MK0507A Clinical Study in Patients With Glaucoma and Ocular Hypertension (0507A-149)(COMPLETED): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for MK0507A Clinical Study in Patients With Glaucoma and Ocular Hypertension (0507A-149)(COMPLETED) (NCT00449956), a randomized phase 3 study. The primary outcome is Change in Intraocular Pressure (IOP) From Baseline at 8 Weeks.

2. Clinical Question

3. Trial Design

The registry describes a Phase 3, randomized, double-blind, parallel-group, active-comparator-controlled study. It was conducted in patients with glaucoma and ocular hypertension who were inadequately controlled on beta-blockers. Enrollment was 474, and the registry status is completed. The listed study dates are 2007-03-12 for study start and 2008-02-16 for primary completion.

Three arms appear in the record: MK0507A, a fixed combination of dorzolamide 1.0% and timolol 0.5%; timolol 0.5%; and concomitant use of dorzolamide 1.0% and timolol 0.5%. The record gives endpoint-analysis counts of 185, 90, and 188, respectively. It does not explain the allocation ratio or the relationship between the enrollment total and the analysis counts.

The primary outcome was change in intraocular pressure from baseline at 8 weeks. It was assessed 2 hours after ocular instillation, at Hour 2. The analysis population is described as the Full Analysis Set, using the last observed value during the 8-week treatment period. The registry also lists two secondary outcomes: percent change from baseline in intraocular pressure and percent change from baseline in outflow pressure reduction rate, both at 8 weeks.

Although the design is described as double-blind and randomized, further implementation details are not reported in the registry record. The randomization sequence, concealment procedures, specific masking arrangements, treatment administration schedule, and protocol deviations are not reported in the registry record. The registry gives no sample-size justification.

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: Outpatients with primary open angle glaucoma (broad definition) and/or ocular hypertension received 4-week timolol 0.5% monotherapy in the wash-out period before the study randomization.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Last observed value during the 8-week treatment period was used in the Full Analysis Set (FAS).

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 Intraocular Pressure (IOP) From Baseline at 8 Weeks, measured over 8 weeks.

The primary endpoint is change in intraocular pressure (IOP) from baseline to 8 weeks, measured in mmHg. The assessment was made 2 hours after ocular instillation. The registry reports least-squares means for the arm-level changes and 95% confidence intervals. A negative change indicates that the measured IOP was lower at the endpoint than at baseline; the clinical implications of a particular change are not established by the statistic alone.

IOP is the measured outcome chosen for this study of patients with glaucoma and ocular hypertension. A baseline-to-follow-up change expresses how the measurement shifted over the treatment period, rather than reporting only the endpoint value. The fixed assessment time after instillation also defines when the pressure measurement was taken. Results from that time point should not be treated as measurements at other times or as a summary of every possible change during the 8-week period.

The analysis used the last observed value during the treatment period in the Full Analysis Set. Thus, the endpoint reflects the registry's stated handling of follow-up values, not necessarily a measurement available for every participant at exactly 8 weeks. The record does not describe additional rules for missing endpoint values, the baseline definition, or any covariate adjustment used to obtain the least-squares means.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is continuous: it is a measurement of change in IOP expressed in mmHg. The registry reports least-squares means, which are model-based estimates of group means. General statistical explanation: least-squares means can account for variables included in a statistical model, but the variables and model specification are not reported in the registry record. They should not automatically be interpreted as simple averages of the observed participant values.

The arm estimates are -2.5 for MK0507A, -1.82 for timolol, and -2.78 for concomitant use. Each has a 95% confidence interval. General statistical explanation: a confidence interval reflects the sampling uncertainty of an estimate under the analysis model. A narrower interval indicates greater precision than a wider interval, but precision is not the same as clinical importance. The arm intervals overlap to some extent; overlap or non-overlap of separate arm intervals is not, by itself, the formal test of a between-arm contrast. The registry's contrast estimates and their own intervals are more directly relevant to comparisons.

The registry reports two pairwise analyses. For MK0507A versus timolol, the posted mean difference (final values) is -0.68, with a 95% confidence interval from -1.30 to -0.06. For MK0507A versus concomitant use, the reported difference is 0.28, with a 95% confidence interval from -0.22 to 0.78. The specific definition and direction convention for “Mean Difference (Final Values)” are not explained in the registry record. The endpoint itself is described as change from baseline, so the contrast label should not be treated as a fully specified model description.

General statistical explanation: for a contrast, zero represents no difference under the contrast's definition. The interval for the comparison with timolol lies below zero; the interval for the comparison with concomitant use includes zero. These observations describe the posted intervals, not a complete account of the analysis. The registry gives no p-values, test statistics, degrees of freedom, or named model. It does not report whether the confidence intervals and tests account for site, baseline IOP, or other covariates.

The comparison with concomitant use is categorized in the registry as non-inferiority or equivalence. These are distinct statistical questions from simply testing whether a difference equals zero. A non-inferiority analysis generally evaluates whether the intervention is not worse than a comparator by more than a prespecified margin; an equivalence analysis generally evaluates whether the difference lies within prespecified bounds. This is general statistical explanation. The margin or bounds, hypotheses, confidence-interval decision rule, and analysis method are not reported in the registry record. The posted interval by itself does not establish either conclusion.

The record describes a Full Analysis Set and says the last observed value during the 8-week treatment period was used. General statistical explanation: using the last observed value can retain a measurement for a participant without an endpoint observation at the planned time, but it assumes that the selected value is an appropriate representation of the endpoint for the analysis. The registry does not report how many values were missing, when the last observations occurred, or whether other missing-data methods were used. It also does not report a separate per-protocol analysis.

There are three arms and two reported pairwise analyses. The record notes that values were missing or not estimable for a two-arm comparison of the continuous endpoint, but does not identify the affected pair or explain why estimates were unavailable. That omitted comparison cannot be reconstructed from the posted information.

Multiplicity concerns arise when several outcomes, comparisons, or analyses are examined. General statistical explanation: considering multiple tests can increase the chance of at least one apparently positive result unless the analysis plan addresses that issue. Two secondary outcomes and two pairwise primary-outcome analyses are listed, but any multiplicity adjustment, testing hierarchy, or prespecified primary contrast is not reported in the registry record. No interim analyses or stopping rules are reported in the registry record.

The registry's sample-size assumptions describe a planning illustration based on the observed effect, with a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is described as a stated fraction of the observed effect. These are planning assumptions, not evidence of the trial's original design rationale or observed power. The trial's own sample-size justification is not reported in the registry record. No numerical planning results are stated in the record summary used for this interpretation.

10. Analyses Reported by the Sponsor

The registry posts sponsor-reported arm estimates and two comparison estimates. The MK0507A versus timolol mean difference (final values) is -0.68, with a 95% confidence interval from -1.30 to -0.06. The MK0507A versus concomitant-use difference is 0.28, with a 95% confidence interval from -0.22 to 0.78. No p-values or analysis methods accompany these comparisons in the registry record.

There is no reported discrepancy between the sponsor's analyses and a recalculation, so there is no conflicting estimate to resolve. Where a discrepancy is flagged, the sponsor's own analysis takes precedence; that condition does not apply to this record. The reported comparisons should therefore be read as the registry's analysis results rather than replaced by an alternative calculation.

The entries do not provide enough detail to reproduce the sponsor's analysis. The registry does not report the statistical model, contrast coding, covariate adjustment, handling of missing data beyond use of the last observed value, or the decision criteria for the analysis categorized as non-inferiority or equivalence. The estimate and confidence interval can be described as posted, but the registry record does not permit a full audit of how they were generated.

11. Multiplicity, Missing Data and Analysis Populations

The primary endpoint population is identified as the Full Analysis Set, and the registry states that the last observed value during the 8-week treatment period was used. This describes the stated endpoint-value approach, but it does not fully define the analysis population or missing-data procedure. The registry does not report the criteria for inclusion in the Full Analysis Set, the number of participants with missing endpoint data, or the timing of last observations.

Using the last observed value is one way of assigning an endpoint value when the planned measurement is unavailable. General statistical explanation: this approach can be sensitive to when a participant's last measurement occurred and to whether the clinical measure would have changed afterward. The record does not report sensitivity analyses, alternative imputation methods, or assumptions about why values might be missing. A separate per-protocol population and its results are not reported in the registry record.

Multiplicity is also relevant because the record lists two secondary outcomes and two analyses of the primary outcome. No adjustment for multiple comparisons, testing sequence, or control of the overall type I error rate is reported in the registry record. The registry does not report whether one contrast was designated as the primary comparison or whether secondary outcomes were considered confirmatory or exploratory.

The record identifies one comparison as non-inferiority or equivalence, but the margin and decision rule are not reported. Without these details, the intended inferential standard cannot be assessed from the label alone. The method used to calculate confidence intervals, the model underlying the least-squares means, and any interim analyses are also not reported in the registry record.

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

The posted endpoint estimates describe changes in IOP over the stated treatment period and at the stated assessment time. The arm-level least-squares mean changes are negative for all three groups. The interval for the reported MK0507A versus timolol contrast lies below zero, while the interval for MK0507A versus concomitant use includes zero. These are descriptions of the estimates and their uncertainty, not conclusions about clinical benefit.

The results do not show how an individual participant's pressure changed, whether changes persisted beyond 8 weeks, or how outcomes varied at other measurement times. The registry reports an assessment 2 hours after ocular instillation; it does not establish that the estimates represent other times in the dosing period. It also does not report a threshold that would define a clinically meaningful change.

The registry's non-inferiority-or-equivalence label does not establish either finding by itself. A non-inferiority margin or equivalence bounds and an analysis decision rule are not reported in the registry record. Likewise, the absence of a p-value and named statistical method limits assessment of the inferential details for the posted comparisons.

The adverse-event entries are counts, not rates, because the numbers at risk are not reported. The record also does not provide death counts. Event definitions, observation duration for adverse events, and complete event-specific comparisons are not available in the posted information. Consequently, the counts should not be used to rank the study arms for safety.

Overall, the registry record describes endpoint estimates and selected contrasts from a randomized, double-blind study, but it does not provide all elements needed to judge clinical importance, reproduce the analysis, or assess the prespecified inferential framework. The findings should be interpreted within the studied population, assessment timing, and 8-week period.

13. Why This Trial Matters Statistically

This trial is statistically informative because it includes three active study arms and reports both arm-level continuous-outcome estimates and pairwise contrasts. The distinction matters: an arm estimate describes change within a group, while a contrast estimates the difference between groups under the registry's stated comparison. The confidence intervals around the contrasts convey information that cannot be inferred reliably from comparing arm estimates alone.

The endpoint is measured at a defined time, 2 hours after ocular instillation, and the analysis uses the last observed value during the 8-week treatment period in the Full Analysis Set. Those choices define what the estimate represents. They also raise questions about missing follow-up and the timing of observations, details that are not fully reported in the registry record.

The record illustrates why an analysis label should not substitute for its statistical specification. A comparison called non-inferiority or equivalence requires a margin and decision rule to interpret. Neither is reported. Similarly, confidence intervals and arm means are useful, but incomplete information about the model, multiplicity, and missing-data handling limits reproducibility and the strength of conclusions that can be drawn from the registry entry.

The study also demonstrates the limits of posted safety counts without denominators. Counts across arms do not directly convey comparative event rates when the numbers at risk are unavailable. This is a statistical limitation, not evidence that an event pattern is or is not important.

14. 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 gives no detailed statistical analysis plan, named model, covariate list, contrast definition, or method for calculating the reported confidence intervals. The difference label refers to final values even though the primary endpoint is described as change from baseline; the relationship between those descriptions is not explained. The analysis cannot be reproduced fully from the posted details.

The Full Analysis Set is named, and last observed values are described, but inclusion criteria, missing-data counts, observation timing, and sensitivity analyses are not reported in the registry record. The record also does not identify the two-arm continuous-endpoint comparison for which values were missing or not estimable.

The interpretation of the comparison labeled non-inferiority or equivalence is limited by the absence of a margin, decision rule, and analysis method. Any adjustment for multiple outcomes or comparisons is not reported. The trial's sample-size justification is not reported in the registry record, and the stated planning assumptions should not be mistaken for the original design rationale or observed power.

For safety, at-risk denominators and death counts are not reported. The registry lists selected serious-event terms, but does not provide enough context in these entries to assess comparative event rates. The record also does not report longer-term follow-up for the primary endpoint, or outcomes beyond the stated 8-week period.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: MK0507A Clinical Study in Patients With Glaucoma and Ocular Hypertension (0507A-149)(COMPLETED) — NCT00449956.
• Registry record last updated 2017-06-20; status last verified 2017-05.
• Results first posted 2009-05-29.
• 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.

18. Record Summary

This completed Phase 3 study randomized 474 patients with glaucoma and ocular hypertension who were inadequately controlled on beta-blockers to MK0507A, timolol 0.5%, or concomitant dorzolamide 1.0% and timolol 0.5%. It was described as double-blind, parallel-group, and active-comparator-controlled.

The primary endpoint was change in IOP from baseline at 8 weeks, assessed 2 hours after ocular instillation. The registry reports least-squares mean changes and two pairwise comparison estimates with 95% confidence intervals. It also identifies two secondary outcomes. Key analysis details—including the model, multiplicity approach, and non-inferiority or equivalence criteria—are not reported in the registry record.

Safety entries provide event counts, but at-risk denominators and death counts are not reported. The posted information supports a description of the estimates and their precision, while leaving important questions about analysis reproducibility and comparative safety unresolved.