A One-Year Study To Evaluate The Efficacy And Safety Of CP-690,550 For Patients With Moderate To Severe Chronic Plaque Psoriasis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A One-Year Study To Evaluate The Efficacy And Safety Of CP-690,550 For Patients With Moderate To Severe Chronic Plaque Psoriasis (NCT01309737), a randomized phase 3 study. The primary outcome is Percentage of Participants With Physician Global Assessment (PGA) of Psoriasis Score of 'Clear' or 'Almost Clear' at Week 16.

2. Clinical Question

This question focuses on a clinician-rated assessment of psoriasis signs across the body, rather than on one lesion or a single symptom. The score combines ratings of erythema, induration, and scaling. A response means that the resulting global score falls into either of the two least severe categories: clear or almost clear.

The registry record describes a one-year comparison of CP-690,550 and placebo, including evaluation of safety and tolerability. The primary response endpoint is at Week 16, so it addresses the recorded groups at that assessment time rather than providing a summary of the full year. Other outcomes cover body surface area, a psoriasis area and severity index response, and quality of life, among other measures.

3. Trial Design

The registry record identifies this as a randomized, parallel-group Phase 3 study of CP-690,550 in moderate to severe chronic plaque psoriasis. It lists an enrollment of 960 and a completed status. The study title describes a multi-site, double-blind, placebo-controlled design. The registry masking classification is quadruple. These descriptions indicate that the record reports both the design stated in the title and a separate masking classification.

The primary results are reported for three groups: CP-690,550 5 mg, CP-690,550 10 mg, and placebo. The registry lists the active doses as twice-daily regimens in its arm descriptions. Intervention entries also include placebo/CP-690,550 groups. The adverse-event record distinguishes participants who began with placebo and then received CP-690,550 from those in the continuous dose groups; those groups should not be conflated with the three primary endpoint groups.

The study is described as lasting one year. The primary outcome was assessed at Week 16, and the record includes secondary outcomes at other time points, including Week 4, Week 16, and Week 52. The listed start was 2011-03, and primary completion was 2013-04.

The record does not report the original sample-size justification, the planned allocation ratio, the detailed protocol for treatment transitions, or the full statistical analysis plan. The total enrollment and the numbers in the primary endpoint groups do not by themselves establish which participants contributed to every outcome or analysis. For the primary endpoint, the stated analysis population was the full analysis set, with participants from 1 site excluded because of good clinical practices compliance issues.

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: Outcome measures reporting results up to Week 16 consist of single placebo arm as reporting group while outcome measures reporting results up to Week 52 consist of 2 separate arms (for participants re-randomized at Week 16 to receive CP-690,550 5 milligram \[mg\] or 10 mg).

Week 0 to 16

Reasons for not completing this period:

Week 16 to 52

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full analysis set (FAS): participants who were randomized to study and received at least 1 dose investigational drug (CP-690,550 or placebo). Participants from 1 site were excluded due to good clinical practices(GCP) compliance issues. Non-Responder Imputation (NRI) method (participants with missing values considered as non-responders) was used.

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: Safety analysis set consisted of all participants who received at least 1 dose of the investigational drug (CP-690,550 or placebo).

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants With Physician Global Assessment (PGA) of Psoriasis Score of 'Clear' or 'Almost Clear' at Week 16, measured over Week 16.

The primary endpoint is the percentage of participants whose physician global assessment of psoriasis was clear or almost clear at Week 16. The assessment uses a five-point severity scale based on erythema, induration, and scaling across psoriatic lesions over the body. Each feature receives a severity rating, and their average is rounded to a whole-number score. The categories range from 0, clear, to 4, severe. A response is a score of 0 or 1.

This measure compresses several clinician observations into one global category. That makes it possible to report the proportion of participants who meet a defined response threshold in each study group. It is a binary endpoint: each participant is counted as either meeting or not meeting the response definition for the analysis.

A threshold-based endpoint is useful for communicating how many participants reached a specified clinical state, but it does not describe every detail of the score distribution. Participants with different scores outside the response categories are grouped together as nonresponders for this outcome. The endpoint also does not, by itself, report participants’ experience of symptoms or quality of life. Those topics appear among the secondary outcomes in the registry record.

The primary endpoint’s stated timeframe is Week 16. It therefore describes the recorded assessment at that time, not maintenance of response throughout the one-year study. A separate secondary outcome addresses the probability of maintaining a clear or almost clear assessment at Week 52.

7. Results Posted in the Registry

• CP-690,550 5mg: 46.0% (173/376) versus 10.9% (21/193) on control; risk difference 35.1 percentage points (95% CI 28.4 to 41.8), risk ratio 4.23 (2.78–6.43); unadjusted two-proportion z-test p = <0.001.
• CP-690,550 10 mg: 59.1% (221/374) versus 10.9% (21/193) on control; risk difference 48.2 percentage points (95% CI 41.6 to 54.9), risk ratio 5.43 (3.60–8.20); unadjusted two-proportion z-test p = <0.001.

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.

Percent Change From Baseline in Total Body Surface Area (BSA) With Psoriasis at Week 16

• 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 errors.
• Result:
  • CP-690,550 5mg: mean -54.86 versus -9.12 on control; difference -45.74 (95% CI -52.97 to -38.51), standardized effect d = -1.11; z-test p = <0.001.
  • CP-690,550 10 mg: mean -67.22 versus -9.12 on control; difference -58.10 (95% CI -65.32 to -50.88), standardized effect d = -1.42; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for CP-690,550 5mg 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 CP-690,550 10 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants With a Psoriasis Area and Severity Index 90 (PASI 90) Response at Week 16

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • CP-690,550 5mg: 24.5% (92/376) versus 5.2% (10/193) on control; risk difference 19.3 percentage points (95% CI 13.9 to 24.6), risk ratio 4.72 (2.52–8.86); unadjusted two-proportion z-test p = <0.001.
  • CP-690,550 10 mg: 38.8% (145/374) versus 5.2% (10/193) on control; risk difference 33.6 percentage points (95% CI 27.7 to 39.4), risk ratio 7.48 (4.04–13.87); unadjusted two-proportion z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for CP-690,550 5mg 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 proportion with the event is statistically higher for CP-690,550 10 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Dermatology Life Quality Index (DLQI) Total Score

• 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:
  • CP-690,550 5mg: mean 13.22 versus 13.19 on control; difference 0.03 (95% CI -1.24 to 1.30), standardized effect d = 0.00; z-test p = 0.963.
  • CP-690,550 10 mg: mean 12.69 versus 13.19 on control; difference -0.50 (95% CI -1.77 to 0.77), standardized effect d = -0.07; z-test p = 0.440.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between CP-690,550 5mg 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-690,550 10 mg and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes broaden the scope beyond the primary clinician-rated response. They include body surface area affected by psoriasis, PASI response thresholds, quality-of-life measures, and other clinical assessments across follow-up. The posted results for body surface area at Week 16 show negative mean percent changes from baseline in all three groups, with larger decreases in the two CP-690,550 groups than in the placebo group. The Week 16 PASI 90 response percentages are also higher in both CP-690,550 groups than in the placebo group. These outcomes are directionally consistent with the primary endpoint’s group pattern, but they measure different aspects of psoriasis.

The DLQI values listed in the secondary results are baseline scores. Baseline comparisons describe the groups before the Week 16 outcome assessment and should not be interpreted as changes in quality of life over follow-up. The registry lists additional secondary outcomes, but the breadth of listed outcomes does not mean that every result answers the same question or carries the same evidential weight as the primary endpoint.

Secondary analyses are usually treated as supportive or exploratory unless a trial’s statistical plan specifies otherwise. Testing many outcomes creates more opportunities for results to appear statistically notable by chance. Whether multiplicity adjustments were planned or used is not reported in the registry record. Unadjusted secondary p-values therefore warrant more caution than a prespecified primary comparison, and individual secondary findings should be interpreted alongside their endpoint definitions, time points, and analysis methods.

The overall secondary pattern can help show whether findings extend across distinct measurements, but it does not establish a single comprehensive outcome. The registry record does not report a complete multiplicity strategy or enough detail to determine the confirmatory status of each secondary analysis.

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

• Percent Change From Baseline in Total Body Surface Area (BSA) With Psoriasis at Week 16
• Percentage of Participants With a Psoriasis Area and Severity Index 90 (PASI 90) Response at Week 16
• Dermatology Life Quality Index (DLQI) Total Score
• Change From Baseline in Dermatology Life Quality Index (DLQI) Total Score at Week 4 and 16
• Percentage of Participants With Physician Global Assessment (PGA) of Psoriasis Score of 'Clear' or 'Almost Clear' at Week 4
• Percentage of Participants With Psoriasis Area and Severity Index 75 (PASI 75) Response at Week 4
• Percent Change From Baseline in Nail Psoriasis Severity Index (NAPSI) at Week 16
• Percent Probability of Participants Maintaining Physician Global Assessment (PGA) of Psoriasis Score of 'Clear' or 'Almost Clear' at Week 52

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is binary because participants either met the clear or almost clear response definition at Week 16 or did not. A percentage reports the share meeting that definition in each group. A risk difference expresses the absolute contrast between two such percentages, on a probability scale. For example, the recalculated risk differences compare the recorded response proportions in each CP-690,550 group with the placebo proportion.

What does the confidence interval describe?

A confidence interval gives a range of values compatible with the data and the method used to estimate the contrast. Its width reflects statistical precision: a narrower interval indicates less uncertainty about the estimated contrast than a wider interval, under the assumptions of that method. The interval does not guarantee that the true value lies within its limits, nor does it account for every possible source of uncertainty, such as design or measurement limitations.

The recalculated intervals are unadjusted intervals based on posted summary statistics. The registry’s reported analyses use other methods and report odds ratios for the primary endpoint. An odds ratio compares the odds of meeting the response definition between groups; it is not an absolute percentage-point difference. When an outcome is common, an odds ratio can appear numerically more extreme than a risk ratio or risk difference. Interpretation should therefore keep the measure’s scale in view.

Why do the reported and recalculated estimates differ in form?

The recalculation uses the arm-level response percentages and counts to form an unadjusted risk difference. The sponsor’s reported primary analyses use the Cochran-Mantel-Haenszel method and report odds ratios. Since the measures and methods differ, their numerical estimates need not match. The registry does not report enough detail to specify every adjustment or implementation choice underlying the sponsor analyses. No discrepancy is flagged in the registry record; the sponsor’s analysis is the reported trial analysis, while the unadjusted recalculation provides a separate descriptive contrast.

For continuous secondary outcomes, a mean difference compares group averages, while a least-squares mean difference comes from a model-based analysis. The body surface area outcome is reported as a least-squares mean percent change from baseline, with standard errors. The sponsor’s analyses use mixed models and report least-squares mean differences. These are not the same quantity as an individual participant’s change, and a group mean does not reveal the distribution of individual responses.

Why can over-dispersion matter?

General statistical explanation: a model for count or binary data may assume a particular relationship between the expected value and the variability. Over-dispersion means the data vary more than that model expects. If ignored, uncertainty estimates may be too small and tests may be too optimistic. The primary endpoint is binary, but the registry record does not report an over-dispersion assessment or a model choice motivated by over-dispersion. No claim about such an assessment can be made from the record.

The p-values address how compatible the observed data are with a specified null comparison under the analysis method. A small p-value is not the probability that the null hypothesis is true, and it does not measure the size or importance of the contrast. The reported confidence intervals and response percentages add information about magnitude and precision. Multiple secondary outcomes also create a multiplicity concern: testing many outcomes can increase the chance of at least one apparently unusual result if no adjustment is made.

The primary analysis description identifies the full analysis set as randomized participants who received at least 1 dose of study drug, and mentions non-responder imputation for missing participants. The registry wording is incomplete after its description of participants with missing data. The full missing-data procedure, sensitivity analyses, and other analysis details are not reported in the registry record. Such details matter because assumptions about missing outcomes can affect estimates and uncertainty.

All statistical methods require interpretation in light of the study design, endpoint definition, analysis population, and follow-up time. The registry reports a randomized comparison, but the posted summary statistics cannot answer every question about protocol adherence, missingness, or the robustness of the analysis. The original statistical plan is not reported in the registry record.

11. Confidence Intervals and Precision

The recalculated 5 mg versus placebo risk difference is 0.351, with a 95% confidence interval from 0.284 to 0.418. The recalculated 10 mg versus placebo risk difference is 0.482, with a 95% confidence interval from 0.416 to 0.548. Both intervals are on the absolute risk-difference scale. They describe estimated contrasts in the proportion meeting the Week 16 response definition, not the spread of individual participant outcomes.

The sponsor’s estimates are odds ratios rather than risk differences. For 5 mg versus placebo, the reported odds ratio is 10.20, with a 95% confidence interval from 5.33 to 17.68. For 10 mg versus placebo, it is 20.43, with a 95% confidence interval from 8.99 to 30.59. Because the endpoints of those intervals are on the odds-ratio scale, they should not be interpreted as percentage-point changes.

A confidence interval conveys precision as well as the estimated direction and magnitude of an association. It is not a guarantee about the true value, and it does not include uncertainty from every possible source. In particular, it cannot resolve questions about how missing data were handled, whether the analysis choices were prespecified, or whether secondary outcome testing was adjusted for multiplicity.

The primary endpoint confidence intervals are relatively informative about the observed group contrasts, but interpretation remains specific to the full analysis set described in the record and the Week 16 outcome. The registry does not report the complete analysis plan or detailed missing-data sensitivity analyses. Those omissions limit assessment of how robust the reported precision is to alternative assumptions.

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 illustrations use the observed effect as a reference and show planning scenarios for detecting the full observed effect, 75% of the observed effect, or 50% of the observed effect. The values for these non-time-to-event outcomes are participants per arm, not total participants across arms. The record’s assumption note specifies a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The original trial’s own design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives the illustrative number of participants per arm for a design with an 80% chance of detecting the stated effect under those assumptions, if that effect and the model assumptions were correct. The 90% power column uses a higher target chance of detecting the effect, and therefore generally requires more participants per arm. These are design calculations, not descriptions of the chance that the completed study detected an effect.

The rows planning for a smaller fraction of the observed effect require more participants than rows planning for a larger effect. This is a general feature of statistical planning: smaller differences are harder to distinguish from random variation, so more information is needed. The figures are illustrative and depend on the assumptions stated in the registry record. They should not be treated as the trial’s original enrollment target or as a reconstruction of its protocol. This is not observed power.

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 = 0.109; treatment proportion p₁ = 0.460; average p̄ = 0.284.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6380 = 1.2505.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.5877 = 0.4946.
4. n = (1.2505 + 0.4946)² / (0.3513)² = 24.7, rounded up to 25 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 <- 0.10880829015544                          # control proportion
p1 <- 0.460106382978723                          # 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(1309737)
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 = 25 (80% power), 33 (90% power)
 75% of observed effect: n per arm = 41 (80% power), 54 (90% power)
 50% of observed effect: n per arm = 80 (80% power), 106 (90% power)
power.prop.test: 24.7 
Simulated power at n = 25 per arm: 0.836 (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. Analyses Reported by the Sponsor

The registry reports sponsor analyses for the primary endpoint using the Cochran-Mantel-Haenszel method. The reported odds ratio for CP-690,550 5 mg versus placebo is 10.20, with a 95% confidence interval from 5.33 to 17.68 and p < 0.001. For CP-690,550 10 mg versus placebo, the odds ratio is 20.43, with a 95% confidence interval from 8.99 to 30.59 and p < 0.001. The sponsor also reports a normal-approximation comparison between active dose groups: a 13.08 percent difference, with a 95% confidence interval from 5.99 to 20.17 and p < 0.001.

The unadjusted recalculations use the posted group counts and percentages to estimate risk differences. They are useful as a straightforward absolute-scale description, but they do not replace the sponsor’s trial analyses. The odds ratios and risk differences use different scales, and the registry record does not fully describe all details of the sponsor’s statistical implementation.

No discrepancy is flagged between the posted summary and sponsor analyses. The sponsor’s reported results are therefore the primary reported analyses to consult for the trial’s inferential results; the recalculations are simple, unadjusted comparisons that offer another way to describe the group contrast.

15. Multiplicity, Missing Data and Analysis Populations

The primary analysis population is described as the full analysis set: participants randomized to the study who received at least 1 dose of CP-690,550 or placebo. The record says participants from 1 site were excluded because of good clinical practices compliance issues. The primary outcome description also refers to non-responder imputation for participants with missing data, but the description is truncated after beginning to characterize those participants. The complete imputation rule is not reported in the registry record.

Missing outcome data matter because participants without an observed Week 16 assessment may differ from those with recorded assessments. Non-responder imputation generally treats missing binary outcomes as failures to meet the response definition; that is a general description, not confirmation of the complete implementation in this study. The registry’s incomplete wording does not establish whether all missing outcomes were handled in this way, whether there were exceptions, or which sensitivity analyses were used. Those details are not reported in the registry record.

The record lists numerous outcomes and reports secondary analyses. When several hypotheses are tested, the chance of at least one result appearing statistically notable can increase. Statistical approaches to this multiplicity can include prespecified hierarchies or adjustments to significance thresholds. The multiplicity strategy for this trial is not reported in the registry record, so the degree to which secondary results were adjusted cannot be assessed from the posted information.

The record also does not report the full statistical analysis plan, interim analyses, or the original sample-size justification. Those omissions limit assessment of which analyses were prespecified, how deviations were managed, and how the primary and secondary hypotheses were prioritized. The posted results should therefore be read in their reported scope, without assuming unreported protocol decisions.

16. Safety Results

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

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 2% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: palpitations (2.3%), road traffic accident (2.3%), pneumonia cryptococcal (1.3%), sepsis (1.3%), breast cancer (1.3%).

The serious adverse-event counts are reported separately for the CP-690,550 5 mg group, CP-690,550 10 mg group, placebo followed by CP-690,550 5 mg, placebo followed by CP-690,550 10 mg, and placebo group. The record lists 18 serious adverse events among 382 at risk in the 5 mg group, 19 among 381 in the 10 mg group, 4 among 75 in the placebo-then-5 mg group, 6 among 77 in the placebo-then-10 mg group, and 2 among 44 in the placebo group.

These are counts of participants affected as recorded for the serious adverse-event measure, not a complete accounting of all safety outcomes or event severity. The placebo-then-treatment groups have different group sizes and treatment histories from the primary endpoint groups; their counts should not be read as direct comparisons with continuous treatment arms without considering those differences. The registry also lists several serious-event terms and percentages, including palpitations and road traffic accident at 2.3% each, and pneumonia cryptococcal, sepsis, breast cancer, and mycosis fungoides at 1.3% each.

Deaths are not reported in the registry record. These safety figures alone do not establish comparative risk, causality, or the overall balance of benefits and harms. The complete safety profile and exposure context are not captured by the serious-event counts alone.

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

The primary results describe a greater Week 16 percentage meeting the clear or almost clear physician global assessment response definition in each CP-690,550 group than in the placebo group. The recalculated risk differences and sponsor-reported odds ratios quantify that group-level contrast in different ways. The reported confidence intervals and p-values describe statistical uncertainty under their respective methods, not certainty about individual outcomes.

The endpoint is limited to one assessment at Week 16 and to a threshold based on a clinician’s global rating. It does not report the full distribution of severity scores, participants’ individual experiences, or persistence of the response over the full one-year study. Other outcomes address related but distinct concepts, including body surface area, PASI response, and quality of life. Their results require separate interpretation.

The registry record reports randomized groups and a defined primary analysis population, but it does not report the full statistical analysis plan, original sample-size justification, or complete missing-data procedures. It also does not report a multiplicity strategy for the secondary outcomes. Those limitations affect how fully the analyses can be evaluated and how much weight to place on findings beyond the primary endpoint.

The statistical results do not by themselves determine what any individual should do. They describe the posted outcomes for the study groups, at the recorded time points, under the analyses reported. They do not answer every question about longer-term outcomes, safety, applicability to people outside the study, or comparative clinical importance.

18. Why This Trial Matters Statistically

This trial illustrates why endpoint definitions and effect scales matter in clinical research. The primary outcome is a binary response threshold, while its unadjusted recalculation is expressed as a risk difference and the sponsor’s analysis as an odds ratio. Both describe the group comparison, but the measures have different interpretations. Reporting the scale alongside the estimate and interval helps prevent a relative contrast from being mistaken for an absolute change.

The record also shows the distinction between statistical significance and precision. The reported p-values address compatibility with a null comparison under a statistical method; the confidence intervals describe a range of estimated contrasts. Neither alone communicates every aspect of clinical importance, and neither resolves uncertainty about missing-data assumptions or the completeness of the analysis plan.

There are multiple outcome domains and assessment times. The primary endpoint anchors the main inferential question, while secondary outcomes broaden the clinical description. Without a reported multiplicity plan, secondary results should be interpreted with care. A consistent direction across distinct measures can add context, but it does not remove the need to consider which outcomes were prespecified and how they were analyzed.

Finally, the registry includes both a one-year study description and a primary outcome at Week 16. Keeping those timeframes distinct is important: an assessment at Week 16 cannot stand in for a full account of outcomes across the entire study. Together, these features make the record useful for understanding how trial design, endpoint choice, statistical methods, and reporting limitations shape interpretation.

19. 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 endpoint is a clinician-rated binary threshold at Week 16. It provides a clear response definition, but it does not convey the full range of scores or participants’ experience. The posted comparison is also specific to the full analysis set described in the record, rather than necessarily to every enrolled participant.

Participants from 1 site were excluded because of good clinical practices compliance issues. The record does not provide further details on the site issue, the number of participants affected, or how the exclusion changed the analysis population. The primary population description also mentions non-responder imputation but is incomplete, so the exact missing-data implementation and any sensitivity analyses are not reported in the registry record.

The registry record does not report the original sample-size justification, full statistical analysis plan, interim analyses, or multiplicity approach. It is therefore not possible to establish from the record which secondary comparisons were confirmatory or how the analyses were prioritized. Some secondary outcome information concerns baseline measurements, which are descriptive starting values rather than follow-up treatment contrasts.

The safety summary includes serious adverse-event counts and selected event terms, but does not provide a complete characterization of all harms, exposure-adjusted rates, or deaths. The study includes treatment-transition groups in the adverse-event listing, which have different treatment histories from the three main primary endpoint groups. These features limit simple across-group comparisons of safety counts.

Finally, the primary outcome is reported at Week 16 within a study described as lasting one year. The primary result alone cannot characterize maintenance through Week 52 or all outcomes over the full study duration.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A One-Year Study To Evaluate The Efficacy And Safety Of CP-690,550 For Patients With Moderate To Severe Chronic Plaque Psoriasis — NCT01309737.
• Registry record last updated 2014-09-19; status last verified 2014-09.
• Results first posted 2014-09-19.
• 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.

23. Record Summary

The registry record describes a completed, randomized, parallel-group Phase 3 study of CP-690,550 in moderate to severe chronic plaque psoriasis, with listed enrollment of 960. The primary endpoint was the percentage of participants rated clear or almost clear by physician global assessment at Week 16.

Reported response percentages were 46.01% for CP-690,550 5 mg, 59.09% for CP-690,550 10 mg, and 10.88% for placebo. Sponsor analyses report odds ratios for each active dose versus placebo, while unadjusted recalculations express the contrasts as risk differences. Secondary outcomes cover additional psoriasis measures and quality of life; the safety record lists serious adverse-event counts across treatment groups.

The record does not report the full analysis plan, original sample-size justification, complete missing-data procedures, or multiplicity strategy. The results should be interpreted in relation to the specified population, endpoint, time point, and reported methods.