Validation & Transparency

Validated. Transparent. Trustworthy.

Name: Zetyra
Price: 99 USD
Rating: 4.9 (47 reviews)
Author: Zetyra

Zetyra's calculators collectively pass 499 automated validation tests against industry gold standards. Our GSD module matches gsDesign within 0.04 z-score units across 5 tested OBF/Pocock configurations (k=3–5). Our Bayesian Toolkit is validated end-to-end—from prior elicitation through sequential monitoring—with schema contracts, MC calibration, and analytical oracle comparisons. Survival/TTE endpoints, SSR, and Bayesian predictive power for survival are all independently validated.

At a Glance

499 automated tests passing

Max deviation: 0.034 z-score

Benchmarked against gsDesign, pwr, scipy

5 real-world clinical trials replicated

Open source (MIT license)

25 scripts, continuous integration

Open Source

Unlike proprietary alternatives, our validation is public.

Our complete validation suite—25 scripts, 499 tests—runs continuously on GitHub Actions. Anyone can verify our accuracy, examine our methodology, and reproduce our results. No black boxes—just glass boxes.

View Live Validation Suite

Results Summary

Table 1

Validation Results by Calculator

Calculator	Tests	Reference	Max Deviation	Status
Group Sequential Design	30	gsDesign R package	0.034 z-score	Pass
GSD PACIFIC OS	17	Antonia et al. (2018) NEJM	0.022 z-score	Pass
GSD MONALEESA-7 OS	20	Im et al. (2019) NEJM	0.022 z-score	Pass
GSD Survival/TTE	15	Schoenfeld (1983), gsDesign	< 0.001	Pass
GSD Survival gsDesign	36	gsDesign R (boundaries, alpha spending)	0.034 z-score	Pass
CUPED	12	Analytical formulas	< 0.001	Pass
CUPED Simulation	43	MC simulation, Deng et al. (2013)	< 0.02	Pass
Bayesian Predictive Power	17	Conjugate priors	< 0.01	Pass
Bayesian Survival	21	Normal-Normal on log(HR)	< 0.01	Pass
Bayesian Survival Benchmark	25	Conjugate oracle, MC PP cross-val	< 0.03	Pass
Prior Elicitation	22	ESS formula, scipy.optimize	< 0.001	Pass
Bayesian Borrowing	18	Power prior, Cochran's Q	< 0.01	Pass
Bayesian Sample Size	26	Binomial CI, MC search (binary + continuous)	CI-based	Pass
Bayesian Two-Arm	24	Binomial CI, MC search (binary + continuous)	CI-based	Pass
Bayesian Sequential	20	Zhou & Ji (2024)	< 0.0001	Pass
Bayesian Sequential Table 3	27	Zhou & Ji (2024) Table 3 + R code	< 0.005	Pass
Bayesian Sequential Survival	24	Zhou & Ji (2024) + Schoenfeld	< 0.0001	Pass
Bayesian Seq. Survival Benchmark	24	Zhou & Ji formula + Type I error	< 0.02	Pass
SSR Blinded	20	Conditional power formulas	< 0.001	Pass
SSR Unblinded	21	Zone classification, CP	< 0.001	Pass
SSR gsDesign Benchmark	14	gsDesign R, reference formulas	0 (exact)	Pass
Offline References	23	Pure math (no API)	< 1e-10	Pass
Total	499	25 scripts		All Pass

Bayesian Toolkit

NEW

271 tests across 13 scripts

Each of the 6 Bayesian calculators has a dedicated test suite. Tests cover 8 categories of validation:

Analytical Correctness

Conjugate posteriors, boundary formulas, and ESS derivations compared against closed-form references

MC Calibration

Type I error and power checked with Clopper-Pearson binomial CIs that scale with simulation count

Schema Contracts

Response keys, types, and value bounds validated for every API call with strict/non-strict lower bounds

Input Guards

Invalid inputs (negative rates, out-of-range priors) return 400/422 with the offending field named

Boundary Conditions

Extreme priors (ESS=1 to 1000), zero/all events, single-look designs, near-zero and near-one rates

Invariants & Properties

Higher power → larger n, larger effect → smaller n, higher discount → higher ESS, monotone boundaries

Seed Reproducibility

Same seed produces identical MC results across repeated calls for sample size and two-arm designs

Symmetry

Null hypothesis gives same type I error regardless of label swap; identical studies yield I²=0

Real-World Validation

HPTN 083

Phase 3 HIV Prevention Trial

Design4-look O'Brien-Fleming

Boundaries tested4

Max deviation0.012 z-score

HeartMate II

LVAD Clinical Trial

Design3-look O'Brien-Fleming

Info fractions[0.27, 0.67, 1.00]

StatusAll properties verified

PACIFIC

SURVIVAL

Durvalumab, Stage III NSCLC (OS)

Design3-look Lan-DeMets OBF

Published boundaryp < 0.00274 (z = 2.78)

Max deviation0.022 z-score

Looks 1–2 match reference exactly (0.000). Look 3 deviation (0.022) is from MVN integration precision.

MONALEESA-7

SURVIVAL

Ribociclib, HR+ Breast Cancer (OS)

Design3-look Lan-DeMets OBF

Published boundariesz = 3.60, 2.32

Max deviation0.022 z-score *

* Looks 1–2 match reference exactly (0.000). The 0.022 gap vs the published paper boundary at look 2 reflects a discrepancy in the published values—both Zetyra and our independent Lan-DeMets reference agree.

REBYOTA (Fecal Microbiota)

BAYESIAN

FDA BLA 125739 — PUNCH CD2 (Phase 2b) & CD3 (Phase 3) for C. difficile infection

PUNCH CD2 (Phase 2b)

Data25/45 responders (55.6%)

Used inPrior, Borrowing, Sample Size

Scenarios11 tests (δ = 0–1)

PUNCH CD3 (Phase 3)

Data126/177 treat, 53/85 placebo

Used inTwo-Arm, Borrowing (MAP)

Cross-phase I²40–90% detected

Boundary Accuracy

Two independent benchmarks validate GSD boundary accuracy against the gsDesign R package: one for standard (non-survival) designs, one for survival/TTE designs with Lan-DeMets spending functions.

Table 2a

Standard GSD Boundaries vs gsDesign (non-survival)

Design	Looks	Max Deviation	Status
O'Brien-Fleming	2	0.0000	Pass
O'Brien-Fleming	3	0.0015	Pass
O'Brien-Fleming	4	0.0117	Pass
O'Brien-Fleming	5	0.0332	Pass
Pocock	2	0.0000	Pass
Pocock	3	0.0010	Pass
Pocock	4	0.0033	Pass

Table 2b

Survival GSD Boundaries vs gsDesign (Lan-DeMets spending)

Design	Looks	Max Deviation	Status
OBF (Lan-DeMets)	3	0.0015	Pass
OBF (Lan-DeMets)	4	0.0117*	Pass
OBF (Lan-DeMets)	5	0.0332*	Pass
Pocock (Lan-DeMets)	3	0.0010	Pass
Pocock (Lan-DeMets)	4	0.0033	Pass

* Deviations occur at later looks (k=4–5) due to accumulated multivariate normal integration precision differences between scipy and R's mvtnorm. Early looks match exactly (0.000). The max deviation of 0.033 is at OBF k=5 final look. Pocock boundaries show negligible deviation at all look counts.

Methodology

gsDesign

Group Sequential Design

Validated against the gold-standard gsDesign R package. O'Brien-Fleming and Pocock spending functions computed to match FDA submission standards. Survival/TTE via Schoenfeld.

VRF = 1 - r²

CUPED

Variance reduction validated against analytical formulas. Sample size reduction proportional to baseline-outcome correlation squared.

Beta(a+x, b+n-x)

Bayesian Toolkit

6 calculators validated end-to-end: conjugate posteriors, Zhou & Ji boundaries, survival log(HR) mapping, Clopper-Pearson MC calibration, power priors, MAP heterogeneity, and ESS-based elicitation.

Var(log HR) = 4/d

Survival/TTE

Event-driven designs validated via Schoenfeld variance mapping. GSD, Bayesian Sequential, and Bayesian Predictive Power all support time-to-event endpoints with HR-scale outputs.

CP(z, n)

Sample Size Re-estimation

Blinded and unblinded SSR validated against conditional power formulas. Zone classification, inflation caps, and threshold ordering verified for continuous, binary, and survival endpoints.

References

1. GSD: Jennison & Turnbull (2000) Group Sequential Methods with Applications to Clinical Trials
2. CUPED: Deng et al. (2013) Improving the Sensitivity of Online Controlled Experiments (WSDM)
3. Bayesian: Gelman et al. (2013) Bayesian Data Analysis
4. gsDesign: Anderson (2022) gsDesign R package
5. Bayesian Sequential: Zhou & Ji (2024) Bayesian sequential monitoring
6. Prior Elicitation: Morita, Thall & Müller (2008) Determining the effective sample size of a parametric prior
7. Survival: Schoenfeld (1983) Sample-size formula for the proportional-hazards regression model
8. SSR: Cui, Hung & Wang (1999) Modification of sample size in group sequential clinical trials

The only clinical trial design platform with public, continuously validated accuracy.

499 tests. 25 scripts. Every calculator validated.

Try Our Calculators Start Free Trial