Randomized Study for Efficacy and Safety of Ranibizumab 0.5mg in Treat-extend and Monthly Regimens in Patients With nAMD: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Randomized Study for Efficacy and Safety of Ranibizumab 0.5mg in Treat-extend and Monthly Regimens in Patients With nAMD (NCT01948830), a randomized phase 3 study. The primary outcome is Change in Best Corrected Visual Acuity (BCVA) From Baseline to Month 12.

2. Clinical Question

The study therefore addresses both a clinical measurement question and a statistical comparison question. The measurement is change in visual acuity over the follow-up interval. The comparison asks whether the observed average change differed between the regimen groups, while the sponsor’s reported analysis is classified as a non-inferiority or equivalence analysis. Those are related but not interchangeable questions: a conventional difference estimate describes the direction and size of a contrast, whereas a non-inferiority or equivalence conclusion depends on a prespecified margin and the analysis used to evaluate it.

The registry record describes a 12-month study and reports a primary endpoint from baseline to month 12. It does not report the margin needed to interpret the sponsor’s non-inferiority or equivalence classification. Accordingly, the classification can be noted, but the precise criterion used and the basis for the sponsor’s conclusion cannot be reconstructed from the registry record.

3. Trial Design

This was a randomized, parallel-group Phase 3b study. The official title describes it as a 12-month, multicenter study with visual-acuity assessor masking. The registry classifies masking as single; the identity of the masked party beyond the title’s reference to the visual-acuity assessor is not reported in the registry record. The study status is completed.

The two groups received the same ranibizumab dose, with different schedules: treat-and-extend or monthly dosing, each described as continuing up to month 11. The registry lists an enrollment of 650. The posted primary endpoint summaries include 320 participants for the treat-and-extend group and 323 for the monthly group. Those analysis counts should not be treated as a restatement of the enrollment figure: the primary analysis description specifies a population and data-availability requirements, and its denominators reflect the endpoint summaries.

The primary outcome was change in best-corrected visual acuity from baseline to month 12. The record describes an analysis using least-squares means and standard errors, and also lists an ANCOVA analysis classified as non-inferiority or equivalence. The ANCOVA estimate and its confidence interval are not reported in the registry record. The record’s primary analysis population was the Full Analysis Set, described as patients to whom a regimen had been assigned, with only patients who had both baseline and study-completion values after last observation carried forward included in this analysis.

The registry lists 14 outcome measures and 13 posted secondary outcomes. These cover visual-acuity change and thresholds, scheduled visits, treatment frequency, and other visual-acuity summaries. The trial’s original sample-size justification, allocation details beyond the randomized parallel design, and prespecified statistical plan are not reported in the registry record. The registry lists Novartis Pharmaceuticals as sponsor.

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: Patients were randomized 1:1 into one of two treatment arms, Treat and Extend or monthly regimens. Safety set: One patient was randomized but did not receive at least one study treatment and did not record at least one post-baseline safety assessment

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The Full Analysis Set (FAS), comprised of all patients to whom treatment regimen had been assigned, was considered for the analysis. Only patients with the value for both Baseline and study completion after last observational carried forward (LOCF) were included in this analysis. LOCF was used as an imputation of missing data.

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.

6. Primary Endpoint

The registry lists the primary outcome as Change in Best Corrected Visual Acuity (BCVA) From Baseline to Month 12, measured over Baseline to month 12.

The primary endpoint is change in best-corrected visual acuity from baseline to month 12, measured in ETDRS letters. The registry describes testing with ETDRS-like charts, with participants seated and assessed at a testing distance of 4 meters. The stated scale ranges from 0 to 100 letters, and a positive average change from baseline indicates improvement on that scale.

Visual acuity is a direct measure of the visual function relevant to this study’s condition. Expressing the result as change from baseline makes the endpoint a measure of how the recorded score shifted over the study interval, rather than only a comparison of final scores. Comparing average changes between randomized groups can estimate the difference in average change associated with the assigned regimens, subject to the analysis population, missing-data handling, and statistical model.

The registry reports least-squares means with standard errors for the primary endpoint. Least-squares means are model-based group estimates; the registry record does not give the underlying model specification for these estimates. The endpoint description also states that last observation carried forward was used, but the explanation of that method is truncated in the registry record. The reasons for selecting this endpoint and the original endpoint hierarchy are not reported in the registry record.

A group average does not describe every participant’s experience or the distribution of individual changes. The endpoint can support a comparison of average change, but by itself it does not show how many patients reached a particular threshold or how their results varied. Several threshold-based visual-acuity outcomes were also listed as secondary outcomes, although their results are not reported in the registry record.

7. Results Posted in the Registry

• Group II Ranibizumab 0.5 mg Monthly: mean 8.10 versus 6.20 on control; difference 1.90 (95% CI -0.04 to 3.84), standardized effect d = 0.15; z-test p = 0.055.

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.

Number of Visits Scheduled

• 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:
  • Group II Ranibizumab 0.5 mg Monthly: mean 11.20 versus 8.90 on control; difference 2.30 (95% CI 1.92 to 2.68), standardized effect d = 0.93; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Group II Ranibizumab 0.5 mg Monthly than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change in BCVA From Baseline to Month 12

• 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:
  • Group II Ranibizumab 0.5 mg Monthly: mean 8.00 versus 6.40 on control; difference 1.60 (95% CI -0.40 to 3.60), standardized effect d = 0.12; z-test p = 0.117.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Group II Ranibizumab 0.5 mg Monthly and the control. The interval gives the range of effects that remain compatible with the data.

Average BCVA Change From Baseline to Month 12

• 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:
  • Group II Ranibizumab 0.5 mg Monthly: mean 7.10 versus 6.30 on control; difference 0.80 (95% CI -0.74 to 2.34), standardized effect d = 0.08; z-test p = 0.309.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Group II Ranibizumab 0.5 mg Monthly and the control. The interval gives the range of effects that remain compatible with the data.

The posted secondary results include a higher mean number of scheduled visits in the monthly group than in the treat-and-extend group. The listed visual-acuity summaries also have positive group averages, with the monthly group’s posted average higher in the reported comparisons. The recalculated contrast for scheduled visits has an interval excluding zero, while the recalculated intervals for the posted visual-acuity change summaries include zero. These are descriptive patterns across the reported continuous outcomes; they do not replace the sponsor’s primary analysis.

These findings relate to the primary result because they concern either visual-acuity change over the study period or the amount of scheduled follow-up. The visual-acuity summaries are broadly consistent in direction with the primary point estimate, but their uncertainty and relationship to the primary endpoint matter. Repeated or alternative summaries of the same underlying construct are not independent replications. The visits outcome describes scheduled contact, not visual function, and it should be interpreted as a separate aspect of the regimens.

The registry lists additional secondary outcomes, including categorical visual-acuity thresholds and treatment frequency, but numerical results for those measures are not reported in the registry record. Their absence from the posted results should not be interpreted as evidence that the outcomes were unchanged or that analyses were not performed.

Unadjusted secondary results carry less weight than a prespecified primary analysis because numerous outcomes can be examined and the registry does not report a multiplicity adjustment or endpoint hierarchy. In general, testing multiple outcomes increases the chance that some results will appear notable by chance. Correlated visual-acuity measures further complicate interpretation: agreement in direction may add context, but it does not provide the same evidential strength as an independent, prespecified confirmation. The secondary results are best read as supporting description, with conclusions anchored to the formal primary analysis and its limitations.

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

• Number of Visits Scheduled
• Change in BCVA From Baseline to Month 12
• Average BCVA Change From Baseline to Month 12
• Mean Change in Visual Acuity BCVA (Letters) From Baseline to Month 12
• Number of Patients With a BCVA Improvement of ≥1, ≥5, ≥10, ≥15, and ≥30 Letters From Baseline to Month 12
• Number of Patients With Best Corrected Visual Acuity (BCVA) Loss <5, <10, and <15 Letters by Visit
• Number of Patients With a BCVA Value of ≥ 73 Letters (Approximate 20/40 Snellen Chart Equivalent) at Month 12
• The Mean Number of Treatment Frequency

9. Statistical Interpretation

10. Statistical Methods Explained

Continuous outcomes such as change in visual-acuity letters are commonly summarized with a mean, a measure of variability, and a comparison between groups. A mean describes the center of the observed measurements; it does not show the full distribution or guarantee that all participants had results near that average. The registry’s primary summary uses least-squares means and standard errors, while the secondary continuous summaries are presented as means and standard deviations. These quantities answer different questions: a standard deviation describes spread among measurements, whereas a standard error describes uncertainty in an estimated mean.

What does the primary model-based estimate represent?

The primary endpoint is reported using least-squares means. In general, a least-squares mean is an estimate from a statistical model and may account for variables included in that model. It is not necessarily identical to the raw arithmetic mean. The registry lists ANCOVA as the method for the sponsor’s analysis but does not report its model estimate, confidence interval, covariates, or other specification. Therefore, the model-based contrast cannot be recreated or fully assessed from the record. The posted arm summaries allow a separate, unadjusted comparison, but that comparison should not be confused with the sponsor’s model-based analysis.

ANCOVA is a general method for comparing outcomes between groups while adjusting for one or more covariates. In a randomized trial, adjustment can account for specified baseline measurements or other prespecified variables and may improve precision. The validity and interpretation of a particular ANCOVA result depend on the variables and model assumptions used. Those details, beyond the label ANCOVA and the analysis classification, are not reported in the registry record.

What does the unadjusted recalculation add?

The recalculated contrast uses the posted group summaries to estimate the difference between the two group means. It is a simple unadjusted calculation and is not an independent participant-level analysis. For the primary endpoint, the posted least-squares means and standard errors are used as the available summaries; the recalculated pooled standard deviation is marked approximate. An approximation matters because it means that the spread used for standardized comparisons is inferred from the reported summary quantities rather than directly reconstructed from participant-level observations.

A confidence interval for a mean difference expresses a range of values compatible with the data and the calculation’s assumptions. If an interval includes zero, the observed summaries are compatible with no difference as well as with differences in either direction at the confidence level used. This does not prove that the groups are identical. It indicates that the estimate is not precise enough, under that calculation, to exclude zero. A p-value gives a related measure of how unusual the data would be under a specified null hypothesis and model; it does not measure the probability that the null hypothesis is true or the size of a clinically important effect.

Why distinguish the sponsor analysis from the recalculation?

The registry’s own primary analysis is identified as ANCOVA and as a non-inferiority or equivalence analysis. The unadjusted recalculation, in contrast, estimates an ordinary mean difference from the posted summaries and reports its own interval and p-value. These procedures can differ because they may address different hypotheses, use different model information, and rely on different assumptions. The sponsor’s analysis takes precedence when describing the trial’s formal result. The recalculation helps readers understand what the posted arm-level summaries imply under a simpler comparison, but it cannot establish why the two results differ or replace the prespecified analysis.

Non-inferiority and equivalence are not established merely by observing a small difference or a nonsignificant ordinary superiority test. In general, non-inferiority evaluates whether an outcome is not worse than a comparator by more than a prespecified margin; equivalence evaluates whether a difference lies within prespecified bounds in both directions. The margin and the sponsor’s estimate and interval are not reported in the registry record. As a result, the p-value reported for the ANCOVA classification cannot be translated into a complete interpretation of the non-inferiority or equivalence claim.

Why can variability affect interpretation?

In general, greater variability makes a mean difference harder to estimate precisely when other features of the study are unchanged. The posted secondary standard deviations indicate variation in individual outcomes, while the primary standard errors describe uncertainty in the reported least-squares means. Differences in variability between arms, departures from distributional assumptions, and missing observations can all affect the reliability of a simple summary-based comparison. The record does not provide individual data or enough model detail to examine these issues directly.

Over-dispersion is a general concern when observed variability exceeds what a statistical model assumes. A model that understates variability can produce standard errors that are too small and intervals that are too narrow. This is a general statistical reason to examine model assumptions, not a finding about this trial: the registry record does not report an over-dispersion assessment. Likewise, the summary data do not permit assessment of outliers, skewness, or participant-level patterns.

How should secondary outcomes be treated?

The registry lists a range of secondary endpoints, including scheduled visits, treatment frequency, visual-acuity changes, and threshold-based outcomes. Several are related measures of visual acuity, so they are not necessarily independent pieces of evidence. When many endpoints or comparisons are examined, the chance of at least one apparently notable result can increase. In general, multiplicity procedures or a prespecified hierarchy can address that issue. Such procedures and a hierarchy are not reported in the registry record, so unadjusted secondary p-values should be interpreted cautiously.

The record posts numeric summaries for selected continuous secondary outcomes, but not numeric results for every listed secondary outcome. For outcomes without posted results, the findings are not reported in the registry record. A lack of a posted result does not show that the outcome was measured or analyzed in a particular way, nor does it establish a null finding.

11. Confidence Intervals and Precision

The primary recalculated mean difference is 1.9 letters in the direction of a higher average change with monthly dosing. Its interval runs from -0.040 to 3.84. The lower end is close to zero and slightly on the other side of it, while the upper end allows a larger positive difference. The interval therefore reflects uncertainty that matters to interpretation: the summaries do not sharply distinguish a small difference from no difference, and they do not rule out either direction around zero.

A confidence interval is not a range containing a fixed proportion of individual participants’ outcomes. It describes uncertainty about an estimated quantity, under the method and assumptions used to construct it. Nor does an interval that includes zero demonstrate equivalence. To support an equivalence interpretation, the interval would need to be assessed against prespecified equivalence bounds. The registry’s reported ANCOVA interval and the margin used for its non-inferiority or equivalence analysis are not reported in the registry record.

The recalculated standard errors and interval are based on posted summary statistics, not a participant-level reanalysis. For the primary contrast, the pooled standard deviation is approximate. That limitation means the recalculated precision should be read as an illustration rather than as a more complete analysis than the sponsor’s ANCOVA. The sponsor’s own analysis takes precedence for the formal trial result, even though the record does not provide enough detail to evaluate its estimate directly.

The interval for a group contrast also does not show the range of participant responses within either group. The group standard errors are not substitutes for individual-level variability, and the confidence interval around the mean difference does not indicate how many patients improved or worsened. The registry lists threshold-based visual-acuity outcomes, but their numerical results are not reported in the registry record. Thus, the available precision information is about average change, not the distribution of clinically defined individual outcomes.

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 fractions of the observed effect. For the continuous outcomes shown, the figures are participants per arm, not total events. The planning assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; the effect to detect is the stated fraction of the observed effect. The original trial’s own design assumptions and sample-size justification are not reported in the registry record.

The 80% power column describes the number of participants per arm that the illustration estimates would be needed to have an 80% chance of detecting the specified effect under the stated assumptions, if that effect and those assumptions were correct. The 90% power column gives the corresponding planning target for a 90% chance. These are design calculations, not estimates of what happened in this completed trial. They do not describe the probability that the observed result is correct or the chance that a treatment effect exists.

Rows for 100% of the observed effect use the full observed effect as the planning target; rows for 75% and 50% use smaller target effects. Smaller effects are harder to distinguish from random variation under otherwise similar assumptions, so they require more participants per arm for the same target power. The displayed counts are illustrations generated from the observed effect, not the trial’s original enrollment plan. This is not observed power.

The sample-size curve should be read in the same planning spirit: it shows how the required participant count changes as the target effect changes under the calculation’s assumptions. It does not forecast outcomes, account for unreported features of the original design, or establish that any particular future study would have the displayed power. The illustration is sensitive to the estimated effect used as its starting point, and an observed effect can be imprecise. It is therefore most useful for comparing planning scenarios, not as a definitive prescription for a later study.

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, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = 1.900; pooled standard deviation σ = 12.551.
2. n = 2 × (1.96 + 0.842)² × 12.551² / 1.900² = 685.0, rounded up to 686 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 <- 1.9                      # observed difference in means
sigma <- 12.5514317883498                     # 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(1948830)
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 = 686 (80% power), 918 (90% power)
 75% of observed effect: n per arm = 1,218 (80% power), 1,631 (90% power)
 50% of observed effect: n per arm = 2,741 (80% power), 3,669 (90% power)
power.t.test: 686 
Simulated power at n = 686 per arm: 0.802 (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.

14. Analyses Reported by the Sponsor

The registry reports a sponsor analysis using ANCOVA, classified as non-inferiority or equivalence, with p < 0.001. It does not report the ANCOVA estimate, confidence interval, tested margin, or detailed model specification. The reported p-value alone is not enough to reconstruct the magnitude or precision of the model-based result or to determine how the margin was applied.

The recalculated comparison uses the posted primary arm summaries and is an unadjusted mean-difference analysis. It estimates a difference of 1.9 letters, with a confidence interval from -0.040 to 3.84 and an unadjusted p-value of 0.055. This differs from the registry’s reported ANCOVA p-value and classification. The two analyses should not be presented as if they were the same test: the registry analysis is model-based and categorized as non-inferiority or equivalence, while the recalculation is a simpler comparison of summary statistics.

Because the record flags a discrepancy, the sponsor’s own analysis takes precedence when describing the formal trial result. The recalculation is a transparent check on the posted summaries, not a correction to the sponsor’s analysis. Without the sponsor’s estimate, interval, margin, and full analysis details, the reason for the discrepancy is not reported in the registry record and should not be guessed.

15. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary endpoint and a range of secondary outcomes. The secondary list includes repeated or related measures of visual acuity, such as change at month 12, average change over monthly assessments, and the numbers of patients crossing specified letter-change thresholds. It also includes scheduled visits and treatment frequency. When multiple outcomes are considered, an apparently unusual result can arise by chance even when no effect is present for any particular outcome. This is the general multiplicity problem.

The registry record does not report whether the trial used a multiplicity adjustment, a prespecified hierarchy among secondary outcomes, or a particular approach to controlling the overall error rate. Without that information, unadjusted secondary p-values should not be treated as if each were the sole planned test. The numerical secondary results can describe patterns, but the record does not establish which outcomes were confirmatory or how their interpretation was intended to relate to the primary endpoint.

Missing-data handling is relevant to the primary endpoint. The registry says the Full Analysis Set comprised patients assigned a regimen and that only those with both baseline and study-completion values after last observation carried forward were included in the analysis. It also states that last observation carried forward was used, but the description ends before giving a complete explanation. The rationale, implementation details, amount and pattern of missing data, and sensitivity analyses are not reported in the registry record.

Last observation carried forward is a general missing-data method in which an earlier observed value is carried forward to represent a later missing value. This approach can be problematic if the outcome would have changed after the last observation, because the carried-forward value may not represent the unobserved result. Its consequences depend on why data are missing and how outcomes change over time. The registry information does not allow assessment of those conditions for this study.

The record does not report details of the original sample-size justification, interim analyses, or the full statistical analysis plan. These omissions limit assessment of which comparisons were planned, how missing outcomes and multiple testing were addressed, and how the sponsor’s non-inferiority or equivalence analysis was specified.

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 1% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: pneumonia (1.2%), transient ischaemic attack (0.9%), myocardial infarction (0.6%), vertigo (0.6%), bronchitis (0.6%).

The registry reports serious adverse events among 39 of 323 participants in the treat-and-extend group and 42 of 326 participants in the monthly group. It lists pneumonia at 1.2%, transient ischaemic attack at 0.9%, and myocardial infarction, vertigo, bronchitis, and femur fracture each at 0.6% among the top serious terms. These figures describe reported events in the registry; they do not by themselves establish that an event was caused by the study treatment.

The other adverse-event counts are 164 of 323 for treat-and-extend and 166 of 326 for monthly dosing. The registry’s serious-event and other-event denominators differ from the primary endpoint analysis counts, so safety and efficacy summaries should be read using their own reported populations. Death counts are not reported in the registry record.

These summaries do not provide a complete comparison of safety. The record does not give event-specific group breakdowns for the listed serious terms, exposure-adjusted rates, severity distributions, or a causal assessment. A simple comparison of counts or percentages cannot account for follow-up exposure or other factors. The figures are descriptive registry data, not a basis for medical advice or a definitive judgment about relative safety.

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

The posted results show positive average change in visual-acuity letters in both groups. The simple unadjusted recalculation gives a monthly-minus-treat-and-extend difference of 1.9 letters, but its interval includes zero and spans values on both sides of no difference. This means the recalculated summary comparison is uncertain; it does not establish that the regimens are identical, nor does it establish a clinically important advantage for either schedule.

The registry’s formal primary analysis is reported as ANCOVA and classified as non-inferiority or equivalence, with p < 0.001. The sponsor’s own analysis takes precedence over the summary-based recalculation, but the registry does not report the model estimate, confidence interval, or margin. Those missing details prevent a complete assessment of the size and precision of the formal result. In particular, a non-inferiority or equivalence classification cannot be fully evaluated without the criterion against which the estimate was judged.

Neither a p-value nor a group average describes every participant’s outcome. The available continuous summaries do not show the number of participants who experienced a particular degree of improvement or loss. Although the registry lists threshold-based outcomes, their numeric results are not reported in the registry record. The scheduled-visit results describe visits, not patient benefit.

The results also do not establish how the findings would apply outside the study population or under different treatment schedules. The record describes the regimens up to month 11 and the primary measurement at month 12; longer-term outcomes are not reported in the registry record. Missing-data handling, the full statistical plan, and the non-inferiority or equivalence margin are insufficiently detailed for a complete independent reconstruction.

Overall, the results should be read as a comparison of recorded average visual-acuity changes and visit schedules in this randomized study, with a formal sponsor analysis that is not fully described in the registry record. They do not support personal treatment decisions, and they should not be reduced to a claim that one regimen works or does not work.

18. Why This Trial Matters Statistically

This study is statistically notable because the formal primary analysis and a simple recalculation from posted summaries do not give the same inferential picture. The registry’s ANCOVA analysis is classified as non-inferiority or equivalence and reports p < 0.001, while the unadjusted recalculation gives a mean difference of 1.9 letters, an interval that includes zero, and p = 0.055. Recognizing that these analyses address different specifications and possibly different hypotheses is essential; neither result should be substituted for the other.

The discrepancy highlights the value of reporting an effect estimate, confidence interval, model details, and the margin for non-inferiority or equivalence. A classification and p-value alone offer limited insight into the magnitude and precision of the treatment contrast. The missing ANCOVA estimate and margin make it difficult for readers to independently assess the sponsor’s formal result.

The study also illustrates why endpoint summaries need context. The primary outcome is a mean change, while the secondary outcomes include other visual-acuity summaries and scheduled visits. Those measures can illuminate different aspects of the comparison, but correlated endpoints and multiple testing reduce the force of unadjusted secondary findings. Clear reporting of endpoint hierarchy and multiplicity methods would help readers distinguish confirmatory evidence from supportive description.

Finally, the registry’s description of last observation carried forward brings attention to missing-data assumptions. The approach can affect estimated change, and interpretation depends on the pattern and reasons for missing measurements. Reporting the amount of missing data and sensitivity analyses would help assess robustness. These statistical reporting issues matter independently of the direction of the observed group averages.

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.

The registry record does not provide the sponsor’s ANCOVA estimate, confidence interval, model covariates, or non-inferiority or equivalence margin. This leaves the formal primary result difficult to evaluate beyond its classification and reported p-value. The unadjusted recalculation is based on summary statistics and cannot resolve that limitation or explain the discrepancy.

The primary endpoint analysis description indicates that only participants with baseline and study-completion values after last observation carried forward were included, but the explanation of this method is incomplete. The record does not report the amount or pattern of missing data, the reasons values were missing, or sensitivity analyses. These details would be needed to judge how missingness might affect estimated change.

The registry lists many related secondary endpoints but does not report a multiplicity strategy or endpoint hierarchy. Numeric results are not reported for all listed outcomes, including threshold-based visual-acuity measures. Consequently, the available secondary summaries cannot provide a complete picture of outcome patterns or establish which comparisons were intended to be confirmatory.

The primary summary-based pooled variability is approximate, and the recalculation is unadjusted. Neither can account for participant-level features unavailable in the registry summaries. The record also does not report the original sample-size justification, interim analyses, or full statistical plan. The safety summaries are descriptive and do not provide the exposure-adjusted or event-specific comparisons needed for a comprehensive safety assessment. These are limitations of what the registry record reports, not evidence that the omitted analyses were or were not performed.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Randomized Study for Efficacy and Safety of Ranibizumab 0.5mg in Treat-extend and Monthly Regimens in Patients With nAMD — NCT01948830.
• Registry record last updated 2017-04-17; status last verified 2017-03.
• Results first posted 2016-12-15.
• 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 describes a completed, randomized, parallel-group Phase 3b study comparing treat-and-extend with monthly ranibizumab 0.5 mg in patients with neovascular age-related macular degeneration. Its primary endpoint was change in best-corrected visual acuity from baseline to month 12, measured in ETDRS letters.

Posted group summaries show positive average visual-acuity changes in both groups. A simple unadjusted recalculation estimates a mean difference of 1.9 letters, with an interval that includes zero. The registry separately reports an ANCOVA analysis classified as non-inferiority or equivalence; its estimate, interval, and margin are not reported in the registry record, so the sponsor’s formal result cannot be fully reconstructed.

Secondary summaries include scheduled visits and additional visual-acuity measures, while numeric results for some listed outcomes are not reported. The record’s missing-data description is incomplete, and multiplicity methods and the original sample-size rationale are not reported. Interpretation should therefore distinguish the sponsor analysis from the summary-based recalculation and treat secondary and safety summaries as descriptive.