This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for A Study to Investigate the Safety and Efficacy of CP-690,550 in Patients With Moderate to Severe Crohn's Disease (NCT00615199), a randomized phase 2 study. The primary outcome is Number of Participants With Clinical Response 70 at Week 4.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT00615199 |
| Phase | Phase 2 |
| Condition | Crohn's Disease |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Triple |
| Enrollment | 139 |
| Arms in the primary outcome | 4 |
| Lead sponsor | Pfizer |
| Results posted | Yes |
2. Clinical Question
Population
Adults with moderate to severe Crohn's disease were the intended study population. The primary endpoint analysis used a Full Analysis Set described as randomized participants who either withdrew as treatment failure or completed at least 1 week of dosing and had at least 1 valid CDAI score during the active double-blind phase. The registry description of this population is truncated when explaining additional exclusions, so the complete analysis-population rules are not reported in the registry record.
Intervention
Participants were assigned to CP-690,550 dose groups identified in the posted results as 1 mg, 5 mg, and 15 mg. The brief summary describes the study as investigating several dose levels. Dosing frequency is indicated as BD in the arm descriptions, but the registry does not give further details in those descriptions.
Comparator
The comparator was placebo. The study is described as randomized, double-blind, placebo-controlled, and parallel-group. Enrollment was 139 participants across the study, while the primary outcome counts are reported for the individual analysis groups.
Primary question
At Week 4, did any CP-690,550 dose group have a different number of participants with clinical response 70 than the placebo group? Clinical response 70 means a reduction in CDAI score from baseline of at least 70 points. The study summary states the hypothesis that at least one tested dose would be more effective than placebo. The posted primary comparisons do not report adjusted analyses, and the record does not report the trial's original statistical analysis plan.
3. Trial Design
This was a Phase 2, randomized, triple-masked, parallel-group study of CP-690,550 in patients with moderate to severe Crohn's disease. The registry title describes the study as double-blind, while its design fields classify masking as triple. The trial compared placebo with three CP-690,550 dose groups, identified in the arm descriptions as 1 mg BD, 5 mg BD, and 15 mg BD. The registry lists an enrollment of 139 participants.
The study is described as multi-center. Its status is completed. The registry lists a start of 2008-01 and primary completion of 2009-10. The brief summary says the study investigated safety and efficacy and states a hypothesis that at least one dose level would be more effective than placebo. The registry record does not report the original sample-size justification, planned statistical analysis details, interim analyses, or a complete account of allocation procedures beyond randomization.
Primary outcome results are counts of participants with clinical response 70 at Week 4. The posted analysis group sizes are 32.0 for placebo, 35.0 for CP-690550 1 mg, 30.0 for CP-690550 5 mg, and 33.0 for CP-690550 15 mg. These analysis counts do not sum to the overall enrollment, and the registry description of the primary analysis population is truncated before it finishes describing exclusions. The record therefore does not permit a full reconciliation of enrollment with the outcome-analysis groups.
The registry also lists outcomes for clinical response at Week 1 and Week 2, clinical remission at Week 4, clinical response 100 at Week 4, and times to first remission and response. Posted numerical results are available for some Week 4 secondary outcomes, but not for every listed secondary outcome. These results supplement rather than replace the primary Week 4 response-70 comparison.
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.
Overall Study
| Stage | Placebo | CP-690550 1 mg | CP-690550 5 mg | CP-690550 15 mg |
|---|---|---|---|---|
| STARTED | 34 | 36 | 34 | 35 |
| COMPLETED | 26 | 34 | 33 | 33 |
| NOT COMPLETED | 8 | 2 | 1 | 2 |
Reasons for not completing this period:
| Reason | Placebo | CP-690550 1 mg | CP-690550 5 mg | CP-690550 15 mg |
|---|---|---|---|---|
| Adverse Event | 3 | 1 | 1 | 0 |
| Lack of Efficacy | 2 | 0 | 0 | 1 |
| Lost to Follow-up | 1 | 0 | 0 | 0 |
| Other | 0 | 0 | 0 | 1 |
| Withdrawal by Subject | 2 | 1 | 0 | 0 |
Analysis population for the primary outcome, as defined in the registry: Full Analysis Set (FAS): all randomized participants who had either withdrawn as treatment failure or completed at least 1 week of dosing and had at least 1 valid CDAI score during the active double-blind phase. Number of participants analyzed excluded those with missing data or who fell outside the visit window.
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.
| Characteristic | Unit | Placebo | CP-690550 1 mg | CP-690550 5 mg | CP-690550 15 mg | Total |
|---|---|---|---|---|---|---|
| Participants analysed | 34 | 36 | 34 | 35 | 139 | |
| Age Continuous | years | 35.7 (SD 12.7) | 36.6 (SD 12.2) | 38.7 (SD 10.2) | 38.1 (SD 11.7) | 37.3 (SD 11.7) |
| Sex: Female, Male: Female | Participants | 22 | 11 | 20 | 17 | 70 |
| Sex: Female, Male: Male | Participants | 12 | 25 | 14 | 18 | 69 |
6. Primary Endpoint
The registry lists the primary outcome as Number of Participants With Clinical Response 70 at Week 4, measured over Week 4.
| Element | Registry entry |
|---|---|
| Result type | Number |
| Measure of spread | not applicable |
| Unit | participants |
| Endpoint classification | Binary Endpoint |
The primary endpoint is the number of participants with clinical response 70 at Week 4. The endpoint definition requires a reduction from baseline of at least 70 points on the Crohn's Disease Activity Index (CDAI). The registry describes CDAI as a composite index based on weighted scoring of eight disease variables: liquid stools, abdominal pain, general well-being, extraintestinal symptoms, use of antidiarrheal drugs, abdominal masses, hematocrit, and body weight. CDAI scores range from 0 to approximately 600, with higher scores indicating higher disease activity.
A threshold-based endpoint turns a change in a composite score into a count of participants who meet a specified response criterion. The posted results therefore allow comparison of counts and estimated response probabilities between each dose group and placebo. They do not show each participant's score change, the distribution of changes, or how close participants were to the threshold. Those details are not reported in the registry record.
As a general statistical point, a clinically defined threshold can make a result easier to interpret as the number meeting a stated response criterion, but it also omits information about the size of changes among participants above or below that threshold. The primary result should consequently be read as a comparison of this particular Week 4 response definition, not as a complete description of all changes in Crohn's disease activity.
7. Results Posted in the Registry
- CP-690550 1 mg: 37.1% (13/35) versus 43.8% (14/32) on control; risk difference -6.6 percentage points (95% CI -30.1 to 16.9), risk ratio 0.85 (0.47–1.52); unadjusted two-proportion z-test p = 0.582.
- CP-690550 5 mg: 60.0% (18/30) versus 43.8% (14/32) on control; risk difference 16.2 percentage points (95% CI -8.3 to 40.8), risk ratio 1.37 (0.84–2.24); unadjusted two-proportion z-test p = 0.201.
- CP-690550 15 mg: 48.5% (16/33) versus 43.8% (14/32) on control; risk difference 4.7 percentage points (95% CI -19.5 to 28.9), risk ratio 1.11 (0.65–1.88); unadjusted two-proportion z-test p = 0.702.
Risk difference: CP-690550 1 mg
95% CI: -30.1 to 16.9 percentage points
Recalculated from the posted summary statistics
8. Secondary Efficacy Endpoints
The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.
| Secondary outcome | Type | Effect measure | Estimate (95% CI) | Planning size, 80% power |
|---|---|---|---|---|
| Number of Participants Achieving Clinical Remission at Week 4 | Binary Endpoint | Risk difference | +9.6 pts (-11.5 to 30.6) | 336 per arm |
| Number of Participants With Clinical Response 100 at Week 4 | Binary Endpoint | Risk difference | +3.3 pts (-18.6 to 25.2) | 3,007 per arm |
Number of Participants Achieving Clinical Remission at Week 4
- Endpoint type: Binary: the number of participants with the event, compared as proportions.
- Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
- Result:
- CP-690550 1 mg: 31.4% (11/35) versus 21.9% (7/32) on control; risk difference 9.6 percentage points (95% CI -11.5 to 30.6), risk ratio 1.44 (0.63–3.25); unadjusted two-proportion z-test p = 0.378.
- CP-690550 5 mg: 26.7% (8/30) versus 21.9% (7/32) on control; risk difference 4.8 percentage points (95% CI -16.6 to 26.1), risk ratio 1.22 (0.50–2.95); unadjusted two-proportion z-test p = 0.660.
- Interpretation:
- The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between CP-690550 1 mg and the control. The interval gives the range of effects that remain compatible with the data.
- The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between CP-690550 5 mg and the control. The interval gives the range of effects that remain compatible with the data.
Number of Participants With Clinical Response 100 at Week 4
- Endpoint type: Binary: the number of participants with the event, compared as proportions.
- Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
- Result:
- CP-690550 1 mg: 31.4% (11/35) versus 28.1% (9/32) on control; risk difference 3.3 percentage points (95% CI -18.6 to 25.2), risk ratio 1.12 (0.53–2.34); unadjusted two-proportion z-test p = 0.768.
- CP-690550 5 mg: 46.7% (14/30) versus 28.1% (9/32) on control; risk difference 18.5 percentage points (95% CI -5.2 to 42.2), risk ratio 1.66 (0.85–3.25); unadjusted two-proportion z-test p = 0.131.
- Interpretation:
- The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between CP-690550 1 mg and the control. The interval gives the range of effects that remain compatible with the data.
- The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between CP-690550 5 mg and the control. The interval gives the range of effects that remain compatible with the data.
The posted Week 4 secondary outcomes add two related views of response: clinical remission and clinical response 100. Their group patterns are not uniform across dose groups. Some active-group estimates are above the placebo estimate, while other comparisons are closer to placebo or point in the opposite direction. Across the posted secondary comparisons, the uncertainty intervals include no difference. This broad pattern does not supply a consistent, precise signal that resolves the uncertainty in the primary response-70 result.
These secondary outcomes relate to the primary result because they use related clinical status measures at the same Week 4 time point, but they ask different questions. A participant can meet one endpoint definition without meeting another, and the thresholds are not interchangeable. The registry also lists response at earlier time points and time-to-first outcomes, but numerical results for every listed secondary endpoint are not posted. The record does not report secondary analyses for the time-to-event outcomes.
Unadjusted secondary findings carry less weight for confirmatory interpretation when multiple endpoints and dose comparisons are examined. As a general statistical issue, testing multiple outcomes creates more opportunities for chance patterns to appear. The registry record does not report a multiplicity adjustment or a prespecified hierarchy that would establish which secondary outcomes were confirmatory. The secondary results are therefore best read as exploratory context around the primary endpoint rather than independent confirmation.
The primary endpoint remains the central outcome for the study's stated hypothesis. The secondary findings neither erase the imprecision in the primary comparisons nor provide a basis to select a dose solely from the observed group patterns. They also do not establish longer-term effects: the posted numerical secondary results are at Week 4, while durability and later outcome results are not reported in the registry record.
Secondary outcomes registered for this trial, for reference (only those above were recalculated):
- Number of Participants With Clinical Response 70 at Week 1 and 2
- Number of Participants Achieving Clinical Remission at Week 4
- Number of Participants With Clinical Response 100 at Week 4
- Time to First Clinical Remission
- Time to First Response 70
- Time to First Response 100
9. Statistical Interpretation
In the placebo group, 14.0 of 32.0 participants were reported with clinical response 70 at Week 4. The corresponding counts were 13.0 of 35.0 in the CP-690550 1 mg group, 18.0 of 30.0 in the 5 mg group, and 16.0 of 33.0 in the 15 mg group. The recalculated unadjusted risk differences compare each active group with placebo. The estimate is negative for 1 mg and positive for 5 mg and 15 mg; however, each confidence interval extends across zero. The unadjusted p-values are 0.582, 0.201, and 0.702, respectively.
These results describe variation in the observed counts across the four groups, but they do not establish a clear difference from placebo. The estimates are uncertain, as indicated by the confidence intervals, and the unadjusted p-values do not provide strong evidence against no difference. The record reports no sponsor analysis for these comparisons, and it does not report an adjusted statistical analysis. The recalculated comparisons are therefore best treated as descriptive, unadjusted estimates rather than a replacement for a prespecified sponsor analysis.
The study summary frames its hypothesis as whether at least one tested dose is more effective than placebo. The posted comparisons are separate dose-versus-placebo contrasts. Interpreting several comparisons together raises a multiplicity issue: the chance of at least one apparently notable result can increase when multiple hypotheses are assessed. No multiplicity procedure is reported in the registry record, so the unadjusted p-values should not be read as if they account for the full set of comparisons.
The primary endpoint is a count at a single time point, Week 4. It does not by itself describe time to response, durability, later outcomes, or the full safety profile. The record lists additional outcomes, including remission and response 100 at Week 4, but these are secondary and their unadjusted findings carry less confirmatory weight. The primary result also depends on the specified CDAI threshold and the analysis population. The registry's population description is incomplete, and details about missing outcome data are not fully reported.
In statistical terms, the posted primary findings are compatible with a range of possible differences between each dose and placebo. They should not be reduced to a binary claim based only on whether a p-value crosses a threshold. The estimates, uncertainty, number of comparisons, and limitations in the registry's analysis description all matter when interpreting the evidence.
10. Statistical Methods Explained
The primary endpoint is binary at the participant level: each participant either met the clinical response 70 definition at Week 4 or did not. The registry reports counts of participants meeting the definition and analysis-group sizes. The recalculated comparisons express the difference between the active-group response probability and the placebo response probability as an unadjusted risk difference. A positive estimate means the observed response probability was higher in the active group; a negative estimate means it was lower. These are simple comparisons from the posted summary counts, not adjusted estimates from a model described by the sponsor.
What does an unadjusted comparison mean?
General statistical explanation: an unadjusted comparison contrasts the groups without accounting for additional covariates or other factors in a model. Randomization is intended to make groups comparable on average, but an unadjusted estimate still reflects the observed participants and the particular sample. The registry record does not report a model-based or covariate-adjusted primary analysis, so the recalculated contrasts should not be attributed to one.
The posted risk differences are accompanied by confidence intervals and unadjusted p-values. A confidence interval describes uncertainty around an estimated contrast under the assumptions of the calculation. When an interval for a risk difference includes zero, the results are compatible with no difference as well as with differences in either direction covered by the interval. Here, all three primary confidence intervals span zero. The p-values are also unadjusted; they do not account for testing three dose groups against the same placebo group or for other outcomes.
How should the endpoint definition be understood?
Clinical response 70 is defined by a reduction in CDAI score from baseline of at least 70 points. CDAI combines weighted information from eight disease variables into a score. The primary analysis then classifies participants according to whether they met the threshold. As a general point, such a classification is straightforward to count, but it discards distinctions among participants who all meet the threshold and among those who do not. The record does not post individual score changes or a continuous-score analysis alongside this primary count outcome.
What does the record say about analysis populations?
The primary outcome description names a Full Analysis Set. It describes this set as all randomized participants who either withdrew as treatment failure or completed at least 1 week of dosing and had at least 1 valid CDAI score during the active double-blind phase. The record then begins describing exclusions for missing data or participants who fell outside a criterion, but the sentence is truncated. The full population definition and the handling of missing Week 4 outcome data are therefore not reported in the registry record. It would be inappropriate to assume a particular missing-data method or to treat the analysis as intention-to-treat without qualification.
The posted group sizes for the primary endpoint are 32.0, 35.0, 30.0, and 33.0, while enrollment is reported as 139. These figures refer to different registry summaries, and the truncated population description prevents a complete account of the relationship between enrolled participants and analyzed participants. The record does not report participant flow or a full accounting of exclusions by group.
What statistical plan can be identified?
The registry record identifies the outcome definitions and posts group counts and recalculated comparisons, but it does not report the trial's original statistical analysis plan. In particular, the record does not report the originally planned comparison method, any covariate adjustment, a multiplicity strategy, interim analyses, or the original sample-size rationale. The posted p-values and intervals should therefore be understood as unadjusted calculations from the recorded summary data, not as a complete account of the trial's prespecified analysis.
General statistical explanation: with binary outcomes, uncertainty depends on both the observed group proportions and the number of participants contributing to each group. Small analysis groups can yield wide intervals, even when the estimated difference appears substantial. Over-dispersion is a concern mainly when observations vary more than a model assumes; this endpoint is reported as individual participant counts, and the registry does not report a model in which over-dispersion was assessed. No additional distributional assumption should be inferred from the posted summaries.
11. Confidence Intervals and Precision
The primary confidence intervals are wide and each spans zero. This means the posted data do not precisely pin down the direction or size of the difference between any CP-690,550 dose group and placebo. For the 1 mg comparison, the point estimate is negative; for the 5 mg and 15 mg comparisons, it is positive. The intervals nevertheless include zero in all three comparisons, so each remains compatible with no difference as well as with effects in either direction within its interval.
General statistical explanation: a confidence interval is a range of values that reflects sampling uncertainty under the method used to calculate it. It is not a guarantee that the true value lies in the interval, nor does its width measure every source of uncertainty. A narrow interval indicates greater precision for the estimated contrast under the calculation's assumptions; a wide interval indicates less precision. Here, the group sizes are modest and the intervals cover both potentially lower and higher response differences.
The interval estimates are recalculated, unadjusted comparisons from the posted summary counts. The registry does not report the confidence-interval method used in a sponsor analysis, and no sponsor analysis is posted for these contrasts. The intervals also do not account for multiplicity. Considered together with the unadjusted p-values, they support a cautious reading: the observed estimates vary by dose, but their uncertainty is substantial and the direction is not established consistently across comparisons.
12. Planning a Similar Trial: Sample Size
This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.
| Effect to detect | Participants per arm, 80% power | Participants per arm, 90% power |
|---|---|---|
| 100% of the observed effect | 865 | 1,158 |
| 75% of the observed effect | 1,549 | 2,073 |
| 50% of the observed effect | 3,505 | 4,692 |
The sample-size figures are planning illustrations based on the observed effect, not the trial's original design assumptions. The calculations assume a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. They ask how many participants per arm would be needed to detect the stated fraction of the observed effect. These figures are participants per arm for 80% power or participants per arm for 90% power; they are not total enrollment figures. The time-to-event calculations, if displayed for other outcomes, instead give total events, but the binary comparisons use participants per arm.
In plain language, the 80% power column gives the illustrative number of participants per arm under which the calculation would have an 80% chance of detecting the specified effect, if the assumptions used in the calculation held. The 90% power column uses a higher target chance of detecting that effect and therefore generally requires more participants. The rows for 100%, 75%, and 50% of the observed effect show how the planning estimate changes when the effect to detect is reduced. Smaller effects need more participants because they are harder to distinguish from random variation.
For example, the 5 mg primary comparison's planning figures are 148 participants per arm for 80% power and 197 for 90% power when planning for 100% of the observed effect. The corresponding figures for planning for 75% of the observed effect are 264 and 352; for 50%, they are 593 and 793. These are hypothetical planning quantities, not observed trial results. This is not observed power: it does not describe the probability that the completed trial succeeded, and it should not be used to reinterpret the observed confidence intervals or p-values. The original trial design assumptions are not reported in the registry record.
13. How the Sample Size Is Derived
Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z1−α/2 = 1.960) and the desired power (z1−β = 0.842 for 80% and 1.282 for 90%).
Formula
n is the number of participants in each arm, p0 and p1 are the control and treatment proportions, and p̄ is their average.
Worked calculation for this trial
- Control proportion p0 = 0.438; treatment proportion p1 = 0.371; average p̄ = 0.404.
- First term: z1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6941 = 1.3604.
- Second term: z1−β × √[p0(1−p0) + p1(1−p1)] = 0.842 × 0.6925 = 0.5828.
- n = (1.3604 + 0.5828)2 / (-0.0661)2 = 865.0, rounded up to 865 participants per arm for 80% power.
The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).
R code
alpha <- 0.05
z_a <- qnorm(1 - alpha / 2) # two-sided
p0 <- 0.4375 # control proportion
p1 <- 0.371428571428571 # treatment proportion
n_per_arm <- function(power, frac = 1) {
q1 <- p0 + (p1 - p0) * frac # smaller effect = fraction of the observed difference
pbar <- (p0 + q1) / 2
z_b <- qnorm(power)
ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^2, 6))
}
for (f in c(1, 0.75, 0.5))
cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))
# Check against R's built-in function (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")
# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(615199)
n <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))
Output from running the code
100% of observed effect: n per arm = 865 (80% power), 1,158 (90% power)
75% of observed effect: n per arm = 1,549 (80% power), 2,073 (90% power)
50% of observed effect: n per arm = 3,505 (80% power), 4,692 (90% power)
power.prop.test: 865
Simulated power at n = 865 per arm: 0.801 (20000 replicates)The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.
14. Multiplicity, Missing Data and Analysis Populations
The registry lists a primary endpoint and multiple secondary outcomes, with three dose groups compared against placebo for posted binary outcomes. The posted p-values are unadjusted. A multiplicity procedure, such as a planned sequence of testing or a correction across comparisons, is not reported in the registry record. Consequently, the p-values should be interpreted as individual unadjusted comparisons, not as error-controlled evidence across all dose groups and outcomes.
The record reports zero posted analyses for the primary outcome and no reported analyses for the listed secondary outcomes, while group counts and summary comparisons are available. This means the registry record does not establish how these comparisons relate to the original statistical analysis plan. The planned testing strategy, any interim analyses, and any decisions about primary or secondary hypothesis families are not reported in the registry record.
Missing-data handling is also incompletely described. The primary endpoint population text says that participants who withdrew as treatment failure or completed at least 1 week of dosing with at least 1 valid CDAI score during the active double-blind phase were included. It then refers to exclusions for missing data or being outside a criterion, but the text ends before the criterion is complete. The specific Week 4 imputation approach, if any, is not reported in the registry record. It is therefore not possible to determine from the record how missing outcome values were handled or whether different assumptions were tested.
The record does not provide a complete participant flow by group or a full account of analysis-set membership. It also does not report sensitivity analyses addressing missing data. These omissions matter because the reported participant counts and outcome counts are interpreted within an analysis population, and different inclusion or missing-data rules can affect binary outcome comparisons. No particular procedure should be assumed in the absence of a complete registry description.
15. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| Placebo | 5 | 34 | 14.7% |
| CP-690550 1 mg | 4 | 36 | 11.1% |
| CP-690550 5 mg | 4 | 34 | 11.8% |
| CP-690550 15 mg | 1 | 35 | 2.9% |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 2% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Placebo | 20 of 34 |
| CP-690550 1 mg | 18 of 36 |
| CP-690550 5 mg | 19 of 34 |
| CP-690550 15 mg | 22 of 35 |
Most frequent serious adverse event terms
| Event term | Organ system | Placebo | CP-690550 1 mg | CP-690550 5 mg | CP-690550 15 mg |
|---|---|---|---|---|---|
| Crohn's disease | Gastrointestinal disorders | 0 of 34 | 2 of 36 | 1 of 34 | 1 of 35 |
| Diarrhoea | Gastrointestinal disorders | 1 of 34 | 0 of 36 | 2 of 34 | 0 of 35 |
| Anal abscess | Infections and infestations | 2 of 34 | 0 of 36 | 0 of 34 | 0 of 35 |
| Atrial fibrillation | Cardiac disorders | 1 of 34 | 0 of 36 | 0 of 34 | 0 of 35 |
| Abdominal pain | Gastrointestinal disorders | 0 of 34 | 0 of 36 | 1 of 34 | 0 of 35 |
| Intestinal obstruction | Gastrointestinal disorders | 1 of 34 | 0 of 36 | 0 of 34 | 0 of 35 |
| Small intestinal obstruction | Gastrointestinal disorders | 0 of 34 | 1 of 36 | 0 of 34 | 0 of 35 |
| Subileus | Gastrointestinal disorders | 0 of 34 | 0 of 36 | 1 of 34 | 0 of 35 |
| Chills | General disorders | 0 of 34 | 0 of 36 | 1 of 34 | 0 of 35 |
| Pyrexia | General disorders | 0 of 34 | 0 of 36 | 1 of 34 | 0 of 35 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Placebo | CP-690550 1 mg | CP-690550 5 mg | CP-690550 15 mg |
|---|---|---|---|---|---|
| Nausea | Gastrointestinal disorders | 2 of 34 | 4 of 36 | 3 of 34 | 3 of 35 |
| Abdominal pain | Gastrointestinal disorders | 3 of 34 | 3 of 36 | 0 of 34 | 3 of 35 |
| Vomiting | Gastrointestinal disorders | 3 of 34 | 2 of 36 | 1 of 34 | 3 of 35 |
| Asthenia | General disorders | 3 of 34 | 3 of 36 | 1 of 34 | 1 of 35 |
| Fatigue | General disorders | 3 of 34 | 4 of 36 | 0 of 34 | 1 of 35 |
| Headache | Nervous system disorders | 1 of 34 | 2 of 36 | 2 of 34 | 3 of 35 |
| Crohn's disease | Gastrointestinal disorders | 1 of 34 | 1 of 36 | 2 of 34 | 2 of 35 |
| Diarrhoea | Gastrointestinal disorders | 0 of 34 | 2 of 36 | 1 of 34 | 3 of 35 |
| Pyrexia | General disorders | 1 of 34 | 0 of 36 | 2 of 34 | 3 of 35 |
| Nasopharyngitis | Infections and infestations | 1 of 34 | 3 of 36 | 1 of 34 | 1 of 35 |
Serious events with the highest arm-level rate: diarrhoea (5.9%), anal abscess (5.9%), crohn's disease (5.6%), atrial fibrillation (2.9%), abdominal pain (2.9%).
The registry reports serious adverse event counts alongside the number at risk. For placebo, 5 of 34 participants were affected; for CP-690550 1 mg, 4 of 36; for 5 mg, 4 of 34; and for 15 mg, 1 of 35. These are descriptive counts from the registry record. The record also lists serious-event terms including diarrhoea, anal abscess, Crohn's disease, atrial fibrillation, abdominal pain, and intestinal obstruction. The listed percentages for those terms are 5.9%, 5.9%, 5.6%, 2.9%, 2.9%, and 2.9%, respectively.
These summaries do not by themselves establish comparative safety. The registry record does not report a formal statistical comparison of serious adverse events, and the group sizes are limited. The number of participants with other adverse events is also posted, but those counts are separate from serious adverse events and should not be conflated with them. Death counts are not reported in the registry record. The posted safety summary does not provide event timing, duration, severity grading beyond serious-event status, or participant-level clinical context.
16. What the Result Does, and Does Not, Mean
The primary result describes how many participants in each analysis group met a specified clinical response threshold at Week 4. The observed counts differ among groups, but the unadjusted comparisons are imprecise: all three confidence intervals include no difference, and the unadjusted p-values do not establish a clear dose-versus-placebo difference. The evidence in the registry record therefore does not support a precise conclusion about the size or direction of a Week 4 response difference for any dose.
This statistical interpretation is narrower than a general claim about treatment benefit. The endpoint captures one CDAI-based threshold at one time point. It does not describe every aspect of disease activity, patient experience, sustained response, or outcomes after Week 4. Nor do the posted results settle the interpretation of the safety findings. The safety information is descriptive and does not include a formal comparative analysis.
The findings also have limits as evidence about the study's original hypothesis. The record states that the hypothesis concerned at least one dose being more effective than placebo, but it does not report the planned multiplicity approach or the complete analysis plan. The posted unadjusted dose comparisons do not account for the full set of tests. The endpoint population description is truncated, and missing-data methods are not reported in the registry record. These details affect how firmly the observed estimates can be interpreted.
In general, absence of a clearly established difference is not proof that groups are identical. Likewise, a point estimate favoring one group is not, by itself, evidence that a difference is reliable. The confidence intervals communicate that substantial uncertainty remains. The registry record should be read as a limited set of posted outcome and safety summaries, rather than as a complete account of the trial's protocol, analysis decisions, or all results.
17. Why This Trial Matters Statistically
This trial illustrates several central issues in clinical-trial statistics. First, randomized group comparisons can produce different point estimates across dose groups even when the results are uncertain. Looking only at which group has the largest observed count would ignore the uncertainty represented by the intervals and the small analysis groups. The primary comparisons show why effect estimates and precision should be considered together.
Second, the trial raises a multiplicity question. The study's stated hypothesis asks whether at least one dose is more effective than placebo, while the posted results compare each dose with the same control and include several secondary outcomes. Without a reported testing strategy, separate unadjusted p-values do not answer a single family-level question with controlled error.
Third, the endpoint converts a composite CDAI score into a threshold-based count. This is interpretable as the number meeting a defined response criterion, but it cannot show the full distribution of score changes. Finally, the incomplete analysis-population description and absent missing-data details highlight why registry outcome summaries need to be read alongside complete protocol and analysis documentation when available. These are statistical interpretation issues, not judgments about individual care.
18. 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 main limitations specific to the registry record are the modest outcome-analysis group sizes and the resulting imprecision in the primary comparisons. All three recalculated primary confidence intervals span zero. The posted comparisons are unadjusted and the record does not give a multiplicity plan, despite several dose comparisons and multiple listed outcomes.
The description of the Full Analysis Set is truncated. It mentions participants who withdrew as treatment failure or completed at least 1 week of dosing and had at least 1 valid CDAI score, then begins to describe exclusions without completing the rule. Missing-data handling, participant flow, and group-specific reasons for exclusion are not reported in the registry record. These gaps limit assessment of who contributed to each outcome count.
The registry also does not report the original sample-size justification, full statistical analysis plan, interim analyses, or the methods underlying sponsor analyses. No sponsor statistical analyses are posted for the reported comparisons. The planning illustrations are based on observed effects and should not be mistaken for design assumptions. The primary endpoint is a Week 4 threshold outcome, and numerical results are not posted for all listed secondary outcomes. The safety summaries lack reported formal between-group analyses and do not report death counts.
19. Related Tutorials
20. Related Statistical Calculators
21. Sources
- ClinicalTrials.gov: A Study to Investigate the Safety and Efficacy of CP-690,550 in Patients With Moderate to Severe Crohn's Disease — NCT00615199.
- Registry record last updated 2013-01-25; status last verified 2013-01.
- Results first posted 2012-12-31.
- 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.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
22. Record Summary
NCT00615199 is a completed Phase 2 randomized, triple-masked, parallel-group, placebo-controlled study of CP-690,550 in adults with moderate to severe Crohn's disease. The registry lists enrollment of 139 and compares placebo with CP-690,550 1 mg, 5 mg, and 15 mg groups.
The primary outcome is the number of participants with clinical response 70 at Week 4, defined as a CDAI reduction from baseline of at least 70 points. The posted counts vary across groups, but the recalculated unadjusted comparisons are imprecise and all confidence intervals include zero. Secondary Week 4 outcomes add context but are also unadjusted. Multiplicity handling, the complete analysis-population definition, missing-data methods, and the original statistical plan are not reported in the registry record.