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 to Evaluate the Safety, Tolerability, and Efficacy of the Addition of Omarigliptin (MK-3102) to Participants With Type 2 Diabetes Mellitus Who Have Inadequate Glycemic Control on Metformin Therapy (MK-3102-024) (NCT01755156), a randomized phase 3 study. The primary outcome is Change From Baseline in Glycosylated Hemoglobin (A1C) at Week 24 (Phase A).
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT01755156 |
| Phase | Phase 3 |
| Condition | Type 2 Diabetes Mellitus |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Triple |
| Enrollment | 402 |
| Arms in the primary outcome | 2 |
| Lead sponsor | Merck Sharp & Dohme LLC |
| Results posted | Yes |
2. Clinical Question
Population
Participants had type 2 diabetes mellitus and inadequate glycemic control on metformin therapy. The primary analysis population included randomized participants who received at least 1 dose of study medication and had a baseline measurement or a post-randomization measurement. The registry record lists enrollment of 402 participants.
Intervention
In Phase A, participants assigned to omarigliptin received 25 mg orally once weekly for 24 weeks. The trial assessed adding omarigliptin to the participants’ metformin therapy. The record also describes treatment assignments for a longer Phase B, but the primary question concerns the Phase A comparison.
Comparator
The comparator was matching placebo to omarigliptin, administered orally once weekly during Phase A. The randomized comparison therefore estimates the difference between assignment to omarigliptin and assignment to placebo in the study population, against the background of metformin therapy.
Primary question
At Week 24, what was the difference between groups in change from baseline in A1C? A1C is a continuous measure reported as a percent. The primary hypothesis stated that adding omarigliptin would produce a greater reduction in A1C than placebo. The registry reports a cLDA estimate of the between-group difference and its 95% confidence interval.
This question is specifically about the randomized Phase A treatment contrast and the prespecified Week 24 A1C endpoint. It does not by itself answer whether results apply to other populations, treatment durations, or comparisons. The registry lists other interventions and a Phase B, including omarigliptin continuation and glimepiride assignments, but those are not the comparator for the primary Phase A result.
3. Trial Design
The registry describes a Phase 3, randomized, parallel-group trial with enrollment of 402 participants and a completed status. The official title describes the study as multicenter and double-blind; the registry’s masking classification is triple. Both descriptions indicate that masking was part of the design, though the specific identities of all masked parties are not reported in the registry record.
The primary comparison was between omarigliptin and matching placebo during Phase A. Each primary arm had 201 participants in the reported endpoint analysis. The omarigliptin regimen was 25 mg orally once weekly for 24 weeks, while the comparator received matching placebo orally once weekly. Participants were studied in the setting of inadequate glycemic control on metformin therapy.
The registry also describes a Phase B lasting 80 weeks. The listed continuation assignment included omarigliptin with matching placebo to glimepiride, while the other described assignment included glimepiride, titrated from 1 or 2 mg up to 6 mg daily, with matching placebo to omarigliptin. Pre-study metformin continuation is mentioned in the arm descriptions, though the wording in the registry record is incomplete. The primary endpoint is measured at Week 24, so the longer-phase assignments do not define the primary contrast.
The record lists a start date of 2013-01-11 and a primary completion date of 2016-03-16. It reports 19 outcome measures and 11 analyses. The complete protocol, detailed allocation procedures, sample-size justification, and statistical analysis plan are not reported in the registry record. These omissions limit what can be concluded about design decisions beyond the features explicitly recorded.
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.
Phase A (Weeks 0-24)
| Stage | Omarigliptin (Phase A) → Omarigliptin (Phase B) | Placebo to Omarigliptin (Phase A) → Glimepiride (Phase B) |
|---|---|---|
| STARTED | 201 | 201 |
| COMPLETED | 184 | 177 |
| NOT COMPLETED | 17 | 24 |
Reasons for not completing this period:
| Reason | Omarigliptin (Phase A) → Omarigliptin (Phase B) | Placebo to Omarigliptin (Phase A) → Glimepiride (Phase B) |
|---|---|---|
| Adverse Event | 2 | 3 |
| Lack of Efficacy | 1 | 0 |
| Lost to Follow-up | 5 | 3 |
| Non-compliance with study drug | 1 | 0 |
| Physician Decision | 0 | 1 |
| Protocol Violation | 1 | 1 |
| Withdrawal by Subject | 6 | 13 |
| Creatinine or eGFR Discon. Criteria | 0 | 2 |
| Need for Excluded Med. Discon. Criteria | 1 | 1 |
Phase B (Weeks 24-104)
| Stage | Omarigliptin (Phase A) → Omarigliptin (Phase B) | Placebo to Omarigliptin (Phase A) → Glimepiride (Phase B) |
|---|---|---|
| STARTED | 183 | 177 |
| COMPLETED | 144 | 141 |
| NOT COMPLETED | 39 | 36 |
Reasons for not completing this period:
| Reason | Omarigliptin (Phase A) → Omarigliptin (Phase B) | Placebo to Omarigliptin (Phase A) → Glimepiride (Phase B) |
|---|---|---|
| Lost to Follow-up | 12 | 5 |
| Withdrawal by Subject | 27 | 31 |
Analysis population for the primary outcome, as defined in the registry: Full analysis set population included all randomized participants who received at least 1 dose of study medication and had a baseline measurement or a post-randomization measurement.
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.
| Characteristic | Unit | Omarigliptin (Phase A) | Placebo to Omarigliptin (Phase A) | Total |
|---|---|---|---|---|
| Participants analysed | 201 | 201 | 402 | |
| Age, Continuous | Years | 57.5 (SD 8.1) | 56.8 (SD 9.1) | 57.2 (SD 8.6) |
| Sex: Female, Male: Female | Participants | 100 | 99 | 199 |
| Sex: Female, Male: Male | Participants | 101 | 102 | 203 |
| Hemoglobin A1C (A1C) | Percent | 8.06 (SD 0.87) | 8.02 (SD 0.89) | 8.04 (SD 0.88) |
| 2-hour post-meal glucose (2-hr PMG) | mg/dL | 240.2 (SD 60.5) | 236.0 (SD 59.9) | 238.1 (SD 60.2) |
| Fasting plasma glucose (FPG) | mg/dL | 168.8 (SD 37.6) | 168.6 (SD 37.2) | 168.7 (SD 37.4) |
6. Primary Endpoint
The registry lists the primary outcome as Change From Baseline in Glycosylated Hemoglobin (A1C) at Week 24 (Phase A), measured over Baseline and Week 24.
| Element | Registry entry |
|---|---|
| Result type | Least Squares Mean |
| Measure of spread | 95% Confidence Interval |
| Unit | Percent |
| Endpoint classification | Continuous Endpoint |
The primary endpoint is change from baseline in glycosylated hemoglobin, or A1C, at Week 24 in Phase A. A1C is measured as a percent and reflects glycemic status over time; it is commonly used in diabetes trials because it provides a continuous outcome that can capture changes across the range of observed values, rather than reducing the result to whether a participant did or did not cross a threshold.
Change from baseline focuses on how the endpoint differs from the participant’s starting measurement. The registry specifies a constrained longitudinal data analysis, or cLDA, with the same baseline mean constrained across treatment groups. The model included treatment, time, and the interaction between time and treatment. The reported treatment contrast is a difference in least squares means at the endpoint, with a 95% confidence interval.
For interpretation, the direction of the difference matters: a more negative change represents a larger reduction in A1C. The primary hypothesis asked whether the addition of omarigliptin produced a greater reduction than placebo after 24 weeks. This endpoint addresses the average modeled change in the analysis population, not the result for every participant, and it does not alone describe safety or longer-term outcomes.
As a general statistical point, a continuous endpoint can retain information that would be lost by classifying participants only according to whether they meet a target. Secondary target-attainment outcomes can still be useful, but their results answer different questions and depend on the chosen threshold.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The reported Phase A least-squares mean change in A1C was -0.54 for omarigliptin, with a 95% confidence interval from -0.69 to -0.4. For placebo, the reported change was 0.0, with a 95% confidence interval from -0.14 to 0.15. The reported cLDA difference in least-squares means was -0.55, with a 95% confidence interval from -0.75 to -0.34 and p < 0.001.
The negative between-group estimate means that the modeled change was more negative in the omarigliptin group than in the placebo group. The confidence interval is entirely below zero, and the reported p-value is small under the null hypothesis of no between-group difference, using the stated analysis. These findings support a difference in the primary endpoint in the direction specified by the primary hypothesis. They do not establish the effect for every individual participant.
A confidence interval describes a range of values compatible with the data and the analysis assumptions; it is not a range containing a known proportion of individual responses. Its width conveys uncertainty about the estimated average contrast. The interval does not include zero, but it still allows a range of possible magnitudes for the difference. Statistical significance should therefore be read together with the estimate and interval, rather than as a complete account of the result.
The secondary outcomes offer a broader but less definitive view. Among the posted numeric comparisons, attainment of the A1C target below 7.0% showed a reported between-group difference, while the stricter below 6.5% target did not show clear evidence of a difference in the sponsor’s analysis. The reported comparison for requiring glycemic rescue therapy also did not show clear evidence of a difference. These endpoints are related to glycemic control but use distinct definitions and analysis methods; they do not replace the primary continuous endpoint.
The registry reports adverse-event counts for Phase A and for the longer Phase A plus Phase B assignments. These counts describe events recorded in each group; they do not establish that a treatment caused an event or provide a complete comparative safety assessment. The registry record does not report deaths in the listed adverse-event data. Interpretation of safety also depends on event definitions, exposure time, ascertainment, and details that are not reported in the registry record.
9. Statistical Methods Explained
The primary endpoint was analyzed using constrained longitudinal data analysis, abbreviated cLDA. The registry describes the constraint as requiring the same baseline mean across treatment groups. The model included treatment, time, and the interaction of time by treatment. The reported parameter was the difference in least-squares means, which is a model-based estimate of the average contrast between randomized groups at the relevant time point.
What does the baseline constraint do?
In general, longitudinal analyses use measurements collected at more than one time, including baseline and follow-up. A cLDA model treats those measurements jointly and can account for the relationship between repeated measurements. The baseline constraint reflects the randomized design: before treatment, group means are modeled as equal rather than as separate treatment effects. This is a modeling choice, not a claim that each participant began at the same value. The exact covariance structure and other model details are not reported in the registry record.
How should the confidence interval and p-value be read?
The reported 95% confidence interval gives a range of contrasts compatible with the observed data under the model and its assumptions. A narrower interval indicates greater precision than a wider interval, while the location of the interval shows which directions and magnitudes remain compatible with the data. The p-value measures how unusual a result at least as extreme as the observed result would be under a specified null hypothesis and analysis procedure. It is not the probability that the null hypothesis is true, and it does not measure clinical importance.
The primary result is reported as a cLDA estimate with its confidence interval and p-value. The registry also gives the arm-level least-squares mean changes and their intervals. These are model-based estimates, not necessarily simple arithmetic averages of raw participant changes. The analysis population was the full analysis set: randomized participants who received at least 1 dose and had a baseline measurement or a post-randomization measurement. The record does not give the number excluded from this population or the reasons for any missing endpoint measurements.
Why do secondary outcomes use different methods?
Some secondary outcomes are percentages, such as the proportions attaining A1C thresholds. A difference in percentages is a contrast in event rates, rather than a difference in a continuous mean. The sponsor’s reported analyses for the two A1C goal outcomes used the Miettinen & Nurminen method for a between-group rate difference. The registry’s rescue-therapy outcome used a Kaplan-Meier estimate and a log-rank comparison, reflecting its time-to-event framing. Results from different methods need not match exactly because they may use different estimands, assumptions, or handling of the outcome.
General statistical context: a confidence interval for a rate difference describes uncertainty in the difference between group proportions. For a time-to-event endpoint, Kaplan-Meier methods account for differing follow-up and censoring, while a log-rank test compares event-time patterns. The registry does not provide enough detail to reconstruct all assumptions, censoring rules, or analysis populations for those secondary analyses.
What do the planning illustrations represent?
The planning illustrations are based on the observed effect and are not the trial’s own design justification. They assume a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; the effect to detect is a stated fraction of the observed effect. General statistical context: such calculations show how a hypothetical future study’s required size can change when the target effect is smaller or larger. They do not show the probability that the completed trial detected an effect, and they are not observed power. The registry’s actual sample-size justification is not reported in the registry record.
What is not documented?
The registry record does not report the complete statistical analysis plan, whether interim analyses occurred, the planned multiplicity strategy, or detailed missing-data procedures. It also does not give enough detail to assess all model diagnostics or sensitivity analyses. These gaps matter because the interpretation of estimates depends on how outcomes, missing observations, and multiple comparisons were handled. The posted methods still identify the primary endpoint model and the reported analysis population, but they do not resolve those broader questions.
10. Analyses Reported by the Sponsor
| Method | Estimate | 95% CI | P-value |
|---|---|---|---|
| cLDA | Difference in least squares means -0.55 | -0.75 to -0.34 | < 0.001 |
The sponsor-reported primary analysis gives a cLDA difference in least-squares means of -0.55, with a 95% confidence interval from -0.75 to -0.34 and p < 0.001. The displayed primary arm estimates and this reported contrast are consistent in direction: the modeled A1C change is more negative for omarigliptin than for placebo. No discrepancy is flagged for the primary result.
For the secondary rate outcomes, the sponsor used the Miettinen & Nurminen method for the A1C target comparisons. The reported difference for attaining the below 7.0% target was 19.2, with a 95% confidence interval from 10.1 to 28.0 and p < 0.001. The sponsor’s result for the below 6.5% target was 4.2, with a 95% confidence interval from -1.8 to 10.5 and p = 0.164. For rescue therapy, the sponsor reported a Kaplan-Meier difference of -1.2, with a 95% confidence interval from -7.0 to 4.7 and p = 0.654.
Simple recalculations from posted summary statistics can differ slightly from sponsor analyses because they are unadjusted and may use different methods. In the below 6.5% comparison and rescue-therapy comparison, the recalculated estimates and p-values are not identical to the sponsor’s; both sets of results remain compatible with uncertainty around a difference. The registry does not flag a discrepancy. Where a discrepancy is flagged, the sponsor’s own analysis takes precedence; that situation is not identified for these results.
11. Multiplicity, Missing Data and Analysis Populations
The registry reports one primary endpoint and multiple secondary outcomes, including additional A1C measures, A1C goal thresholds, fasting plasma glucose, post-meal glucose, and rescue therapy. It also lists 19 outcome measures and 11 analyses. The number and range of outcomes make multiplicity relevant: when many statistical comparisons are considered, some results may appear notable by chance even if no corresponding effect exists.
The multiplicity strategy is not reported in the registry record. It is therefore not possible to determine from the registry whether secondary hypotheses were tested in a hierarchy, whether p-values were adjusted, or whether a formal family of hypotheses was defined. The secondary p-values should not be interpreted as though a multiplicity adjustment had necessarily been applied. The primary result remains the principal confirmatory result described in the record; secondary findings add context but require more caution.
The primary analysis population is defined as randomized participants who received at least 1 dose of study medication and had a baseline measurement or a post-randomization measurement. The registry describes the population but does not report the number of participants with missing Week 24 A1C data, the reasons for missingness, or the methods used to handle missing values. The complete missing-data plan and sensitivity analyses are not reported in the registry record. General statistical context: missing-data assumptions can affect estimates when participants without observed outcomes differ systematically from those with observed outcomes.
The record also does not report whether interim analyses were conducted or whether any associated decision rules were used. Without the full protocol and statistical analysis plan, the timing of analyses and the prespecification of every comparison cannot be established from the registry record. These are limits on evaluating the analysis process, not evidence that a particular procedure was or was not used.
12. 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 |
|---|---|---|---|
| Omarigliptin (Phase A) | 5 | 201 | 2.5% |
| Placebo to Omarigliptin (Phase A) | 10 | 201 | 5.0% |
| Omarigliptin (Phase A) → Omarigliptin (Phase B) | 12 | 201 | 6.0% |
| Placebo to Omarigliptin (Phase A) → Glimepiride (Phase B) | 18 | 201 | 9.0% |
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 |
|---|---|
| Omarigliptin (Phase A) | 27 of 201 |
| Placebo to Omarigliptin (Phase A) | 17 of 201 |
| Omarigliptin (Phase A) → Omarigliptin (Phase B) | 53 of 201 |
| Placebo to Omarigliptin (Phase A) → Glimepiride (Phase B) | 58 of 201 |
Most frequent serious adverse event terms
| Event term | Organ system | Omarigliptin (Phase A) | Placebo to Omarigliptin (Phase A) | Omarigliptin (Phase A) → Omarigliptin (Phase B) | Placebo to Omarigliptin (Phase A) → Glimepiride (Phase B) |
|---|---|---|---|---|---|
| Intervertebral disc protrusion | Musculoskeletal and connective tissue disorders | 1 of 201 | 1 of 201 | 2 of 201 | 1 of 201 |
| Pancreatitis acute | Gastrointestinal disorders | 0 of 201 | 1 of 201 | 0 of 201 | 2 of 201 |
| Pneumonia | Infections and infestations | 0 of 201 | 1 of 201 | 0 of 201 | 2 of 201 |
| Lung neoplasm malignant | Neoplasms benign, malignant and unspecified (incl cysts and polyps) | 0 of 201 | 1 of 201 | 0 of 201 | 2 of 201 |
| Acute coronary syndrome | Cardiac disorders | 0 of 201 | 1 of 201 | 0 of 201 | 1 of 201 |
| Supraventricular tachycardia | Cardiac disorders | 1 of 201 | 0 of 201 | 1 of 201 | 0 of 201 |
| Gastric polyps | Gastrointestinal disorders | 1 of 201 | 0 of 201 | 1 of 201 | 0 of 201 |
| Chest pain | General disorders | 0 of 201 | 1 of 201 | 0 of 201 | 1 of 201 |
| Non-cardiac chest pain | General disorders | 0 of 201 | 1 of 201 | 0 of 201 | 1 of 201 |
| Seroma | Injury, poisoning and procedural complications | 0 of 201 | 1 of 201 | 0 of 201 | 1 of 201 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Omarigliptin (Phase A) | Placebo to Omarigliptin (Phase A) | Omarigliptin (Phase A) → Omarigliptin (Phase B) | Placebo to Omarigliptin (Phase A) → Glimepiride (Phase B) |
|---|---|---|---|---|---|
| Hypoglycaemia | Metabolism and nutrition disorders | 7 of 201 | 5 of 201 | 17 of 201 | 32 of 201 |
| Blood glucose increased | Investigations | 9 of 201 | 7 of 201 | 14 of 201 | 10 of 201 |
| Headache | Nervous system disorders | 5 of 201 | 5 of 201 | 8 of 201 | 11 of 201 |
| Nasopharyngitis | Infections and infestations | 5 of 201 | 1 of 201 | 11 of 201 | 7 of 201 |
| Arthralgia | Musculoskeletal and connective tissue disorders | 2 of 201 | 0 of 201 | 11 of 201 | 8 of 201 |
Serious events with the highest arm-level rate: pancreatitis acute (1.0%), pneumonia (1.0%), intervertebral disc protrusion (1.0%), lung neoplasm malignant (1.0%), acute coronary syndrome (0.5%).
For Phase A, the registry lists serious adverse events in 5 of 201 participants assigned to omarigliptin and 10 of 201 assigned to placebo. Other adverse events are listed for 27 of 201 and 17 of 201 participants, respectively. For the longer Phase A plus Phase B assignments, serious adverse events are listed for 12 of 201 participants in the omarigliptin continuation group and 18 of 201 in the placebo-to-glimepiride group; other adverse events are listed for 53 of 201 and 58 of 201, respectively.
These are event counts within the recorded groups, not proof of causation or a complete comparative safety analysis. The longer-phase counts concern different treatment assignments and should not be read as a simple continuation of the Phase A randomized comparison. The registry lists serious-event terms including acute pancreatitis, pneumonia, intervertebral disc protrusion, malignant lung neoplasm, acute coronary syndrome, and second-degree atrioventricular block, with percentages as recorded. The listed terms are not assigned to a particular treatment group in the record. Deaths are not reported in the registry record.
General statistical context: rare serious events can be estimated imprecisely, and event counts alone do not account for differences in exposure or establish a treatment-related risk. Detailed event definitions, causal assessments, and exposure-adjusted comparisons are not reported in the registry record.
13. What the Result Does, and Does Not, Mean
The primary analysis estimates the average modeled difference in A1C change between randomized treatment groups at Week 24 among participants included in the defined full analysis set. The estimate is negative, its 95% confidence interval excludes zero, and the reported p-value is less than 0.001. In the context of the stated endpoint, the posted data show a greater modeled reduction in A1C for the omarigliptin group than for the placebo group.
This result does not mean that every participant in the omarigliptin group had a reduction, or that every participant’s response was larger than a placebo participant’s response. A group average can coexist with substantial variation among individuals. The confidence interval describes uncertainty about the estimated average contrast under the model; it is not a prediction interval for individual outcomes.
The result also does not establish whether the difference is clinically important for every patient or how it compares with treatments not studied in the primary contrast. The trial addresses a defined population, treatment assignment, background therapy, and time point. It does not by itself establish long-term effects beyond the outcomes and follow-up recorded in the registry. The secondary endpoints provide different perspectives but are not substitutes for the primary analysis.
Nor does a statistically significant primary result answer safety questions on its own. Adverse-event counts are reported separately, and the record does not provide enough detail to establish causation or characterize every possible safety outcome. A treatment effect on a glycemic measure and the assessment of harms are distinct parts of a trial’s interpretation.
Finally, a small p-value is not the probability that the observed difference is due to chance, nor a measure of effect size. The estimate and confidence interval are essential to understanding both direction and precision. Missing-data procedures, multiplicity planning, and the full analysis plan are not reported in the registry record, so conclusions about those aspects should remain limited.
14. Why This Trial Matters Statistically
This trial illustrates the distinction between a continuous primary outcome and threshold-based secondary outcomes. The primary A1C analysis uses the full scale of a continuous measure and reports a model-based difference in change. The secondary goal-attainment outcomes ask whether participants crossed specific thresholds. Because thresholds compress a range of measurements into categories, they answer a different question and can yield a different degree of statistical precision.
The example also shows why the analysis method should be read alongside the result. The primary endpoint uses cLDA, which models baseline and follow-up measurements under a shared baseline mean constraint. The secondary outcomes use methods suited to rates or time-to-event data. Sponsor-reported analyses and unadjusted recalculations may not match exactly when methods differ, even when their overall interpretation is similar.
Uncertainty matters beyond whether an interval includes zero. The primary confidence interval gives a range of plausible average differences, while the secondary comparisons vary in precision. Multiple outcomes also create a need to understand whether a testing strategy was planned. In this record, the multiplicity plan is not reported, so the primary result has a clearer role than isolated secondary findings.
The study further demonstrates the limits of registry summaries. The record identifies the analysis population and several methods, yet does not report the complete missing-data plan, interim-analysis details, or sample-size justification. Statistical interpretation depends on these design and analysis details, and their absence constrains independent evaluation. The distinction between what is explicitly reported and what remains unknown is itself an important part of reading clinical trial results.
15. 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’s primary endpoint description identifies the model terms and the shared baseline mean constraint, but it does not report all details needed to reproduce the analysis. Model covariance assumptions, diagnostic checks, sensitivity analyses, and the handling of missing Week 24 outcomes are not reported in the registry record. The analysis population is defined, but participant flow into that population and the number with missing endpoint data are not given.
The multiplicity strategy for the many listed outcomes is not reported. This limits the strength of conclusions drawn from secondary p-values, particularly where several outcomes and time points are considered. The record also does not report whether interim analyses occurred, or provide a sample-size justification. Planning illustrations based on observed effects cannot fill those gaps or establish the trial’s original design assumptions.
The secondary results available for interpretation cover only a subset of the listed outcomes. Consequently, the overall pattern across all secondary endpoints cannot be assessed from the results recorded. The posted comparisons also use different statistical methods, so their estimates are not directly interchangeable.
Safety interpretation is limited by the event summaries. The registry does not report deaths in the adverse-event data, does not attribute the listed serious-event terms to specific groups, and does not provide detailed exposure-adjusted comparisons or causal assessments. The longer-phase treatment groups also differ from the primary Phase A comparison, so their counts should not be treated as though they arose from the same treatment contrast.
16. Related Tutorials
17. Related Statistical Calculators
18. Sources
- ClinicalTrials.gov: A Study to Evaluate the Safety, Tolerability, and Efficacy of the Addition of Omarigliptin (MK-3102) to Participants With Type 2 Diabetes Mellitus Who Have Inadequate Glycemic Control on Metformin Therapy (MK-3102-024) — NCT01755156.
- Registry record last updated 2018-09-10; status last verified 2018-08.
- Results first posted 2017-03-20.
- 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.
19. Record Summary
The registry record describes a completed Phase 3 randomized parallel-group trial of omarigliptin versus matching placebo in participants with type 2 diabetes and inadequate glycemic control on metformin. Enrollment was 402. The primary endpoint was change from baseline in A1C at Week 24, analyzed using cLDA in the defined full analysis set.
The sponsor-reported primary difference in least-squares means was -0.55, with a 95% confidence interval from -0.75 to -0.34 and p < 0.001. The secondary comparisons cover A1C goal attainment and rescue therapy, with results that vary by endpoint. Adverse-event counts are reported for Phase A and longer treatment assignments, but the registry record does not provide the complete safety-analysis context.
Important details—including the full sample-size justification, multiplicity strategy, interim analyses, and missing-data plan—are not reported in the registry record. Those omissions limit assessment of the trial’s complete statistical plan while leaving the posted primary estimate and its reported precision interpretable as stated.