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 An Investigational Drug Study in Patients With Type 2 Diabetes Mellitus (0431-024) (NCT00094770), a randomized phase 3 study. The primary outcome is Change From Baseline in HbA1c at Week 52.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT00094770 |
| Phase | Phase 3 |
| Condition | Diabetes Mellitus, Type 2 |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Double |
| Enrollment | 1172 |
| Arms in the primary outcome | 2 |
| Lead sponsor | Merck Sharp & Dohme LLC |
| Results posted | Yes |
2. Clinical Question
Population
Participants had type 2 diabetes and inadequate glycemic control while taking metformin monotherapy. The primary endpoint used a per-protocol population requiring HbA1c measurements at baseline and Week 52, without major protocol violations. The registry record does not report further eligibility details in the information.
Intervention
The intervention was sitagliptin (MK0431), described as 100 mg oral tablets once daily. The study evaluated adding this drug to the existing metformin treatment context.
Comparator
The active comparator was glipizide. Participants began at 1 tablet (5 mg) per day, with possible up-titration according to glycemic control to a total daily dose of 4 tablets twice daily (20mg/day).
Primary question
At Week 52, what was the mean change from baseline in HbA1c in each study arm? The posted primary results give least-squares means and 95% confidence intervals for each arm, but a direct between-arm estimate and test are not reported in the registry record.
The registry identifies this as a multicenter, double-blind, randomized study with a parallel-group design. Its official title frames the comparison as adding MK0431 versus sulfonylurea therapy for people with type 2 diabetes whose control on metformin alone was inadequate. The named comparator intervention and arm description identify glipizide as the active alternative.
The record reports enrollment of 1172 participants. Enrollment is not the same as the number contributing to every endpoint: the primary per-protocol analysis includes participants who met its measurement and protocol requirements, while the safety figures use different at-risk group sizes. Those populations answer different descriptive questions and should not be interchanged.
3. Trial Design
This was a Phase 3, randomized, double-blind, parallel-group study sponsored by Merck Sharp & Dohme LLC. It is listed as completed. The registry record gives a start of 2004-09 and primary completion in 2006-05. The stated purpose was to evaluate safety and efficacy when sitagliptin was added in comparison with sulfonylurea therapy among patients with type 2 diabetes and inadequate glycemic control on metformin monotherapy.
The two named arms were Sitagliptin 100 mg and Glipizide. Sitagliptin was administered as oral tablets once daily. In the glipizide arm, the starting description was 1 tablet (5 mg) per day; participants could then be up-titrated according to glycemic control to a total daily dose of 4 tablets twice daily (20mg/day). The registry describes masking as double, but additional details about who was masked and how masking was maintained are not reported in the registry record.
There were 1172 enrolled participants in total. For the primary endpoint, the posted arm summaries include 382 participants in the sitagliptin arm and 411 in the glipizide arm. The primary population was per protocol: participants needed measurements at baseline and Week 52 and could not have major protocol violations, with examples including drug compliance < 75%, addition of a prohibited antihyperglycemic agent, or incorrect double-blind study medication. The number randomized to each arm and the handling of missing primary endpoint values are not reported in the registry record.
The registry record does not report the planned sample-size justification, allocation ratio, randomization procedure, detailed masking procedures, or the full statistical analysis plan. The record identifies a Week 52 primary endpoint and lists secondary outcomes through Week 104. These details establish the broad structure of the trial, but they are not enough to reconstruct all planned analyses or explain why particular design choices were made.
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: Participants 18-78 years of age with type 2 diabetes mellitus (T2DM) and inadequate glycemic control (Hemoglobin A1c \>6.5% and \< 10%) on metformin at a dose of \>1500mg/day.
Year 1 ( Week 0 to Week 52)
| Stage | Sitagliptin 100 mg | Glipizide |
|---|---|---|
| STARTED | 588 | 584 |
| COMPLETED | 386 | 412 |
| NOT COMPLETED | 202 | 172 |
Reasons for not completing this period:
| Reason | Sitagliptin 100 mg | Glipizide |
|---|---|---|
| Adverse Event | 25 | 26 |
| Lack of Efficacy | 86 | 58 |
| Lost to Follow-up | 19 | 10 |
| Protocol Violation | 10 | 10 |
| Protocol Specified Discontinuation | 19 | 25 |
| Patient Moved | 6 | 2 |
| Withdrawal by Subject | 25 | 28 |
| Site Terminated | 2 | 2 |
| Other | 10 | 11 |
Year 2 (Week 0 to Week 104)
| Stage | Sitagliptin 100 mg | Glipizide |
|---|---|---|
| STARTED | 588 | 584 |
| COMPLETED | 255 | 264 |
| NOT COMPLETED | 333 | 320 |
Reasons for not completing this period:
| Reason | Sitagliptin 100 mg | Glipizide |
|---|---|---|
| Adverse Event | 35 | 36 |
| Lack of Efficacy | 180 | 162 |
| Lost to Follow-up | 25 | 15 |
| Protocol Violation | 13 | 12 |
| Protocol Specified Discontinuation | 29 | 30 |
| Patient Moved | 6 | 2 |
| Withdrawal by Subject | 28 | 38 |
| Site Terminated | 2 | 2 |
| Other | 15 | 23 |
Analysis population for the primary outcome, as defined in the registry: The per protocol population required that a participant had measurements both at baseline and at Week 52, and did not have any major protocol violations (e.g. drug compliance \< 75%, addition of prohibited antihyperglycemic agent, incorrect double-blind study medication). No missing data were imputed.
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 | Sitagliptin 100 mg | Glipizide | Total |
|---|---|---|---|---|
| Participants analysed | 588 | 584 | 1172 | |
| Age, Continuous | years | 56.8 (SD 9.3) | 56.6 (SD 9.8) | 56.7 (SD 9.55) |
| Sex: Female, Male: Female | Participants | 252 | 226 | 478 |
| Sex: Female, Male: Male | Participants | 336 | 358 | 694 |
| Race/Ethnicity, Customized: Asian | participants | 50 | 49 | 99 |
| Race/Ethnicity, Customized: Black | participants | 41 | 35 | 76 |
| Race/Ethnicity, Customized: Hispanic | participants | 43 | 46 | 89 |
| Race/Ethnicity, Customized: White | participants | 432 | 434 | 866 |
| Race/Ethnicity, Customized: Other | participants | 22 | 20 | 42 |
| Hemoglobin A1c (HbA1c) | Percent | 7.7 (SD 0.9) | 7.6 (SD 0.9) | 7.7 (SD 0.9) |
6. Primary Endpoint
The registry lists the primary outcome as Change From Baseline in HbA1c at Week 52, measured over Baseline and Week 52.
| Element | Registry entry |
|---|---|
| Result type | Least Squares Mean |
| Measure of spread | 95% Confidence Interval |
| Unit | Percent |
| Endpoint classification | Continuous Endpoint |
The primary endpoint was change from baseline in HbA1c at Week 52, measured in percent. HbA1c is a measure of glycemic status; in this trial, the recorded change is defined as the Week 52 HbA1c percent minus the Week 0 HbA1c percent. A negative change therefore represents a lower measured HbA1c at Week 52 than at baseline for the participant-level quantity being summarized. This describes the direction of change, not the cause of that change.
The registry reports least-squares means for each arm and 95% confidence intervals. A least-squares mean is a model-based estimate of an arm average; the registry record does not provide enough detail about the model to explain its adjustment structure. The per-protocol population required both baseline and Week 52 measurements and no major protocol violations. As a result, this endpoint summary does not describe every enrolled participant.
HbA1c was selected as the primary measure of glycemic change for the study’s stated comparison. In general, a continuous endpoint can retain information about the magnitude of individual measurements rather than reducing them to a yes-or-no category. The posted summary is useful for describing the mean change in each arm and its precision, but a pair of arm-specific means does not by itself quantify the uncertainty in the difference between arms. A direct between-arm estimate or test for this endpoint is not reported in the registry record.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
For the primary endpoint, the least-squares mean change from baseline in HbA1c at Week 52 was -0.67 percent in the Sitagliptin 100 mg arm and -0.67 percent in the Glipizide arm. Each arm’s 95% confidence interval was -0.75 to -0.59. These are arm-specific estimates in the per-protocol population. The posted summaries therefore describe the average change within each arm, not a direct estimate of the difference between arms.
The identical rounded means and intervals should not be read as a formal finding of equivalence. A between-arm estimate, its confidence interval, and a primary-endpoint hypothesis test are not reported in the registry record. Without those results, the degree of precision for the arm-to-arm contrast cannot be assessed from the two separate confidence intervals alone. The registry record also does not report a noninferiority or equivalence margin, so these arm summaries do not establish either type of conclusion.
The endpoint population is important to interpretation. It required baseline and Week 52 measurements and excluded participants with major protocol violations. Thus, the primary result describes the qualifying per-protocol participants rather than necessarily all randomized or enrolled participants. The registry record does not report the number excluded for each reason or a complementary analysis in a broader population.
The posted secondary information includes a comparison for participants with drug-related laboratory adverse experiences through Week 104. Its unadjusted p-value is 0.61, and its risk-difference confidence interval is -0.015 to 0.026. That interval includes zero, so the posted data do not establish a clear difference for this secondary comparison. This outcome is not the primary HbA1c endpoint, and the unadjusted result should be read cautiously in the context of multiple listed secondary outcomes. A multiplicity adjustment plan is not reported in the registry record.
Overall, the primary summaries show the same rounded mean change in both arms, with the same arm-specific interval limits. They do not supply the direct comparative inference needed to determine how precisely the arms differ. The secondary comparison likewise has uncertainty compatible with no difference, but it addresses a different outcome. Neither result alone supports a broad conclusion about all efficacy or safety outcomes in the study.
9. Statistical Methods Explained
What does the primary estimate describe? The primary outcome is continuous: change in HbA1c percent from baseline to Week 52. The posted statistic is a least-squares mean for each arm, accompanied by a 95% confidence interval. In general, a mean summarizes the center of measured values, while a confidence interval conveys uncertainty in the estimated mean under the analysis assumptions. It is not a range containing 95% of individual participants’ values. The registry record does not describe the model used to obtain the least-squares means, so its covariates and other modeling details are not reported.
The two posted arm means are -0.67 and -0.67, and each 95% confidence interval is -0.75 to -0.59. These quantities answer an arm-specific question: what mean change was estimated in each qualifying group? A direct comparison asks a different question: how large is the estimated difference between the groups, and how uncertain is that difference? The registry record does not report a primary between-arm estimate, its confidence interval, or a p-value. Separate confidence intervals cannot substitute for a reported contrast, particularly when the covariance structure and analysis model are not given.
Why distinguish analysis populations? The primary endpoint is reported for a per-protocol population requiring both baseline and Week 52 measurements and no major protocol violations. This focuses the primary summary on participants satisfying those stated conditions. It also means the reported primary sample sizes do not match total enrollment. In general, excluding participants after randomization can change which participants are represented in an analysis, so the population definition is part of the result’s meaning. The registry record does not report the count or reasons for all exclusions, a full participant flow, or results from an intention-to-treat analysis. Missing-data handling beyond the stated measurement requirement is not reported in the registry record.
How should a confidence interval be read? A confidence interval expresses uncertainty around an estimate, conditional on the method and assumptions used. In repeated use of a valid procedure, intervals constructed in this way would cover the underlying quantity at the stated rate. This general interpretation does not mean there is a 95% probability that this particular fixed interval contains the true value. The primary intervals are narrow at the displayed precision, but they concern arm-specific means, not the unreported between-arm contrast. Precision for one quantity should not be transferred to another.
What does the secondary comparison add? One posted secondary comparison concerns participants with drug-related laboratory adverse experiences through Week 104. Its risk difference is 0.005, with a 95% confidence interval from -0.015 to 0.026 and an unadjusted p-value of 0.61. In general, a risk difference compares the proportions with an event between groups; zero represents no difference on that scale. Here, the interval crosses zero, so the estimate remains compatible with differences in either direction. The reported relative-risk interval is 0.632 to 2.182 and the odds-ratio interval is 0.623 to 2.241; both include 1, the usual no-association value on those scales. These are distinct ways to express the same binary comparison, not independent confirmations.
The p-value is unadjusted. In general, a p-value describes how unusual data at least as incompatible with a specified null hypothesis would be if that hypothesis and the test assumptions held. It is not the probability that the null hypothesis is true, and it does not measure clinical importance. Because the registry record lists multiple secondary outcomes and does not report a multiplicity plan, an isolated unadjusted secondary p-value carries limited confirmatory weight.
What are the planning illustrations? The registry’s planning illustration uses the observed effect for the secondary binary comparison, with a two-sided significance level of 0.05, equal allocation, and a normal approximation. It gives participants per arm for 80% and 90% power under scenarios using 100%, 75%, and 50% of that observed effect. For 100% of the observed effect, the figures are 17,669 and 23,653 participants per arm; for 75%, they are 30,803 and 41,235; for 50%, they are 67,933 and 90,943. These are planning illustrations, not observed power, and are not the trial’s own design justification. The registry record does not report the trial’s original sample-size assumptions or justification.
In general, planning calculations depend on assumptions about the effect to detect, variability or event frequency, allocation, significance threshold, and analysis method. A calculation based on an observed effect is especially sensitive to uncertainty in that estimate. The illustrations do not show what power the completed study had, do not establish the likelihood of a result, and do not repair missing or unreported analyses. The registry record does not report interim analyses or a prespecified statistical plan for the outcomes described.
10. Multiplicity, Missing Data and Analysis Populations
The registry record lists a primary endpoint and multiple secondary outcomes, but a complete statistical analysis plan is not reported. In particular, it does not report a strategy for controlling multiplicity across secondary endpoints, time points, or any other analyses. When many hypotheses are tested, unadjusted p-values do not account for the possibility of chance findings across the collection. This is a general statistical concern, not evidence that a particular result is false. The available secondary p-value is explicitly unadjusted and should therefore be treated as limited, supportive information rather than a standalone confirmatory conclusion.
For the primary endpoint, the posted record gives the two arm-specific least-squares means and their 95% confidence intervals, but not a direct between-arm contrast or test. The record also does not report a noninferiority margin, an equivalence margin, or a hierarchy of hypotheses. Without these elements, the primary summaries cannot be used to infer that the arms are equivalent or to reconstruct a prespecified confirmatory decision rule. Details of interim analyses and any alpha-spending approach are not reported in the registry record.
Missing-data handling is also incompletely described. The primary per-protocol population required measurements at baseline and Week 52, but the registry does not report how many participants lacked measurements, why measurements were missing, or how missing values were handled in other analyses. Its population description includes the incomplete wording “No missing data were impute”; this does not provide a complete account of an imputation method or confirm how missing data were handled. The registry record does not report sensitivity analyses examining alternative assumptions about missing outcomes.
The per-protocol definition excludes participants with major protocol violations and requires endpoint measurements. This population may differ from the full randomized population, so its summary has a narrower interpretation. The registry record does not report a corresponding intention-to-treat result for the primary endpoint or a full accounting of participants by analysis population. It is therefore not possible from the reported information to assess how robust the primary summary is to population choice or missing-data assumptions.
These omissions do not invalidate the posted estimates, but they limit the conclusions that can be drawn from them. The arm-level primary results describe a defined subset and lack a direct comparative test; the secondary result is unadjusted; and the analysis plan, missing-data procedures, and multiplicity handling are not fully reported. Those limits should remain explicit when interpreting statistical evidence.
11. 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 |
|---|---|---|---|
| Sitagliptin 100 mg | 64 | 588 | 10.9% |
| Glipizide | 73 | 584 | 12.5% |
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 |
|---|---|
| Sitagliptin 100 mg | 318 of 588 |
| Glipizide | 374 of 584 |
Most frequent serious adverse event terms
| Event term | Organ system | Sitagliptin 100 mg | Glipizide |
|---|---|---|---|
| Angina Pectoris | Cardiac disorders | 1 of 588 | 3 of 584 |
| Non-Cardiac Chest Pain | General disorders | 2 of 588 | 2 of 584 |
| Cholelithiasis | Hepatobiliary disorders | 4 of 588 | 0 of 584 |
| Pneumonia | Infections and infestations | 1 of 588 | 3 of 584 |
| Basal Cell Carcinoma | Neoplasms benign, malignant and unspecified (incl cysts and polyps) | 1 of 588 | 3 of 584 |
| Atrial Fibrillation | Cardiac disorders | 3 of 588 | 0 of 584 |
| Cardiac Failure Congestive | Cardiac disorders | 2 of 588 | 1 of 584 |
| Supraventricular Tachycardia | Cardiac disorders | 2 of 588 | 1 of 584 |
| Cellulitis | Infections and infestations | 1 of 588 | 2 of 584 |
| Meniscus Lesion | Injury, poisoning and procedural complications | 1 of 588 | 2 of 584 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Sitagliptin 100 mg | Glipizide |
|---|---|---|---|
| Hypoglycaemia | Metabolism and nutrition disorders | 31 of 588 | 199 of 584 |
| Upper Respiratory Tract Infection | Infections and infestations | 73 of 588 | 79 of 584 |
| Nasopharyngitis | Infections and infestations | 71 of 588 | 61 of 584 |
| Diarrhoea | Gastrointestinal disorders | 42 of 588 | 40 of 584 |
| Bronchitis | Infections and infestations | 40 of 588 | 37 of 584 |
| Influenza | Infections and infestations | 32 of 588 | 37 of 584 |
| Urinary Tract Infection | Infections and infestations | 44 of 588 | 25 of 584 |
| Headache | Nervous system disorders | 33 of 588 | 35 of 584 |
| Back Pain | Musculoskeletal and connective tissue disorders | 35 of 588 | 32 of 584 |
| Arthralgia | Musculoskeletal and connective tissue disorders | 34 of 588 | 32 of 584 |
Serious events with the highest arm-level rate: cholelithiasis (0.7%), angina pectoris (0.5%), pneumonia (0.5%), basal cell carcinoma (0.5%), atrial fibrillation (0.5%).
The posted safety figures describe participants at risk and participants with serious adverse events in each arm. The Sitagliptin 100 mg group had 588 participants at risk and 64 participants with serious adverse events; the Glipizide group had 584 participants at risk and 73 participants with serious adverse events. These are participant counts, not a direct estimate of the comparative effect. The registry record does not report a statistical comparison or confidence interval for these serious-event counts.
The listed serious adverse event terms include Cholelithiasis (0.7%), Angina Pectoris (0.5%), Pneumonia (0.5%), Basal Cell Carcinoma (0.5%), Atrial Fibrillation (0.5%), and Acute Myocardial Infarction (0.3%). These are reported term frequencies; they do not establish that an event was caused by study medication. The registry record does not report a comparative analysis for these terms, and the list should not be treated as a complete account of all adverse events.
The other adverse-event participant counts are 318 of 588 in the Sitagliptin 100 mg group and 374 of 584 in the Glipizide group. Death counts are not reported in the registry record. Safety group sizes differ from the primary per-protocol sample sizes because the endpoints and populations differ. These descriptive counts do not, by themselves, determine whether there is a meaningful difference in safety between arms.
12. What the Result Does, and Does Not, Mean
The primary posted result establishes what was estimated in the defined per-protocol population: the least-squares mean change in HbA1c from baseline to Week 52 was -0.67 percent in each arm, and each arm-specific 95% confidence interval was -0.75 to -0.59. This is a description of the observed study results as summarized by the registry. It does not by itself establish that the treatments have the same effect, because the registry record does not report a direct between-arm estimate or test for this endpoint.
Nor do these summaries establish that one treatment is superior, inferior, equivalent, or noninferior to the other. Those conclusions require an appropriate comparative analysis and, for equivalence or noninferiority, prespecified margins and a suitable analysis plan. Such margins and a primary contrast are not reported in the registry record. Similar rounded arm estimates are informative descriptively but are not a substitute for those elements.
The result also should not be generalized beyond the population and outcome that were analyzed without considering the trial’s eligibility criteria and per-protocol restrictions. The primary result requires baseline and Week 52 measurements and excludes major protocol violations. The registry record does not report enough information about missing data or broader-population analyses to determine how closely the per-protocol result represents every randomized participant.
The secondary outcomes add distinct questions about later measurements, body weight, hypoglycemic events, and adverse experiences. The available secondary comparison is uncertain and unadjusted, and results for the other listed outcomes are not reported in the registry record. The serious-event counts are descriptive rather than a comparative safety analysis. Taken together, the available results do not provide a complete assessment of all efficacy and safety questions posed by the study.
In general, statistical results quantify patterns and uncertainty under specified methods; they do not alone determine clinical importance or individual outcomes. The registry record does not report enough detail to evaluate every analysis assumption, the full analysis plan, or all planned outcomes. The appropriate interpretation is therefore limited to the posted estimates and counts, with the absent comparative and methodological information kept in view.
13. Why This Trial Matters Statistically
This trial illustrates why the form of a reported estimate matters. Its primary outcome is continuous, and the registry reports a least-squares mean and confidence interval for each arm. Those summaries describe within-arm change. They do not directly answer the randomized comparison question unless a between-arm contrast is also reported. Two similar arm estimates may look reassuringly alike, but a comparative conclusion requires the estimated contrast and its uncertainty, which are not reported for the primary endpoint.
The record also makes clear that the analyzed population matters. Although enrollment was 1172, the primary outcome summaries use a per-protocol population with baseline and Week 52 measurements and no major protocol violations. A reader needs to distinguish the full enrolled group from the endpoint-specific group and from the safety populations. These are not interchangeable denominators, and a result from a restricted analysis population has a correspondingly specific interpretation.
The secondary comparison demonstrates another general issue: an unadjusted p-value and confidence interval belong to one outcome among several listed measures. In general, multiple comparisons can make isolated findings more likely by chance, so the analysis hierarchy and multiplicity plan are important. The registry record does not report those details. A confidence interval that includes the no-difference value also communicates uncertainty more directly than a simple claim based on whether a p-value crosses a threshold.
Finally, sample-size planning illustrations are not the same as the trial’s original design justification or observed power. The posted illustration is based on an observed secondary effect and assumptions about allocation and testing. Treating it as a design fact about the completed study would misstate what it represents. These distinctions—arm summary versus contrast, per-protocol versus broader populations, unadjusted secondary inference, and planning versus observed evidence—are central to reading clinical trial statistics accurately.
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.
Several limitations are specific to the information reported for this study. The primary endpoint has arm-level least-squares means and confidence intervals, but the direct comparison between arms is not reported in the registry record. That prevents assessment of the estimated primary contrast and its precision from the posted primary summaries. The record also does not state a noninferiority or equivalence margin, so the similar rounded arm estimates cannot be interpreted as evidence for either claim.
The primary population is per protocol and requires observed measurements at baseline and Week 52, with exclusions for major protocol violations. The record does not provide a full participant flow, the number excluded for each reason, or a primary result in a broader randomized population. Missing-data handling is not fully described, and sensitivity analyses are not reported. This restricts assessment of how the endpoint summary might depend on participant inclusion or missingness.
Although the registry lists 11 secondary outcomes, comparative results are not reported for the remaining listed endpoints in the information described. The available secondary comparison is unadjusted, and multiplicity handling is not reported. The serious adverse event data are participant counts and selected term frequencies without a posted comparative statistical analysis. Death counts are not reported in the registry record. These gaps limit broad conclusions across efficacy and safety outcomes.
Other details needed to fully evaluate the design and analysis are not reported in the registry record, including the sample-size justification, randomization procedure, detailed masking procedures, interim analyses, and complete statistical plan. The planning illustration is based on an observed secondary effect rather than the trial’s original design assumptions. These reporting limits do not change the posted numbers, but they constrain how far statistical interpretation can go.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: An Investigational Drug Study in Patients With Type 2 Diabetes Mellitus (0431-024) — NCT00094770.
- Registry record last updated 2016-08-26; status last verified 2016-08.
- Results first posted 2009-12-22.
- 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.
18. Record Summary
The registry record identifies NCT00094770 as a completed Phase 3, multicenter, double-blind, randomized, parallel-group study sponsored by Merck Sharp & Dohme LLC. Enrollment was 1172. The study compared sitagliptin 100 mg once daily with glipizide, beginning at 1 tablet (5 mg) per day with possible up-titration according to glycemic control.
The primary endpoint was change from baseline in HbA1c at Week 52. In the per-protocol population, the least-squares mean was -0.67 percent in each arm, with a 95% confidence interval of -0.75 to -0.59 for each. A direct primary between-arm estimate and test are not reported in the registry record.
The registry lists secondary outcomes concerning later HbA1c and body-weight changes, hypoglycemic events, and clinical adverse experiences. Comparative results for most listed secondary outcomes, multiplicity handling, full missing-data methods, and the detailed statistical plan are not reported in the registry record. Serious adverse event counts are available as descriptive figures, without a reported comparative analysis.