Safety and Efficacy Trial of RPC1063 for Moderate to Severe Ulcerative Colitis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety and Efficacy Trial of RPC1063 for Moderate to Severe Ulcerative Colitis (NCT02435992), a randomized phase 3 study. The primary outcome is Percentage of Participants in Clinical Remission at 10 Weeks.

2. Clinical Question

This is a question about a defined outcome at a defined time, rather than a general measure of all possible benefits or harms. Clinical remission at 10 weeks is the primary endpoint recorded for this trial. Other outcomes listed in the registry include clinical response, endoscopic improvement, mucosal healing, and outcomes assessed at 52 weeks. Those measures address related but distinct aspects of disease status and follow-up. The primary result should therefore be read as evidence about the stated induction-period endpoint and comparison, not as a summary of every outcome recorded in the trial.

3. Trial Design

The registry describes a Phase 3, multicenter, randomized, double-blind, placebo-controlled trial of oral RPC1063 as induction and maintenance therapy for moderate to severe ulcerative colitis. The allocation is recorded as randomized, masking as quadruple, and the model as parallel. The registry does not describe the practical details of the randomization or masking procedures, or which roles were included in its quadruple-masking designation.

The record reports enrollment of 1012 and a completed status. The study start date is 2015-06-17, and the primary completion date is 2020-03-27. These are registry entries; they do not by themselves describe how long any individual participant was followed or how participants moved through the trial.

The primary endpoint is the percentage of participants in clinical remission at 10 weeks in the ITT Population. The posted primary comparison uses RPC1063 Cohort 1 during induction, with 429.0 participants listed, and the placebo cohort during induction, with 216.0 listed. The registry also lists RPC1063 Cohort 2 during induction, with 367.0 participants and a remission value, but its reported primary analysis does not include that cohort. Maintenance-period entries for the primary outcome have no values and list 0.0 participants; they do not provide a maintenance-period estimate for this endpoint.

The official title identifies induction and maintenance as trial periods, and the listed secondary outcomes include measures at 10 weeks and 52 weeks. The registry record does not report the detailed transition rules, follow-up schedule, or analysis plan for those periods. It also does not report the rationale for the enrollment target or whether interim analyses were planned.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Before assignment: 1012 Participants randomized and treated

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: ITT Population

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants in Clinical Remission at 10 Weeks, measured over At 10 Weeks.

The primary endpoint is the percentage of participants in clinical remission at 10 weeks, assessed in the ITT Population. The registry describes it as the percentage of participants in clinical remission at that time. It is a binary-status outcome summarized as a percentage: each participant is classified according to whether the remission criterion was met, and the group result expresses the proportion meeting it.

In general, clinical remission is used as a trial endpoint because it represents a defined clinical state at a specified assessment time. A percentage is readily interpretable as a group-level summary, but it does not show how each participant's condition changed or how long remission lasted. The registry record does not provide the clinical criteria used to define remission, the assessment procedures, or details about how missing assessments were handled. Those omissions limit the ability to assess precisely what counted as remission and how the endpoint was operationalized.

The registry reports values of 18.4 for RPC1063 Cohort 1 and 6.0 for placebo at 10 weeks. It also reports 21.0 for RPC1063 Cohort 2, but no corresponding primary comparison involving that cohort. The stated primary analysis is therefore interpreted for Cohort 1 versus placebo; the Cohort 2 value is not evidence of a separately reported treatment contrast.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary result combines a descriptive endpoint summary with an inferential comparison. The descriptive values are the reported clinical remission percentages at 10 weeks: 18.4 for RPC1063 Cohort 1 and 6.0 for placebo. The inferential result is an odds ratio estimated using the Cochran-Mantel-Haenszel method. These statistics answer related but different questions. The percentages describe the observed endpoint in each group; the odds ratio summarizes the relative odds under the reported method.

What does an odds ratio express?

In general, odds compare the chance of an event with the chance of its non-occurrence. An odds ratio compares those odds between groups. It is not the same quantity as a difference in percentages or a ratio of percentages, and its numerical size should not be translated directly into a change in the remission percentage. The odds ratio of 3.586 is the reported comparative estimate for the Cohort 1 and placebo analysis. Its direction indicates higher estimated odds of remission in the RPC1063 Cohort 1 group than in the placebo group, under the endpoint coding and analysis reported.

What does the confidence interval add?

In general, a confidence interval gives a range of values compatible with the data and the method used, reflecting sampling uncertainty. It is not a guarantee that the true effect lies in that particular interval, and it does not cover uncertainties caused by unreported design or analysis choices. The registry reports a 95% confidence interval from 1.938 to 6.636 for the odds ratio. Because this interval is entirely on the higher-odds side of the null value, the estimate is inconsistent with no difference at the corresponding confidence level under the method's assumptions. The breadth of the interval also shows that the effect is not pinned down to a single precise odds ratio.

What does the p-value mean?

In general, a p-value measures how incompatible the observed data, or results more extreme, are with a specified null hypothesis under the statistical model. It is not the probability that the null hypothesis is true, nor a measure of how important the result is. The reported p-value is < 0.001. It is small under conventional interpretations, but it should be read alongside the estimate, confidence interval, endpoint definition, and analysis context. It does not resolve limitations in reporting or establish effects on outcomes that were not part of this comparison.

Why use the Cochran-Mantel-Haenszel method?

In general, the Cochran-Mantel-Haenszel method can estimate an association across strata, rather than simply pooling all observations without regard to stratification. This can be useful when an analysis is intended to account for specified strata. The registry names the method but does not report the strata used, their definitions, or the detailed model implementation. It is therefore possible to explain the method's general purpose, but not to determine from the registry record which factors were accounted for in this analysis.

The reported analysis is specifically the comparison of RPC1063 Cohort 1 with placebo during induction. The registry lists a separate value for Cohort 2 but does not state a corresponding odds ratio, confidence interval, or p-value for that cohort. It would be inappropriate to infer an unreported test or combine the cohort results into a new treatment estimate. The record also does not provide a separate unadjusted recalculated estimate in the registry record for this interpretation.

In general, analyses of binary outcomes can be sensitive to the definition of the outcome, the handling of participants without an assessment, and the population included. The endpoint is labelled ITT Population, but the registry record does not provide the complete population rules, participant flow, missing-data method, or sensitivity analyses. Those omissions are relevant to assessing the reported estimate, even though the point estimate and interval are stated.

The record includes a sample-size planning illustration based on the observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. Such planning values are hypothetical illustrations under stated assumptions, not observed properties of the trial and not observed power. They do not substitute for a registry-reported sample-size justification, which is not reported in the registry record. The record does not state whether a different design calculation informed enrollment.

10. Analyses Reported by the Sponsor

The registry reports the sponsor's primary comparison as a Cochran-Mantel-Haenszel odds ratio of 3.586, with a 95% confidence interval from 1.938 to 6.636 and p < 0.001. The underlying group values are 18.4 for RPC1063 Cohort 1 and 6.0 for placebo. This is the inferential result to use when describing the primary comparison, because it is the analysis reported for that endpoint and comparison.

No separate recalculated estimate is stated in the registry record for this result. The registry entries do not include enough detail to reproduce the Cochran-Mantel-Haenszel analysis, including its strata or full implementation. A simple unadjusted recalculation from summary values, if available elsewhere, would answer a different and more limited question; it would not replace the sponsor's stated method. The registry record does not flag a discrepancy between the sponsor's result and a recalculation.

The reported result should therefore be described using its stated odds ratio, interval, and p-value, while keeping the descriptive percentages distinct from the odds-ratio scale. Neither the registry's inferential result nor a hypothetical unadjusted calculation supplies information about unreported outcomes, missing-data handling, or the clinical criteria for remission.

11. Multiplicity, Missing Data and Analysis Populations

The registry identifies clinical remission at 10 weeks as the primary endpoint and lists a range of secondary outcomes, including clinical response, endoscopic improvement, mucosal healing, remission at 52 weeks, and corticosteroid-free remission. Testing many outcomes can increase the chance of observing at least one apparently notable result by chance if each is assessed independently without an adjustment or prespecified testing strategy. In general, multiplicity procedures address this issue by controlling the interpretation of a family of tests or by defining a testing order.

The registry record does not report whether multiplicity adjustments were used, how outcome tests were ordered, or whether a hierarchy governed interpretation of the secondary outcomes. It does not report a full statistical analysis plan. Accordingly, the primary result can be described as the registry's reported primary comparison, but the information available does not establish how the other outcome tests were incorporated into an overall error-control strategy.

The primary endpoint is labelled for the ITT Population. The record does not provide detailed rules for inclusion in that population, participant disposition, missing endpoint assessments, or the method used to handle missing data. In general, missing outcomes can affect both the estimated group percentages and the uncertainty around a treatment comparison, depending on their frequency and the assumptions made. Without these details, the sensitivity of the primary result to missingness cannot be evaluated from the registry record.

Also not reported in the registry record are the sample-size justification, interim-analysis plans, and any stopping rules. The sample-size planning illustration is based on the observed effect and stated assumptions; it is not evidence of the original design rationale or observed power. These reporting gaps do not change the numerical result that is posted, but they limit assessment of the broader testing strategy and the robustness of the analysis.

12. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: colitis ulcerative (4.0%), anaemia (0.9%), complicated appendicitis (0.9%), appendicitis (0.5%), gastroenteritis (0.5%).

The registry lists serious adverse events by group and period. During induction, serious adverse events affected 17 of 429 participants in RPC1063 Cohort 1 and 11 of 216 in the placebo cohort. In RPC1063 Cohort 2, the corresponding count was 23 of 367. During maintenance, the registry lists 12 of 230 for RPC1063 and 18 of 227 for placebo. These are group-specific counts and denominators; they should not be combined across periods or cohorts.

The listed deaths were 0 for RPC1063 Cohort 1, 0 for induction placebo, 1 for RPC1063 Cohort 2, 0 for maintenance RPC1063, and 0 for maintenance placebo. The record also names serious-event terms, with ulcerative colitis at 4.0%, anaemia at 0.9%, complicated appendicitis at 0.9%, appendicitis at 0.5%, gastroenteritis at 0.5%, and diarrhoea at 0.5% among the listed terms.

These counts do not establish whether an event was caused by treatment. The registry record does not report the detailed event definitions, severity grading, exposure-adjusted rates, or full follow-up context for these figures. Induction and maintenance groups also represent different trial periods and should be interpreted in their stated contexts. The counts are descriptive safety information, not a standalone causal comparison.

13. What the Result Does, and Does Not, Mean

The posted primary result describes a difference in clinical remission at 10 weeks between RPC1063 Cohort 1 and placebo in the ITT Population. The reported percentages are 18.4 and 6.0, and the reported odds ratio is 3.586 with a 95% confidence interval from 1.938 to 6.636 and p < 0.001. These data support the statement that the reported analysis found higher odds of remission in Cohort 1 than in the placebo group at that assessment, under the stated method.

The result does not show that every participant in one group had a better outcome than every participant in the other. Group-level percentages and an odds ratio summarize distributions across participants; they do not describe each individual's course. Nor does the odds ratio translate directly into a percentage-point change. The registry's results concern the defined endpoint at 10 weeks, rather than all possible measures of ulcerative colitis or all periods of treatment.

The registry record also lists a remission value of 21.0 for RPC1063 Cohort 2, but it does not report a corresponding primary inferential comparison for that cohort. That value should not be treated as an additional controlled estimate. The record lists maintenance and 52-week outcomes, but their results are not included in the primary result details. No conclusion about those endpoints follows from the 10-week comparison alone.

Statistical evidence and clinical importance are related but not interchangeable. A p-value describes compatibility with a null hypothesis under assumptions; it does not establish importance to patients. The confidence interval conveys uncertainty in the odds-ratio estimate, but it does not address every uncertainty arising from endpoint definition, missing data, or analysis choices. The registry record does not provide the remission criteria or detailed missing-data methods needed to assess those aspects fully.

The safety counts offer descriptive information about serious adverse events and deaths in the listed groups. They do not by themselves establish causation or provide a complete benefit-harm assessment. Taken together, the registry supports a focused interpretation of the reported induction-period primary comparison, while leaving important questions about other outcomes and analytic details unanswered.

14. Why This Trial Matters Statistically

This trial illustrates why the scale of a reported treatment effect matters. The remission percentages are direct group summaries, while the odds ratio is a comparative measure on the odds scale. Reading the odds ratio as if it were a ratio of remission percentages would misstate the result. Statistical interpretation depends on identifying what each estimate represents before drawing conclusions from its direction or magnitude.

The confidence interval and p-value also serve different roles. The interval shows a range of effect estimates compatible with the data and method, whereas the p-value expresses evidence against a specified null hypothesis under model assumptions. Neither replaces the group values or conveys clinical importance on its own. Keeping these pieces distinct is central to transparent reporting of a binary clinical endpoint.

The record also makes clear that multiple trial cohorts and periods do not automatically form one comparison. The primary inferential result is for RPC1063 Cohort 1 versus placebo during induction. Cohort 2 has a posted remission percentage but no corresponding primary contrast, and maintenance entries for this primary endpoint are not estimable in the record. Preserving those distinctions avoids creating an analysis that the registry does not report.

Finally, the endpoint name alone is not a complete measurement description. Missing criteria, analysis-population details, multiplicity plans, and missing-data methods constrain how fully a reader can evaluate the result. Statistical literacy includes recognizing both what a reported estimate supports and which questions remain unresolved by the registry record.

15. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The registry record does not provide the operational definition of clinical remission or the procedures used to assess it. Without those details, readers cannot determine precisely which clinical findings qualified a participant as being in remission at 10 weeks. The primary endpoint is labelled for the ITT Population, but population rules and participant disposition are not reported in the record.

The primary inferential analysis covers RPC1063 Cohort 1 and placebo. Although a remission value of 21.0 is listed for RPC1063 Cohort 2, there is no corresponding reported odds ratio, confidence interval, or p-value for a Cohort 2 comparison. The primary result should not be generalized to that cohort by treating its descriptive value as a controlled estimate. The maintenance-period entries for this primary endpoint have no values and list 0.0 participants, so they do not supply a maintenance result for clinical remission at 10 weeks.

The reported method is Cochran-Mantel-Haenszel, but the registry record does not identify the strata or describe the detailed analysis implementation. It also does not report missing-data handling, sensitivity analyses, multiplicity adjustment, the full statistical analysis plan, interim analyses, or the sample-size justification. These omissions prevent a complete assessment of model choices and robustness from the registry record alone.

The serious adverse-event counts are reported for separate cohorts and periods. The record does not provide enough detail on event definitions, timing, exposure, or causal assessment to support a comprehensive comparison of safety. These limitations are specific to the detail available in the registry record and do not alter the numerical values that are posted.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Safety and Efficacy Trial of RPC1063 for Moderate to Severe Ulcerative Colitis — NCT02435992.
• Registry record last updated 2021-09-01; status last verified 2021-08.
• Results first posted 2021-09-01.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

19. Record Summary

The registry record describes a completed Phase 3, multicenter, randomized, double-blind, placebo-controlled trial of oral RPC1063 for moderate to severe ulcerative colitis. Enrollment is recorded as 1012. The study began on 2015-06-17, with primary completion on 2020-03-27.

The primary endpoint was the percentage in clinical remission at 10 weeks in the ITT Population. For RPC1063 Cohort 1 versus placebo, the posted values were 18.4 and 6.0. The reported Cochran-Mantel-Haenszel odds ratio was 3.586, with a 95% confidence interval from 1.938 to 6.636 and p < 0.001. RPC1063 Cohort 2 has a listed remission value of 21.0, without a corresponding reported primary comparison.

The record lists secondary clinical and endoscopic outcomes and serious adverse-event counts. Important details—including remission criteria, missing-data methods, multiplicity procedures, and the full statistical analysis plan—are not reported in the registry record.