A Study of Intravenous Mircera for the Correction of Anemia in Dialysis Patients.: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of Intravenous Mircera for the Correction of Anemia in Dialysis Patients. (NCT00546481), a randomized phase 3 study. The primary outcome is Percentage of Participants Who Achieved Hemoglobin Response up to Week 24.

2. Clinical Question

The clinical question is about correction of anemia during the study period, not about every aspect of longer-term treatment or safety. A response required an increase in hemoglobin of at least 1 g/dL compared with baseline, a hemoglobin value of at least 11 g/dL, and no red blood cell transfusion during the 24-week correction phase. The registry record reports each arm’s response percentage and 95% confidence interval, as well as a recalculated unadjusted comparison.

This definition combines a change from baseline with an absolute hemoglobin threshold and a transfusion condition. A participant had to meet the hemoglobin criteria while also remaining free of transfusion during the specified phase to count as a responder. The trial was open-label, so participants and study personnel were not masked to assigned treatment. The registry record does not report whether any outcome assessment used additional procedures to limit the influence of that knowledge.

The question is therefore narrowly framed: how often was the prespecified response recorded in each correction-phase arm, and what uncertainty surrounds the estimated difference? It should not be read as a general comparison of all outcomes, nor as a conclusion about treatment effects beyond the populations and time periods represented in the posted results.

3. Trial Design

This was a Phase 3, randomized, open-label, multicenter, parallel-group study sponsored by Hoffmann-La Roche. It is identified as NCT00546481 and is listed as completed. The record gives an enrollment of 80. The start is recorded as 2007-11, and primary completion as 2009-12. The brief summary describes a two-arm study in dialysis patients with chronic kidney disease and anemia, comparing intravenous Mircera with intravenous epoetin.

Participants in the correction phase were assigned to CERA or epoetin beta. The brief summary specifies Mircera 0.6 micrograms/kg intravenously every 2 weeks and epoetin intravenously 3 times per week according to approved treatment recommendations. The anticipated time on study treatment is described as 3-12 months. The posted primary outcome concerns response up to Week 24; other listed outcomes include selected measures through Week 24 or Week 49.

Randomization helps make groups comparable on average at assignment, but it does not ensure that every characteristic is balanced in a study of this size. Open-label treatment means allocation was not masked. The record calls the study multicenter but does not report the number or names of participating centers in the information. It also does not report details of the randomization sequence or allocation concealment.

The primary outcome population is the Intent-to-Treat population, which the registry record defines as all randomized participants. The primary arm results list 39.0 participants for Correction Phase: CERA and 41.0 for Correction Phase: Epoetin Beta. The registry record does not report the original sample-size justification or the assumptions used to choose enrollment for the trial. Planning illustrations based on the observed results are separate from that original design rationale.

A Maintenance Phase: CERA group also appears among posted secondary results and adverse-event summaries. The registry record does not describe its allocation or relationship to the correction-phase groups in sufficient detail to treat it as a randomized correction-phase comparator. The randomized primary comparison is between the two correction-phase arms.

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.

Correction Phase (CERA or Epoetin Beta)

Reasons for not completing this period:

Maintenance Phase (CERA)

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The Intent-to-Treat population included all randomized participants.

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: The Intent-to-Treat (ITT) population included all randomized participants.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants Who Achieved Hemoglobin Response up to Week 24, measured over Up to Week 24.

The primary endpoint is the percentage of participants who achieved hemoglobin response up to Week 24. The registry definition requires an increase in hemoglobin of at least 1 g/dL compared with baseline, a hemoglobin concentration of at least 11 g/dL, and no red blood cell transfusion during the 24-week correction phase. The average baseline value was estimated from values recorded between the day of the first study dose and the previous 20 days.

This binary endpoint turns several clinical conditions into a responder or non-responder classification. It captures whether participants met the specified laboratory response while avoiding transfusion during the defined period. A percentage is useful for describing the share of the analysis population meeting that combined criterion in each arm. It does not convey the full pattern of individual hemoglobin measurements, the timing of response, or the size of each participant’s change.

The registry reports response percentages of 79.5 for Correction Phase: CERA and 87.8 for Correction Phase: Epoetin Beta, each with a 95% confidence interval. The comparison is summarized by an estimated risk difference and its confidence interval. The endpoint is clinically interpretable as a prespecified response status, but its interpretation depends on the exact definition, the time window, and how missing measurements or transfusion information were handled. Those missing-data procedures are not reported in the registry record.

The endpoint should be read as a trial outcome, not as a complete account of anemia control or a measure of every possible benefit and harm. Other posted outcomes address hemoglobin change, transfusions, selected safety measures, and adverse events.

7. Results Posted in the Registry

• Correction Phase: Epoetin Beta: 87.8% (36/41) versus 79.5% (31/39) on control; risk difference 8.3 percentage points (95% CI -7.8 to 24.5), risk ratio 1.10 (0.91–1.34); unadjusted two-proportion z-test p = 0.313.

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.

Mean Change From Baseline in Hemoglobin Concentration at Week 24

• 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:
  • Correction Phase: Epoetin Beta: mean 2.03 versus 2.00 on control; difference 0.03 (95% CI -0.60 to 0.66), standardized effect d = 0.02; z-test p = 0.926.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Correction Phase: Epoetin Beta and the control. The interval gives the range of effects that remain compatible with the data.

Number of Participants Who Received Red Blood Cells Transfusions up to Week 49

• 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:
  • Correction Phase: Epoetin Beta: 4.9% (2/41) versus 20.5% (8/39) on control; risk difference -15.6 percentage points (95% CI -29.9 to -1.3), risk ratio 0.24 (0.05–1.05); unadjusted two-proportion z-test p = 0.035.
  • Maintenance Phase: CERA: 1.9% (1/54) versus 20.5% (8/39) on control; risk difference -18.7 percentage points (95% CI -31.8 to -5.5), risk ratio 0.09 (0.01–0.69); unadjusted two-proportion z-test p = 0.003.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically lower for Correction Phase: Epoetin Beta 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 lower for Maintenance Phase: CERA than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Number of Participants With Abnormal Changes in Electrocardiogram up to Week 24

• 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:
  • Correction Phase: Epoetin Beta: 9.4% (3/32) versus 8.3% (3/36) on control; risk difference 1.0 percentage points (95% CI -12.5 to 14.6), risk ratio 1.12 (0.24–5.18); unadjusted two-proportion z-test p = 0.880.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Correction Phase: Epoetin Beta and the control. The interval gives the range of effects that remain compatible with the data.

The posted secondary outcomes add several perspectives on the primary question but do not form a consistent, complete set of confirmatory evidence. Hemoglobin change and the primary responder definition address related aspects of anemia correction: one describes average change, while the other classifies whether a combined threshold and transfusion condition was met. The transfusion outcome broadens the observation period beyond the primary response window. Electrocardiogram changes and the listed vital-sign outcomes address other aspects of monitoring, rather than directly measuring the primary hemoglobin response.

The posted pattern is mixed. The hemoglobin-change and electrocardiogram comparisons do not provide a precise distinction between the correction-phase groups. The transfusion comparison has a more notable unadjusted result, but it is secondary and should not override the primary result. The Maintenance Phase: CERA entries are a separate labeled group; the registry record does not give enough information about its relationship to the correction-phase groups to interpret it as a comparable randomized arm.

The registry lists additional outcomes, including time maintaining hemoglobin within a target range, blood pressure, heart rate, and adverse events. Results for every listed secondary outcome are not reported in the registry record. Absence of a posted result should not be treated as evidence that no difference or event occurred.

Multiple outcomes create multiple opportunities for apparently notable findings, especially when each comparison is interpreted without adjustment. The registry record does not report a multiplicity strategy or identify which secondary analyses were intended as confirmatory. Consequently, unadjusted secondary results carry less weight than a prespecified primary result, and their p-values should be viewed as exploratory evidence rather than as standalone proof. The overall secondary pattern can generate questions for further study, but it does not establish a broad conclusion about comparative efficacy or safety.

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

• Mean Change From Baseline in Hemoglobin Concentration at Week 24
• Median Time in Which Hemoglobin Value Was Maintained Within Target Range of >/= 11g/dL up to Week 24
• Number of Participants Who Received Red Blood Cells Transfusions up to Week 49
• Number of Participants With Any Adverse Events and Serious Adverse Events
• Mean Change From Baseline in Vital Signs: Systolic Blood Pressure and Diastolic Blood Pressure up to Week 24
• Mean Change From Baseline in Vital Sign: Heart Rate Measurements up to Week 24
• Number of Participants With Abnormal Changes in Electrocardiogram up to Week 24

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is binary: each participant either met the response definition or did not. For a binary endpoint, the arm-specific percentage describes the observed fraction with the event. The comparison uses a risk difference, which expresses the difference between the two arm proportions on the probability scale. In the posted comparison, the direction is epoetin beta relative to CERA. A positive estimate indicates a higher observed response proportion in the epoetin beta arm; a negative estimate would indicate a higher proportion in the CERA arm.

What does a confidence interval represent?

A confidence interval describes the uncertainty around an estimated effect under the assumptions of the statistical method. It is not a range containing a known true effect with certainty, and it does not measure the chance that the observed estimate is correct. For the primary comparison, the 95% confidence interval runs from -0.078 to 0.245. Because it includes zero, the data are compatible with no difference as well as with differences in either direction. The interval’s breadth also matters: a point estimate should not be read without the uncertainty around it.

How should a p-value be read?

The unadjusted p-value for the primary comparison is 0.313. A p-value describes how unusual results at least as inconsistent with a specified no-difference model would be under that model and the method’s assumptions. It is not the probability that the no-difference model is true, and it does not describe clinical importance. A p-value above a conventional threshold does not establish equivalence. An equivalence conclusion would require an appropriate design and prespecified equivalence margins, neither of which is reported in the registry record.

What does “unadjusted” mean in these comparisons?

The posted comparisons are simple unadjusted recalculations from the arm-level summaries, rather than adjusted analyses accounting for baseline covariates or other modeling choices. No reported analyses are listed for the posted secondary outcomes. The record does not report a sponsor analysis for these comparisons, so the displayed recalculations should be understood as descriptive comparisons of the posted summary data. They do not substitute for a prespecified analysis plan or a full participant-level analysis.

How do continuous outcomes differ?

Hemoglobin change is reported as a mean and standard deviation for each arm. A mean difference compares the arm means; the reported estimate is 0.03, with a 95% confidence interval from -0.603 to 0.663 and an unadjusted p-value of 0.926. A mean summarizes the center of the observed values, while a standard deviation describes their spread around the mean. Neither statistic alone describes the full distribution or whether assumptions used by a particular inferential method are appropriate. The registry record does not report a detailed analysis model for this outcome.

What can the population label tell readers?

The primary population is the Intent-to-Treat population, defined as all randomized participants. This label identifies who is intended to contribute to the primary analysis, but it does not tell readers how unavailable outcome measurements were handled. The record does not report the extent or pattern of missing primary outcome data, imputation methods, or sensitivity analyses. The endpoint’s definition also includes transfusion status, but the record does not detail how incomplete transfusion data were treated.

How should secondary comparisons be approached?

Secondary outcomes cover different kinds of data: continuous measurements, event counts, and safety summaries. The statistical interpretation depends on the outcome scale and observation window. For example, a count of participants receiving transfusions is a binary participant-level outcome over a defined period, while a mean change in hemoglobin retains information about measurement magnitude. Unadjusted comparisons across multiple outcomes can produce apparently notable results by chance, especially when no multiplicity procedure is reported. The registry record does not report a multiplicity plan or a set of prespecified confirmatory secondary hypotheses.

All statistical explanations above are general. They do not establish which analysis choices were made beyond the methods and results reported in the registry record. The record does not report interim analyses, a detailed statistical analysis plan, or the trial’s original sample-size assumptions.

11. Confidence Intervals and Precision

The primary response estimates are 79.5% for Correction Phase: CERA, with a 95% confidence interval from 63.5 to 90.7, and 87.8% for Correction Phase: Epoetin Beta, with a 95% confidence interval from 73.8 to 95.9. These intervals show uncertainty around each arm’s estimated response percentage. Their overlap is consistent with the uncertainty in the direct comparison, but overlap alone is not a formal test of the difference.

The more direct summary is the risk difference for epoetin beta relative to CERA: 0.083, with a 95% confidence interval from -0.078 to 0.245. The interval includes zero, so the posted data do not rule out no difference under this unadjusted calculation. It also spans effects on both sides of zero, leaving uncertainty about direction. The estimate is not precise enough to support a firm claim that one correction-phase group had a higher response rate.

Confidence intervals generally become narrower when there is more information and less variability, and wider when information is limited or outcomes are variable. That general principle helps explain why a result can have a noticeable point estimate yet remain uncertain. The interval is more informative than the point estimate by itself because it makes the range of estimates compatible with the data visible.

The other posted comparisons also vary in precision. The hemoglobin mean-difference interval includes zero and spans negative and positive values. The electrocardiogram comparison has a broad interval that also includes zero. The transfusion comparison between correction-phase groups has an interval that does not include zero in the unadjusted calculation; however, it is a secondary outcome and must be considered alongside the lack of a reported multiplicity plan and the limited detail on analysis methods.

These intervals are not guarantees about future results or individual outcomes. They quantify sampling uncertainty under the calculation’s assumptions and do not account for every possible source of bias, missing data, outcome measurement limitations, or differences between a trial population and other settings. The registry record does not report adjusted confidence intervals for these results.

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 display gives planning illustrations based on the observed effect sizes, not the trial’s original design rationale. For the binary outcomes, the figures are participants per arm. The assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; each planning scenario uses the stated fraction of the observed effect. The original trial’s sample-size assumptions are not reported in the registry record.

The 80% power column gives an illustrative number of participants per arm for a future study to have an 80% chance of detecting the specified effect under those assumptions, if that effect were the true one. The 90% power column gives the corresponding planning target for a higher chance of detection. These are design calculations, not guarantees that a study of the listed size will reach a particular result. The figures depend on the assumed effect and the stated statistical conditions.

Each set of planning entries considers the full observed effect and smaller fractions of it. The sample size needed increases as the effect to be detected becomes smaller, because a less pronounced difference is harder to distinguish from random variation. The large planning requirements for some outcomes reflect the very small observed differences used in those illustrations; they should not be mistaken for recommendations without considering the scientific question and design.

For time-to-event outcomes, such a display would report total events, whereas the outcomes posted for this trial are not time-to-event planning entries. The posted planning figures therefore refer to participants per arm. These figures are not observed power: observed power is not a useful substitute for interpreting the estimated effect and its confidence interval after a trial. The planning calculations are illustrations, not a retrospective measure of how likely the completed study was to detect its actual result.

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 = 0.795; treatment proportion p₁ = 0.878; average p̄ = 0.836.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.5231 = 1.0252.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.5197 = 0.4374.
4. n = (1.0252 + 0.4374)² / (0.0832)² = 309.2, rounded up to 310 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 <- 0.794871794871795                          # control proportion
p1 <- 0.878048780487805                          # 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(546481)
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 = 310 (80% power), 414 (90% power)
 75% of observed effect: n per arm = 579 (80% power), 774 (90% power)
 50% of observed effect: n per arm = 1,364 (80% power), 1,825 (90% power)
power.prop.test: 309.2 
Simulated power at n = 310 per arm: 0.803 (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 identifies a primary endpoint, but it does not report a detailed statistical analysis plan or a multiplicity procedure for the several secondary outcomes and comparisons. Multiplicity arises when researchers examine multiple outcomes, time points, groups, or statistical contrasts. Even when each individual analysis uses a conventional threshold, considering many analyses increases the opportunity for at least one apparently notable result to arise by chance. This is a general statistical concern, not evidence that a particular posted result is false.

The primary comparison is therefore the clearest result to prioritize. Secondary comparisons can help describe other dimensions of the study, but unadjusted p-values do not account for the full set of outcomes. The record does not state which secondary outcomes were designated as confirmatory, whether an order of testing was planned, or whether any adjustments were made. These details are not reported in the registry record.

The primary analysis population is the Intent-to-Treat population, defined as all randomized participants. That definition is important, but it does not resolve how missing measurements were handled. The registry record does not report missing-data counts for the primary endpoint, reasons for missingness, imputation methods, or sensitivity analyses. It also does not report whether every randomized participant had evaluable data for each secondary outcome. Different handling of missing data can affect estimates, particularly for outcomes requiring both laboratory values and information about transfusions.

For safety summaries, the at-risk groups differ across the correction and maintenance phases. The record does not provide enough information to reconstruct the analysis populations or exposure time behind every safety summary. It also does not report a detailed approach to exposure adjustment or a formal statistical comparison of adverse events.

Interim analyses are not reported in the registry record. The trial’s original sample-size justification, stopping rules, and any planned handling of multiple primary analyses are also not reported. These gaps do not invalidate the posted summaries, but they limit assessment of how the analyses were prespecified and how robust conclusions are to alternative assumptions.

15. 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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: glaucoma (2.6%), diarrhoea (2.6%), haematemesis (2.6%), pneumonia (2.6%), femoral neck fracture (2.6%).

The registry record reports serious adverse events for the correction-phase groups using at-risk denominators of 38 for CERA and 39 for epoetin beta. Serious adverse events were reported for 10 participants in the CERA group and 6 in the epoetin beta group. Other adverse events were reported for 34 of 38 at risk in the CERA group and 39 of 39 at risk in the epoetin beta group. These are descriptive counts, not a formal adjusted comparison.

A Maintenance Phase: CERA group is also listed, with 8 serious adverse events among 54 at risk and other adverse events among 51 of 54 at risk. Because the registry record does not explain the relationship of this group to the randomized correction-phase comparison, it should be read separately rather than treated as a direct randomized contrast.

The serious-event terms with the highest listed percentages are Glaucoma, Diarrhoea, Haematemesis, Pneumonia, Femoral neck fracture, and Femur fracture, each reported as 2.6%. Death counts are not reported in the registry record. These summaries do not establish that an event was caused by a treatment, nor do they provide a complete assessment of comparative safety. Interpretation is limited by the absence of reported exposure-adjusted analyses, a detailed safety analysis plan, and further information about event ascertainment.

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

The primary result describes the proportion of participants in each correction-phase group who met a specific hemoglobin response definition during the stated period. The observed percentages were 79.5 for CERA and 87.8 for epoetin beta. The unadjusted difference estimate favors a higher response proportion in the epoetin beta group, but its confidence interval includes zero and values in both directions. The result therefore leaves meaningful uncertainty about the size and direction of the group difference.

This is not evidence of equivalence. Failure to establish a clear difference is not the same as showing that treatments are equivalent or interchangeable. The registry record does not report an equivalence or non-inferiority design, a prespecified margin, or analyses intended to establish either conclusion.

Nor does the result establish that either treatment works or does not work. The registry data describe outcomes among participants in this study under its conditions. They do not, by themselves, establish what would happen in other populations, care settings, or treatment periods. The open-label design, the reported outcome definition, and unreported details of missing-data handling all matter when considering how broadly to interpret the findings.

Secondary findings can contribute context but should not be combined into a single overall judgment without a prespecified approach. The transfusion result is not the primary outcome, and several listed outcomes do not have posted results. Adverse-event counts are descriptive and do not demonstrate causality. The Maintenance Phase: CERA group is also not adequately described as a direct randomized comparator in the registry record.

The most defensible interpretation is limited: the posted primary response estimates are high in both correction-phase groups, while the unadjusted comparison is imprecise and does not resolve whether the groups differ. The result should be read with its confidence interval, the endpoint definition, and the reporting limitations, rather than as a categorical statement about treatment benefit or safety.

17. Why This Trial Matters Statistically

This study illustrates why the point estimate and its uncertainty should be considered together. The arm-specific response percentages are easy to interpret, but the comparison interval is broad and includes zero. A single observed difference does not settle whether a true group difference exists or how large it might be. For clinical researchers, the central statistical task is to distinguish the direction suggested by a point estimate from the strength of evidence and precision around it.

The endpoint also demonstrates how outcome definitions shape conclusions. Hemoglobin response combines a minimum increase, an absolute threshold, and absence of transfusion. That composite classification is clinically interpretable, but it differs from a continuous measure of hemoglobin change and from a transfusion count considered over a longer period. These outcomes answer related but not identical questions.

The registry record also highlights the importance of separating the primary endpoint from multiple secondary analyses. A secondary result may appear more compelling than the primary comparison, yet its weight depends on prespecification, multiplicity handling, and analytic details. Those details are not reported, so secondary results remain supportive or exploratory rather than definitive.

Finally, the planning illustrations show how sample-size requirements depend on the size of the effect a future study aims to detect. Smaller target effects require more participants under the stated planning assumptions. These calculations help with prospective design, but they are not a retrospective score of the completed study. The original trial’s design assumptions are not reported, so the illustrations should not be confused with its actual planning rationale.

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 registry record leaves important design and analysis details unreported. It does not give the original sample-size justification, detailed statistical analysis plan, interim-analysis procedures, or a multiplicity strategy for secondary outcomes. It also does not report missing-data counts, methods for handling unavailable primary endpoint components, or sensitivity analyses. These omissions limit independent assessment of how prespecified analyses align with the posted summaries.

The trial was open-label, and the record does not describe procedures that might reduce the influence of treatment awareness on outcome ascertainment. The primary endpoint includes laboratory values and transfusion status, but the registry record does not explain how missing or incomplete information was treated. The primary confidence interval is broad, leaving substantial uncertainty about the comparative effect.

Some listed secondary outcomes do not have results reported in the registry record, including outcomes concerning time within the hemoglobin target range and vital signs. The absence of posted results is not evidence that those outcomes were unchanged. The adverse-event summaries provide counts but do not report exposure-adjusted comparisons or sufficient detail to assess differences in duration or intensity of exposure. Death counts are not reported in the registry record.

The Maintenance Phase: CERA group appears in secondary and safety summaries, but the record does not describe its relationship to the randomized correction-phase groups sufficiently for a direct comparative interpretation. It should not be merged conceptually with the randomized correction-phase contrast.

Finally, the posted comparisons are unadjusted recalculations from summary statistics, not a substitute for a full prespecified participant-level analysis. The record reports no sponsor analyses for the posted secondary outcomes. These limitations affect how confidently the estimates can be interpreted and how far conclusions can be generalized.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: A Study of Intravenous Mircera for the Correction of Anemia in Dialysis Patients. — NCT00546481.
• Registry record last updated 2016-09-19; status last verified 2016-08.
• Results first posted 2016-07-18.
• 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

NCT00546481 is a completed randomized, open-label, parallel-group Phase 3 study of intravenous Mircera and epoetin in dialysis patients with chronic kidney disease and anemia. The registry lists enrollment of 80 and primary completion in 2009-12.

The primary endpoint was the percentage achieving the defined hemoglobin response up to Week 24. The reported percentages were 79.5 for Correction Phase: CERA and 87.8 for Correction Phase: Epoetin Beta. The unadjusted risk-difference estimate was 0.083, with a 95% confidence interval from -0.078 to 0.245 and p = 0.313. The interval includes zero, so the comparison remains uncertain.

Posted secondary results address hemoglobin change, transfusions, and abnormal electrocardiogram changes, alongside adverse-event summaries. Other listed outcomes are not reported in the registry record. The record does not report the original sample-size assumptions, detailed statistical analysis plan, multiplicity handling, or missing-data procedures.