt"]],
  prob_X1 = d_params_covar[["prob_X1"]],
  prob_ice_X1 = d_params_covar[["prob_ice_X1"]],
  prob_ice_X0 = d_params_covar[["prob_ice_X0"]],
  fu_max = d_params_covar[["fu_max"]],  
  T0T_rate = d_params_covar[["T0T_rate"]],
  T0N_rate = d_params_covar[["T0N_rate"]],
  T1T_rate = d_params_covar[["T1T_rate"]],
  T1N_rate = d_params_covar[["T1N_rate"]] 
)
m_params_covar <- list(
  tg = 48,
  p = 2, 
  prior_delta = matrix(
    c(0, 5, 0, 5),
    nrow = 2, byrow = TRUE),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2,
  n_iter = 3000,
  warmup = 1500,
  cores = 2,
  open_progress = FALSE,
  show_messages = FALSE   
)

fit_single <- fit_single_exp_covar(
  data = dat_single_trial,
  params = m_params_covar,
  summarize_fit = FALSE
)
print(fit_single) 

d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 48*7,       
  T0T_rate = 0.2,     
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
dat_single_trial <- sim_dat_one_trial_exp_covar(
  n = d_params_covar[["n"]], 
  nt = d_params_covar[["nt"]],
  prob_X1 = d_params_covar[["prob_X1"]],
  prob_ice_X1 = d_params_covar[["prob_ice_X1"]],
  prob_ice_X0 = d_params_covar[["prob_ice_X0"]],
  fu_max = d_params_covar[["fu_max"]],  
  T0T_rate = d_params_covar[["T0T_rate"]],
  T0N_rate = d_params_covar[["T0N_rate"]],
  T1T_rate = d_params_covar[["T1T_rate"]],
  T1N_rate = d_params_covar[["T1N_rate"]] 
)
m_params_covar <- list(
  tg = 48,
  p = 2, 
  prior_delta = matrix(
    c(0, 5, 0, 5),
    nrow = 2, byrow = TRUE),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2,
  n_iter = 3000,
  warmup = 1500,
  cores = 2,
  open_progress = FALSE,
  show_messages = FALSE   
)

fit_single <- fit_single_exp_covar(
  data = dat_single_trial,
  params = m_params_covar,
  summarize_fit = FALSE
)
print(fit_single)

Fit single model to data from a two-arm trial with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Description

Fit single model to data from a two-arm trial with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Usage

fit_single_exp_nocovar(data, params, summarize_fit = TRUE)
fit_single_exp_nocovar(data, params, summarize_fit = TRUE)

Arguments

data

Data frame of a structure as generated by sim_dat_one_trial_exp_nocovar().

params

List, containing model parameters:

tg Positive integer value, number of intervals to calculate restricted mean survival time using the trapezoidal rule.
prior_piT Numeric vector of length 2, containing parameters (alpha, beta) of the beta prior on pi, indicating the probability of belonging to the stratum of subjects developing the intercurrent event if given treatment.
prior_0N Numeric vector of length 2, containing parameters (alpha, beta) of the gamma prior on lambda_0N.
prior_1N Numeric vector of length 2, containing parameters (alpha, beta) of the gamma prior on lambda_1N.
prior_0T Numeric vector of length 2, containing parameters (alpha, beta) of the gamma prior on lambda_0T.
prior_1T Numeric vector of length 2, containing parameters (alpha, beta) of the gamma prior on lambda_1T.
t_grid Numeric vector of length tg, containing time points defining the time grid (in months) to calculate restricted mean survival time using the trapezoidal rule.
chains Positive integer value, specifying the number of Markov chains.
n_iter Positive integer value, specifying the number of iterations for each chain (including warmup).
warmup Positive integer value, specifying the number of warmup (aka burnin) iterations per chain.
cores Positive integer value, specifying the number of cores to use when executing the chains in parallel.
open_progress Logical value, indicating whether the progress of the chains will be redirected to a file that is automatically opened for inspection.
show_messages Logical value, indicating whether to print the summary of informational messages.

summarize_fit

Logical, if TRUE (default), the output is restricted to a summary of results on key parameters over all chains, if FALSE, the complete stanfit object is returned.

Details

Value

tibble() containing a summary of results on key parameters, or a stanfit object, depending on summarize_fit.

Examples

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
dat_single_trial <- sim_dat_one_trial_exp_nocovar(
  n = d_params_nocovar[["n"]], 
  nt = d_params_nocovar[["nt"]],
  prob_ice = d_params_nocovar[["prob_ice"]],
  fu_max = d_params_nocovar[["fu_max"]],  
  T0T_rate = d_params_nocovar[["T0T_rate"]],
  T0N_rate = d_params_nocovar[["T0N_rate"]],
  T1T_rate = d_params_nocovar[["T1T_rate"]],
  T1N_rate = d_params_nocovar[["T1N_rate"]] 
)
m_params_nocovar <- list(
  tg = 48L,
  prior_piT = c(0.5, 0.5),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2L,
  n_iter = 3000L,
  warmup = 1500L,
  cores = 2L,
  open_progress = FALSE,
  show_messages = TRUE
)

fit_single <- fit_single_exp_nocovar(
  data = dat_single_trial,
  params = m_params_nocovar,
  summarize_fit = TRUE
)
print(fit_single)

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
dat_single_trial <- sim_dat_one_trial_exp_nocovar(
  n = d_params_nocovar[["n"]], 
  nt = d_params_nocovar[["nt"]],
  prob_ice = d_params_nocovar[["prob_ice"]],
  fu_max = d_params_nocovar[["fu_max"]],  
  T0T_rate = d_params_nocovar[["T0T_rate"]],
  T0N_rate = d_params_nocovar[["T0N_rate"]],
  T1T_rate = d_params_nocovar[["T1T_rate"]],
  T1N_rate = d_params_nocovar[["T1N_rate"]] 
)
m_params_nocovar <- list(
  tg = 48L,
  prior_piT = c(0.5, 0.5),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2L,
  n_iter = 3000L,
  warmup = 1500L,
  cores = 2L,
  open_progress = FALSE,
  show_messages = TRUE
)

fit_single <- fit_single_exp_nocovar(
  data = dat_single_trial,
  params = m_params_nocovar,
  summarize_fit = TRUE
)
print(fit_single)

Inverse logit function

Description

Inverse logit function

Usage

inv_logit(x)
inv_logit(x)

Arguments

`x`	Numeric value (usually a logarithm of odds).

Details

The inverse logit function is also known as logistic function.

Value

Numeric value on the interval $[0,1]$ , result of log(pi/(1-pi)).

Numeric value, result of exp(x)/(1+exp(x)).

Examples

# probabilities 
prob_ICE_base <- 0.3
prob_ICE_risk <- 0.6
# model coefficients
(beta1 <- logit(prob_ICE_base))
(beta2 <- logit(prob_ICE_risk) - logit(prob_ICE_base))
# linear predictor 
logit(prob_ICE_base); (lin_pred1 <- beta1 + beta2*0)
logit(prob_ICE_risk); (lin_pred2 <- beta1 + beta2*1)
# inverse logit of linear predictor 
(inv_logit(lin_pred1)) # prob for X1 = 0
(inv_logit(lin_pred2)) # prob for X1 = 1
# probabilities 
prob_ICE_base <- 0.3
prob_ICE_risk <- 0.6
# model coefficients
(beta1 <- logit(prob_ICE_base))
(beta2 <- logit(prob_ICE_risk) - logit(prob_ICE_base))
# linear predictor 
logit(prob_ICE_base); (lin_pred1 <- beta1 + beta2*0)
logit(prob_ICE_risk); (lin_pred2 <- beta1 + beta2*1)
# inverse logit of linear predictor 
(inv_logit(lin_pred1)) # prob for X1 = 0
(inv_logit(lin_pred2)) # prob for X1 = 1

Logit function

Description

Logit function

Usage

logit(pi)
logit(pi)

Arguments

`pi`	Numeric value on the interval $[0,1]$ (usually a probability).

Value

Numeric value, result of log(pi/(1-pi)).

Examples

# probabilities 
prob_ICE_base <- 0.3
prob_ICE_risk <- 0.6
# model coefficients
(beta1 <- logit(prob_ICE_base))
(beta2 <- logit(prob_ICE_risk) - logit(prob_ICE_base))
# linear predictor 
logit(prob_ICE_base); (lin_pred1 <- beta1 + beta2*0)
logit(prob_ICE_risk); (lin_pred2 <- beta1 + beta2*1)
# inverse logit of linear predictor 
(inv_logit(lin_pred1)) # prob for X1 = 0
(inv_logit(lin_pred2)) # prob for X1 = 1
# probabilities 
prob_ICE_base <- 0.3
prob_ICE_risk <- 0.6
# model coefficients
(beta1 <- logit(prob_ICE_base))
(beta2 <- logit(prob_ICE_risk) - logit(prob_ICE_base))
# linear predictor 
logit(prob_ICE_base); (lin_pred1 <- beta1 + beta2*0)
logit(prob_ICE_risk); (lin_pred2 <- beta1 + beta2*1)
# inverse logit of linear predictor 
(inv_logit(lin_pred1)) # prob for X1 = 0
(inv_logit(lin_pred2)) # prob for X1 = 1

Determine operating characteristics of fits from two-arm trials with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Description

Determine operating characteristics of fits from two-arm trials with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Usage

ocs_exp_covar(multiple_fits, d_params, m_params)
ocs_exp_covar(multiple_fits, d_params, m_params)

Arguments

`multiple_fits`	List of model fits from `fit_mult_exp_covar`.
`d_params`	List of data parameters as used in `sim_dat_one_trial_exp_covar`.
`m_params`	List of model parameters as used in `fit_single_exp_covar`.

Details

This function is used in run_sim_exp_covar(), the output of the two functions is the same.

Value

A list of length 3, containing objects call ocs, d_params, m_params, where ocs is a tibble containing averaged parameter estimates and operating characteristics, and d_params and m_params are the objects supplied to the function.

Examples

d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 48*7,
  prop_cens = 0.15,       
  T0T_rate = 0.2,     
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
dat_mult_trials <- sim_dat_mult_trials_exp_covar(
  n_iter = 2,
  params = d_params_covar 
)
m_params_covar <- list(
  tg = 48,
  p = 2, 
  prior_delta = matrix(
    c(0, 5, 0, 5),
    nrow = 2, byrow = TRUE),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2,
  n_iter = 3000,
  warmup = 1500,
  cores = 2,
  open_progress = FALSE,
  show_messages = TRUE
)

fit_multiple <- fit_mult_exp_covar(
  dat_mult_trials = dat_mult_trials,
  params = m_params_covar,
  seed = 12
)
list_ocs <- ocs_exp_covar(
  multiple_fits = fit_multiple, 
  d_params = d_params_covar, 
  m_params = m_params_covar
)
print(list_ocs)


d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 48*7,
  prop_cens = 0.15,       
  T0T_rate = 0.2,     
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
dat_mult_trials <- sim_dat_mult_trials_exp_covar(
  n_iter = 2,
  params = d_params_covar 
)
m_params_covar <- list(
  tg = 48,
  p = 2, 
  prior_delta = matrix(
    c(0, 5, 0, 5),
    nrow = 2, byrow = TRUE),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2,
  n_iter = 3000,
  warmup = 1500,
  cores = 2,
  open_progress = FALSE,
  show_messages = TRUE
)

fit_multiple <- fit_mult_exp_covar(
  dat_mult_trials = dat_mult_trials,
  params = m_params_covar,
  seed = 12
)
list_ocs <- ocs_exp_covar(
  multiple_fits = fit_multiple, 
  d_params = d_params_covar, 
  m_params = m_params_covar
)
print(list_ocs)

Determine operating characteristics of fits from two-arm trials with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Description

Determine operating characteristics of fits from two-arm trials with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Usage

ocs_exp_nocovar(multiple_fits, d_params, m_params)
ocs_exp_nocovar(multiple_fits, d_params, m_params)

Arguments

`multiple_fits`	List of model fits from `fit_mult_exp_nocovar`.
`d_params`	List of data parameters as used in `sim_dat_one_trial_exp_nocovar`.
`m_params`	List of model parameters as used in `fit_single_exp_nocovar`.

Details

This function is used in run_sim_exp_nocovar(), the output of the two functions is the same.

Value

Examples

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  prop_cens = 0.15,
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
dat_mult_trials <- sim_dat_mult_trials_exp_nocovar(
  n_iter = 2,
  params = d_params_nocovar 
)
m_params_nocovar <- list(
  tg = 48L,
  prior_piT = c(0.5, 0.5),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2L,
  n_iter = 3000L,
  warmup = 1500L,
  cores = 2L,
  open_progress = FALSE,
  show_messages = TRUE  
)

fit_multiple <- fit_mult_exp_nocovar(
  dat_mult_trials = dat_mult_trials,
  params = m_params_nocovar,
  seed = 12
)
list_ocs <- ocs_exp_nocovar(
  multiple_fits = fit_multiple, 
  d_params = d_params_nocovar, 
  m_params = m_params_nocovar
)
print(list_ocs)

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  prop_cens = 0.15,
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
dat_mult_trials <- sim_dat_mult_trials_exp_nocovar(
  n_iter = 2,
  params = d_params_nocovar 
)
m_params_nocovar <- list(
  tg = 48L,
  prior_piT = c(0.5, 0.5),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2L,
  n_iter = 3000L,
  warmup = 1500L,
  cores = 2L,
  open_progress = FALSE,
  show_messages = TRUE  
)

fit_multiple <- fit_mult_exp_nocovar(
  dat_mult_trials = dat_mult_trials,
  params = m_params_nocovar,
  seed = 12
)
list_ocs <- ocs_exp_nocovar(
  multiple_fits = fit_multiple, 
  d_params = d_params_nocovar, 
  m_params = m_params_nocovar
)
print(list_ocs)

Run simulation of two-arm trials with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Description

Run simulation of two-arm trials with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Usage

run_sim_exp_covar(n_iter, d_params, m_params, seed)
run_sim_exp_covar(n_iter, d_params, m_params, seed)

Arguments

`n_iter`	Positive integer value, number of trials to be simulated.
`d_params`	List of data parameters as used in `sim_dat_one_trial_exp_nocovar`.
`m_params`	List of model parameters as used in `fit_single_exp_nocovar`.
`seed`	Numeric value, seed for reproducibility.

Value

Examples

d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 336L,
  prop_cens = 0.15,       
  T0T_rate = 0.2,     
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
m_params_covar <- list(
  tg = 48,
  p = 2, 
  prior_delta = matrix(
    c(0, 5, 0, 5),
    nrow = 2, byrow = TRUE),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2,
  n_iter = 3000,
  warmup = 1500,
  cores = 2,
  open_progress = FALSE,
  show_messages = TRUE
)
 
dat_ocs <- run_sim_exp_covar(
  n_iter = 3, 
  d_params = d_params_covar, 
  m_params = m_params_covar, 
  seed = 12
  )
print(dat_ocs)


d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 336L,
  prop_cens = 0.15,       
  T0T_rate = 0.2,     
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
m_params_covar <- list(
  tg = 48,
  p = 2, 
  prior_delta = matrix(
    c(0, 5, 0, 5),
    nrow = 2, byrow = TRUE),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2,
  n_iter = 3000,
  warmup = 1500,
  cores = 2,
  open_progress = FALSE,
  show_messages = TRUE
)
 
dat_ocs <- run_sim_exp_covar(
  n_iter = 3, 
  d_params = d_params_covar, 
  m_params = m_params_covar, 
  seed = 12
  )
print(dat_ocs)

Run simulation of two-arm trials with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Description

Run simulation of two-arm trials with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Usage

run_sim_exp_nocovar(n_iter, d_params, m_params, seed)
run_sim_exp_nocovar(n_iter, d_params, m_params, seed)

Arguments

`n_iter`	Positive integer value, number of trials to be simulated.
`d_params`	List of data parameters as used in `sim_dat_one_trial_exp_nocovar`.
`m_params`	List of model parameters as used in `fit_single_exp_nocovar`.
`seed`	Numeric value, seed for reproducibility.

Value

Examples

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  prop_cens = 0.15,
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
m_params_nocovar <- list(
  tg = 48L,
  prior_piT = c(0.5, 0.5),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2L,
  n_iter = 3000L,
  warmup = 1500L,
  cores = 2L,
  open_progress = FALSE,
  show_messages = TRUE  
)
 
dat_ocs <- run_sim_exp_nocovar(
  n_iter = 3, 
  d_params = d_params_nocovar, 
  m_params = m_params_nocovar, 
  seed = 12
  )
print(dat_ocs)

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  prop_cens = 0.15,
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
m_params_nocovar <- list(
  tg = 48L,
  prior_piT = c(0.5, 0.5),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2L,
  n_iter = 3000L,
  warmup = 1500L,
  cores = 2L,
  open_progress = FALSE,
  show_messages = TRUE  
)
 
dat_ocs <- run_sim_exp_nocovar(
  n_iter = 3, 
  d_params = d_params_nocovar, 
  m_params = m_params_nocovar, 
  seed = 12
  )
print(dat_ocs)

Simulate data from multiple two-arm trials with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Description

Simulate data from multiple two-arm trials with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Usage

sim_dat_mult_trials_exp_covar(n_iter, params)
sim_dat_mult_trials_exp_covar(n_iter, params)

Arguments

`n_iter`	Positive integer value, number of trials to be simulated.
`params`	List of data parameters as used in `sim_dat_one_trial_exp_covar`.

Value

A list of length n_iter, containing objects of class tibble(), each containing one simulated trial dataset.

Examples

d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 336L,   
  prop_cens = 0.15,    
  T0T_rate = 0.2,     
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
dat_mult_trials <- sim_dat_mult_trials_exp_covar(
  n_iter = 3L,
  params = d_params_covar 
)
lapply(dat_mult_trials, dim)
head(dat_mult_trials[[1]]) 

d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 336L,   
  prop_cens = 0.15,    
  T0T_rate = 0.2,     
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
dat_mult_trials <- sim_dat_mult_trials_exp_covar(
  n_iter = 3L,
  params = d_params_covar 
)
lapply(dat_mult_trials, dim)
head(dat_mult_trials[[1]])

Simulate data from multiple two-arm trials with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Description

Simulate data from multiple two-arm trials with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Usage

sim_dat_mult_trials_exp_nocovar(n_iter, params)
sim_dat_mult_trials_exp_nocovar(n_iter, params)

Arguments

`n_iter`	Positive integer value, number of trials to be simulated.
`params`	List of data parameters as used in `sim_dat_one_trial_exp_nocovar`.

Value

A list of length n_iter, containing objects of class tibble(), each containing one simulated trial dataset.

Examples

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  prop_cens = 0.15,
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
dat_mult_trials <- sim_dat_mult_trials_exp_nocovar(
  n_iter = 3L,
  params = d_params_nocovar 
)
lapply(dat_mult_trials, dim)
head(dat_mult_trials[[1]]) 

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  prop_cens = 0.15,
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
dat_mult_trials <- sim_dat_mult_trials_exp_nocovar(
  n_iter = 3L,
  params = d_params_nocovar 
)
lapply(dat_mult_trials, dim)
head(dat_mult_trials[[1]])

Simulate data from a single two-arm trial with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Description

Simulate data from a single two-arm trial with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Usage

sim_dat_one_trial_exp_covar(
  n,
  nt,
  prob_X1,
  prob_ice_X1,
  prob_ice_X0,
  fu_max,
  prop_cens = 0,
  T0T_rate,
  T0N_rate,
  T1T_rate,
  T1N_rate
)
sim_dat_one_trial_exp_covar(
  n,
  nt,
  prob_X1,
  prob_ice_X1,
  prob_ice_X0,
  fu_max,
  prop_cens = 0,
  T0T_rate,
  T0N_rate,
  T1T_rate,
  T1N_rate
)

Arguments

`n`	Positive integer value, number of subjects in the trial.
`nt`	Positive integer value, number of treated subjects.
`prob_X1`	Numeric value on the interval $(0,1)$ , probability of being at high risk of experiencing the intercurrent event of interest when treated (i.e. the event that determines the principal stratum membership).
`prob_ice_X1`	Numeric value on the interval $(0,1)$ , probability of the intercurrent event of interest if treated and at high risk of the intercurrent event.
`prob_ice_X0`	Numeric value on the interval $(0,1)$ , probability of the intercurrent event of interest if treated and not at high risk of the intercurrent event.
`fu_max`	Positive integer value, maximum follow-up time in days (administrative censoring assumed afterwards).
`prop_cens`	Numeric value on the interval $[0,1)$ , proportion of uniformly censored patients (default is 0).
`T0T_rate`	Positive numeric value, monthly event rate in control subjects that would develop the intercurrent event if treated.
`T0N_rate`	Positive numeric value, monthly event rate in control subjects that never develop the intercurrent event.
`T1T_rate`	Positive numeric value, monthly event rate in treated subjects that develop the intercurrent event.
`T1N_rate`	Positive numeric value, monthly event rate in treated subjects that never develop the intercurrent event.

Value

...

Examples

d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 48*7, 
  prop_cens = 0.15,
  T0T_rate = 0.2,      
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
dat_single_trial <- sim_dat_one_trial_exp_covar(
  n = d_params_covar[["n"]], 
  nt = d_params_covar[["nt"]],
  prob_X1 = d_params_covar[["prob_X1"]],
  prob_ice_X1 = d_params_covar[["prob_ice_X1"]],
  prob_ice_X0 = d_params_covar[["prob_ice_X0"]],
  fu_max = d_params_covar[["fu_max"]],
  prop_cens = d_params_covar[["prop_cens"]],  
  T0T_rate = d_params_covar[["T0T_rate"]],
  T0N_rate = d_params_covar[["T0N_rate"]],
  T1T_rate = d_params_covar[["T1T_rate"]],
  T1N_rate = d_params_covar[["T1N_rate"]] 
)
dim(dat_single_trial)
head(dat_single_trial)
                  
d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 48*7, 
  prop_cens = 0.15,
  T0T_rate = 0.2,      
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
dat_single_trial <- sim_dat_one_trial_exp_covar(
  n = d_params_covar[["n"]], 
  nt = d_params_covar[["nt"]],
  prob_X1 = d_params_covar[["prob_X1"]],
  prob_ice_X1 = d_params_covar[["prob_ice_X1"]],
  prob_ice_X0 = d_params_covar[["prob_ice_X0"]],
  fu_max = d_params_covar[["fu_max"]],
  prop_cens = d_params_covar[["prop_cens"]],  
  T0T_rate = d_params_covar[["T0T_rate"]],
  T0N_rate = d_params_covar[["T0N_rate"]],
  T1T_rate = d_params_covar[["T1T_rate"]],
  T1N_rate = d_params_covar[["T1N_rate"]] 
)
dim(dat_single_trial)
head(dat_single_trial)

Simulate data from a single two-arm trial with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Description

Simulate data from a single two-arm trial with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Usage

sim_dat_one_trial_exp_nocovar(
  n,
  nt,
  prob_ice,
  fu_max,
  prop_cens = 0,
  T0T_rate,
  T0N_rate,
  T1T_rate,
  T1N_rate
)
sim_dat_one_trial_exp_nocovar(
  n,
  nt,
  prob_ice,
  fu_max,
  prop_cens = 0,
  T0T_rate,
  T0N_rate,
  T1T_rate,
  T1N_rate
)

Arguments

`n`	Positive integer value, number of subjects in the trial.
`nt`	Positive integer value, number of treated subjects.
`prob_ice`	Numeric value on the interval $(0,1)$ , probability of the intercurrent event of interest (i.e. the event that determines the principal stratum membership).
`fu_max`	Positive integer value, maximum follow-up time in days (administrative censoring assumed afterwards).
`prop_cens`	Numeric value on the interval $[0,1)$ , proportion of uniformly censored patients (default is 0).
`T0T_rate`	Positive numeric value, monthly event rate in control subjects that would develop the intercurrent event if treated.
`T0N_rate`	Positive numeric value, monthly event rate in control subjects that never develop the intercurrent event.
`T1T_rate`	Positive numeric value, monthly event rate in treated subjects that develop the intercurrent event.
`T1N_rate`	Positive numeric value, monthly event rate in treated subjects that never develop the intercurrent event.

Value

A tibble()containing the trial data for analysis.

Examples

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  prop_cens = 0.15,
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
dat_single_trial <- sim_dat_one_trial_exp_nocovar(
  n = d_params_nocovar[["n"]], 
  nt = d_params_nocovar[["nt"]],
  prob_ice = d_params_nocovar[["prob_ice"]],
  fu_max = d_params_nocovar[["fu_max"]],
  prop_cens = d_params_nocovar[["prop_cens"]],  
  T0T_rate = d_params_nocovar[["T0T_rate"]],
  T0N_rate = d_params_nocovar[["T0N_rate"]],
  T1T_rate = d_params_nocovar[["T1T_rate"]],
  T1N_rate = d_params_nocovar[["T1N_rate"]] 
)
dim(dat_single_trial)
head(dat_single_trial)

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  prop_cens = 0.15,
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
dat_single_trial <- sim_dat_one_trial_exp_nocovar(
  n = d_params_nocovar[["n"]], 
  nt = d_params_nocovar[["nt"]],
  prob_ice = d_params_nocovar[["prob_ice"]],
  fu_max = d_params_nocovar[["fu_max"]],
  prop_cens = d_params_nocovar[["prop_cens"]],  
  T0T_rate = d_params_nocovar[["T0T_rate"]],
  T0N_rate = d_params_nocovar[["T0N_rate"]],
  T1T_rate = d_params_nocovar[["T1T_rate"]],
  T1N_rate = d_params_nocovar[["T1N_rate"]] 
)
dim(dat_single_trial)
head(dat_single_trial)

Adding true values to estimates for models with an exponential endpoint and consideration of predictors of the intercurrent event

Description

Adding true values to estimates for models with an exponential endpoint and consideration of predictors of the intercurrent event

Usage

true_vals_exp_covar(x, d_params, m_params)
true_vals_exp_covar(x, d_params, m_params)

Arguments

`x`	Model object as returned by `fit_single_exp_covar()`.
`d_params`	List of data parameters as used in `fit_single_exp_covar()`.
`m_params`	List of model parameters as used in `fit_single_exp_covar()`.

Value

A summary table with parameter estimates, true values and differences.

Examples

d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 48*7,       
  T0T_rate = 0.2,     
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
dat_single_trial <- sim_dat_one_trial_exp_covar(
  n = d_params_covar[["n"]], 
  nt = d_params_covar[["nt"]],
  prob_X1 = d_params_covar[["prob_X1"]],
  prob_ice_X1 = d_params_covar[["prob_ice_X1"]],
  prob_ice_X0 = d_params_covar[["prob_ice_X0"]],
  fu_max = d_params_covar[["fu_max"]],  
  T0T_rate = d_params_covar[["T0T_rate"]],
  T0N_rate = d_params_covar[["T0N_rate"]],
  T1T_rate = d_params_covar[["T1T_rate"]],
  T1N_rate = d_params_covar[["T1N_rate"]] 
)
m_params_covar <- list(
  tg = 48,
  p = 2, 
  prior_delta = matrix(
    c(0, 5, 0, 5),
    nrow = 2, byrow = TRUE),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2,
  n_iter = 3000,
  warmup = 1500,
  cores = 2,
  open_progress = FALSE,
  show_messages = TRUE   
)

fit_single <- fit_single_exp_covar(
  data = dat_single_trial,
  params = m_params_covar,
  summarize_fit = TRUE
)
print(fit_single)
tab_obs_truth <- true_vals_exp_covar(
  x = fit_single,
  d_params = d_params_covar,
  m_params = m_params_covar
)
print(tab_obs_truth)
 
d_params_covar <- list(
  n = 1000,        
  nt = 500,       
  prob_X1 = 0.4, 
  prob_ice_X1 = 0.5, 
  prob_ice_X0 = 0.2,
  fu_max = 48*7,       
  T0T_rate = 0.2,     
  T0N_rate = 0.2,     
  T1T_rate = 0.15,     
  T1N_rate = 0.1
 )
dat_single_trial <- sim_dat_one_trial_exp_covar(
  n = d_params_covar[["n"]], 
  nt = d_params_covar[["nt"]],
  prob_X1 = d_params_covar[["prob_X1"]],
  prob_ice_X1 = d_params_covar[["prob_ice_X1"]],
  prob_ice_X0 = d_params_covar[["prob_ice_X0"]],
  fu_max = d_params_covar[["fu_max"]],  
  T0T_rate = d_params_covar[["T0T_rate"]],
  T0N_rate = d_params_covar[["T0N_rate"]],
  T1T_rate = d_params_covar[["T1T_rate"]],
  T1N_rate = d_params_covar[["T1N_rate"]] 
)
m_params_covar <- list(
  tg = 48,
  p = 2, 
  prior_delta = matrix(
    c(0, 5, 0, 5),
    nrow = 2, byrow = TRUE),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2,
  n_iter = 3000,
  warmup = 1500,
  cores = 2,
  open_progress = FALSE,
  show_messages = TRUE   
)

fit_single <- fit_single_exp_covar(
  data = dat_single_trial,
  params = m_params_covar,
  summarize_fit = TRUE
)
print(fit_single)
tab_obs_truth <- true_vals_exp_covar(
  x = fit_single,
  d_params = d_params_covar,
  m_params = m_params_covar
)
print(tab_obs_truth)

Adding true values to estimates for models with an exponential endpoint and no consideration of predictors of the intercurrent event

Description

Adding true values to estimates for models with an exponential endpoint and no consideration of predictors of the intercurrent event

Usage

true_vals_exp_nocovar(x, d_params, m_params)
true_vals_exp_nocovar(x, d_params, m_params)

Arguments

`x`	Model object as returned by `fit_single_exp_nocovar()`.
`d_params`	List of data parameters as used in `fit_single_exp_nocovar()`.
`m_params`	List of model parameters as used in `fit_single_exp_nocovar()`.

Value

A summary table with parameter estimates, true values and differences.

Examples

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
dat_single_trial <- sim_dat_one_trial_exp_nocovar(
  n = d_params_nocovar[["n"]], 
  nt = d_params_nocovar[["nt"]],
  prob_ice = d_params_nocovar[["prob_ice"]],
  fu_max = d_params_nocovar[["fu_max"]],  
  T0T_rate = d_params_nocovar[["T0T_rate"]],
  T0N_rate = d_params_nocovar[["T0N_rate"]],
  T1T_rate = d_params_nocovar[["T1T_rate"]],
  T1N_rate = d_params_nocovar[["T1N_rate"]] 
)
m_params_nocovar <- list(
  tg = 48L,
  prior_piT = c(0.5, 0.5),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2L,
  n_iter = 3000L,
  warmup = 1500L,
  cores = 2L,
  open_progress = FALSE,
  show_messages = TRUE  
)

fit_single <- fit_single_exp_nocovar(
  data = dat_single_trial,
  params = m_params_nocovar,
  summarize_fit = TRUE 
)
print(fit_single) 
tab_obs_truth <- true_vals_exp_nocovar(
  x = fit_single,
  d_params = d_params_nocovar,
  m_params = m_params_nocovar
)
print(tab_obs_truth)

d_params_nocovar <- list(
  n = 500L,
  nt = 250L,
  prob_ice = 0.5,
  fu_max = 336L,
  T0T_rate = 0.2,
  T0N_rate = 0.2,
  T1T_rate = 0.15,
  T1N_rate = 0.1
)
dat_single_trial <- sim_dat_one_trial_exp_nocovar(
  n = d_params_nocovar[["n"]], 
  nt = d_params_nocovar[["nt"]],
  prob_ice = d_params_nocovar[["prob_ice"]],
  fu_max = d_params_nocovar[["fu_max"]],  
  T0T_rate = d_params_nocovar[["T0T_rate"]],
  T0N_rate = d_params_nocovar[["T0N_rate"]],
  T1T_rate = d_params_nocovar[["T1T_rate"]],
  T1N_rate = d_params_nocovar[["T1N_rate"]] 
)
m_params_nocovar <- list(
  tg = 48L,
  prior_piT = c(0.5, 0.5),
  prior_0N = c(1.5, 5),
  prior_1N = c(1.5, 5),
  prior_0T = c(1.5, 5),
  prior_1T = c(1.5, 5),
  t_grid =  seq(7, 7 * 48, 7) / 30,
  chains = 2L,
  n_iter = 3000L,
  warmup = 1500L,
  cores = 2L,
  open_progress = FALSE,
  show_messages = TRUE  
)

fit_single <- fit_single_exp_nocovar(
  data = dat_single_trial,
  params = m_params_nocovar,
  summarize_fit = TRUE 
)
print(fit_single) 
tab_obs_truth <- true_vals_exp_nocovar(
  x = fit_single,
  d_params = d_params_nocovar,
  m_params = m_params_nocovar
)
print(tab_obs_truth)

Package 'BPrinStratTTE'

Help Index

The 'BPrinStratTTE' package.

Description

References

Fit multiple models to data from two-arm trials with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Description

Usage

Arguments

Value

See Also

Examples

Fit multiple models to data from two-arm trials with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Description

Usage

Arguments

Value

See Also

Examples

Fit single model to data from a two-arm trial with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Description

Usage

Arguments

Details

Value

See Also

Examples

Fit single model to data from a two-arm trial with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Description

Usage

Arguments

Details

Value

See Also

Examples

Inverse logit function

Description

Usage

Arguments

Details

Value

See Also

Examples

Logit function

Description

Usage

Arguments

Value

See Also

Examples

Determine operating characteristics of fits from two-arm trials with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Description

Usage

Arguments

Details

Value

See Also

Examples

Determine operating characteristics of fits from two-arm trials with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Description

Usage

Arguments

Details

Value

See Also

Examples

Run simulation of two-arm trials with an exponentially distributed time-to-event endpoint and one predictor of the intercurrent event

Description

Usage

Arguments

Value

See Also

Examples

Run simulation of two-arm trials with an exponentially distributed time-to-event endpoint and no predictor of the intercurrent event

Description

Usage

Arguments

Value

See Also

Examples