All examples · Example 12 of 34
Stacked Bar: Treatment Outcomes
Best overall response (CR, PR, SD, PD) as a percentage of patients in each arm (n = 50 per arm).
Key findings
- Objective response ranges from 14.0% (Placebo) to 54.0% (Drug A + B), n = 50 per arm.
- The Placebo complete-response rate is 0 / 50: Wilson still gives a sensible upper bound, while Wald gives the impossible interval 0% – 0%.
- A chi-square test of outcome × arm is not part of the LabTools stats engine yet; the per-arm intervals are reported instead.
Objective response rate by arm
Objective response = complete + partial response. Each rate gets a 95% Wilson interval — LabTools' default — next to the textbook Wald interval, which misbehaves near 0% (it can run below zero). With 50 patients per arm, the intervals are wide: that width is the honest uncertainty.
Objective response (CR + PR)
| Proportion | Count | Estimate | 95% Wilson CI | 95% Wald CI |
|---|---|---|---|---|
| Placebo | 7 / 50 | 14.0% | 7.0% – 26.2% | 4.4% – 23.6% |
| Drug A | 11 / 50 | 22.0% | 12.8% – 35.2% | 10.5% – 33.5% |
| Drug B | 23 / 50 | 46.0% | 33.0% – 59.6% | 32.2% – 59.8% |
| Drug A + B | 27 / 50 | 54.0% | 40.4% – 67.0% | 40.2% – 67.8% |
LabTools calls (2)
stats.cilabtools stats ci --kind proportion --successes 7 --n 50 --method wilson
stats.cilabtools stats ci --kind proportion --successes 7 --n 50 --method wald
The same method is available as an MCP tool (stats_ci) and from the desktop app's statistics panel.
Complete response rate
The rarest outcome is where the two interval methods disagree most — Placebo has 0 complete responses, and Wald collapses to a zero-width interval there.
Complete response
| Proportion | Count | Estimate | 95% Wilson CI | 95% Wald CI |
|---|---|---|---|---|
| Placebo | 0 / 50 | 0.0% | 0.0% – 7.1% | 0.0% – 0.0% |
| Drug A | 1 / 50 | 2.0% | 0.4% – 10.5% | 0.0% – 5.9% |
| Drug B | 10 / 50 | 20.0% | 11.2% – 33.0% | 8.9% – 31.1% |
| Drug A + B | 15 / 50 | 30.0% | 19.1% – 43.8% | 17.3% – 42.7% |
LabTools calls (2)
stats.cilabtools stats ci --kind proportion --successes 0 --n 50 --method wilson
stats.cilabtools stats ci --kind proportion --successes 0 --n 50 --method wald
The same method is available as an MCP tool (stats_ci) and from the desktop app's statistics panel.
Progressive disease rate
Progressive disease
| Proportion | Count | Estimate | 95% Wilson CI | 95% Wald CI |
|---|---|---|---|---|
| Placebo | 22 / 50 | 44.0% | 31.2% – 57.7% | 30.2% – 57.8% |
| Drug A | 15 / 50 | 30.0% | 19.1% – 43.8% | 17.3% – 42.7% |
| Drug B | 8 / 50 | 16.0% | 8.3% – 28.5% | 5.8% – 26.2% |
| Drug A + B | 9 / 50 | 18.0% | 9.8% – 30.8% | 7.4% – 28.6% |
LabTools calls (2)
stats.cilabtools stats ci --kind proportion --successes 22 --n 50 --method wilson
stats.cilabtools stats ci --kind proportion --successes 22 --n 50 --method wald
The same method is available as an MCP tool (stats_ci) and from the desktop app's statistics panel.
Methods paragraph
Written to go straight into a manuscript.
Objective response rate (CR + PR) is reported per arm with 95% Wilson confidence intervals: placebo 14% (7–26%), Drug A 22% (13–35%), Drug B 46% (33–60%), Drug A + B 54% (40–67%).
Every number on this page was computed by the LabTools statistics engine (version 0.14.3) from the example's CSV on 2026-09-23. Where a value was derived before the data reached LabTools (replicate means, paired differences, log odds ratios), the text says so. The data are simulated from a fixed random seed.
Get started
Run the same analysis on your data
Every test on this page is built into LabTools — from the statistics panel, the command line, or an AI assistant through MCP.