D55: EHR/registry-like world (noisy severity), non-random trial consent, trial analyses at 12/24/60 months

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

simulations/04_summarise.R

@@ -14,6 +14,9 @@ cat(sprintf("%d files, %d rows\n", length(files), nrow(d)))
 # rare failures (sequential V4: fixed effects not estimable in a trial month) are dropped and counted
 cat(sprintf("dropped %d estimates with NA\n", d[is.na(est), .N]))
 d <- d[!is.na(est)]
+# trials are analysed at 12, 24 and 60 months (D55); everything else at 60
+if (!"horizon" %in% names(d)) d[, horizon := NA_integer_]
+d[is.na(horizon), horizon := 60L]
 
 tr <- rbind(fread("simulations/truths/truths.csv"), fread("simulations/truths/truths_rct.csv"))
 tr <- tr[, .(world, scenario, outcome, estimand, truth = value, truth_mcse = mcse)]
@@ -23,12 +26,19 @@ tr <- tr[, .(world, scenario, outcome, estimand, truth = value, truth_mcse = mcs
 d[, estimand := fcase(design == "ccw" & contrast == "A_B1", "rd_A_B1",
                       design == "ccw" & contrast == "A_B2", "rd_A_B2",
                       design == "seq", "seq_itt",
-                      design %like% "^rct_" & contrast == "itt", paste0(design, "_itt"),
+                      design %like% "^rct_" & contrast == "itt",
+                        paste0(design, "_itt", fifelse(horizon == 60L, "", paste0("_h", horizon))),
                       default = NA_character_)]
 d <- merge(d, tr[, .(world, scenario, outcome, estimand, own = truth)],
            by = c("world", "scenario", "outcome", "estimand"), all.x = TRUE)
 d <- merge(d, tr[estimand == "rd_A_B1", .(world, scenario, outcome, ref = truth)],
            by = c("world", "scenario", "outcome"), all.x = TRUE)
+# at the shorter trial horizons the reference is RD(A - B1) at that month, from the risk curves
+cv <- dcast(fread("simulations/truths/risk_curves.csv")[policy %in% c("A", "B1")],
+            world + scenario + outcome + month ~ policy, value.var = "cuminc")
+d <- merge(d, cv[, .(world, scenario, outcome, horizon = month, ref_h = A - B1)],
+           by = c("world", "scenario", "outcome", "horizon"), all.x = TRUE)
+d[horizon != 60L, ref := ref_h][, ref_h := NULL]
 # landmark and naive: own estimand = the paired oracle estimate in the same replicate (D47)
 orc <- d[variant == "oracle", .(world, scenario, rep, design, outcome, oracle = est)]
 d <- merge(d, orc, by = c("world", "scenario", "rep", "design", "outcome"), all.x = TRUE)
@@ -39,7 +49,7 @@ d[, `:=`(lo = est - 1.96 * se, hi = est + 1.96 * se)]
 fwrite(d, file.path(outdir, "reps.csv"))
 
 # ---- performance by cell (plan 9) -----------------------------------------------------
-keys <- c("world", "scenario", "analysis", "design", "contrast", "variant", "outcome")
+keys <- c("world", "scenario", "analysis", "design", "contrast", "variant", "outcome", "horizon")
 perf <- d[variant != "oracle", {
   err <- est - own; R <- .N; own_m <- mean(own)
   .(reps = R, mean_est = mean(est), own = own_m, ref = ref[1],
@@ -83,8 +93,8 @@ ncs <- rbindlist(lapply(c("nco1", "nco2", "nce", "any_nc"), function(k) rbind(
   nc[, c(control = k, level = "cell", acc(get(k), biased_cell)), by = world],
   nc[, c(world = "all", control = k, level = "replicate", acc(get(k), biased_rep))],
   nc[, c(world = "all", control = k, level = "cell", acc(get(k), biased_cell))])))
-hide <- nc[any_nc == FALSE, .(control = "any_nc", med_absbias_clean = median(abs(cell_bias)),
-                              p90_absbias_clean = quantile(abs(cell_bias), 0.9)), by = world]
+hide <- nc[any_nc == FALSE, .(control = "any_nc", med_absbias_clean = median(abs(cell_bias), na.rm = TRUE),
+                              p90_absbias_clean = quantile(abs(cell_bias), 0.9, na.rm = TRUE)), by = world]
 ncs <- merge(ncs, hide, by = c("world", "control"), all.x = TRUE)
 fwrite(ncs, file.path(outdir, "nc_summary.csv"))
 cat("wrote", outdir, "\n")

simulations/config/calibrated.yml

@@ -102,3 +102,16 @@ WR:
       intercept: -7.5233
     death:
       intercept: -5.6489
+WE:
+  treatment:
+    window:
+      intercept: -6.3552
+    deferred:
+      intercept: -7.7172
+  outcomes:
+    repeat_revasc:
+      intercept: -5.6375
+    clti:
+      intercept: -7.4903
+    death:
+      intercept: -5.6504

simulations/config/experiments.yml

@@ -1,6 +1,6 @@
 # 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]
+  worlds: [W0, W1, W1_rho0, W2, W3, W4, W5, WE, WR]   # WE: EHR/registry-like measurement (D55)
   scenarios: ["null", harm, benefit_harm]
   designs: [naive, landmark, landmark_m5, ccw, seq]   # landmark_m5: also adjusts for month-5 severity (supplement, D53)
   variants: [V1_ignore, V3_random, V4_within]     # V1 also yields V2 (cluster-robust SE)