The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

Complete Workflow: From Data to Decision

Deniz Akdemir

2026-03-26

Overview

This vignette demonstrates the complete causaldef workflow, from data specification through to policy decision-making. We show how Le Cam deficiency theory translates abstract statistical concepts into actionable clinical insights.

The workflow consists of four stages:

  1. Specify → Define the causal problem
  2. Estimate → Compute deficiency for different adjustment strategies
  3. Diagnose → Validate assumptions using negative controls and sensitivity analysis
  4. Decide → Compute policy regret bounds and make informed decisions

Part 1: Gene Perturbation Study (Continuous Outcome)

We begin with the gene_perturbation dataset, which simulates a CRISPR knockout experiment. This illustrates the core workflow for continuous outcomes.

1.1 Data Description

Variables:

Causal Structure:

      [Batch, Library Size]
             |
             v
   [Knockout] -----> [Target Expression]
             \
              \---X--> [Housekeeping Gene]  (no causal effect)

The housekeeping gene is affected by the same technical variations but NOT by the knockout, making it an ideal negative control.

1.2 Step 1: Specification

1.3 Step 2: Deficiency Estimation

We compare three adjustment strategies:

  1. Unadjusted: Ignores technical confounders
  2. IPTW: Reweights samples to balance batch and library size
  3. AIPW: Augmented IPTW (doubly robust)

Interpretation:

1.4 Step 3: Diagnose with Negative Control

The negative control diagnostic tests whether our adjustment removes ALL confounding, not just the measured confounders.

Decision Logic:

Result Interpretation Action
falsified = FALSE No evidence of residual confounding Proceed with analysis
falsified = TRUE Residual confounding detected Add covariates or acknowledge limitations

1.5 Step 4: Policy Decision

Suppose we’re deciding whether to pursue this gene target for drug development. The utility is measured on a scale where: - 0 = no promise (no effect on expression) - 10 = maximum promise (strong effect)

Regret Bounds:

policy_regret_bound() reports:

Decision Rule: - If transfer_penalty < acceptable risk threshold → Proceed with confidence - If transfer_penalty > acceptable risk threshold → Seek more evidence

1.6 Effect Estimation

Finally, we estimate the causal effect using the best-performing method:

Complete Report:

Gene Perturbation Analysis Report

Treatment Effect (IPTW-adjusted): -1.71 log2 expression units Deficiency (δ): 0.037 Negative Control Test: PASSED (p = 0.109) Transfer Penalty: 0.368 on [0, 10] scale Minimax Safety Floor: 0.184 on [0, 10] scale

Conclusion: Strong evidence supporting treatment effect.

Part 2: Hematopoietic Cell Transplantation (Survival Outcome)

Next, we analyze the hct_outcomes dataset, which mimics a retrospective registry study comparing conditioning regimens in HCT.

2.1 Data Description

Clinical Context:

The key challenge is confounding by indication: doctors assign treatment based on patient status, making naive comparisons biased.

2.2 Step 1: Survival Specification

Executable survival-effect code in this section requires a compatible survival runtime. In the current support matrix, that means R >= 4.0.

2.3 Step 2: Deficiency Estimation

Clinical Interpretation:

The deficiency tells us how much our observational evidence differs from what an RCT would provide:

2.4 Step 3: Confounding Frontier

Beyond point estimates, we can map a sensitivity analysis showing how deficiency varies with hypothetical unmeasured confounding:

Reading the Frontier Map:

If an unmeasured confounder would need extreme strength (beyond observed benchmarks) to substantially increase δ, conclusions are robust.

2.5 Step 4: Policy Regret and RMST Effect

Clinical Regret Bounds:

If δ = 0.05 with M = 24 months: - Transfer penalty = 24 × 0.05 = 1.2 months - Minimax safety floor = 0.5 × 24 × 0.05 = 0.6 months

This means even with perfect decision-making, the observational evidence can inflate regret by up to about 1.2 months on the 0–24 month utility scale, and there is an unavoidable worst-case floor of about 0.6 months when \(\delta>0\).

2.6 Complete Decision Framework

delta_iptw <- deficiency_hct$estimates["iptw"]
transfer_penalty <- bounds_hct$transfer_penalty
minimax_floor <- bounds_hct$minimax_floor
rmst_diff <- effect_hct$estimate

# Decision logic
if (delta_iptw < 0.05) {
    evidence_quality <- "HIGH (approximates RCT)"
} else if (delta_iptw < 0.15) {
    evidence_quality <- "MODERATE (acceptable with caveats)"
} else {
    evidence_quality <- "LOW (substantial bias risk)"
}

# Benefit-to-risk ratio
if (!is.na(rmst_diff) && !is.na(transfer_penalty) && transfer_penalty > 0) {
    benefit_to_risk <- abs(rmst_diff) / transfer_penalty
    recommendation <- ifelse(benefit_to_risk > 2,
        "Recommend treatment with stronger effect",
        "Evidence inconclusive; consider shared decision-making"
    )
} else {
    benefit_to_risk <- NA
    recommendation <- "Unable to calculate benefit-to-risk ratio"
}

cat(sprintf(
    "
## HCT Treatment Decision Report

**RMST Difference (IPTW):** %.2f months (%s favored)
**Deficiency:** %.3f
**Evidence Quality:** %s
**Transfer Penalty:** %.2f months
**Minimax Safety Floor:** %.2f months

**Benefit-to-Risk Ratio:** %.1f:1
**Recommendation:** %s

### Clinical Translation

The observational evidence suggests %s conditioning provides approximately
%.1f additional months of relapse-free survival within the first 2 years.

However, the transfer penalty is %.1f months and the minimax safety floor is %.1f months
on the 0--24 month utility scale. Clinicians should weigh this against individual patient factors.
",
    abs(rmst_diff),
    ifelse(rmst_diff > 0, "Myeloablative", "Reduced"),
    delta_iptw,
    evidence_quality,
    transfer_penalty,
    minimax_floor,
    benefit_to_risk,
    recommendation,
    ifelse(rmst_diff > 0, "myeloablative", "reduced-intensity"),
    abs(rmst_diff),
    transfer_penalty,
    minimax_floor
))

Part 3: Comparative Analysis Across Studies

3.1 When Is Observational Evidence Sufficient?

Study δ (IPTW) Transfer Penalty Evidence Quality
Gene Perturbation Low (~0.01) Very Low Excellent
HCT Outcomes Moderate (~0.05-0.15) 1-4 months Acceptable with caveats

3.2 General Workflow Summary

┌─────────────────────────────────────────────────────────────────┐
│  SPECIFY: causal_spec() / causal_spec_survival()                │
│           ↓ Define treatment, outcome, covariates, NC           │
├─────────────────────────────────────────────────────────────────┤
│  ESTIMATE: estimate_deficiency()                                │
│            ↓ Compare unadjusted, IPTW, AIPW, TMLE, etc.        │
│            ↓ Select method with lowest δ                        │
├─────────────────────────────────────────────────────────────────┤
│  DIAGNOSE: nc_diagnostic() + confounding_frontier()             │
│            ↓ Test whether assumptions are falsified             │
│            ↓ Map sensitivity to unmeasured confounding          │
├─────────────────────────────────────────────────────────────────┤
│  DECIDE: policy_regret_bound() + estimate_effect()              │
│          ↓ Compute transfer penalty / minimax floor             │
│          ↓ Report effect with uncertainty qualification         │
└─────────────────────────────────────────────────────────────────┘

References

  1. Akdemir, D. (2026). Constraints on Causal Inference as Experiment Comparison: A Framework for Identification, Transportability, and Policy Learning. DOI: 10.5281/zenodo.18367347

  2. Le Cam, L., & Yang, G. L. (2000). Asymptotics in Statistics: Some Basic Concepts. Springer.

  3. VanderWeele, T. J., & Ding, P. (2017). Sensitivity Analysis in Observational Research: Introducing the E-value. Annals of Internal Medicine.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.