Refactor to take new format for aggregate level data input to outstandR()

NAMESPACE

@@ -18,9 +18,11 @@ export(calculate_ate)
 export(calculate_trial_mean)
 export(calculate_trial_mean_binary)
 export(calculate_trial_mean_continuous)
+export(calculate_trial_mean_count)
 export(calculate_trial_variance)
 export(calculate_trial_variance_binary)
 export(calculate_trial_variance_continuous)
+export(calculate_trial_variance_count)
 export(get_treatment_effect)
 export(marginal_treatment_effect)
 export(marginal_variance)

R/calc_ALD_stats.R

@@ -18,9 +18,11 @@
 #' @examples
 #' \dontrun{
 #' strategy <- list(family = list(family = "binomial"))  # basic version
-#' ald <- data.frame(trial = 1:5,
-#'                   n_B = c(10, 20, 15, 30, 25),
-#'                   n_C = c(12, 18, 20, 25, 22))
+#' ald <- data.frame(trt = c("B","C","B","C"),
+#'                   variable = c(NA, NA, "y", "y"),
+#'                   statistic = c("N", "N", "sum", "sum"),
+#'                   value = c(100, 100, 50, 60) 
+#'
 #' calc_ALD_stats(strategy, ald, treatments = list("B", "C"), scale = "log")
 #' }
 #'
@@ -43,8 +45,6 @@ calc_ALD_stats <- function(strategy,
 #' Marginal effect variance using the delta method
 #' 
 #' Computes the total variance of marginal treatment effects using the delta method.
-#' For binomial data, calculates:
-#' \deqn{\frac{1}{n_C} + \frac{1}{n_{\bar{C}}} + \frac{1}{n_B} + \frac{1}{n_{\bar{B}}}}.
 #'
 #' @param ald Aggregate-level data
 #' @param treatments A list of treatment labels; default _B_ vs _C_
@@ -54,7 +54,10 @@ calc_ALD_stats <- function(strategy,
 #' @return The total variance of marginal treatment effects.
 #' @examples
 #' \dontrun{
-#' ald <- data.frame(trial = 1:5, n_B = c(10, 20, 15, 30, 25), n_C = c(12, 18, 20, 25, 22))
+#' ald <- data.frame(trt = c("B","C","B","C"),
+#'                   variable = c(NA, NA, "y", "y"),
+#'                   statistic = c("N", "N", "sum", "sum"),
+#'                   value = c(100, 100, 50, 60)
 #' marginal_variance(ald, treatments = list("B", "C"), scale = "log", family = "binomial")
 #' }
 #' @export
@@ -73,12 +76,6 @@ marginal_variance <- function(ald,
 #' Marginal treatment effect from reported event counts
 #' 
 #' Computes the relative treatment effect from aggregate-level data using event counts.
-#' For binomial data, calculates:
-#' \deqn{
-#' \log\left( \frac{n_B/(N_B-n_B)}{n_C/(N_B-n_{B})} \right) = \log(n_B n_{\bar{C}}) - \log(n_C n_{\bar{B}})
-#' }
-#' where \eqn{\bar{C}} is the compliment of \eqn{C}
-#' so e.g. \eqn{n_{\bar{C}} = N_C - n_c}.
 #'
 #' @param ald Aggregate-level data
 #' @param treatments A list of treatment labels. Last variable is reference; default `B`, `C` (common; e.g. placebo)
@@ -88,7 +85,10 @@ marginal_variance <- function(ald,
 #' @return The relative treatment effect.
 #' @examples
 #' \dontrun{
-#' ald <- data.frame(trial = 1:5, n_B = c(10, 20, 15, 30, 25), n_C = c(12, 18, 20, 25, 22))
+#' ald <- data.frame(trt = c("B","C","B","C"),
+#'                   variable = c(NA, NA, "y", "y"),
+#'                   statistic = c("N", "N", "sum", "sum"),
+#'                   value = c(100, 100, 50, 60)
 #' marginal_treatment_effect(ald, treatments = list("B", "C"), scale = "log", family = "binomial")
 #' }
 #' @export

R/calc_IPD_stats.R

@@ -7,7 +7,7 @@
 #' including Matching-Adjusted Indirect Comparison (MAIC), Simulated Treatment Comparison (STC),
 #' and G-computation via Maximum Likelihood Estimation (MLE) or Bayesian inference.
 #' 
-#' @param strategy A list corresponding to different approaches
+#' @param strategy A list corresponding to different modelling approaches
 #' @eval study_data_args(include_ipd = TRUE, include_ald = TRUE)
 #' @param scale A scaling parameter for the effect calculation.
 #' @param ... Additional arguments
@@ -20,8 +20,13 @@
 #' @examples
 #' \dontrun{
 #' strategy <- strategy_maic()
-#' ipd <- data.frame(id = 1:100, treatment = sample(c("A", "C"), 100, replace = TRUE), outcome = rnorm(100))
-#' ald <- data.frame(treatment = c("A", "C"), mean = c(0.2, 0.1), var = c(0.05, 0.03))
+#' ipd <- data.frame(trt = sample(c("A", "C"), 100, replace = TRUE),
+#'                   X1 = rnorm(100, 1, 1),
+#'                   y = rnorm(100, 10, 2))
+#' ald <- data.frame(trt = c(NA, "B", "C", "B", "C"),
+#'                   variable = c("X1", "y", "y", NA, NA),
+#'                   statistic = c("mean", "sum", "sum", "N", "N"),
+#'                   value = c(0.5, 10, 12, 20, 25))
 #' calc_IPD_stats(strategy, ipd, ald, scale = "log_odds")
 #' }
 #' @export
@@ -43,7 +48,7 @@ calc_IPD_stats.default <- function(...) {
 #' @rdname calc_IPD_stats
 #' 
 #' @section Multiple imputation marginalisation:
-#' Using Stan, compute marginal relative treatment effect for _A_ vs _C_ for each MCMC sample
+#' Using Stan, compute marginal relative treatment effect for IPD comparator "A" vs reference "C" arms for each MCMC sample
 #' by transforming from probability to linear predictor scale. Approximate by 
 #' using imputation and combining estimates using Rubin's rules, in contrast to [calc_IPD_stats.gcomp_stan()].
 #' @import stats
@@ -86,7 +91,7 @@ calc_IPD_stats.mim <- function(strategy,
 
 #' Factory function for creating calc_IPD_stats methods
 #'
-#' Creates a method for computing mean and variance statistics based on the supplied function.
+#' Creates a method for computing IPD mean and variance statistics based on the supplied function.
 #'
 #' @param ipd_fun A function that computes mean and variance statistics for individual-level patient data.
 #' @return A function that computes mean and variance statistics for a given strategy.
@@ -128,7 +133,7 @@ IPD_stat_factory <- function(ipd_fun) {
 
 #' @rdname calc_IPD_stats
 #' @section Simulated treatment comparison statistics:
-#' IPD from the _AC_ trial are used to fit a regression model describing the
+#' IPD for reference "C" and comparator "A" trial arms are used to fit a regression model describing the
 #' observed outcomes \eqn{y} in terms of the relevant baseline characteristics \eqn{x} and
 #' the treatment variable \eqn{z}.
 #' @export
@@ -137,7 +142,7 @@ calc_IPD_stats.stc <- IPD_stat_factory(outstandR:::calc_stc)
 
 #' @rdname calc_IPD_stats
 #' @section Matching-adjusted indirect comparison statistics:
-#' Marginal _A_ vs _C_ treatment effect estimates
+#' Marginal IPD comparator treatment "A" vs reference treatment "C" treatment effect estimates
 #' using bootstrapping sampling.
 #' @export
 #'
@@ -152,7 +157,7 @@ calc_IPD_stats.gcomp_ml <- IPD_stat_factory(outstandR:::calc_gcomp_ml)
 
 #' @rdname calc_IPD_stats
 #' @section G-computation Bayesian statistics:
-#' Using Stan, compute marginal log-odds ratio for _A_ vs _C_ for each MCMC sample
+#' Using Stan, compute marginal relative effects for IPD comparator "A" vs reference "C" treatment arms for each MCMC sample
 #' by transforming from probability to linear predictor scale.
 #' @export
 #'

R/calc_stc.R

@@ -1,5 +1,10 @@
 
 #' Calculate simulated treatment comparison statistics
+#' @return A list:
+#' \describe{
+#'   \item{`mean_A`}{Mean for comparator treatment group "A".}
+#'   \item{`mean_C`}{Mean for reference treatment group "C".}
+#' }
 #' @importFrom stats glm
 #' @export
 #'