A Clinical Trial Comparing Efficacy and Safety of Insulin Degludec/Liraglutide (IDegLira) Versus Basal-bolus Therapy in Subjects With Type 2 Diabetes Mellitus: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Clinical Trial Comparing Efficacy and Safety of Insulin Degludec/Liraglutide (IDegLira) Versus Basal-bolus Therapy in Subjects With Type 2 Diabetes Mellitus (NCT02420262), a randomized phase 3 study. The primary outcome is Change in HbA1c (Glycosylated Haemoglobin).

2. Clinical Question

The central statistical question is a comparison of change in a continuous measure, rather than a comparison of the proportion of participants who reached a particular HbA1c threshold. The registry reports least-squares mean changes for the two groups and a sponsor analysis described as a treatment contrast. It also lists responder outcomes and hypoglycaemic episodes among the secondary outcomes, which address other aspects of the treatment comparison.

This distinction matters when reading the results. A change in the group mean describes the average trajectory, while a responder outcome describes how many participants meet a defined threshold. Neither alone describes every participant’s experience. The registry record does not report the protocol’s exact clinical question wording, the non-inferiority margin, or a detailed definition of basal-bolus dosing. Those details should not be inferred from the treatment names.

3. Trial Design

This was a completed, randomized, Phase 3, parallel-group trial sponsored by Novo Nordisk A/S. The registry lists no masking, so the trial is described as unmasked. The trial summary says it was conducted globally and compared IDegLira with basal-bolus therapy, with both regimens used in combination with metformin. The named drugs were insulin degludec/liraglutide, insulin glargine, and insulin aspart.

Registry enrollment was 506. For the primary endpoint, the posted arm summaries include 244 participants in the IDegLira group and 245 in the IGlar + IAsp group. These endpoint analysis counts are not the same thing as the overall enrollment figure. The primary endpoint description says that the FAS included all randomized subjects and that evaluation followed the intention-to-treat principle, with subjects contributing as randomized. It also notes that 8 subjects in IDegLira and 9 in IGlar + IAsp did not contribute to the analysis for this endpoint.

The primary outcome was change in glycosylated haemoglobin from Week 0 to Week 26. The registry also lists secondary outcomes concerning treatment-emergent severe or blood glucose confirmed symptomatic hypoglycaemic episodes, change in body weight, and HbA1c responder thresholds. The posted material includes detailed numerical summaries for change in body weight, but not numerical results for every outcome named in the record.

The registry lists a start date of 2015-07-26 and a primary completion date of 2016-10-05, and marks the study completed. Its detailed protocol, original sample-size justification, allocation ratio, dose schedules, and fuller descriptions of the arms are not reported in the registry record. The trial label and posted outcomes identify the broad comparison, but do not fill in those protocol details.

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: Subjects with type 2 diabetes mellitus were on treatment with stable daily dose of insulin glargine (IGlar) between 20 units and 50 units (both inclusive) for at least 56 days prior to screening in combination with a stable daily dose of metformin (≥1500 mg or maximum tolerated dose) for at least 90 days prior to screening.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The FAS included all randomised subjects. The statistical evaluation of the FAS followed the intention-to-treat (ITT) principle and subjects contributed to the evaluation "as randomised". 8 subjects in IDegLira and 9 subjects in IGlar + IAsp arm did not contribute to the analysis for this endpoint.

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: The full analysis set (FAS) included all randomised subjects. The statistical evaluation of the FAS followed the intention-to-treat (ITT) principle and subjects contributed to the evaluation "as randomised"

6. Primary Endpoint

The registry lists the primary outcome as Change in HbA1c (Glycosylated Haemoglobin), measured over Week 0, Week 26.

The primary endpoint is change in HbA1c, or glycosylated haemoglobin, from Week 0 to Week 26. HbA1c is a continuous measure, and the endpoint records how its value changed during the stated treatment period. The registry reports the group results as least-squares means with standard errors. A least-squares mean is a model-based group estimate; it is not necessarily a simple arithmetic average. The registry record does not provide enough detail to reconstruct the model specification.

As a general statistical explanation, a continuous endpoint preserves information about the size and direction of change across the measured scale. It can therefore address whether average change differed between groups without reducing the outcome to a yes-or-no threshold. The trial separately lists HbA1c responder thresholds as secondary outcomes, which answer a different question about reaching specified cut-offs.

HbA1c is used in this trial as a measure relevant to glycaemic control. The purpose of describing this endpoint is to explain what was measured, not to make a treatment recommendation. The primary endpoint description specifies a change after 26 weeks of treatment. It also says that the FAS included all randomized subjects and was evaluated according to the intention-to-treat principle, as randomized, while identifying participants who did not contribute to this endpoint analysis. The registry record does not report further details about how missing endpoint values were handled.

7. Results Posted in the Registry

• IGlar + IAsp: mean -1.46 versus -1.48 on control; difference 0.02 (95% CI -0.12 to 0.16), standardized effect d = 0.03; z-test p = 0.777.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Change in Body Weight

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • IGlar + IAsp: mean 2.64 versus -0.93 on control; difference 3.57 (95% CI 2.96 to 4.18), standardized effect d = 1.04; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for IGlar + IAsp than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes extend the trial’s questions beyond average HbA1c change. They include hypoglycaemic episodes, change in body weight, and responder outcomes based on HbA1c thresholds. These outcomes can add context because they describe different dimensions of the comparison, but they do not replace the primary endpoint or resolve its statistical uncertainties.

The registry includes numerical summaries for the body-weight outcome. Numerical results for the other named secondary outcomes are not reported in the registry record. As a result, the posted material does not support a complete account of whether the secondary outcomes point in a consistent direction, or how their estimates compare in precision. A broad pattern across all secondary endpoints cannot be inferred from outcome names alone.

As a general statistical explanation, secondary outcomes may be used to explore additional effects, but examining multiple outcomes creates a multiplicity concern. Unless a testing hierarchy or adjustment is described, a nominal p-value for a secondary comparison may carry less evidential weight than a prespecified primary analysis. The registry record does not report a multiplicity procedure or the complete analysis plan for secondary outcomes.

The secondary findings should therefore be read as complementary evidence, not as independent confirmation of the primary result. Their meaning depends on the outcome definitions, analysis populations, and multiplicity plan. Those details are not fully available for every listed outcome. In particular, absence of numerical results in the registry record does not establish that an outcome was measured without difference; it means the record does not provide a result from which to assess that question.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Number of Treatment Emergent Severe or Blood Glucose Confirmed Symptomatic Hypoglycaemic Episodes.
• Change in Body Weight
• Responder for HbA1c Below 7.0%
• Responder for HbA1c Below or Equal to 6.5 %

9. Statistical Interpretation

10. Statistical Methods Explained

There are two distinct statistical accounts for the primary comparison: the registry’s sponsor-reported mixed-model analysis and a simple recalculation from posted group summaries. They answer closely related questions but use different statistical information. Keeping them separate prevents the simple calculation from being mistaken for the trial’s primary model-based inference.

What a group mean describes

The primary endpoint is continuous. Its arm-level results are least-squares mean changes, and the spread reported alongside each estimate is a standard error. A group estimate describes an average change under the analysis used. It does not say that each participant changed by that amount, nor does it show the distribution of individual changes.

As a general explanation, a standard error describes the uncertainty of an estimated mean under a statistical model. It is not a measure of the full range of participant-level outcomes. The registry gives a standard error of 0.05 for each primary arm estimate. The record does not provide the full model specification, so the model-based estimates should be understood as reported rather than reconstructed from assumed covariates or procedures.

What the unadjusted recalculation describes

The recalculated comparison uses the posted arm summaries to form an unadjusted mean difference. Its estimate is 0.02, with a 95% confidence interval from -0.119 to 0.159 and p = 0.777. The calculation is a descriptive statistical check based on the available summary values; it is not a replacement for the sponsor’s analysis. The recalculated standard deviation is approximate, as indicated in the posted calculation details. This matters because the arm summaries provide standard errors rather than the individual participant data and full analysis model.

As a general explanation, an unadjusted comparison does not incorporate model adjustments unless those are explicitly part of the calculation. A model-based treatment contrast can differ in its construction and inferential result. Such differences do not automatically mean one calculation is erroneous: they may reflect different estimands, model assumptions, contrast coding, or handling of available data. The registry record does not report enough detail to attribute the difference in reported p-values to a specific cause.

How to read the sponsor’s analysis

The sponsor labels its primary result a mixed-model treatment contrast and classifies it as non-inferiority or equivalence. It reports a contrast of -0.02, a 95% confidence interval from -0.16 to 0.12, and p < 0.001. A contrast’s sign depends on group ordering. The reported contrast has the reverse sign from the recalculated mean difference, consistent with a different subtraction order; the registry does not fully describe the coding. The important distinction is that the sponsor reports a model-based analysis, while the recalculation is explicitly unadjusted.

As a general explanation, non-inferiority analysis asks whether the data rule out a loss larger than a prespecified margin, under a specified direction and decision rule. Equivalence analysis generally asks whether the uncertainty lies within prespecified bounds on both sides. These interpretations depend on the margin and analysis plan. Neither the margin nor the complete decision criteria are reported in the registry record. The p-value’s meaning is therefore not fully interpretable from the posted summary alone, and it should not be read as a conventional test of whether the groups differ.

Confidence intervals and p-values

As a general explanation, a confidence interval gives a range of values compatible with the data and the assumptions of the analysis at its stated confidence level. A 95% interval that includes zero for a mean difference does not establish that the true difference is exactly zero; it indicates that the interval includes no difference as one possibility. The recalculated interval includes zero. The sponsor’s reported interval also spans values on both sides of zero, but its inferential role depends on the unreported non-inferiority or equivalence bounds.

A p-value summarizes how compatible observed data are with a specified null hypothesis under the analysis assumptions. It does not measure the probability that a treatment effect is true, and it does not measure clinical importance. Because the reported sponsor p-value is attached to a non-inferiority or equivalence analysis, the test hypothesis and margin are essential context. The registry record does not report them. The recalculated p-value is an unadjusted result and should not be substituted for the sponsor’s prespecified analysis.

Multiplicity and secondary analyses

Several secondary outcomes are listed, including hypoglycaemic episodes, body-weight change, and HbA1c responder outcomes. When many outcomes or comparisons are examined, the chance of finding a nominally notable result by chance can rise. As a general statistical explanation, multiplicity procedures may control that risk, but the registry record does not report a multiplicity adjustment or the complete testing hierarchy. The posted unadjusted secondary comparisons should therefore be interpreted cautiously, particularly when the overall plan for confirmatory and exploratory testing is unavailable.

11. Confidence Intervals and Precision

Precision concerns how narrowly an estimate is bounded by its uncertainty interval. For the primary endpoint, the simple recalculation gives a mean difference of 0.02 and a 95% confidence interval from -0.119 to 0.159. The interval includes zero and also includes values on either side of zero. Thus, the recalculated estimate alone does not pin down the direction of a small difference with certainty. The registry’s arm-level standard errors are 0.05 for both groups.

As a general explanation, a confidence interval is not a guarantee that the true value lies inside the particular interval, nor does it show the range of individual participant outcomes. It describes statistical uncertainty in an estimate under the assumptions of the calculation. A narrow interval indicates greater precision than a broad interval on the same scale, but precision is not the same as clinical importance.

The sponsor’s model-based interval is -0.16 to 0.12 around a treatment contrast of -0.02. It is close to the recalculated interval but is not identical, and it comes from a different analysis. Its interpretation as non-inferiority or equivalence depends on the margin and decision rules, which are not reported in the registry record. The sponsor’s analysis takes precedence over the unadjusted recalculation for describing the trial’s own analysis, while the recalculation remains a separate check based on posted summaries.

The body-weight comparison also has a reported interval, but its precision does not resolve uncertainty about outcomes whose numerical results are absent. More generally, confidence intervals address sampling uncertainty under stated methods; they do not correct for missing outcomes, unknown analysis choices, or incomplete protocol information. Those limits matter when judging how much detail the registry record supports.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The sample-size illustrations are planning calculations based on the observed effect, not a report of the trial’s original design calculation. For these continuous outcomes, the entries are participants per arm, not a total across both groups. The assumptions listed for the illustration are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set at the stated fraction of the observed effect.

The 80% power column gives an illustrative number of participants per arm for a design that would have an 80% chance of detecting the specified effect under the stated assumptions, if that effect and assumptions were correct. The 90% power column gives the corresponding illustration for a higher chance of detection. These are prospective planning quantities, not measures of what power the completed trial actually had.

Rows for 100%, 75%, and 50% of the observed effect show how the illustration changes when the target effect is reduced. Smaller effects are harder to distinguish from random variation and therefore require more participants under the same assumptions. This is why the entries rise as the planning effect becomes smaller. The illustrations use the observed effect as their starting point, so they should not be interpreted as an independent estimate of a clinically important effect.

The original trial’s own sample-size assumptions, target effect, and justification are not reported in the registry record. The planning illustrations are not observed power and do not establish whether the trial was adequately designed for a particular clinical or statistical objective. For time-to-event outcomes, the stated convention would be total events, but that convention does not apply to these continuous outcomes.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = 0.020; pooled standard deviation σ = 0.782.
2. n = 2 × (1.96 + 0.842)² × 0.782² / 0.020² = 23,988.2, rounded up to 23,989 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- 0.02                      # observed difference in means
sigma <- 0.781826430056642                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(2420262)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 23,989 (80% power), 32,114 (90% power)
 75% of observed effect: n per arm = 42,646 (80% power), 57,091 (90% power)
 50% of observed effect: n per arm = 95,953 (80% power), 128,454 (90% power)
power.t.test: 23989.2 
Simulated power at n = 23,989 per arm: 0.795 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

14. Analyses Reported by the Sponsor

The sponsor’s primary analysis is reported as a mixed-model treatment contrast of -0.02, with a 95% confidence interval from -0.16 to 0.12 and p < 0.001. The registry classifies this analysis as non-inferiority or equivalence. The separate recalculation from posted group summaries gives an unadjusted mean difference of 0.02, a 95% confidence interval from -0.119 to 0.159, and p = 0.777. These values should not be blended into a single result: the sponsor’s estimate comes from its reported model-based analysis, while the recalculation is a simple unadjusted comparison.

The opposite signs of the two point estimates are consistent with reversing the group order in a contrast. A sign change alone does not mean that the analyses indicate opposite substantive directions. The sponsor’s model-based result takes precedence when describing the trial’s own analysis. The recalculation can help readers see how the posted arm means relate to a simple difference, but it does not supersede that result.

The registry record does not report the non-inferiority margin, complete hypothesis, or full model specification. Without that context, the reported p-value cannot be interpreted as a conventional test of difference or as a complete account of the sponsor’s decision rule. The sponsor’s analysis is the primary reported inferential result, but the registry summary leaves important details of its interpretation unavailable.

15. Multiplicity, Missing Data and Analysis Populations

The registry describes the primary analysis population as the FAS, including all randomized subjects, with statistical evaluation following the intention-to-treat principle and participants contributing as randomized. It also specifies that 8 subjects in IDegLira and 9 in IGlar + IAsp did not contribute to the primary endpoint analysis. This is useful information about the analysis population, but it does not explain how their missing endpoint data were handled.

The registry record does not report whether missing values were imputed, whether a model used available observations under particular assumptions, or whether sensitivity analyses assessed alternative missing-data assumptions. It also does not report a detailed account of withdrawals or reasons for missing primary endpoint values. These details matter because missing-data methods can affect estimates and their uncertainty, especially when missingness may be related to participant outcomes.

Several secondary outcomes are listed, and multiple statistical analyses are posted. The registry record does not report a complete testing hierarchy, a multiplicity adjustment, or which outcomes were intended to be confirmatory versus exploratory. As a general statistical explanation, testing multiple outcomes can increase the chance of at least one apparently notable result arising by chance if each is assessed separately. Without the analysis plan, the strength of unadjusted secondary findings is difficult to place in the overall evidence hierarchy.

The non-inferiority or equivalence label also requires context: the margin, direction of the hypothesis, analysis population requirements, and decision criteria are not reported in the registry record. The sponsor’s reported analysis should be distinguished from the unadjusted recalculation, but the missing plan details prevent a full audit of how the reported inference was reached. These omissions do not prove that appropriate procedures were absent; they limit what can be concluded from the registry summary.

16. Safety Results

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

Other (non-serious) adverse events

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

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: angina unstable (0.4%), atrial fibrillation (0.4%), atrial flutter (0.4%), cardiac failure (0.4%), chest pain (0.4%).

The registry lists serious adverse events affecting 12 of 252 participants at risk in the IDegLira group and 10 of 253 participants at risk in the IGlar + IAsp group. It also lists other adverse events affecting 84 of 252 and 79 of 253 participants, respectively. These are descriptive counts in the registry record; they do not by themselves establish that treatment caused an event or that the groups differ in safety.

The record lists the following serious-event terms, each at 0.4%: angina unstable, atrial fibrillation, atrial flutter, cardiac failure, chest pain, and diabetic foot infection. The posted summary does not provide enough detail to interpret these terms as a complete account of all events, their timing, severity beyond the serious classification, or relationship to treatment. Death counts are not reported in the registry record.

As a general statistical explanation, comparisons of adverse events depend on how events and affected participants are defined, the duration of observation, and the level of detail available for each group. The registry figures should be read as a limited descriptive safety summary, not as a standalone estimate of comparative risk.

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

The primary endpoint results show similar posted average HbA1c changes in the two randomized groups over the stated 26-week period. The sponsor reports a mixed-model treatment contrast and labels the analysis non-inferiority or equivalence. The recalculated unadjusted mean difference is close to zero, with an interval that includes zero. These are descriptions of the posted estimates and statistical analyses, not medical advice or a conclusion about what any individual should use.

The sponsor’s analysis takes precedence over the simple recalculation for reporting the trial’s own inferential result. However, the registry record does not report the non-inferiority margin or full decision rules, so the label and p-value cannot be independently interpreted in full from the record alone. In particular, p < 0.001 should not be read as a conventional test demonstrating that the treatments differ; its meaning depends on the hypothesis tested.

The group averages do not describe every participant’s response. They also do not establish that the treatments are identical. An interval spanning zero indicates that the corresponding analysis includes no difference among the values compatible with its assumptions, while other values remain possible. Statistical uncertainty, clinical importance, and individual experience are related but distinct considerations.

Secondary outcomes provide additional questions about body weight, hypoglycaemic episodes, and HbA1c thresholds. The registry includes numerical summaries for body-weight change, while numerical results for the other named secondary outcomes are not reported in the registry record. Safety figures are also limited descriptive counts. Therefore, the posted information does not support a complete assessment across all benefits and harms, nor does it disclose every protocol or analysis choice needed for a full evaluation.

18. Why This Trial Matters Statistically

This trial is statistically informative because it compares two treatment strategies using randomization and a continuous primary endpoint. Randomization supports a group comparison by allocating participants to treatment groups, while the parallel design allows outcomes to be assessed over the same study period. The reported endpoint summarizes average change, and the sponsor’s model-based contrast presents the trial’s own primary inferential analysis.

The record also illustrates why estimates, uncertainty intervals, and analysis labels need to be read together. The recalculated unadjusted comparison and the sponsor’s mixed-model result are related but not interchangeable. The non-inferiority or equivalence label signals that the sponsor’s analysis addresses a different decision framework from an ordinary test of whether the groups differ. Without the margin and full plan, that framework cannot be completely assessed.

Its registry record is also a useful example of the limits of outcome reporting. It identifies several secondary endpoints and gives numerical detail for some, but not all. It reports a primary analysis population and identifies participants who did not contribute to that endpoint, yet does not explain the missing-data procedure. Such gaps matter because statistical interpretation relies not only on point estimates but also on how outcomes, populations, and analyses were defined.

The main statistical lesson is that a close point estimate is not, by itself, proof of equivalence, and a small p-value cannot be interpreted without knowing the hypothesis. A careful reading separates what the record directly reports from what requires protocol details that are not reported. This keeps the results informative without overstating their reach.

19. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The registry record does not report the non-inferiority margin or the complete decision criteria for the sponsor’s primary analysis. That omission limits interpretation of the classification as non-inferiority or equivalence and of the reported p-value. The model specification and contrast coding are also not described in enough detail to reconstruct the sponsor’s analysis from the registry summary.

The record notes that 8 IDegLira participants and 9 IGlar + IAsp participants did not contribute to the primary endpoint analysis, but does not report the reasons or missing-data methods. It does not provide sensitivity analyses for missing outcomes. The primary endpoint population description therefore clarifies who was intended for the FAS while leaving uncertainty about how unavailable values affected the analysis.

Numerical results are not reported for every listed secondary outcome, and a multiplicity plan is not reported. The available secondary summaries cannot establish a consistent pattern across all outcomes. Safety reporting is also limited: the registry provides counts for serious and other adverse events and lists serious-event terms, but does not report death counts in the posted data or enough detail to assess timing and attribution.

The trial’s original sample-size assumptions, detailed protocol, dose schedules, fuller arm descriptions, and complete analysis plan are not reported in the registry record. The planning illustrations based on observed effects are not evidence of the trial’s original design rationale. Together, these limitations restrict independent evaluation of design choices and the full meaning of the posted statistical results.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Clinical Trial Comparing Efficacy and Safety of Insulin Degludec/Liraglutide (IDegLira) Versus Basal-bolus Therapy in Subjects With Type 2 Diabetes Mellitus — NCT02420262.
• Registry record last updated 2018-03-29; status last verified 2018-02.
• Results first posted 2017-12-07.
• 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.

23. Record Summary

The registry describes a completed, randomized, unmasked, parallel-group Phase 3 trial sponsored by Novo Nordisk A/S. The global trial compared IDegLira with IGlar + IAsp in combination with metformin for people with type 2 diabetes mellitus. Registry enrollment was 506.

The primary endpoint was change in HbA1c from Week 0 to Week 26. The posted arm estimates are -1.48 for IDegLira and -1.46 for IGlar + IAsp. The sponsor reports a mixed-model treatment contrast of -0.02 with a 95% confidence interval from -0.16 to 0.12, classifying the analysis as non-inferiority or equivalence. A separate unadjusted recalculation is not a substitute for that sponsor analysis.

Secondary outcomes include body-weight change, hypoglycaemic episodes, and HbA1c responder thresholds. Numerical results for some named outcomes are not reported in the registry record. The non-inferiority margin, detailed missing-data approach, and complete statistical plan are also not reported, limiting further interpretation of the posted results.