A Study to Compare LY2963016 and US-approved Lantus® After Single Dose Administration to Healthy Participants: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Compare LY2963016 and US-approved Lantus® After Single Dose Administration to Healthy Participants (NCT01688635), a randomized phase 1 study. The primary outcome is Pharmacokinetics (PK): Area Under the Concentration Time Curve (AUC) of LY2963016 and US-Approved Lantus.

2. Clinical Question

This was a comparison of exposure after single-dose administration in healthy participants, not a study of long-term clinical outcomes. The treatment schedule included four single injections across four periods, with each treatment administered twice. A clamp procedure followed each injection. The question is therefore about the measured concentration-time exposure associated with each study treatment under those conditions. It does not directly answer questions about repeated use, outcomes in people with a condition, or differences in clinical benefit.

3. Trial Design

The registry identifies this as a phase 1, randomized, double-blind crossover study. It enrolled 91 healthy participants and is marked completed. The study started in 2012-09, and primary completion was recorded in 2013-02. The sponsor was Eli Lilly and Company.

The treatment schedule comprised four periods, with one single subcutaneous injection in each period. Participants received two doses of LY2963016 and two doses of US-approved Lantus; each dose was 0.5 U/kg. At least a 7 day washout was planned between periods. Each injection was followed by a euglycemic clamp lasting 24 hours. The brief summary states that participation was expected to last up to 14 weeks and that side effects would be documented.

In a crossover design, participants receive more than one treatment over different periods. This allows treatment observations to be made within the same participant, which can be useful when participants differ in baseline characteristics that affect the outcome. The design also makes period, sequence, and carryover considerations relevant to analysis. The registry record does not report the statistical model or explain how these design features were handled.

The primary pharmacokinetic analysis included participants who were randomized, received at least one dose, and had evaluable data for AUC(0-24). The posted treatment-arm counts for that analysis are 87.0 for LY2963016 and 89.0 for US-approved Lantus. These are analysis counts, not the enrollment figure, and they should not be added to estimate the number of participants in the crossover study. The registry record does not report the allocation sequence, the masking procedures, or the number of participants who completed every period.

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: The study comprised 2 sequences with 4 treatment periods. Participants were randomly assigned to 1 of the 2 sequences.

Period 1

Washout 1

Reasons for not completing this period:

Period 2

Washout 2

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full analysis set (FAS): All randomized participants who received at least 1 dose of study drug and had evaluable PK data to calculate AUC(0-24). Participants were analyzed based on the treatment they received.

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: All randomized participants

6. Primary Endpoint

The registry lists the primary outcome as Pharmacokinetics (PK): Area Under the Concentration Time Curve (AUC) of LY2963016 and US-Approved Lantus, measured over 30 minutes predose up to 24 hours postdose in all treatment periods.

The primary endpoint was the area under the concentration-time curve for LY2963016 and US-approved Lantus from 0 to 24 hours after dosing. AUC represents the accumulated drug concentration over a specified time interval. It combines information across the concentration-time profile rather than describing concentration at only one measurement time. The registry describes the measurement timeframe as 30 minutes predose up to 24 hours postdose in all treatment periods and gives the endpoint unit as picomoles*hour/liter (pmol*h/L).

The endpoint is a pharmacokinetic measure: it characterizes drug exposure, rather than a clinical outcome. The registry reports the treatment values as geometric means and identifies geometric coefficient of variation as the dispersion measure. A geometric mean is commonly used for positive measurements that are better described through multiplicative than additive variation. The coefficient of variation conveys relative dispersion around the geometric mean; it is not a confidence interval for the treatment comparison.

The primary endpoint can describe the exposure observed after the study doses and within the study timeframe. On its own, it does not establish that the treatments are equivalent. That conclusion would require a defined comparison and an appropriate inferential framework, such as a treatment ratio with uncertainty and a prespecified margin. Those details are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry record identifies the primary measure as a geometric mean and the accompanying dispersion measure as geometric coefficient of variation. It does not report the statistical model, the inferential procedure, or a confidence interval for the treatment comparison. The explanations below describe general statistical concepts; they should not be read as a description of undocumented analysis procedures.

What does AUC measure?

In general, area under the concentration-time curve summarizes exposure over a defined interval. Concentration is observed at times across the interval, and the area represents accumulated concentration over time. AUC is useful when a single concentration measurement would not capture the pattern of exposure. In this study, the specified interval was 0 to 24 hours, and the recorded measurement timeframe extended from 30 minutes predose up to 24 hours postdose in all treatment periods. The endpoint unit was picomoles*hour/liter (pmol*h/L).

Why report a geometric mean?

In general, the arithmetic mean describes an additive center: individual values contribute through their absolute distances from the mean. A geometric mean is suited to positive values with multiplicative variation, where proportional changes are more relevant than fixed absolute changes. It is often interpreted on a logarithmic scale, although the registry record does not report whether a log-scale model was used for this analysis. Reporting a geometric mean does not identify the method used to estimate a treatment comparison.

What does the coefficient of variation convey?

In general, a coefficient of variation expresses dispersion relative to the scale of a measurement. A geometric coefficient of variation is associated with multiplicative variability. It is not a measure of the precision of an estimated treatment effect, and it is not interchangeable with a confidence interval. The posted entries are 42.0 for LY2963016 and 35.0 for US-approved Lantus. The registry record does not give additional detail about how these values were calculated or their uncertainty.

Why does crossover structure matter?

In a crossover study, the same participant can contribute observations under more than one treatment. A within-participant comparison can account for stable characteristics that might otherwise contribute to between-person variability. However, observations from the same participant are related rather than independent. Period effects, treatment sequence, and possible carryover are design considerations that may influence how a treatment contrast is estimated. The four-period schedule and washout are described in the registry record, but the analysis method for these design features is not reported there.

Consequently, arm-level geometric means are not enough to recover a paired treatment estimate. The individual paired observations, their covariance, and the fitted model would be needed for that. The registry record gives neither a treatment ratio nor a confidence interval for a primary comparison. No statistical test or model should be inferred from the descriptive summaries alone.

What does a confidence interval add?

In general, a confidence interval gives a range of values compatible with an estimate under a specified statistical procedure. Its width reflects precision: a narrower interval indicates greater precision than a wider interval under the same framework. It can also show whether the data remain compatible with effects that differ meaningfully from the point estimate. A confidence interval is not a probability statement about a fixed parameter after the interval has been calculated. No confidence interval for the primary treatment comparison is reported in the registry record.

For a comparison of positive exposure measures, investigators may express a treatment contrast as a ratio. In general, a ratio near a prespecified equivalence range would be assessed against the limits of that range, together with uncertainty. Merely observing two geometric means does not define an equivalence assessment. The registry record does not report a treatment ratio, an equivalence range, or a non-inferiority criterion.

How should planning calculations be read?

General sample-size calculations estimate how many observations or participants a hypothetical future study may need under stated assumptions. The planning illustration associated with this record uses a two-sided significance level of 0.05, equal allocation, and a normal approximation; its target effect is expressed as a stated fraction of the observed effect. For non-time-to-event outcomes, planning quantities are expressed as participants per arm. Such calculations are planning illustrations, not observed power and not evidence that this trial was designed around those assumptions. The trial's own sample-size justification is not reported in the registry record.

Planning calculations based on an observed effect should be treated cautiously. The observed effect is itself uncertain, and the calculation does not add evidence about the treatment contrast. It does not compensate for missing uncertainty estimates or establish that the original study had a particular probability of detecting an effect. The registry record does not report an interim analysis plan or a statistical analysis plan.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary pharmacokinetic outcome and two secondary outcomes: maximum glucose infusion rate (Rmax) and total amount of glucose infused (Gtot) over the clamp procedure. It also records four outcome measures. The posted results identify no analyses, and values were missing or not estimable for a two-arm comparison for another endpoint. The record does not explain the relationship between the listed outcome-measure count and the posted secondary outcomes.

When several outcomes or comparisons are examined, multiplicity can increase the chance of obtaining an apparently notable result by chance. General approaches include identifying a primary outcome in advance, adjusting significance thresholds, or treating secondary outcomes as exploratory. The registry record does not report a multiplicity adjustment, a testing hierarchy, or a prespecified analysis plan. It is therefore not possible to determine how multiple outcomes were addressed or whether any unreported analyses were conducted.

For the primary endpoint, the analysis population is described as randomized participants who received at least one dose and had evaluable pharmacokinetic data to calculate AUC(0-24). Participants were analyzed according to treatment received. The reported analysis counts are 87.0 for LY2963016 and 89.0 for US-approved Lantus. The record does not report the number or reasons for missing endpoint observations, or the procedures used to address missing data.

The registry also does not report whether all randomized participants were included in a separate intention-to-treat analysis, how protocol deviations were handled, or whether sensitivity analyses were performed. These omissions limit assessment of how robust the results are to exclusions and missing measurements. The analysis population description is useful, but it does not provide a full account of participant flow or the statistical handling of incomplete data.

11. Safety Results

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

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 4% reporting threshold.

Most frequent non-serious adverse event terms

The safety figures list 0 serious adverse events among 89 participants at risk for LY2963016 and 0 among 90 participants at risk for US-approved Lantus. These are treatment-specific entries in a crossover study; they should not be added to estimate the number of distinct participants. The registry record lists 42 participants with other adverse events for each treatment, with 89 and 90 participants at risk, respectively.

These counts are not equivalent to a comparison of event rates adjusted for exposure time or within-participant treatment sequence. The record does not report event timing, severity details for the other adverse events, or a statistical comparison of safety outcomes. It also does not report a confidence interval for a safety contrast. The serious adverse event terms list is empty.

The deaths field is not populated for either treatment, so deaths are not reported in the registry record; an empty field should not be interpreted as a reported count of zero. The figures describe what the registry records for the study and do not establish that either treatment has a particular safety profile beyond these observations.

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

The posted primary outcome describes pharmacokinetic exposure after single-dose administration of LY2963016 and US-approved Lantus in healthy participants. The reported geometric means are 1720.0 and 1900.0, with geometric coefficient of variation entries of 42.0 and 35.0. Those summaries help characterize the measurements but do not provide a formal estimate of the treatment contrast or its precision.

The registry record does not report a ratio of geometric means, a confidence interval for the comparison, or an equivalence or non-inferiority margin. As a result, the posted summaries do not establish that exposure was equivalent, non-inferior, or statistically different. A statistical conclusion about a contrast requires a defined estimand and a comparison method, along with uncertainty. The record does not provide enough information to reconstruct those elements.

The results also have a specific scope. Participants were healthy, the study used single subcutaneous doses, and each treatment period included a clamp lasting 24 hours. The findings described by these records concern exposure in that setting. They do not establish outcomes with repeated administration or outcomes in people with a condition. The primary measure is pharmacokinetic, not a measure of clinical benefit.

The safety counts are likewise descriptive. The registry reports no serious adverse events in the listed treatment groups and reports 42 participants with other adverse events for each treatment. Without further detail about event type, timing, exposure, or comparative uncertainty, these counts do not support a broad comparative safety conclusion.

Overall, the registry record documents the design, endpoint, arm-level summaries, and some safety counts. It does not report enough inferential detail to support a precise treatment-comparison claim. The distinction between a descriptive result and a formal conclusion is especially important in a crossover study, where paired observations and period-related features can affect the comparison.

13. Why This Trial Matters Statistically

This study is statistically useful as an example of how design and outcome summaries need to be read together. The crossover structure means that participants received both treatments across periods. Such designs can make within-participant comparisons informative, because stable participant characteristics are shared across treatment observations. At the same time, the analysis must account for the relationship between measurements from the same participant and consider period or sequence effects. The registry describes the schedule but does not report how those features were modeled.

The primary outcome also illustrates the difference between describing each treatment and estimating a treatment contrast. Geometric means and geometric coefficients of variation characterize the reported arm summaries. They do not reveal the paired treatment differences or quantify their uncertainty. A treatment ratio and confidence interval would address a different statistical question than two separate arm-level summaries.

The record gives a defined analysis population, but it does not provide a full account of missing observations, exclusions, or sensitivity analyses. For readers evaluating a trial, those details help establish which observations support the outcome and whether conclusions may depend on analysis choices. Their absence in the registry record constrains the level of statistical interpretation that is justified.

Finally, planning illustrations should not be confused with evidence about the study's design or observed certainty. A calculation based on an observed effect is a hypothetical planning exercise under assumptions, not observed power. The trial's own sample-size justification is not reported in the registry record. Together, these features make the study a practical example of why endpoint summaries, inferential estimates, design-aware analysis, and transparent reporting serve different roles.

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 primary result is reported as treatment-specific geometric means and geometric coefficients of variation, without a treatment contrast or confidence interval. This limits assessment of the magnitude and precision of the comparison. The registry record does not report an equivalence or non-inferiority margin, so the descriptive values cannot establish either conclusion.

The crossover design makes paired analysis and period-related considerations relevant. Although the record describes four periods and at least a 7 day washout, it does not report the statistical model, treatment sequence details, handling of period effects, or assessment of carryover. The arm-level summaries do not make those analyses recoverable.

The analysis population is defined, and treatment-specific analysis counts are posted, but participant flow and missing-data handling are not reported in the registry record. Reasons for unevaluable pharmacokinetic data, protocol deviations, sensitivity analyses, and any separate analysis population are also not reported in the registry record.

The posted record lists secondary outcomes but does not provide a complete set of inferential results. It does not report a multiplicity procedure or explain how multiple outcomes were considered. Safety information is also limited to counts, without detailed event descriptions, exposure-adjusted comparisons, or comparative uncertainty. The deaths field is not populated.

Finally, the study concerns single-dose exposure in healthy participants under a clamp procedure. Its results do not directly describe longer-term use or outcomes in other populations. These limitations concern the information available in the registry record and should not be mistaken for proof that particular analyses or procedures were absent from the study itself.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: A Study to Compare LY2963016 and US-approved Lantus® After Single Dose Administration to Healthy Participants — NCT01688635.
• Registry record last updated 2014-10-07; status last verified 2014-10.
• Results first posted 2014-10-07.
• 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.

18. Record Summary

This completed phase 1 study was randomized, double-blind, and crossover, and enrolled 91 healthy participants. It compared two single subcutaneous doses of LY2963016 with two single subcutaneous doses of US-approved Lantus, each at 0.5 U/kg, across four periods. Each dose was followed by a 24-hour euglycemic clamp, with at least a 7 day washout between periods.

The primary endpoint was AUC(0-24), reported as a geometric mean with geometric coefficient of variation. The posted values were 1720.0 for LY2963016 and 1900.0 for US-approved Lantus. The record does not report a treatment-comparison confidence interval or a formal equivalence analysis. Serious adverse event counts were 0 in each listed treatment group; other adverse events were recorded for 42 participants in each group.

Important details, including the statistical model, sample-size justification, missing-data procedures, and multiplicity handling, are not reported in the registry record.