This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for A Study of Subcutaneous Mircera for the Treatment of Anemia in Peritoneal Dialysis Patients. (NCT00442416), a randomized phase 3 study. The primary outcome is Mean Change From Baseline in Hb Concentration to Average Over the Evaluation Period.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT00442416 |
| Phase | Phase 3 |
| Condition | Anemia |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | None (open label) |
| Enrollment | 80 |
| Arms in the primary outcome | 2 |
| Lead sponsor | Hoffmann-La Roche |
| Results posted | Yes |
2. Clinical Question
Population
Patients with anemia receiving peritoneal dialysis were eligible. The primary analysis population was per-protocol: randomized participants who received at least one dose, met study entry criteria, had no major protocol violations, and had data available at evaluation.
Intervention
RO0503821, identified as methoxy polyethylene glycol-epoetin beta (Mircera), was administered by subcutaneous injection monthly. The registry describes a titration period and an evaluation period, with the arm description specifying eight months of treatment.
Comparator
The comparator was subcutaneous epoetin alfa administered according to standard of care. Participants continued their existing pattern of self-administration or clinic injections, as applicable.
Primary question
What was the difference between the groups in mean change in hemoglobin concentration from baseline to the average during the evaluation period? The evaluation period is described as Month 7 to 9. The registry reports the outcome in g/dL.
The study was registered as a two-arm, randomized, open-label, multicenter phase 3 trial. The clinical question is comparative: it concerns the reported group-level change in hemoglobin concentration under the two assigned treatment strategies, not an individual participant’s response. The primary outcome is a continuous measure, so its summary uses group means and standard deviations.
The registry also describes safety assessment, injection-site reactions, patient satisfaction, and laboratory measures. Those outcomes are distinct from the primary hemoglobin comparison. The posted primary result is from the per-protocol population rather than all randomized participants. The registry record does not report a clinical threshold for interpreting the size of a hemoglobin change or a prespecified margin for judging the treatments equivalent.
3. Trial Design
This was a randomized, parallel-group, open-label, multicenter phase 3 study sponsored by Hoffmann-La Roche. The registry records a start in 2007-02 and primary completion in 2008-01, and lists the study status as terminated. Enrollment is recorded as 80. The brief summary gives a target sample size of 380 individuals; the reason for the difference between that target and recorded enrollment is not reported in the registry record.
Participants were assigned to RO0503821 (Mircera) or epoetin alfa. The Mircera arm description specifies monthly subcutaneous injections, while the epoetin alfa arm continued subcutaneous standard-of-care dosing. The brief summary describes dose adjustments intended to reach or maintain a hemoglobin level of 10-12g/dL. It also describes an anticipated treatment duration of 3-12 months. The arm descriptions separately specify eight months of treatment, including titration and evaluation, followed by 15 days of follow-up after the final study visit. The registry does not explain the different duration descriptions.
The primary endpoint timeframe is baseline (Day 0) to the average during the evaluation period, described as Month 7 to 9. The analysis population included randomized participants who received at least one dose, met entry criteria, had no major protocol violations, and had data available at evaluation. This is a narrower population than all randomized participants. The registry does not report details of allocation concealment, the randomization sequence, or the reasons for termination. It lists no posted statistical analyses. The original sample-size justification and the trial’s own planned analysis procedures are not reported in the registry record.
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: A total of 80 participants were randomized, of which 78 participants received the study drug and 2 participants did not receive the study drug nor had post baseline safety assessments.
Overall Study
| Stage | RO0503821 | Epoetin Alfa |
|---|---|---|
| STARTED | 39 | 41 |
| COMPLETED | 2 | 2 |
| NOT COMPLETED | 37 | 39 |
Reasons for not completing this period:
| Reason | RO0503821 | Epoetin Alfa |
|---|---|---|
| Adverse Event | 4 | 1 |
| Death | 1 | 0 |
| Lack of Efficacy | 2 | 0 |
| Protocol Violation | 2 | 3 |
| Withdrew consent | 1 | 2 |
| Administrative/Other | 27 | 33 |
Analysis population for the primary outcome, as defined in the registry: Per-protocol population included all randomized participants who received at least one dose of the study drug and met all study entry criteria with no major protocol violations. Participants with available data at the time of evaluation were analyzed.
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 population included all participants who received at least one dose of the study drug and had at least one post-baseline safety assessment.
| Characteristic | Unit | RO0503821 | Epoetin Alfa | Total |
|---|---|---|---|---|
| Participants analysed | 38 | 40 | 78 | |
| Age, Continuous | Years | 58.5 (SD 12.59) | 53.6 (SD 15.86) | 56.0 (SD 14.48) |
| Sex: Female, Male: Female | Participants | 18 | 20 | 38 |
| Sex: Female, Male: Male | Participants | 20 | 20 | 40 |
6. Primary Endpoint
The registry lists the primary outcome as Mean Change From Baseline in Hb Concentration to Average Over the Evaluation Period, measured over From Baseline (D 0) to 9 months.
| Element | Registry entry |
|---|---|
| Result type | Mean |
| Measure of spread | Standard Deviation |
| Unit | g/dL |
| Endpoint classification | Continuous Endpoint |
The primary endpoint is mean change from baseline in hemoglobin concentration, measured in g/dL, to the average over the evaluation period. Hemoglobin concentration is a continuous measurement, and change from baseline expresses how the group’s average measurement at evaluation compares with its starting measurement. Averaging across the evaluation period can represent the group’s measurement over that period rather than a single evaluation visit.
The registry defines baseline as Day 0 and the evaluation period as Month 7 to 9. It reports the mean change for each treatment arm, along with a standard deviation, and gives a between-group mean difference. The posted analysis is restricted to the per-protocol population with available evaluation data. This endpoint therefore describes the observed average change among analyzed participants; it does not describe every randomized participant’s outcome.
As a general statistical matter, continuous endpoints retain information about the magnitude of measurements rather than reducing them to a binary category. A mean difference gives the average contrast between groups, while the standard deviation describes participant-to-participant variability within a group. Neither statistic alone determines whether a change is clinically important. A threshold for clinical importance is not reported in the registry record, so the numerical contrast should be interpreted as a statistical result rather than a clinical judgment.
7. Results Posted in the Registry
- Epoetin Alfa: mean 0.51 versus -0.32 on control; difference 0.83 (95% CI 0.20 to 1.46), standardized effect d = 0.63; z-test p = 0.010.
Mean difference: Epoetin Alfa
95% CI: 0.20 to 1.46
Recalculated from the posted summary statistics
8. Statistical Interpretation
For the per-protocol analysis, the mean change in hemoglobin concentration was -0.32 g/dL in the RO0503821 arm and 0.51 g/dL in the epoetin alfa arm. The registry-reported mean difference was 0.83 g/dL, expressed as epoetin alfa minus RO0503821. Thus, the posted group means show a higher average change in the epoetin alfa arm during the evaluation period. This describes the observed contrast; it does not establish what caused it or whether it is clinically important.
The reported confidence interval for the mean difference lies above zero, and the unadjusted p-value is 0.01. In the context of the reported comparison, the interval is compatible with a positive difference in mean change for epoetin alfa relative to RO0503821. The p-value describes how unusual data at least as incompatible with a zero-difference model would be under the statistical model and its assumptions. It is not the probability that the treatments are the same, nor does it measure the probability that the result is due to chance.
The displayed means and contrast are estimates from a per-protocol population that required treatment receipt, satisfaction of entry criteria, absence of major protocol violations, and data at evaluation. Such a population can differ from the full randomized population. The registry does not report an all-randomized primary analysis alongside the per-protocol result, so the posted contrast should not be treated as an intention-to-treat estimate.
The standard deviations were 1.31 g/dL for RO0503821 and 1.33 g/dL for epoetin alfa. These values indicate variation among analyzed participants around their respective group means. The registry reports 33 participants in the RO0503821 primary analysis and 35 in the epoetin alfa primary analysis. The total enrollment figure does not describe the denominator used for this endpoint, and those figures should not be substituted for the analysis-specific group counts.
No adjustment for multiple comparisons is reported for the primary result, and the p-value is explicitly unadjusted. The registry lists additional outcomes, including safety and laboratory measures, but does not report a complete statistical strategy for interpreting them alongside the primary endpoint. The finding therefore supports a description of the posted data and its uncertainty, not a broad conclusion about all study outcomes, all randomized participants, or treatment effects in other populations. A clinically important difference threshold is not reported in the registry record.
9. Statistical Methods Explained
The primary outcome is continuous, so the registry summarizes it using a mean and standard deviation for each arm. A mean is the arithmetic average of the observed changes in the analyzed group. A standard deviation describes the spread of individual changes around that mean. These summaries answer different questions: the mean describes the group’s central result, while the standard deviation describes variability among participants.
What does the mean difference represent?
The reported contrast is the difference between the epoetin alfa and RO0503821 mean changes. Its stated direction is epoetin alfa minus RO0503821. The estimate of 0.83 g/dL therefore represents the average difference in change between the two analyzed groups, not the change for a typical individual and not a difference in the proportion of participants reaching a threshold.
As a general statistical explanation, a mean difference is an effect estimate on the endpoint’s original measurement scale. That makes its units interpretable as g/dL. It does not by itself indicate whether the difference is large enough to matter clinically. That judgment depends on clinical context and a prespecified meaningful threshold, which is not reported in the registry record.
What does the p-value tell us?
The registry reports an unadjusted p-value of 0.01. In general, a p-value assesses how compatible the observed data are with a statistical model in which the specified null difference is zero, assuming the model and its assumptions hold. A smaller p-value indicates greater incompatibility with that null model, but does not quantify the size or importance of the difference. It also does not give the probability that the null hypothesis is true. The posted p-value is unadjusted; any multiplicity adjustment is not reported in the registry record.
Why use a confidence interval?
A confidence interval presents a range of values compatible with the data under a specified statistical procedure. It communicates uncertainty about the estimated mean difference. The registry’s reported interval is entirely on the positive side of zero. As a general explanation, an interval that excludes zero is consistent with a two-sided test that rejects a zero-difference null at the corresponding significance level, provided the interval and test use matching methods and assumptions. The registry does not report all details needed to verify those procedures independently.
A confidence interval is not a range containing a known fixed percentage of individual participant results. It concerns uncertainty in an estimate, not the spread of individual changes. The standard deviations describe participant-level spread; the confidence interval describes uncertainty in the group contrast. These quantities should not be conflated.
What does the analysis population mean?
The primary outcome population is described as per-protocol. It included randomized participants who received at least one dose, met all study entry criteria, had no major protocol violations, and had data available at evaluation. The posted arm counts for the primary analysis are 33 and 35. Because eligibility for this analysis depends on events after randomization and on data availability, it does not retain the full protection of randomization in the same way as an analysis of all randomized participants would. This is a general consideration; the registry does not report the reasons individual participants were excluded from the primary analysis.
The registry describes analysis of participants with available evaluation data. A method for handling missing primary outcome data, such as imputation or sensitivity analysis, is not reported in the registry record. The impact of missing data therefore cannot be assessed from the posted primary summary alone.
Why can variation matter?
As a general statistical matter, greater variability makes a group mean less precise when other design features are unchanged. Standard deviations help show how dispersed participant results are, while the confidence interval incorporates uncertainty in the between-group estimate. The two arms have reported standard deviations of 1.31 and 1.33 g/dL. These figures do not establish that the individual distributions have the same shape or that every modeling assumption holds.
Some clinical outcomes can have more variability than a simple model assumes. In general, over-dispersion means that observed variability exceeds what a model expects; accounting for it can affect standard errors and uncertainty intervals. The primary endpoint is a continuous mean change, and the registry does not identify an over-dispersion adjustment. That concept should not be taken as evidence that over-dispersion occurred in this trial.
The registry lists no posted analysis records. It does not report the full statistical analysis plan, model details, covariate adjustments, missing-data sensitivity analyses, or multiplicity procedures. The reported summaries can be interpreted as posted, but those missing details limit independent evaluation of how the estimates were produced.
10. Confidence Intervals and Precision
The registry reports a mean difference of 0.83 g/dL, with a confidence interval that lies above zero. The interval represents uncertainty in the estimated group contrast, not the range of individual participant changes. Its position indicates that the posted estimate and interval favor a positive mean difference for epoetin alfa minus RO0503821 under the reported analysis. The interval’s exact endpoints are available in the posted statistical display.
Precision depends on the width of the confidence interval: a narrower interval indicates less uncertainty about the estimate, while a wider interval indicates more. The interval should be read together with the estimate, the analysis population, and the endpoint definition. Here, the estimate is based on a per-protocol population with available data at evaluation, rather than all randomized participants. Missing-data handling is not reported in the registry record, so the interval does not resolve uncertainty arising from unobserved outcomes or population selection.
The arm-level standard deviations, 1.31 g/dL and 1.33 g/dL, describe variability among analyzed participants. They are not confidence limits. The reported group counts for this endpoint are 33 for RO0503821 and 35 for epoetin alfa. Those counts, the variability, and the analysis method all bear on precision, but the registry does not provide enough methodological detail to reconstruct every step of the interval calculation.
Statistical precision is not the same as clinical importance. The registry does not report a threshold for a clinically meaningful difference, so the interval cannot be used by itself to classify the result as clinically important or unimportant. It quantifies uncertainty in the reported statistical contrast under the analysis, rather than uncertainty about every possible population or treatment setting.
11. Planning a Similar Trial: Sample Size
This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.
| Effect to detect | Participants per arm, 80% power | Participants per arm, 90% power |
|---|---|---|
| 100% of the observed effect | 40 | 54 |
| 75% of the observed effect | 71 | 95 |
| 50% of the observed effect | 159 | 213 |
The sample-size figures are planning illustrations based on fractions of the observed effect, not the original trial’s design calculation. The original sample-size justification and the assumptions used for the trial’s own design are not reported in the registry record. The displayed figures are participants per arm, not total events. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation; the effect to detect is the stated fraction of the observed effect.
For planning at 100% of the observed effect, the display gives 40 participants per arm for 80% power and 54 participants per arm for 90% power. Planning for 75% of the observed effect gives 71 participants per arm for 80% power and 95 participants per arm for 90% power. Planning for 50% of the observed effect gives 159 participants per arm for 80% power and 213 participants per arm for 90% power.
In plain terms, the 80% power column describes the planned group size under which the assumed study would have an 80% chance of detecting the specified effect at the stated significance level, if the planning assumptions hold. The 90% column uses the same idea with a higher target probability. Smaller assumed effects require more participants to distinguish the effect from random variation with the same planned power. These are planning illustrations, not observed power.
The illustrations use the effect estimated in this trial as their reference, so they should not be read as proof that the original trial was designed around that estimate. They also do not account for unreported design choices or missing-data procedures. A power calculation is conditional on its assumptions; changing the target effect, variability, allocation, or analysis can change the required group size.
12. How the Sample Size Is Derived
Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z1−α/2 = 1.960) and the desired power (z1−β = 0.842 for 80% and 1.282 for 90%).
Formula
n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.
Worked calculation for this trial
- Observed difference Δ = 0.830; pooled standard deviation σ = 1.320.
- n = 2 × (1.96 + 0.842)2 × 1.3202 / 0.8302 = 39.7, rounded up to 40 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
delta <- 0.83 # observed difference in means
sigma <- 1.32034086507992 # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^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 (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")
# Simulation: exact two-sample t-test using simulated means and variances
set.seed(442416)
n <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n)) # difference in sample means
s2 <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1)) # pooled sample variance
tstat <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))
Output from running the code
100% of observed effect: n per arm = 40 (80% power), 54 (90% power)
75% of observed effect: n per arm = 71 (80% power), 95 (90% power)
50% of observed effect: n per arm = 159 (80% power), 213 (90% power)
power.t.test: 40.7
Simulated power at n = 40 per arm: 0.793 (20000 replicates)The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-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.
13. Multiplicity, Missing Data and Analysis Populations
The registry identifies the primary outcome as mean change in hemoglobin concentration and reports an unadjusted p-value for the group comparison. It also lists secondary safety and laboratory outcomes, including safety-related hemoglobin measures, marked laboratory abnormalities, iron, ferritin, transferrin saturation, serum transferrin, total iron-binding capacity, and temperature. The record does not report a multiplicity strategy for interpreting the primary and secondary results together. It is therefore not possible to determine from the registry record whether a particular family of comparisons was prespecified or whether any adjustment was planned.
The posted primary population is per-protocol, with participants required to have received at least one dose, met entry criteria, had no major protocol violations, and had available evaluation data. The registry does not report the corresponding all-randomized analysis for the primary endpoint. Nor does it explain how participants were selected into the per-protocol population or give participant-level reasons for exclusion. This limits assessment of how the analysis population may differ from the randomized groups.
The description says that participants with available data at evaluation were analyzed. A missing-data method, imputation procedure, or sensitivity analysis is not reported in the registry record. Without that information, the effect of unavailable measurements on the primary estimate cannot be assessed. The record also does not specify whether the analysis adjusted for baseline values, site, or other covariates.
The registry lists zero posted analysis records. Details such as a complete statistical analysis plan, model specification, handling of protocol deviations, and multiplicity procedures are not reported. These omissions do not change the numerical results that are posted, but they limit the ability to evaluate whether the reported analysis followed a prespecified plan or how robust the conclusion would be under alternative reasonable choices.
14. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| RO0503821 | 11 | 38 | 28.9% |
| Epoetin Alfa | 2 | 40 | 5.0% |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 5% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| RO0503821 | 18 of 38 |
| Epoetin Alfa | 15 of 40 |
Most frequent serious adverse event terms
| Event term | Organ system | RO0503821 | Epoetin Alfa |
|---|---|---|---|
| Peritonitis | Gastrointestinal disorders | 0 of 38 | 2 of 40 |
| Abdominal pain | Gastrointestinal disorders | 1 of 38 | 0 of 40 |
| Ileus | Gastrointestinal disorders | 1 of 38 | 0 of 40 |
| Pancreatitis | Gastrointestinal disorders | 1 of 38 | 0 of 40 |
| Upper gastrointestinal haemorrhage | Gastrointestinal disorders | 1 of 38 | 0 of 40 |
| Angina unstable | Cardiac disorders | 1 of 38 | 0 of 40 |
| Cardiac arrest | Cardiac disorders | 1 of 38 | 0 of 40 |
| Myocardial infarction | Cardiac disorders | 1 of 38 | 0 of 40 |
| Gastroenteritis | Infections and infestations | 1 of 38 | 0 of 40 |
| Pneumonia | Infections and infestations | 1 of 38 | 0 of 40 |
Most frequent non-serious adverse event terms
| Event term | Organ system | RO0503821 | Epoetin Alfa |
|---|---|---|---|
| Fatigue | General disorders | 5 of 38 | 0 of 40 |
| Peritonitis | Gastrointestinal disorders | 2 of 38 | 2 of 40 |
| Abdominal pain | Gastrointestinal disorders | 1 of 38 | 2 of 40 |
| Bronchitis | Infections and infestations | 2 of 38 | 1 of 40 |
| Catheter site infection | Infections and infestations | 0 of 38 | 3 of 40 |
| Dizziness | Nervous system disorders | 2 of 38 | 1 of 40 |
| Dyspnoea | Respiratory, thoracic and mediastinal disorders | 2 of 38 | 1 of 40 |
| Diarrhoea | Gastrointestinal disorders | 2 of 38 | 0 of 40 |
| Asthenia | General disorders | 2 of 38 | 0 of 40 |
| Nasopharyngitis | Infections and infestations | 0 of 38 | 2 of 40 |
Serious events with the highest arm-level rate: peritonitis (5.0%), abdominal pain (2.6%), ileus (2.6%), pancreatitis (2.6%), upper gastrointestinal haemorrhage (2.6%).
The registry reports serious adverse events in 11 of 38 participants at risk in the RO0503821 group and in 2 of 40 at risk in the epoetin alfa group. For other adverse events, it reports 18 of 38 at risk in the RO0503821 group and 15 of 40 at risk in the epoetin alfa group. These are counts of participants affected, with the corresponding at-risk group size as the denominator. They are descriptive safety summaries, not adjusted comparisons.
The registry lists peritonitis at 5.0% among the top serious adverse event terms. Abdominal pain, ileus, pancreatitis, upper gastrointestinal haemorrhage, and unstable angina are each listed at 2.6%. The record does not provide further context in these figures about timing, duration, severity grading, or causal attribution. A participant may have experienced more than one event, so event terms should not be treated as mutually exclusive participant categories.
Deaths are not reported in the registry record. The safety counts use their own at-risk group sizes and should not be replaced by the primary endpoint analysis counts. The figures alone do not establish whether an event was caused by a study drug.
15. What the Result Does, and Does Not, Mean
The posted primary result describes a difference in mean hemoglobin change between the analyzed groups during the evaluation period. The RO0503821 group mean change was -0.32 g/dL, and the epoetin alfa group mean change was 0.51 g/dL. The registry-reported mean difference, defined as epoetin alfa minus RO0503821, was 0.83 g/dL. Its confidence interval lies above zero, and the unadjusted p-value is 0.01. These statistics summarize the observed per-protocol data and the uncertainty in the estimated contrast.
The result does not establish that the difference is clinically important. A clinical-importance threshold is not reported in the registry record. Nor does a small p-value establish the probability that a treatment works, the probability that the result will recur, or the probability that the null hypothesis is true. The estimate applies to the analyzed population and endpoint as recorded, not necessarily to all randomized participants or to other settings.
The result also does not establish equivalence or non-equivalence under a prespecified margin. The registry does not report such a margin. Because the primary analysis is per-protocol and includes participants with available data at evaluation, it should not be described as an all-randomized comparison. The registry record does not report how missing primary outcome data were handled or the full analysis plan.
Safety counts are separate descriptive findings. They report how many participants were affected by serious and other adverse events in each at-risk group; they do not by themselves establish causation or provide a complete comparison of all possible harms. The record does not report deaths. Overall, the posted information supports a careful account of the primary mean contrast and the listed safety counts, while leaving clinical importance, missing-data effects, multiplicity, and several analysis details unresolved.
16. Why This Trial Matters Statistically
This trial illustrates why the analysis population matters when reading a randomized comparison. Random assignment is intended to make groups comparable, but the posted primary result is per-protocol and restricted to participants with available evaluation data. Participants excluded after randomization may differ from those analyzed. The primary contrast therefore describes the recorded analysis population and should not automatically be interpreted as a result for everyone assigned to treatment.
It also shows the value of reading an estimate alongside its uncertainty. The reported mean difference gives the size and direction of the average contrast, while the confidence interval communicates how precisely that contrast is estimated. The unadjusted p-value addresses compatibility with a zero-difference model, but does not answer whether the difference matters clinically. A clinical threshold is not reported, so statistical evidence and clinical importance remain separate questions.
The registry’s enrollment figure is 80, while its brief summary gives a target sample size of 380 individuals. The reason for the difference is not reported in the registry record. That context matters when considering the size of the primary analysis groups and the planning illustrations based on the observed effect. Those illustrations are not the trial’s original design calculation and are not observed power.
Finally, the safety summaries use their own denominators and are not interchangeable with the primary outcome counts. A sound reading keeps efficacy-related endpoint summaries, safety counts, analysis populations, and planning assumptions distinct. The trial offers a useful example of how randomization, post-randomization analysis choices, uncertainty, and incomplete reporting can all shape the interpretation of a registry result.
17. Limitations
- The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
- Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.
The registry lists the study as terminated, but the reason for termination is not reported in the registry record. Enrollment is recorded as 80, whereas the brief summary states a target sample size of 380 individuals; the record does not explain the difference. The original sample-size justification and the trial’s own design assumptions are not reported, so the planning illustrations based on the observed effect cannot fill that gap.
The primary result is limited to a per-protocol population with available evaluation data. The registry does not report a primary analysis of all randomized participants, participant-level reasons for exclusion, or the method used to handle missing outcome data. These omissions make it difficult to assess whether the analyzed groups retained the comparability expected from randomization.
The study was open-label, with no masking. Allocation concealment and details of the randomization procedure are not reported. The registry also does not provide the full statistical analysis plan, covariate adjustment details, multiplicity procedures, or a clinical-importance threshold for the primary endpoint. The unadjusted p-value should therefore be read in the context of the incomplete reporting of the broader analysis strategy.
Safety summaries are descriptive. The registry does not report deaths, and the available event figures do not give full information about timing, severity, duration, or causal attribution. The posted record also does not provide a basis for interpreting every secondary outcome alongside the primary result. These limitations concern what can be evaluated from the registry record; they do not establish that unreported procedures were or were not carried out.
18. Related Tutorials
19. Related Statistical Calculators
20. Sources
- ClinicalTrials.gov: A Study of Subcutaneous Mircera for the Treatment of Anemia in Peritoneal Dialysis Patients. — NCT00442416.
- Registry record last updated 2016-08-17; status last verified 2016-07.
- Results first posted 2016-08-17.
- Data retrieved from ClinicalTrials.gov on 2026-11-09.
- Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
21. Record Summary
NCT00442416 is a randomized, open-label, multicenter phase 3 study of subcutaneous RO0503821 (Mircera) versus subcutaneous epoetin alfa in peritoneal dialysis patients with anemia. The registry records enrollment of 80, a start in 2007-02, primary completion in 2008-01, and terminated status.
The primary endpoint was mean change in hemoglobin concentration from baseline to the evaluation-period average, in g/dL. In the per-protocol analysis, the mean changes were -0.32 for RO0503821 and 0.51 for epoetin alfa; the reported mean difference was 0.83, with an unadjusted p-value of 0.01. The confidence interval for the difference lies above zero.
Serious adverse events were reported for 11 of 38 at risk in the RO0503821 group and 2 of 40 at risk in the epoetin alfa group. The reason for termination, original sample-size justification, missing-data methods, and full statistical analysis plan are not reported in the registry record.