Safety and Efficacy Study of Bimatoprost, Latanoprost, and Travoprost in Patients With Elevated Intraocular Pressure (IOP) and Open-angle Glaucoma (OAG): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety and Efficacy Study of Bimatoprost, Latanoprost, and Travoprost in Patients With Elevated Intraocular Pressure (IOP) and Open-angle Glaucoma (OAG) (NCT00716742), a registered phase not stated study. The primary outcome is Change From Baseline in Bilateral Intraocular Pressure (IOP) at One Year.

2. Clinical Question

The registry describes a clinical-practice investigation of pressure-lowering therapies, rather than documenting a randomized assignment procedure. Its primary question is framed around change from baseline in eye pressure over follow-up. The reported outcome definition does not by itself establish whether a difference between treatment groups would be attributable to the treatments: treatment assignment, group comparability, and the statistical analysis would all matter to that interpretation.

3. Trial Design

The study is listed as completed, with enrollment of 1099. The registry gives a start date of 2004-09 and a primary completion date of 2007-09. Allergan is listed as sponsor. The brief summary says the aim was to investigate the effectiveness of newer intraocular-pressure-lowering therapies as prescribed in normal clinical practice, in larger patient numbers. It describes assessments at baseline, at follow-up visits whose timing was at physician discretion, and at a final follow-up visit.

The record lists bimatoprost 0.03%, latanoprost 0.005%, and travoprost 0.004% as the drug intervention. The adverse-event groups are identified by the product names Lumigan®, Travatan®, and Xalatan®. However, the record does not describe how patients were allocated to treatment, and allocation is not stated. It should not be read as a randomized trial or as establishing that the treatment groups were comparable at the outset. The record itself cautions that these are not like-for-like control groups.

The single listed primary outcome is a continuous measure: change from baseline in bilateral intraocular pressure at one year. The record describes bilateral pressure as the average of both eyes’ measurements. The primary analysis population is described as patients who started the study, completed the one-year follow-up visit, and had data available for this outcome. Although the population is labeled intent-to-treat, the stated eligibility requirements exclude people without one-year completion or available outcome data.

The registry lists one outcome measure and zero analyses. It does not report group-specific outcome estimates, variability values, confidence intervals, or a statistical test. It also does not report the treatment-allocation procedure, visit schedules beyond physician discretion, or the planned statistical analysis. These gaps limit what can be concluded about the relative outcomes of the treatment groups from 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.

Baseline

1 Year Follow-up

2 Year Follow-up

3 Year Follow-up

Analysis population for the primary outcome, as defined in the registry: Intent-to-treat, which includes all patients who started the study and completed the one-year follow-up visit and whose data was available for this outcome measure.

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 From Baseline in Bilateral Intraocular Pressure (IOP) at One Year, measured over Baseline, 1 Year.

The primary endpoint is change from baseline in bilateral intraocular pressure at the one-year follow-up visit. Pressure is measured in millimeters of mercury. The registry defines bilateral pressure as the average of the pressure measurements from both eyes, and it states that a negative change indicates a reduction in pressure.

As a continuous outcome, this measure can describe the amount of change rather than merely whether a threshold was crossed. Reporting a mean can communicate the average change in the analyzed population, while a standard deviation describes how spread out individual changes are around that mean. Those summaries would be needed to understand both the average pattern and variability. The registry identifies the mean and standard deviation as the outcome’s summary and dispersion types, but does not report their numerical values.

General: measuring change from baseline can account descriptively for where participants began, making the endpoint about change over follow-up rather than a final measurement alone. Bilateral averaging produces one value representing both eyes under the registry’s stated definition. That simplification also means the endpoint does not separately describe changes in each eye or the range of responses among patients.

The endpoint is defined at one year, but the record does not report the observed mean change, its standard deviation, or a confidence interval. It therefore does not permit a reader to assess the magnitude or precision of the recorded outcome. Nor does an endpoint definition alone establish the clinical importance of any particular amount of change.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies the primary measure as continuous and names the mean as its summary statistic and the standard deviation as its measure of dispersion. It gives no numerical values for either. The record also lists zero analyses, so there is no posted inferential result for the primary endpoint to explain. The following concepts are general and describe how such methods are commonly interpreted; they are not claims about analyses performed in this study.

What does a mean change describe?

For a continuous outcome, a mean summarizes the average value in the analyzed group. Here the outcome is each patient’s change in bilateral intraocular pressure from baseline to one year. The registry defines bilateral pressure as the average of measurements from both eyes. A group mean change would describe the average change among those included in that group’s analysis. It would not show whether every participant changed by a similar amount, nor would it describe the full distribution of individual outcomes.

The sign convention is specified in the outcome description: a negative change indicates a reduction in pressure. That direction can guide reading of a reported estimate, but the registry gives no estimate to interpret. It also does not report the standard deviation. A standard deviation describes the spread of values around the mean; it is not the uncertainty of the mean itself. The latter is typically conveyed by a standard error or confidence interval, neither of which is reported for this endpoint.

What would a treatment contrast mean?

General: comparing group means can estimate a difference in average outcome between groups. Such a contrast is meaningful as a treatment effect only when the design and analysis support that interpretation. Random assignment can help balance measured and unmeasured characteristics on average, while observational treatment allocation can leave groups different in ways that also affect outcome. In this record, allocation is not stated, and the record cautions that the arms are not a like-for-like control comparison. No adjusted or unadjusted contrast is reported.

General: adjustment can account for measured baseline factors included in an analysis, but it cannot automatically remove bias from unmeasured factors or poorly measured variables. The registry does not report which covariates, if any, were considered. It also does not give enough analysis detail to determine whether the primary result, if calculated, would have been based on raw changes, a model, or another approach.

How should uncertainty be assessed?

General: a confidence interval describes statistical uncertainty around an estimate, conditional on the analysis assumptions. Its width reflects both the amount of information and the variability in the data. An interval that includes values on both sides of no difference can be compatible with a range of effects; an interval that excludes no difference does not, by itself, establish that an effect is important to patients. The registry does not report a confidence interval or a test for the primary outcome, so neither precision nor statistical evidence for a group difference can be judged.

General: a p-value measures how unusual data at least as incompatible with a specified null hypothesis would be under the statistical model, assuming that model and hypothesis are appropriate. It does not measure the probability that the null hypothesis is true, and it does not express the size or clinical relevance of an effect. No p-value for the primary endpoint is reported in the registry record.

What do the planning assumptions describe?

The record describes a sample-size planning illustration based on an observed effect, with a two-sided significance level of 0.05, equal allocation between 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 that the trial was designed or conducted under those assumptions. The actual design justification and planned sample-size calculation are not reported in the registry record. No numerical planning outputs appear in the registry record for this analysis.

General: sample-size calculations estimate how many participants an imagined future study might need to detect a specified effect under chosen assumptions. They are not observed power and do not establish what the completed study found. An illustration based on an observed effect also depends on that effect estimate, which may itself be uncertain. The planning assumptions should therefore be understood as hypothetical inputs rather than an account of the trial’s original protocol.

General: normal approximations can be used to simplify calculations for a continuous outcome, but their suitability depends on the data and design. Equal allocation is a planning choice and does not show that the enrolled groups were equal in size. The registry’s sample-size description refers to two-arm planning, whereas the adverse-event information lists three named groups. The record does not explain that distinction or identify a trial-level calculation based on the actual group structure.

Why do visit timing and outcome availability matter?

The brief summary says follow-up visits were variable according to physician discretion, while the primary endpoint is defined at the one-year follow-up visit. General: when assessment timing varies, the analysis needs a clear rule for which measurements represent the target visit and how timing differences are handled. The registry does not describe such a rule. It also does not report the number of participants with an available one-year measurement, or how incomplete follow-up was addressed.

General: statistical methods are interpretable only in relation to their target population, assumptions, and missing-data handling. The stated primary population requires both completion of one-year follow-up and available data for the measure. That condition means the endpoint population is defined partly by post-baseline events. Without participant-flow information or a missing-data analysis, it is not possible to assess whether the analyzed group represents all people who started the study. No method details resolving these questions are reported in the registry record.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists one outcome measure and zero analyses. It identifies a primary endpoint, but does not provide a statistical analysis plan, a list of planned hypotheses, or an account of any interim analyses. Those details are not reported in the registry record. In particular, it is not possible to determine whether other outcomes or subgroup analyses were planned or whether any adjustment for multiple testing was intended.

General: when several hypotheses are tested, the chance of at least one false-positive finding can increase if each test is treated independently at the same threshold. A prespecified testing strategy or multiplicity adjustment can address that issue. This general concern should not be taken as evidence that multiple testing occurred in this study; the relevant plan is not reported.

The primary outcome population is described as patients who started the study, completed the one-year follow-up visit, and had data available. Thus, despite the registry’s intent-to-treat label, the stated population excludes those without one-year completion or an available outcome value. The number of patients meeting the definition is not reported in the registry record. Nor does the record describe participant flow by treatment group, reasons for missing follow-up, or a method for handling missing measurements.

General: excluding participants with missing outcomes can lead to bias if missingness is related to prognosis, treatment, or the unobserved outcome. Alternative methods may make different assumptions about missingness, but no such method is identified in the record. Without the amount and pattern of missing data and the analysis approach, the robustness of the endpoint estimate cannot be evaluated. The record also does not report whether sensitivity analyses were conducted.

11. Safety Results

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

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

Most frequent serious adverse event terms

Serious events with the highest arm-level rate: death (1.6%).

The registry reports serious adverse events in each of the three named product groups. Lumigan® lists 5 affected among 364 at risk; Travatan® lists 2 among 370; and Xalatan® lists 6 among 365. These are group-specific registry counts, not a randomized comparative estimate. Allocation is not stated, and the record cautions that the groups are not like-for-like controls. The counts alone therefore do not establish that one treatment caused more or fewer serious events than another.

The record lists zero affected by other adverse events in each group. Its top serious-event term is Death, reported as 1.6%, but the registry does not assign that term to a particular group in the information available. The deaths field for each group is not reported in the registry record. The term and percentage should not be treated as a group-specific death count or as a complete account of mortality.

General: an affected-participant count is different from a count of event episodes; one person may experience more than one event. The registry’s safety summaries should therefore be read according to the reported measure and not assumed to represent every event occurrence. The record does not provide event definitions, follow-up duration for the safety summaries, or details about how events were collected. These omissions limit interpretation and comparison.

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

The registry record establishes that the study was completed, enrolled 1099 patients, and listed a one-year change in bilateral intraocular pressure as its primary outcome. It also describes the population intended for that outcome and provides serious adverse-event counts for three named product groups. These registry entries describe the registered study and its posted information; they do not reveal the primary endpoint result.

The record does not report the mean change in pressure, the standard deviation, a between-group contrast, a confidence interval, or a p-value. As a result, the direction and magnitude of the observed primary outcome cannot be determined from the registry information. The record also does not report how many patients contributed endpoint data, so the size and composition of the analyzed population cannot be assessed.

Even if numerical differences between the named groups were available, their interpretation would depend on how treatment was selected, how baseline differences were handled, and how missing follow-up was addressed. Allocation is not stated, and the registry explicitly cautions that the arms are not a like-for-like control comparison. The posted safety counts likewise do not establish comparative safety, especially without a reported allocation method, detailed event definitions, and group-specific information for the listed serious-event term.

General: statistical significance, if reported, would not alone show that a difference is clinically meaningful. Precision, the size of an estimate, the design, and the outcome’s relevance all matter. Here, the primary numerical estimate and its uncertainty are not reported, so even those basic dimensions cannot be evaluated. The absence of a result in the registry record should not be interpreted as evidence that there was no change or no difference.

The appropriate reading is therefore limited: the registry describes a clinical-practice investigation and its planned primary measure, but does not provide the results needed to judge the measured change or compare treatments. The result, analysis details, and missing-data approach are not reported in the registry record.

13. Why This Trial Matters Statistically

This study illustrates why a registered outcome definition and a reported outcome result are different kinds of information. The record clearly defines a continuous endpoint, its unit, its time point, and the direction of change interpreted as a reduction in pressure. Those details help specify what the investigators intended to measure. But without the mean change, variability, and uncertainty, readers cannot assess the observed outcome or its precision.

It also highlights the importance of design information for comparative inference. The registry describes treatment use in normal clinical practice, and allocation is not stated. It cautions that the arms are not like-for-like controls. In such a setting, treatment groups may differ for reasons that affect the outcome. A comparison between groups requires careful consideration of allocation, baseline characteristics, follow-up, and analysis; group labels and enrollment alone do not establish a causal contrast.

The endpoint population definition also matters. The registry calls the population intent-to-treat while specifying that participants must have started the study, completed one-year follow-up, and had available outcome data. Reporting how many participants met those conditions and how missing measurements were handled would be important for understanding the analysis population and possible selection effects.

Finally, safety counts are most informative when their definitions, exposure period, and group context are clear. The posted figures describe affected participants in named groups, but do not support a like-for-like safety comparison. Together, these features show why statistical interpretation depends not only on the chosen measure, but also on transparent reporting of results, design, uncertainty, and analysis decisions. Several of those details are not reported in the registry record.

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 most important limitation for interpreting the primary outcome is that its numerical result is not reported in the registry record. The record gives the endpoint definition and identifies the mean and standard deviation as the intended summary, but supplies no group-specific estimates, uncertainty measures, or statistical tests. It therefore does not support an assessment of the size, direction, or precision of change.

The registry does not state how patients were allocated to treatment. It also cautions that the groups are not like-for-like controls. This prevents a straightforward causal interpretation of any potential between-group difference. The record does not describe baseline characteristics or an adjustment strategy that could help assess group comparability.

Follow-up visits are described as variable at physician discretion, while the primary outcome is defined at one year. The record does not explain how visit timing was handled, how many participants completed follow-up, or how missing measurements were addressed. The outcome population requires completion and available data, but its size is not reported.

The registry identifies one outcome measure and zero analyses, but does not report a statistical analysis plan, multiplicity strategy, interim analyses, or subgroup methods. The listed sample-size assumptions are described as planning illustrations based on an observed effect; the trial’s own design justification is not reported. The numerical planning outputs are not reported in the registry record.

For safety, affected counts are posted by named group, but the record does not explain event definitions or provide enough context to establish comparative safety. The serious-event term Death is reported as 1.6%, while group-specific death counts are not reported in the registry record. These limitations restrict interpretation to the registry’s descriptive information.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Safety and Efficacy Study of Bimatoprost, Latanoprost, and Travoprost in Patients With Elevated Intraocular Pressure (IOP) and Open-angle Glaucoma (OAG) — NCT00716742.
• Registry record last updated 2012-01-06; status last verified 2011-11.
• Results first posted 2012-01-06.
• 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

NCT00716742 is listed as a completed study sponsored by Allergan, with enrollment of 1099. Its stated purpose was to investigate newer intraocular-pressure-lowering therapies as prescribed in normal clinical practice. Follow-up timing was described as variable according to physician discretion.

The primary outcome is change from baseline in bilateral intraocular pressure at one year, measured in millimeters of mercury. The record defines bilateral pressure as the average from both eyes and notes that a negative change indicates a reduction. The stated outcome population includes patients who started the study, completed one-year follow-up, and had data available.

The record lists bimatoprost 0.03%, latanoprost 0.005%, and travoprost 0.004%, and gives adverse-event counts for Lumigan®, Travatan®, and Xalatan®. Allocation is not stated, and the groups are not described as like-for-like controls. The primary outcome’s numerical results, statistical analysis, and missing-data methods are not reported in the registry record.