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 Efficacy and Safety of Oral Semaglutide Versus Liraglutide and Versus Placebo in Subjects With Type 2 Diabetes Mellitus (NCT02863419), a randomized phase 3 study. The primary outcome is Change in HbA1c (Week 26).
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT02863419 |
| Phase | Phase 3 |
| Condition | Diabetes, Diabetes Mellitus, Type 2 |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Double |
| Enrollment | 711 |
| Arms in the primary outcome | n/a |
| Lead sponsor | Novo Nordisk A/S |
| Results posted | Yes |
2. Clinical Question
Population
Participants with type 2 diabetes mellitus were eligible for this global phase 3 trial. The registry reports enrollment of 711 participants and says the full analysis set comprised all randomized participants. Eligibility details beyond the condition are not reported in the registry record.
Intervention
The trial investigated oral semaglutide. The registry’s safety groups identify an Oral Semaglutide 14 mg group, but arm descriptions are blank, and further intervention details are not reported in the registry record.
Comparator
The comparators were liraglutide and placebo. The safety groups identify Liraglutide 1.8 mg and Placebo, but the registry does not describe additional arm procedures in its arm descriptions.
Primary question
The primary endpoint was change in HbA1c from baseline at week 26. The registry’s aim was to investigate efficacy and safety of oral semaglutide versus liraglutide and versus placebo. A single numerical treatment comparison is not reported in the registry record, so the magnitude and precision of any between-group difference cannot be described from this record alone.
These elements define the broad clinical question, but do not establish the exact statistical contrast used for each comparison. The registry identifies three treatment groups and a continuous primary measure, yet the available endpoint description includes multiple observation periods. That distinction matters: an analysis that includes observations after rescue medication or treatment discontinuation answers a different question from one that excludes those periods. The registry describes both periods but does not report one reduced comparison to represent the primary result.
3. Trial Design
This was a phase 3, randomized, double-masked, parallel-group trial sponsored by Novo Nordisk A/S. The registry describes three groups: oral semaglutide, liraglutide, and placebo. Enrollment was 711. The trial status is completed, and the registry records a start date of 2016-08-10 and a primary completion date of 2017-08-19. The brief description says the trial was conducted globally.
Randomization assigns participants to treatment groups by chance, helping make groups comparable at the start of a trial. Double masking means that the registry classifies the trial as masked for two parties, although the identities of those parties and the practical masking procedures are not reported in the registry record. A parallel design means participants are assigned to a group and followed in that group rather than crossing through multiple treatment conditions.
The registry records 40 outcome measures and 14 analyses. It lists secondary outcomes involving HbA1c, body weight, fasting plasma glucose, body mass index, waist circumference, and a total cholesterol ratio to baseline. These descriptions indicate a broad set of outcomes and follow-up assessments, but do not specify all analysis choices or the results for those measures. The arm descriptions are blank. Apart from the treatment-group labels and the doses included in the safety-group titles, treatment schedules and other arm procedures are not reported in the registry record.
Enrollment is not the same as the number with available observations for a particular endpoint. For the primary outcome, the registry defines the full analysis set as all randomized participants and says the number analyzed is the number with available data. Group-specific numbers analyzed for the primary endpoint are not reported in the registry record. The allocation ratio, details of randomization, and reasons for any unavailable endpoint data are also not reported in 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.
Before assignment: Data presented in "participant flow" is based on the in-trial observation period, which was the time period from when a participant was randomised until the final scheduled visit, including any period after initiation of rescue medication and/or premature discontinuation of trial product.
Overall Study
| Stage | Oral Semaglutide 14 mg | Liraglutide 1.8 mg | Placebo |
|---|---|---|---|
| STARTED | 285 | 284 | 142 |
| Full Analysis Set (FAS) | 285 | 284 | 142 |
| Safety Analysis Set (SAS) | 285 | 284 | 142 |
| COMPLETED | 277 | 274 | 134 |
| NOT COMPLETED | 8 | 10 | 8 |
Reasons for not completing this period:
| Reason | Oral Semaglutide 14 mg | Liraglutide 1.8 mg | Placebo |
|---|---|---|---|
| Lost to Follow-up | 0 | 1 | 4 |
| Withdrawal by Subject | 5 | 5 | 3 |
| Died | 3 | 4 | 1 |
Analysis population for the primary outcome, as defined in the registry: Overall number of participants analyzed = full analysis set (FAS) which comprised all randomised participants. Number Analyzed = number of participants with available data.
5. Baseline Characteristics
The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.
Population: Full analysis set (FAS) included all randomised participants.
| Characteristic | Unit | Oral Semaglutide 14 mg | Liraglutide 1.8 mg | Placebo | Total |
|---|---|---|---|---|---|
| Participants analysed | 285 | 284 | 142 | 711 | |
| Age, Continuous | Years | 56 (SD 10) | 56 (SD 10) | 57 (SD 10) | 56 (SD 10) |
| Sex: Female, Male: Female | Participants | 138 | 135 | 68 | 341 |
| Sex: Female, Male: Male | Participants | 147 | 149 | 74 | 370 |
| Ethnicity (NIH/OMB): Hispanic or Latino | Participants | 17 | 18 | 5 | 40 |
| Ethnicity (NIH/OMB): Not Hispanic or Latino | Participants | 268 | 266 | 137 | 671 |
| Ethnicity (NIH/OMB): Unknown or Not Reported | Participants | 0 | 0 | 0 | 0 |
| Race/Ethnicity, Customized: White | Participants | 208 | 212 | 99 | 519 |
| Race/Ethnicity, Customized: Black or African American | Participants | 12 | 9 | 8 | 29 |
| Race/Ethnicity, Customized: Asian | Participants | 39 | 36 | 19 | 94 |
| Race/Ethnicity, Customized: American Indian or Alaska Native | Participants | 0 | 1 | 1 | 2 |
| Race/Ethnicity, Customized: Native Hawaiian or Other Pacific Islander | Participants | 0 | 1 | 0 | 1 |
| Race/Ethnicity, Customized: Other | Participants | 3 | 8 | 3 | 14 |
| Race/Ethnicity, Customized: Not Applicable | Participants | 23 | 17 | 12 | 52 |
| Baseline HbA1c | Percentage of HbA1c | 8.0 (SD 0.7) | 8.0 (SD 0.7) | 7.9 (SD 0.7) | 8.0 (SD 0.7) |
6. Primary Endpoint
The registry lists the primary outcome as Change in HbA1c (Week 26), measured over Week 0, week 26.
| Element | Registry entry |
|---|---|
| Result type | Mean |
| Measure of spread | Standard Deviation |
| Unit | Percentage of HbA1c |
| Endpoint classification | Continuous Endpoint |
The primary endpoint measures change in glycosylated haemoglobin, or HbA1c, from week 0 to week 26. HbA1c is a continuous measure, and the registry specifies that the outcome is expressed as a percentage of HbA1c. The analysis parameter is the mean, with standard deviation as the dispersion measure. Change from baseline is used to describe how the measured value at follow-up differs from the participant’s starting value; comparing such changes between randomized groups can summarize differences in the outcome over the follow-up period.
HbA1c is used in diabetes trials as a measure of glycemic status over time. In statistical terms, a continuous outcome retains more gradation than a simple event indicator: participants’ measurements can vary across a range rather than being classified only as having or not having an event. A group mean summarizes the average change, while the standard deviation describes the spread of individual changes around that mean. Neither measure alone reveals the distribution’s full shape or the precision of a between-group estimate.
The endpoint description distinguishes two observation periods. The in-trial period runs from randomization to the final scheduled visit and includes time after rescue medication begins or trial product is discontinued. The on-treatment without rescue medication period includes time while participants are on trial product but excludes time after rescue medication or premature treatment discontinuation. These definitions address different estimands and can lead to different interpretations. Numerical endpoint results for either period are not reported in the registry record.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The central statistical limitation is that the registry identifies the primary outcome but does not report one numerical comparison that can be interpreted as the primary treatment effect. No group means, changes, between-group estimates, confidence intervals, or p-values for week 26 HbA1c are available in the registry record used for this analysis. Consequently, neither the size of a difference nor its statistical precision can be assessed from the recorded information. The absence of a numerical comparison is not evidence that the groups were equal; it means the comparison cannot be evaluated from this record.
The endpoint’s definition also matters for interpretation. The in-trial observation period includes data after rescue medication and after premature discontinuation of trial product. The on-treatment without rescue medication period excludes those observations after rescue or treatment discontinuation. The first period describes outcomes across the follow-up after randomization, including events that can occur during treatment changes. The second focuses on observations during treatment before those specified events. These are different ways to handle post-randomization events, not interchangeable labels for the same dataset. The registry does not report which period is represented by a numerical primary result, because it does not provide a single numerical comparison.
Means and standard deviations describe a continuous outcome at the group level. A mean can conceal variation among participants, while a standard deviation describes dispersion but does not give the uncertainty of a treatment contrast. A confidence interval, if reported, would express the range of estimates compatible with the data under the analysis assumptions; it would help show precision as well as direction and magnitude. No such interval is reported in the registry record for the primary comparison. Without it, a reader cannot judge whether an estimated difference is precise or highly uncertain.
The registry reports that the primary outcome was evaluated in the full analysis set, defined as all randomized participants, while the number analyzed is defined as those with available data. The actual available-data counts by treatment group are not reported in the registry record. This distinction is important because a stated analysis population does not by itself show how many participants contributed outcome data, how missing measurements were handled, or whether the available participants differed from those without measurements.
Safety information is recorded separately from the primary endpoint. The group counts include participants at risk and participants affected by serious adverse events, other adverse events, and deaths. Those counts describe events recorded in the safety listing; without further details about event definitions, follow-up, and statistical comparisons, they should not be interpreted as comparative risk estimates. The serious adverse event terms listed in the record each have an associated percentage, but the record does not provide enough context to treat those percentages as treatment-effect estimates.
Thus, the available registry information supports a description of the study design, endpoint, outcome-handling periods, and selected safety counts. It does not support a conclusion about the magnitude, direction, or precision of the primary comparison. Such conclusions would require numerical outcome results and the analysis details underlying them.
9. Statistical Methods Explained
The registry describes the primary endpoint as a mean change in HbA1c, a continuous outcome, and gives standard deviation as its dispersion measure. Understanding these statistics helps distinguish a group summary from a treatment comparison. The mean is the average of the observed values within a group. The standard deviation describes how spread out those values are around the mean. A group-level mean change is not itself the between-group treatment effect: the treatment effect is generally expressed through a contrast between groups, with an estimate and an account of its uncertainty.
What does a mean change represent?
Change from baseline is calculated for each participant by comparing a follow-up measurement with a starting measurement, then summarized across participants. Using change can focus the analysis on within-participant movement over time, although the interpretation still depends on which follow-up observations are included and how missing values are handled. The registry specifies week 0 and week 26 for the primary endpoint. It does not report the group-level change values or the resulting between-group estimates.
Standard deviation and confidence interval answer different questions. Standard deviation describes variation among participant measurements. A confidence interval describes uncertainty around an estimated quantity, such as a difference between group means, under the assumptions of the analysis. A narrow interval indicates greater precision than a wide interval, but precision is not the same as clinical importance. The registry record does not report confidence intervals for the primary comparison, so neither precision nor compatibility with a range of possible effects can be assessed.
Why do observation periods matter?
The endpoint description identifies an in-trial observation period and an on-treatment without rescue medication observation period. In-trial follow-up begins at randomization and continues to the final scheduled visit, including data after rescue medication starts and after premature treatment discontinuation. The on-treatment period is limited to time on trial product and excludes the specified periods after rescue medication or premature discontinuation. A result based on the in-trial period can reflect outcomes after treatment changes, whereas an on-treatment result is more restricted to observations while assigned product is being taken and before rescue. Those approaches address different questions about what happens after randomization and treatment changes.
Neither approach is automatically a complete solution to the statistical challenges caused by rescue medication or discontinuation. An analysis must define how those events affect the outcome being estimated and how measurements outside the relevant period are handled. The registry describes the two observation-period definitions, but the full statistical methods for each and the numerical results are not reported in the registry record.
What is the analysis population?
The registry says the full analysis set comprises all randomized participants. It separately defines the number analyzed as participants with available data. This distinction indicates that the intended analysis population and the participants contributing a particular outcome measurement need not be identical. The record does not give the week 26 available-data counts by group or explain whether missing outcomes were imputed, modeled, or handled by another method. Such details affect how much information contributes to the estimate and whether assumptions are needed about unobserved outcomes.
Randomized comparisons are designed to use the balance created by chance assignment. An analysis that excludes participants or measurements can alter that balance if the exclusions are related to treatment assignment or outcome. This is a general statistical concern, not a claim that such imbalance occurred in this trial. The registry description alone does not establish the extent or causes of missing outcome data.
How should statistical significance and multiplicity be considered?
A p-value, when reported, summarizes how inconsistent the observed data are with a specified null model, under the analysis assumptions. It does not measure the probability that a treatment is effective, and it does not describe the size or practical importance of an estimate. A confidence interval is often more informative for considering magnitude and precision. The registry record does not report a primary comparison p-value or confidence interval.
Multiplicity arises when several outcomes, time points, groups, or analyses are examined. Repeated testing can increase the chance of at least one result appearing statistically unusual by chance if no adjustment or prespecified testing strategy is used. This is a general issue; it does not establish that a particular adjustment was or was not applied in this trial. The registry records 40 outcome measures and 14 analyses, and its primary outcome is not reduced to one comparison in the available record. The multiplicity plan is not reported in the registry record.
Statistical methods should also distinguish prespecified analyses from exploratory analyses, and should clarify whether estimates are adjusted or unadjusted. The analysis plan, covariates, model form, and interim-analysis details are not reported in the registry record. It is therefore not possible to characterize those choices or judge their influence on the results. A planning illustration based on an observed effect, where available, is not observed power and does not replace a reported treatment estimate or its uncertainty.
10. Multiplicity, Missing Data and Analysis Populations
The registry records a broad outcome set: 40 outcome measures and 14 analyses. The primary outcome is change in HbA1c at week 26, while listed secondary outcomes include HbA1c at week 52 and several measures of body weight and metabolic status. When multiple outcomes, comparisons, or time points are considered, multiplicity is a statistical concern because repeated testing can make chance findings more likely. A prespecified testing hierarchy or adjustment can address that concern, but neither a multiplicity strategy nor a hierarchy is reported in the registry record. This does not establish that no such strategy was used; it means the record does not describe one.
The record defines the full analysis set as all randomized participants and defines the number analyzed as participants with available data. It also describes an in-trial period and an on-treatment without rescue medication period for the primary endpoint. These definitions clarify the target populations and time periods in broad terms, but do not explain the treatment of missing measurements. The number with available week 26 data in each group, reasons for missingness, imputation procedures, and sensitivity analyses are not reported in the registry record.
Missing data can affect interpretation when the likelihood of having an observed measurement is related to treatment assignment or the outcome. Statistical approaches make assumptions about unobserved values, and sensitivity analyses can examine how conclusions change under alternative assumptions. These are general considerations; the registry information does not establish which assumptions or methods were used for this trial. Details of the statistical analysis plan, including any interim analyses, are not reported in the registry record.
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 |
|---|---|---|---|
| Oral Semaglutide 14 mg | 31 | 285 | 10.9% |
| Liraglutide 1.8 mg | 22 | 284 | 7.7% |
| Placebo | 15 | 142 | 10.6% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| Oral Semaglutide 14 mg | 3 of 285 |
| Liraglutide 1.8 mg | 4 of 284 |
| Placebo | 1 of 142 |
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 |
|---|---|
| Oral Semaglutide 14 mg | 148 of 285 |
| Liraglutide 1.8 mg | 120 of 284 |
| Placebo | 47 of 142 |
Most frequent serious adverse event terms
| Event term | Organ system | Oral Semaglutide 14 mg | Liraglutide 1.8 mg | Placebo |
|---|---|---|---|---|
| Myocardial infarction | Cardiac disorders | 2 of 285 | 1 of 284 | 0 of 142 |
| Acute myocardial infarction | Cardiac disorders | 1 of 285 | 0 of 284 | 1 of 142 |
| Atrial fibrillation | Cardiac disorders | 1 of 285 | 1 of 284 | 0 of 142 |
| Epistaxis | Respiratory, thoracic and mediastinal disorders | 1 of 285 | 0 of 284 | 1 of 142 |
| Meniscus injury | Injury, poisoning and procedural complications | 1 of 285 | 1 of 284 | 0 of 142 |
| Osteoarthritis | Musculoskeletal and connective tissue disorders | 0 of 285 | 2 of 284 | 0 of 142 |
| Accidental overdose | Injury, poisoning and procedural complications | 0 of 285 | 0 of 284 | 1 of 142 |
| Ankle fracture | Injury, poisoning and procedural complications | 0 of 285 | 1 of 284 | 0 of 142 |
| Aphasia | Nervous system disorders | 0 of 285 | 0 of 284 | 1 of 142 |
| Arthralgia | Musculoskeletal and connective tissue disorders | 0 of 285 | 0 of 284 | 1 of 142 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Oral Semaglutide 14 mg | Liraglutide 1.8 mg | Placebo |
|---|---|---|---|---|
| Nausea | Gastrointestinal disorders | 55 of 285 | 51 of 284 | 5 of 142 |
| Nasopharyngitis | Infections and infestations | 41 of 285 | 37 of 284 | 15 of 142 |
| Diarrhoea | Gastrointestinal disorders | 43 of 285 | 31 of 284 | 11 of 142 |
| Headache | Nervous system disorders | 27 of 285 | 17 of 284 | 8 of 142 |
| Vomiting | Gastrointestinal disorders | 24 of 285 | 13 of 284 | 3 of 142 |
| Constipation | Gastrointestinal disorders | 22 of 285 | 11 of 284 | 4 of 142 |
| Decreased appetite | Metabolism and nutrition disorders | 16 of 285 | 20 of 284 | 0 of 142 |
| Back pain | Musculoskeletal and connective tissue disorders | 11 of 285 | 17 of 284 | 5 of 142 |
| Dyspepsia | Gastrointestinal disorders | 16 of 285 | 12 of 284 | 0 of 142 |
| Abdominal pain | Gastrointestinal disorders | 16 of 285 | 6 of 284 | 3 of 142 |
Serious events with the highest arm-level rate: accidental overdose (0.7%), acute myocardial infarction (0.7%), aphasia (0.7%), arthralgia (0.7%), atrial flutter (0.7%).
The safety listing gives group-level counts for serious adverse events, other adverse events, and deaths. For Oral Semaglutide 14 mg, 285 participants were at risk for serious adverse events and 31 were affected; 285 were at risk for other adverse events and 148 were affected; deaths numbered 3. For Liraglutide 1.8 mg, the corresponding counts were 284 at risk and 22 affected by serious adverse events, 284 at risk and 120 affected by other adverse events, and 4 deaths. For Placebo, the counts were 142 at risk and 15 affected by serious adverse events, 142 at risk and 47 affected by other adverse events, and 1 death.
These are counts, not adjusted comparisons. The groups differ in their recorded numbers at risk, and the registry excerpt does not provide exposure time, event rates, confidence intervals, or a statistical comparison of safety outcomes. The counts alone therefore do not establish whether an apparent difference is due to treatment, chance, follow-up duration, or other factors. The record lists Accidental overdose, Acute myocardial infarction, Aphasia, Arthralgia, Atrial flutter, and Cerebellar syndrome among the top serious adverse event terms, each with a recorded percentage of 0.7%. The denominators and event-specific analysis details are not reported in the registry record, so these terms and percentages should be read as descriptive entries rather than comparative estimates.
12. What the Result Does, and Does Not, Mean
The registry record establishes that a randomized, double-masked, parallel-group phase 3 trial compared oral semaglutide with liraglutide and placebo in participants with type 2 diabetes. It identifies change in HbA1c at week 26 as the primary endpoint, describes the analysis population in broad terms, and records selected safety counts. This information can clarify what the study was designed to investigate and what kinds of measurements were collected.
It does not establish the size or direction of the primary treatment differences. Numerical HbA1c changes, between-group estimates, confidence intervals, and p-values are not reported in the registry record. Without those results, it is not possible to assess the magnitude of any observed difference or how precisely it was estimated. It would also be inappropriate to interpret the absence of a reported comparison as evidence that the groups had identical outcomes.
The endpoint has two described observation periods, and the choice between them affects the question being answered. An in-trial analysis includes data after rescue medication or treatment discontinuation, while an on-treatment analysis without rescue medication excludes those specified periods. The registry does not report a single numerical result tied to one of these periods, nor does it provide the analysis details needed to reconcile them.
The safety counts are descriptive. They do not, on their own, demonstrate a causal relationship between an intervention and an event or provide a reliable comparison of event risks. Interpreting them as treatment contrasts would require additional information about event definitions, exposure, follow-up, and statistical uncertainty.
In general, trial findings are best read by considering the estimated effect, its uncertainty, the population and outcome analyzed, and how missing data and multiple comparisons were addressed. Several of those details are not reported in the registry record. Accordingly, the available record supports a careful account of study structure and selected observations, but not a conclusion about comparative efficacy or safety.
13. Why This Trial Matters Statistically
This trial is statistically informative as an example of why a clearly named endpoint is only one part of interpreting a randomized comparison. The registry identifies change in HbA1c from baseline at week 26 and specifies the mean and standard deviation as its summary measures. It also defines distinct in-trial and on-treatment observation periods. Those choices shape the interpretation of an estimated effect: the same endpoint can answer different questions depending on whether post-rescue or post-discontinuation observations are included.
The study’s three-group design also raises the importance of identifying the exact contrast. A comparison of oral semaglutide with liraglutide is a different contrast from a comparison with placebo. The registry aim names both comparisons, but a single numerical primary result is not reported in the registry record. Without estimates and uncertainty for the relevant contrasts, the reader cannot judge their magnitude or precision.
The record lists 40 outcome measures and 14 analyses, which makes clear why analysis planning and multiplicity information matter. Looking across many outcomes and time points can complicate interpretation, particularly when it is unclear which analyses were prespecified or how statistical testing was organized. The multiplicity plan is not reported in the registry record, so the reported information cannot establish how that issue was handled.
Finally, the full analysis set definition and the available-data definition highlight the difference between randomized participants and those contributing a particular measurement. Transparent reporting of group-specific data availability, missing-data methods, estimates, and confidence intervals is important for judging both bias and precision. These details are not reported in the registry record. The trial therefore illustrates both the value of registry descriptions and the limits of drawing statistical conclusions from design and safety counts alone.
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 this trial from the registry record is the absence of a numerical result for the primary week 26 HbA1c comparison. Group-level changes, between-group estimates, confidence intervals, and p-values are not reported in the registry record. The listed primary endpoint is therefore identifiable, but its observed magnitude and precision cannot be evaluated.
The endpoint description contains two observation-period definitions, but the record does not reduce the primary outcome to one comparison. It does not identify a single numerical result tied to the in-trial period or the on-treatment without rescue medication period. Consequently, the impact of including observations after rescue medication or treatment discontinuation cannot be assessed from the available information.
The registry states that the full analysis set comprised all randomized participants and that the number analyzed means participants with available data. It does not report the available-data counts for the primary endpoint by group, the reasons for missing measurements, the method used to handle missing data, or sensitivity analyses. These omissions limit evaluation of how representative the analyzed measurements were of the randomized groups.
The arm descriptions are blank. The safety-group titles name Oral Semaglutide 14 mg and Liraglutide 1.8 mg, but the registry excerpt does not describe additional intervention schedules or procedures. Details of eligibility beyond the condition, randomization procedures, allocation ratio, the statistical analysis plan, and multiplicity handling are not reported in the registry record. These gaps restrict assessment of how closely the planned analyses, treatment implementation, and reported outcome definitions align.
The safety information is also limited to counts and selected serious adverse event terms. Exposure duration, event-specific denominators, comparative estimates, and uncertainty measures are not reported in the registry record. These limitations make the safety information descriptive rather than sufficient for a comparative statistical assessment.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: Efficacy and Safety of Oral Semaglutide Versus Liraglutide and Versus Placebo in Subjects With Type 2 Diabetes Mellitus — NCT02863419.
- Registry record last updated 2022-07-20; status last verified 2022-07.
- Results first posted 2019-11-07.
- 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 describes a completed, randomized, double-masked, parallel-group phase 3 trial sponsored by Novo Nordisk A/S. It enrolled 711 participants and compared oral semaglutide, liraglutide, and placebo in a global study of type 2 diabetes mellitus. The recorded start date is 2016-08-10, and the primary completion date is 2017-08-19.
The primary endpoint was mean change in HbA1c from week 0 to week 26, with standard deviation as the dispersion measure. The endpoint description specifies both in-trial and on-treatment without rescue medication observation periods. The registry identifies the full analysis set as all randomized participants and defines the number analyzed as those with available data.
The record lists 40 outcome measures and 14 analyses, as well as selected safety counts for serious adverse events, other adverse events, and deaths. Numerical results for a single primary comparison, details of missing-data methods, and the multiplicity strategy are not reported in the registry record.