Clinical Study of CDP870/Certolizumab Pegol in Patients With Active Crohn's Disease: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Clinical Study of CDP870/Certolizumab Pegol in Patients With Active Crohn's Disease (NCT00291668), a randomized phase 2 study. The primary outcome is Crohn's Disease Activity Index (CDAI) Response (Clinical Response or Remission) at Week 6.

2. Clinical Question

3. Trial Design

The registry describes a Phase II, randomized, parallel-group, placebo-controlled dose-response study of certolizumab pegol in people with active Crohn’s disease. It reports enrollment of 94 and a completed study. The study began on 2006-03-02, and primary completion was recorded as 2007-11-08. It was sponsored by UCB Pharma.

Participants were assigned to placebo, certolizumab pegol 200 mg, or certolizumab pegol 400 mg. All regimens involved subcutaneous injections at Weeks 0, 2 and 4. To maintain masking, the 200 mg group received one active injection and one placebo injection at each listed visit; the 400 mg group received two active injections; and the placebo group received two placebo injections.

The official title calls the study double-blind, while the registry masking field records triple masking. The record does not identify the roles included in that masking designation or explain the difference in wording. It does not report allocation concealment procedures, randomization details, site counts, or protocol-specific monitoring procedures. These design details should not be inferred from the general descriptions.

The primary endpoint was assessed at Week 6 in a Full Analysis Set defined as randomized subjects allocated to study medication, with exclusions determined through data review before unblinding. The registry lists exclusion circumstances involving Good Clinical Practice violations, lack of a definite Crohn’s disease diagnosis, and not receiving a dose of study medication; the final exclusion wording is incomplete. The record does not give arm-level participant flow or a fuller account of the analysis population.

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: Participant Flow refers to the Safety Set, including all randomized subjects who received at least one dose of study medication (Placebo or Certolizumab Pegol).

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set defined as subjects randomized and allocated to study medication, excluding the following subjects determined by data review prior to unblinding: Subjects * with Good Clinical Practice (GCP) violations * who were not diagnosed (definitely) with CD * who received no dose of study medication * with no data after randomization

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.

Population: Baseline Characteristics refer to the Safety Population, including all randomized subjects who received at least one dose of study medication (Placebo or Certolizumab Pegol).

6. Primary Endpoint

The registry lists the primary outcome as Crohn's Disease Activity Index (CDAI) Response (Clinical Response or Remission) at Week 6, measured over Baseline, Week 6.

The primary endpoint is the percentage of subjects who met the registry’s definition of CDAI response or remission at Week 6. CDAI is a disease activity score. The endpoint combines two ways of meeting the specified Week 6 criterion: a clinical response, defined as a decrease of at least 100 points from the Week 0 CDAI score, or remission, defined as a Week 6 CDAI score of <= 150. A subject meeting either condition is counted as having a response or remission for this endpoint.

A binary endpoint expressed as a percentage gives a direct description of how many people in each analysis group met a prespecified clinical criterion. It is different from comparing average CDAI scores: it classifies each subject according to whether the response-or-remission definition was met. The endpoint therefore communicates the frequency of reaching the defined threshold rather than the size of every individual score change.

The record’s rationale for selecting this endpoint is not reported in the registry record. In general, a threshold-based outcome can be useful when the clinical question concerns the proportion of participants meeting a defined response criterion. Its interpretation depends on the precise definition, the analysis population, and the time point. Here the stated time point is Week 6, and the endpoint combines response and remission rather than reporting those components as the primary result separately.

7. Results Posted in the Registry

• Full Analysis Set (CZP 200 mg Treated Subjects): 43.3% (13/30) versus 25.0% (8/32) on control; risk difference 18.3 percentage points (95% CI -4.9 to 41.6), risk ratio 1.73 (0.84–3.58); unadjusted two-proportion z-test p = 0.127.
• Full Analysis Set (CZP 400 mg Treated Subjects): 48.4% (15/31) versus 25.0% (8/32) on control; risk difference 23.4 percentage points (95% CI 0.3 to 46.5), risk ratio 1.94 (0.96–3.90); unadjusted two-proportion z-test p = 0.054.

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.

Crohn's Disease Activity Index (CDAI) Score at Week 2

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Full Analysis Set (CZP 200 mg Treated Subjects): mean 214.20 versus 255.90 on control; difference -41.70 (95% CI -80.90 to -2.50), standardized effect d = -0.55; z-test p = 0.037.
  • Full Analysis Set (CZP 400 mg Treated Subjects): mean 224.90 versus 255.90 on control; difference -31.00 (95% CI -69.85 to 7.85), standardized effect d = -0.40; z-test p = 0.118.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Full Analysis Set (CZP 200 mg Treated Subjects) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Full Analysis Set (CZP 400 mg Treated Subjects) and the control. The interval gives the range of effects that remain compatible with the data.

Crohn's Disease Activity Index (CDAI) Score at Week 4

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Full Analysis Set (CZP 200 mg Treated Subjects): mean 199.70 versus 243.10 on control; difference -43.40 (95% CI -86.18 to -0.62), standardized effect d = -0.54; z-test p = 0.047.
  • Full Analysis Set (CZP 400 mg Treated Subjects): mean 204.60 versus 243.10 on control; difference -38.50 (95% CI -75.48 to -1.52), standardized effect d = -0.53; z-test p = 0.041.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Full Analysis Set (CZP 200 mg Treated Subjects) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Full Analysis Set (CZP 400 mg Treated Subjects) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Crohn's Disease Activity Index (CDAI) Score at Week 6

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Full Analysis Set (CZP 200 mg Treated Subjects): mean 211.00 versus 232.40 on control; difference -21.40 (95% CI -71.54 to 28.74), standardized effect d = -0.23; z-test p = 0.403.
  • Full Analysis Set (CZP 400 mg Treated Subjects): mean 198.10 versus 232.40 on control; difference -34.30 (95% CI -79.93 to 11.33), standardized effect d = -0.39; z-test p = 0.141.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Full Analysis Set (CZP 200 mg Treated Subjects) 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 Full Analysis Set (CZP 400 mg Treated Subjects) and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcome summaries cover mean CDAI scores at Weeks 2, 4 and 6. At each of those time points, the posted mean scores in both certolizumab pegol groups were lower than the placebo mean. The comparisons do not show an equally consistent pattern of inferential evidence across time and dose: some unadjusted comparisons have p-values below 0.05, while others do not. At Week 6, neither dose-group comparison has an unadjusted p-value below 0.05.

This broad pattern offers context for the primary endpoint but does not independently confirm it. CDAI mean scores and the primary response-or-remission percentage summarize different features of the data. A difference in group average score does not directly reveal the proportion of people crossing the primary endpoint threshold, and the threshold-based endpoint does not describe the full distribution of scores. The two types of outcome can therefore give related but non-identical views of disease activity.

The registry also lists secondary outcomes based on CDAI response and score reductions at specified visits. Numerical results for those listed outcomes are not reported in the registry record. The available secondary score summaries should not be used to fill in those missing results or to infer the distribution of individual responses.

Unadjusted secondary results carry less weight when many outcomes, time points, or comparisons are considered. Testing multiple questions increases the chance that some results may appear notable by chance, and the record does not report a multiplicity strategy or identify a hierarchy among secondary outcomes. The secondary findings are therefore best read as descriptive and exploratory context, rather than as a collection of independent confirmatory conclusions.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Crohn's Disease Activity Index (CDAI) Score at Week 2
• Crohn's Disease Activity Index (CDAI) Score at Week 4
• Crohn's Disease Activity Index (CDAI) Score at Week 6
• Percentage of Subjects Who Achieve CDAI Response at Week 2
• Percentage of Subjects Who Achieve CDAI Response at Week 4
• Percentage of Subjects Who Achieve a Reduction in CDAI Scores of at Least 70 Points at Week 2
• Percentage of Subjects Who Achieve a Reduction in CDAI Scores of at Least 70 Points at Week 4
• Percentage of Subjects Who Achieve a Reduction in CDAI Scores of at Least 70 Points at Week 6

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is binary at the participant level: each person either met the registry’s response-or-remission definition at Week 6 or did not. The arm-level percentages describe the proportion meeting that definition. The reported comparison measure is a risk difference, which expresses the difference between the event probabilities in two groups. A risk difference of zero corresponds to equal probabilities; positive or negative values indicate the direction of the contrast according to the order used for the comparison.

A confidence interval describes the precision of an estimate under the statistical procedure used to construct it. It gives a range of values that are reasonably compatible with the observed data and that procedure. It is not a probability statement that the true value lies in that particular interval. Wider intervals indicate less precision than narrower intervals. In this trial, the posted risk-difference intervals are broad relative to their point estimates, so meaningful uncertainty remains about the size and direction of the population contrast.

A p-value describes how unusual the observed data, or more extreme data, would be under a specified null hypothesis and the assumptions of the test. It is not the probability that the null hypothesis is true, and it does not measure the size or clinical importance of an effect. The registry lists unadjusted p-values for the two primary comparisons. The exact test specification and any adjustment for multiple comparisons are not reported in the registry record. Since the p-values are explicitly unadjusted, they should not be treated as accounting for the set of comparisons or outcomes.

The posted summaries also include relative risks and odds ratios for the primary comparisons. These are alternative ways of describing a binary outcome contrast. A relative risk compares the event probabilities between groups, while an odds ratio compares the event odds. They use different scales from a risk difference, and their numerical values should not be read as interchangeable. For interpretation, the group percentages and risk differences make the absolute contrast visible, while relative measures describe the contrast on a ratio scale. These measures do not remove the sampling uncertainty shown by their confidence intervals.

General statistical interpretation also depends on how participants are handled after randomization. The Full Analysis Set is described as randomized subjects allocated to medication, excluding certain subjects identified by review before unblinding. That is the registry’s stated population definition; it should not automatically be equated with a complete intention-to-treat analysis. The record does not report how missing Week 6 outcomes were handled, whether any imputation was used, or how withdrawals and protocol deviations were addressed beyond the exclusions described.

The secondary CDAI score outcomes are continuous measurements, summarized by means and standard deviations at Weeks 2, 4 and 6. A mean difference compares the group averages; its sign depends on the comparison order. The standard deviation describes variation among individual scores within a group, not uncertainty in the mean difference itself. The confidence interval for a mean difference is the relevant posted summary of precision for that comparison. A score difference and a binary response difference answer different questions: average scores retain the magnitude of scores across participants, while the primary endpoint counts whether a threshold was met.

General concepts such as over-dispersion matter when a statistical model assumes a particular amount of variation but the data vary more than that assumption permits; uncertainty can then be understated if the model is not suitable. The registry does not report a model-based primary analysis, a dispersion assessment, or a justification for a particular model. The primary results should therefore be described using the reported summaries rather than assigning an unreported modeling framework.

The record lists 27 outcome measures and 26 posted secondary outcomes, but the analysis count is zero and no reported analyses are listed for the secondary summaries. That does not establish that no analyses were performed; it means that inferential analysis details are not reported in the registry record. The posted comparisons and planning illustrations are statistical summaries, not a substitute for a complete prespecified statistical analysis plan.

11. Confidence Intervals and Precision

For the primary endpoint, the placebo response-or-remission percentage was 25.0%, with a 95% confidence interval from 10.0% to 40.0%. The 200 mg group had a percentage of 43.3%, with an interval from 25.6% to 61.1%; the 400 mg group had a percentage of 48.4%, with an interval from 30.8% to 66.0%. These arm-level intervals show that the percentages are estimated with appreciable uncertainty.

The comparison intervals provide another view of precision. For 200 mg versus placebo, the risk-difference estimate was 0.183 and the interval ran from -0.049 to 0.416. For 400 mg versus placebo, the estimate was 0.234 and the interval ran from 0.003 to 0.465. The first interval includes zero; the second has a lower bound just above zero. Both intervals allow a broad range of possible effect sizes, so the point estimates should not be treated as exact measures of the underlying differences.

Confidence intervals quantify sampling uncertainty under the method used; they do not address every possible source of uncertainty. They do not by themselves account for bias from missing data, population selection, outcome measurement, or choices made among multiple outcomes and comparisons. The registry does not report the complete analysis specification or missing-data procedures, which limits assessment of those issues.

The per-arm sample sizes for the primary endpoint were 32 in placebo, 30 in the 200 mg group, and 31 in the 400 mg group. Smaller groups generally yield less precise estimates, all else being equal. The intervals are therefore important context alongside the observed percentages and the unadjusted p-values. They show why the data are more informative about a range of plausible contrasts than about a single definitive effect size.

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.

The sample-size figures are planning illustrations based on the observed effects, not the original trial’s documented design calculation. For these non-time-to-event outcomes, the figures are participants per arm, not a combined total across arms. The calculation assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect used for planning is a stated fraction of the observed effect. The original trial’s own sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the estimated participants per arm under those assumptions for a design with an 80% chance of detecting the specified effect if that effect were the true one and the calculation assumptions held. The 90% power column gives the corresponding planning figure for a higher target chance of detection. These are design quantities, not evidence that the completed study had a particular probability of producing a statistically significant result.

Rows that plan for 75% or 50% of the observed effect use smaller target effects than the row based on 100% of the observed effect. Smaller effects are harder to distinguish from random variation and therefore require more participants per arm under the stated assumptions. The planning curve should be read as illustrating how the required group size changes as the effect assumed for future planning becomes smaller or larger.

This is not observed power. It is a forward-looking illustration derived from the observed effect, and the observed effect itself may be imprecise. The numbers are useful for understanding how design requirements depend on the effect targeted, but they should not be interpreted as a reconstruction of the trial’s original planning process.

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 z_1−α/2 = 1.960) and the desired power (z_1−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

1. Control proportion p₀ = 0.250; treatment proportion p₁ = 0.433; average p̄ = 0.342.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6707 = 1.3146.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6581 = 0.5538.
4. n = (1.3146 + 0.5538)² / (0.1833)² = 103.9, rounded up to 104 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 <- 0.25                          # control proportion
p1 <- 0.433333333333333                          # 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(291668)
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 = 104 (80% power), 139 (90% power)
 75% of observed effect: n per arm = 180 (80% power), 240 (90% power)
 50% of observed effect: n per arm = 388 (80% power), 519 (90% power)
power.prop.test: 103.9 
Simulated power at n = 104 per arm: 0.805 (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 record lists a primary endpoint and many secondary outcome measures. It records 27 outcome measures, with 26 secondary outcomes posted, but the analysis count is zero and no reported analyses are listed for the secondary summaries. The primary comparisons are accompanied by unadjusted p-values. A prespecified multiplicity procedure, such as an adjustment across dose comparisons or outcome measures, is not reported in the registry record.

Multiplicity matters because the chance of at least one apparently unusual result can increase as more hypotheses are tested. That is a general statistical concern, not evidence that any particular posted result is false. Without the planned testing hierarchy or adjustment method, the p-values should be understood as unadjusted summaries rather than family-wise confirmatory evidence. The record does not state whether the primary comparison was intended to be tested separately by dose or how the dose-response objective was to be evaluated.

The primary endpoint population is a Full Analysis Set of randomized participants allocated to study medication, excluding subjects identified through review before unblinding. The listed exclusion circumstances include Good Clinical Practice violations, absence of a definite Crohn’s disease diagnosis, and not receiving a dose of study medication. The registry wording for the last circumstance is incomplete. The number of people excluded for each reason and a complete participant flow are not reported in the registry record.

Missing-data handling is also not reported in the registry record. It does not specify whether a Week 6 outcome was required for inclusion, how missing outcomes were classified, whether values were imputed, or whether sensitivity analyses were conducted. These omissions matter because the estimated response percentage can depend on how unavailable outcomes are handled. The record’s analysis population and observed endpoint denominators should be kept distinct from a claim that all randomized participants were analyzed under a particular missing-data rule.

15. 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: crohn's disease (9.4%), pyrexia (6.2%), pneumonia aspiration (3.3%), disseminated intravascular coagulation (3.1%), abdominal pain (3.1%).

The serious adverse event summaries report 3 affected subjects among 32 at risk in the placebo group, 1 among 30 at risk in the certolizumab pegol 200 mg group, and 3 among 32 at risk in the 400 mg group. Deaths were recorded as 0 in each group. These are descriptive counts; the registry record does not provide a comparative statistical analysis of serious adverse events.

The listed serious event terms include Crohn’s disease at 9.4%, pyrexia at 6.2%, pneumonia aspiration at 3.3%, disseminated intravascular coagulation at 3.1%, abdominal pain at 3.1%, and gastrointestinal haemorrhage at 3.1%. The record does not provide the group-specific denominators or further context for those listed term percentages in the safety summary.

Small counts can be unstable summaries, and differences in raw counts do not establish that one group has a higher or lower underlying risk. The record does not report event timing, severity grading, relatedness assessments, or a detailed method for classifying events. Safety findings should therefore be read as the registry’s reported descriptive information, not as a complete comparative safety assessment.

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

The posted results show that the Week 6 CDAI response-or-remission percentage was higher in each certolizumab pegol group than in placebo in this trial’s Full Analysis Set. The risk-difference estimates are positive for both comparisons. The confidence intervals and unadjusted p-values convey substantial uncertainty about the comparisons, and the registry record does not provide a direct test comparing the two active doses.

These findings do not establish a precise size of benefit in a broader population, a durable response beyond the reported time point, or a dose-response relationship. They also do not separate the clinical response component from the remission component of the primary endpoint. The record does not report later primary endpoint results, and the listed secondary categorical outcomes do not have numerical results in the registry record.

A result from a randomized trial is interpreted in light of the way participants were selected, assigned, followed, and analyzed. The registry describes random allocation and a Full Analysis Set, but does not give complete details on missing outcomes, the analysis plan, multiplicity, or participant flow. Those gaps limit how fully the statistical evidence can be evaluated from the posted record alone.

The result does not mean that every participant in a group experienced the group average outcome, nor does it predict an individual person’s response. Group percentages summarize observed proportions under a defined endpoint. Confidence intervals describe statistical precision under an analysis procedure; they do not resolve uncertainty about external applicability or unreported methods.

Nothing in these summaries is medical advice. The statistical reading is limited to what the registry reports: observed endpoint proportions, comparison estimates, uncertainty intervals, and unadjusted p-values in a relatively small Phase II study. Judgments about clinical importance, treatment choices, or evidence from other studies require information beyond this record.

17. Why This Trial Matters Statistically

This trial illustrates why an observed difference and its precision should be read together. The point estimates for the primary endpoint are higher in both active-dose groups than in placebo, while the comparison intervals remain broad. Reporting the estimates alone could suggest more certainty than the data support; reporting only p-values would hide the range of plausible contrasts and the scale of the observed differences.

It also shows that different summaries answer different questions. The primary endpoint counts participants who meet a response-or-remission threshold. The secondary CDAI score outcomes compare average scores. Those approaches can complement one another, but they are not substitutes. An average shift does not identify how many people met a threshold, and a threshold response rate does not describe the distribution of scores.

The registry’s unadjusted comparisons and numerous outcome measures make multiplicity an important interpretive issue. Without a reported testing hierarchy or adjustment plan, isolated secondary findings deserve restraint. The record’s incomplete account of missing data and analysis populations further demonstrates why statistical interpretation depends on methods as well as numerical results.

Finally, the planning illustrations show how future sample-size requirements depend on the effect a study aims to detect. Their assumptions are explicit, but they are not a record of the original trial design calculation and are not observed power. Keeping these planning calculations separate from the trial’s results prevents a common misreading of retrospective power summaries.

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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

The primary analysis population is described but not fully documented. The Full Analysis Set excludes certain participants identified before unblinding, yet the record gives no counts for those exclusions and its description of one exclusion criterion is truncated. Complete participant flow, including the numbers randomized and analyzed by arm, is not reported in the registry record.

Methods for missing Week 6 outcomes are not reported in the registry record. The endpoint group sizes are not identical across arms, and the record does not explain the reasons for unavailable observations or how these were handled. This makes it difficult to assess whether the posted percentages might be sensitive to missing-data assumptions.

The registry does not provide a complete statistical analysis plan, the primary test specification, a multiplicity adjustment strategy, or the rationale for the sample size. The record identifies the study as a dose-response trial but does not report a direct statistical comparison of the two certolizumab pegol doses. It also does not explain the different masking descriptions in the official title and masking field.

The primary outcome combines response and remission, and separate numerical results for those components are not reported in the registry record. The registry lists additional secondary categorical outcomes, but their numerical results are not posted. The available secondary summaries cover CDAI means at selected visits and do not provide a complete account of the outcome measures listed.

These limitations do not negate the posted summaries, but they narrow the conclusions that can be drawn from them. The study is Phase II, and its primary endpoint groups are modest in size. Its estimates are consequently best viewed with their confidence intervals and the registry’s reporting gaps in mind.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Clinical Study of CDP870/Certolizumab Pegol in Patients With Active Crohn's Disease — NCT00291668.
• Registry record last updated 2020-08-03; status last verified 2020-07.
• Results first posted 2020-08-03.
• 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.

22. Record Summary

The registry describes a completed randomized Phase II, parallel-group, placebo-controlled study of certolizumab pegol in active Crohn’s disease, with enrollment of 94. Participants received placebo, 200 mg, or 400 mg by subcutaneous injection at Weeks 0, 2 and 4. The primary endpoint was the Week 6 percentage meeting the CDAI response-or-remission definition.

Posted primary percentages were 25.0% for placebo, 43.3% for 200 mg, and 48.4% for 400 mg. Risk-difference estimates versus placebo were 0.183 and 0.234, with broad reported confidence intervals; unadjusted p-values were 0.127 and 0.054. Secondary score summaries and descriptive safety counts are also reported, while important details about multiplicity, missing data, and the full analysis plan are not reported in the registry record.