Validation, NCE analysis, per-replicate oracle for landmark/naive, RCT truths script, resumable experiment runner

- W0 harm validation (40 reps): CCW and sequential ITT unbiased for their truths (|z| <= 0.7)
- PVI models fitted separately inside and after the window
- experiments.yml grid (8 worlds x 3 scenarios; designs x V1-V4; NCE; RCTs); smoke run clean

Co-Authored-By: Claude Opus 5.5 <[email protected]>

simulations/03_limits.R

@@ -0,0 +1,20 @@
+# RCT ITT truths for every world x scenario (the landmark and naive own estimands are
+# estimated within replicates by run_oracle()). Writes simulations/truths/truths_rct.csv.
+# Usage: Rscript simulations/03_limits.R [n] [cores]
+pkgload::load_all("pvisim", quiet = TRUE)
+suppressPackageStartupMessages(library(data.table))
+a <- commandArgs(TRUE)
+n <- if (length(a) >= 1) as.numeric(a[1]) else 5e5
+cores <- if (length(a) >= 2) as.integer(a[2]) else 6L
+raw <- yaml::read_yaml(default_params_path())
+jobs <- CJ(world = names(raw$worlds), scenario = names(raw$scenarios), sorted = FALSE)
+res <- parallel::mclapply(seq_len(nrow(jobs)), function(i) {
+  w <- jobs$world[i]; s <- jobs$scenario[i]
+  par <- load_params(w, s)
+  rbind(rct_truth(par, "realistic", n = 1e6)[outcome %in% c("male", "disease", "nco1", "nco2")],
+        rct_truth(par, "ideal", n = 1e6)[outcome %in% c("male", "disease", "nco1", "nco2")])
+}, mc.cores = cores)
+bad <- vapply(res, inherits, TRUE, "try-error")
+if (any(bad)) stop(res[bad][[1]])
+fwrite(rbindlist(res), "simulations/truths/truths_rct.csv")
+cat("wrote simulations/truths/truths_rct.csv\n")

simulations/config/experiments.yml

@@ -0,0 +1,12 @@
+# Experiment grids (plan sections 5.2, 7, 9). Run with simulations/run_experiment.R <grid> [--scale draft|final]
+main:
+  worlds: [W0, W1, W1_rho0, W2, W3, W4, W5, WR]
+  scenarios: ["null", harm, benefit_harm]
+  designs: [naive, landmark, ccw, seq]
+  variants: [V1_ignore, V3_random, V4_within]     # V1 also yields V2 (cluster-robust SE)
+  nce: true                                        # negative-control exposure (landmark, CCW), D32/D36
+  rct: [realistic, ideal]
+scales:
+  smoke: {n_patients: 20000, reps: 1}
+  draft: {n_patients: 50000, reps: 100}
+  final: {n_patients: 50000, reps: 500}                     # to be revisited after the draft (sample size, D25/D29)

simulations/run_experiment.R

@@ -0,0 +1,60 @@
+# Run an experiment grid; one CSV per world x scenario x replicate, so runs are resumable.
+# Usage: Rscript simulations/run_experiment.R main [--scale draft] [--cores 10] [--worlds W0,W2]
+pkgload::load_all("pvisim", quiet = TRUE)
+suppressPackageStartupMessages(library(data.table))
+a <- commandArgs(TRUE)
+opt <- function(flag, default) { i <- match(flag, a); if (is.na(i)) default else a[i + 1] }
+grid_name <- a[1]
+scale <- opt("--scale", "draft")
+cores <- as.integer(opt("--cores", "10"))
+cfg <- yaml::read_yaml("simulations/config/experiments.yml")
+g <- cfg[[grid_name]]; sc <- cfg$scales[[scale]]
+worlds <- if (is.null(opt("--worlds", NULL))) g$worlds else strsplit(opt("--worlds", NULL), ",")[[1]]
+outdir <- file.path("results", grid_name, scale)
+jobs <- CJ(world = worlds, scenario = unlist(g$scenarios), rep = seq_len(sc$reps), sorted = FALSE)
+jobs[, file := file.path(outdir, world, scenario, sprintf("rep%03d.csv", rep))]
+todo <- jobs[!file.exists(file)]
+cat(sprintf("%s/%s: %d jobs, %d to do, %d cores\n", grid_name, scale, nrow(jobs), nrow(todo), cores))
+
+one_job <- function(i) {
+  j <- todo[i]
+  par <- load_params(j$world, j$scenario)
+  rec <- simulate_records(par, rep = j$rep, n = sc$n_patients)
+  out <- list()
+  for (v in g$variants) {
+    for (d in g$designs) {
+      r <- run_design(rec, d, v)
+      if (v == "V1_ignore") {   # same fit, two SEs
+        r2 <- copy(r)[, `:=`(variant = "V2_cluster", se = se_cluster)]
+        r <- rbind(r, r2)
+      }
+      out[[length(out) + 1]] <- r[, analysis := "main"]
+    }
+    if (isTRUE(g$nce)) for (d in c("landmark", "ccw")) {
+      r <- run_design(nce_records(rec), d, v, outcomes = c(male = "t_male", disease = "t_disease"))
+      if (v == "V1_ignore") r <- rbind(r, copy(r)[, `:=`(variant = "V2_cluster", se = se_cluster)])
+      out[[length(out) + 1]] <- r[, analysis := "nce"]
+    }
+  }
+  for (d in c("landmark", "ccw")) {     # unadjusted NCE (supplement, D36), V1/V2 only
+    r <- run_design(nce_records(rec, adjust_pvi = FALSE), d, "V1_ignore", outcomes = c(male = "t_male", disease = "t_disease"))
+    out[[length(out) + 1]] <- r[, analysis := "nce_unadjusted"]
+  }
+  out[[length(out) + 1]] <- run_oracle(rec)[, analysis := "main"]   # own estimand of landmark / naive
+  for (dz in g$rct) {
+    r <- run_rct(par, dz, rep = j$rep)
+    out[[length(out) + 1]] <- r[, `:=`(contrast = analysis, analysis = "rct", variant = "none", se = se_patient)]
+  }
+  res <- rbindlist(out, fill = TRUE)[, `:=`(world = j$world, scenario = j$scenario, rep = j$rep)]
+  dir.create(dirname(j$file), recursive = TRUE, showWarnings = FALSE)
+  fwrite(res, j$file)
+  NULL
+}
+t0 <- Sys.time()
+res <- parallel::mclapply(seq_len(nrow(todo)), function(i) tryCatch(one_job(i), error = function(e)
+  sprintf("%s/%s/%d: %s", todo$world[i], todo$scenario[i], todo$rep[i], conditionMessage(e))),
+  mc.cores = cores, mc.preschedule = FALSE)
+err <- unlist(res[!vapply(res, is.null, TRUE)])
+cat(sprintf("done in %.1f h; %d errors\n", as.numeric(Sys.time() - t0, units = "hours"), length(err)))
+dir.create(outdir, recursive = TRUE, showWarnings = FALSE)
+if (length(err)) { writeLines(err, file.path(outdir, sprintf("errors_%s.txt", format(Sys.time(), "%Y%m%d_%H%M")))); cat(head(err, 3), sep = "\n") }

simulations/validate_designs.R

@@ -19,7 +19,8 @@ res <- rbindlist(parallel::mclapply(seq_len(reps), function(r) {
     fill = TRUE)
 }, mc.cores = cores), fill = TRUE)
 
-tr <- fread("simulations/truths/truths.csv")[world == ..world & scenario == ..scenario]
+w_ <- world; s_ <- scenario
+tr <- fread("simulations/truths/truths.csv")[world == w_ & scenario == s_]
 map <- data.table(design = c("ccw", "ccw", "seq"), contrast = c("A_B1", "A_B2", "now_not"),
                   estimand = c("rd_A_B1", "rd_A_B2", "seq_itt"))
 s <- res[, .(mean_est = mean(est), emp_se = sd(est), mean_se = mean(se), reps = .N),