A Study of LY2944876 in Healthy Japanese and Non-Japanese Participants: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of LY2944876 in Healthy Japanese and Non-Japanese Participants (NCT02188303), a randomized phase 1 study. The primary outcome is Number of Participants With One or More Serious Adverse Event(s) (SAEs) Considered by the Investigator to Be Related to Study Drug Administration.

2. Clinical Question

3. Trial Design

This was a Phase 1, randomized, double-blind, sequential study of LY2944876 in healthy participants. The registry gives an enrollment of 48 and lists the study status as terminated. The study began in 2014-07, with primary completion in 2014-12. The reason for termination is not reported in the registry record.

The design combined single-dose and multiple-dose assessments. Part A concerned single doses in Japanese participants, while Part B concerned multiple doses in non-Japanese participants. The listed single-dose cohorts compared placebo with LY2944876 at 10 mg, 30 mg, or 50 mg. For the multiple-dose cohorts, one LY2944876 regimen was 40 mg once daily on Days 1-7. Another was titrated, with scheduled doses of 15 mg on Day 1, 30 mg on Day 4, up to 60 mg on Day 6, and up to 80 mg on Days 8, 10, and 12. Matching placebo regimens are also listed.

Sequential means that the study proceeded through cohorts in sequence; the registry does not describe the rules governing progression between cohorts. The record identifies randomization and double masking, but the allocation method, who was masked, and details of dose escalation are not reported in the registry record. All listed doses were administered by subcutaneous injection. Participation was expected to last up to about 7 weeks in Part A and about 8 weeks in Part B, excluding screening. A post-study safety assessment was planned approximately 6 weeks after the final dose.

The study also listed pharmacokinetic outcomes: area under the concentration-versus-time curve from time zero to 168 hours after dosing and maximum concentration. Numerical results for those outcomes are 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.

Only the first 6 of 8 groups are shown.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All enrolled participants, whether or not they completed all protocol requirements.

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.

Only the first 6 of 9 groups are shown.

6. Primary Endpoint

The registry lists the primary outcome as Number of Participants With One or More Serious Adverse Event(s) (SAEs) Considered by the Investigator to Be Related to Study Drug Administration, measured over Pre-dose (PRD) through Study Completion (Up to Day 40).

The primary endpoint is the number of participants with one or more serious adverse events (SAEs) that the investigator considered related to study-drug administration. The observation period ran from pre-dose through study completion, up to Day 40. The registry defines an SAE as an event involving specified serious consequences, including death, life-threatening events, persistent or significant disability, certain important medical events, congenital anomalies or birth defects, or events requiring or prolonging hospitalization.

The endpoint is a count of participants, rather than a count of separate events. A participant with more than one qualifying SAE would still contribute as one participant to this measure. The relatedness qualification also matters: the primary endpoint counts only SAEs considered by the investigator to be related to study-drug administration. The registry separately notes that summaries of SAEs and other adverse events, regardless of causality, are presented in the adverse-events record.

In an early-phase study, counting serious events is a direct way to describe a key safety outcome during exposure. It does not by itself establish that an observed event was caused by treatment, nor does a zero count establish the absence of risk. The number of participants exposed and the duration of observation are relevant to how much information a zero count conveys. The posted primary outcome count was zero in every arm, but the study was small and the record does not provide an inferential comparison for this endpoint.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What kind of outcome is this?

General: A binary participant outcome classifies each participant according to whether the specified event occurred at least once during the observation period. A count of affected participants can then be reported for each arm. Here, the event definition is narrower than “any adverse event”: it is one or more SAEs that the investigator considered related to study-drug administration. The posted measure is the number of participants meeting that definition. The registry lists the count as 0.0 in every arm.

Because the endpoint counts participants rather than all event occurrences, it does not show whether any participant experienced multiple events. It also does not include non-serious events in the primary count. Separate adverse-event figures describe participants with other adverse events regardless of causality. Keeping these outcome definitions distinct is important when interpreting safety summaries.

What does a confidence interval usually convey?

General: A confidence interval is a range of values compatible with the observed data under a specified statistical procedure. It expresses uncertainty around an estimate; it is not a guarantee that the true value lies in the interval. For a binary event rate or a difference between groups, a confidence interval can show how imprecise the estimate is, particularly when the number of participants or events is small. No confidence interval for the primary endpoint is reported in the registry record, so no interval-based precision claim can be made from these posted results.

Why is a zero count not proof of zero risk?

General: An event that is uncommon can fail to appear in a limited group of participants simply by chance. The absence of observed events therefore describes the study sample and observation period, not every possible future exposure. Precision depends on such factors as the number of participants, duration of follow-up, and event frequency. The small arm sizes listed in this study limit how much can be inferred about rare events. A zero count also does not provide a comparative estimate if the analysis does not report one.

What can the design contribute?

Randomization and double masking are stated features of this study. In general, randomization aims to reduce systematic differences between groups, and masking can reduce the influence of knowledge about treatment assignment on care or assessment. The registry does not report the allocation procedure, masking roles, or cohort progression rules. The study is described as sequential, and its listed cohorts have different regimens and participant counts. Consequently, the record does not justify treating every arm as part of one simple, balanced comparison.

What analyses are reported?

The registry reports 0 analyses for the outcomes and notes that comparison values are missing or not estimable for a two-arm comparison of the binary endpoint. It does not report the statistical analysis plan, a particular test, adjusted estimates, or confidence intervals. The stated sample-size assumptions describe a planning illustration based on an observed effect, but no comparison-specific planning results are reported for this endpoint. Such planning illustrations, when available, are not observed power and do not establish that a study had adequate power for rare-event safety assessment.

General: Over-dispersion is a concern when data vary more than a statistical model expects, which can make model-based uncertainty estimates too narrow if ignored. It is mainly relevant to outcomes analyzed as counts or rates under particular models. The primary outcome is reported as a participant count, and the registry does not report a model-based analysis or any adjustment for over-dispersion. It would therefore be inappropriate to infer that such a method was used.

Pharmacokinetic outcomes are listed as secondary outcomes, including AUC(0-168h) and Cmax. These measures describe drug concentration over time and peak concentration, respectively, in general. Their numerical summaries and analysis methods are not reported in the registry record. The reported evidence thus supports descriptive reading of the event counts, not reconstruction of an unreported inferential analysis.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Cohorts 1-3 - Placebo", "Cohort 1 - 10 mg LY2944876", "Cohort 2 - 30 mg LY2944876", "Cohort 3 - 50 mg LY2944876", "Cohort 4 - Placebo", "Cohort 4 - 40 mg LY2944876")
n      <- c(6, 6, 6, 6, 4, 12)
events <- c(0, 0, 0, 0, 0, 0)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Cohorts 1-3 - Placebo  6  0  0.0  0.0  45.9  0.0  39.0  0.4  41.0
ARM  Cohort 1 - 10 mg LY2944876  6  0  0.0  0.0  45.9  0.0  39.0  0.4  41.0
ARM  Cohort 2 - 30 mg LY2944876  6  0  0.0  0.0  45.9  0.0  39.0  0.4  41.0
ARM  Cohort 3 - 50 mg LY2944876  6  0  0.0  0.0  45.9  0.0  39.0  0.4  41.0
ARM  Cohort 4 - Placebo  4  0  0.0  0.0  60.2  0.0  49.0  0.5  52.2
ARM  Cohort 4 - 40 mg LY2944876  12  0  0.0  0.0  26.5  0.0  24.2  0.2  24.7

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary safety endpoint and two secondary pharmacokinetic outcomes: AUC(0-168h) and Cmax for LY2944876. The numerical results for the secondary outcomes are not reported in the registry record. The registry also reports 0 analyses, and it does not report a statistical analysis plan or a multiplicity strategy.

Multiplicity arises when several outcomes, doses, cohorts, or comparisons are examined. General: conducting multiple statistical tests can increase the chance of at least one apparently unusual result, so a prespecified approach may control or otherwise address that issue. Without a reported plan, it is not possible to determine whether adjustments were intended, which comparisons were considered primary, or how the secondary measures were to be interpreted. No claim about adjustment or absence of adjustment can be made from the record.

The primary endpoint population is described as all enrolled participants, whether or not they completed all protocol requirements. The record does not provide a separate analysis population, participant-level missingness, handling rules for incomplete observations, or details of withdrawals by arm. It therefore does not establish how incomplete safety follow-up was handled beyond the stated population definition. The reason for termination is not reported in the registry record.

For the primary binary endpoint, values for a two-arm comparison are reported as missing or not estimable. No sponsor analysis takes precedence over a recalculation because no recalculated result is presented. The posted results should consequently be read as arm-level descriptive counts, without a reported adjusted or unadjusted treatment contrast.

12. 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 non-serious adverse event terms

The serious adverse-event figure is the number of participants with at least one SAE considered by the investigator to be related to study-drug administration. It is not the number of all serious events, and it does not include every adverse event regardless of causality. The registry reports 0.0 participants with this primary outcome in each listed arm during pre-dose through study completion, up to Day 40.

The separate adverse-event figures count participants with other adverse events regardless of causality. Those counts are distinct from the primary SAE endpoint and do not establish that treatment caused the events. The registry does not provide event-level descriptions in the listed summary or report deaths in these arm entries; the death values are not populated. The serious-event terms list is empty.

Zero observed related SAEs is a descriptive finding, not proof that serious events cannot occur. The arm sizes are small, ranging from 2.0 to 12.0 participants, and the follow-up period is finite. No confidence interval or statistical comparison is reported for the primary outcome. These summaries therefore do not quantify the precision of a between-arm difference or the frequency of rare events beyond the observed participants and period.

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

The result means that the registry’s primary endpoint recorded no participants with an SAE considered by the investigator to be related to study-drug administration in any listed arm. It also means that non-serious adverse events were recorded in several arms when events were summarized regardless of causality. Both statements are limited to the participants and observation period represented in the posted record.

It does not mean that LY2944876 has no serious safety risks, that all adverse events were absent, or that the drug was proven safe. A finite study may not observe an uncommon event, and a zero count cannot establish that its true occurrence probability is zero. The endpoint also depends on the investigator’s assessment of relatedness, while the separate adverse-event figures include events regardless of causality.

It does not establish a difference between LY2944876 and placebo. Although the study was randomized and double-blind, the registry reports no inferential analysis for this endpoint, and comparison values are missing or not estimable. The cohorts have different doses, schedules, and arm sizes; the results are not a single pooled dose comparison. No effect estimate or confidence interval is available to characterize comparative precision.

Nor does the primary endpoint answer whether the drug changes diabetes outcomes. The participants were healthy volunteers, and this study focused on safety, tolerability, and pharmacokinetics. The record lists pharmacokinetic outcomes but does not report their numerical results. It gives no basis for a conclusion about clinical benefit or effectiveness. The study status is terminated, but the reason is not reported in the registry record. The most defensible interpretation is therefore narrow: no qualifying related SAEs were posted for these arms, and other adverse events were reported separately, without a reported statistical comparison.

14. Why This Trial Matters Statistically

This trial illustrates why safety summaries need careful attention to the event definition. The primary outcome is not “all adverse events” or even all SAEs. It is the number of participants with one or more serious events that investigators considered related to study-drug administration. The registry separately reports participants with other adverse events regardless of causality. Those are different summaries, and merging them would change the question being answered.

It also illustrates the limits of zero-event evidence in small early-phase cohorts. A zero count is informative about what was observed in the study, but its interpretation depends on the number of participants exposed and the duration of observation. Small cohorts provide limited information about rare outcomes. Descriptive counts should not be mistaken for a precise estimate of risk or a demonstration that an event cannot occur.

The sequential design and varied dosing regimens make context essential. The listed cohorts include single-dose and multiple-dose exposures, with distinct dose schedules and arm sizes. A single overall comparison would obscure those differences unless an analysis plan explicitly justified pooling. No such analysis plan is reported in the registry record, and no inferential results are posted for the primary endpoint.

Finally, a trial can list several scientifically relevant outcomes without reporting numerical results for all of them. Here, pharmacokinetic outcomes are listed, but their estimates are not reported in the registry record. The distinction between an outcome being named and its result being available is important for transparent interpretation. The available evidence supports a limited account of observed safety counts, not broader conclusions about pharmacokinetics, clinical benefit, or comparative safety.

15. Limitations

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

The main limitation is the small size of the individual cohorts, with listed arm sizes from 2.0 to 12.0 participants. Such counts offer limited ability to characterize uncommon serious events. The absence of observed primary endpoint events should therefore be understood as a sample-specific result, not as evidence that the event risk is absent.

The study includes multiple cohorts with different participant groups, doses, and schedules. Part A involved single doses in Japanese participants, and Part B involved multiple doses in non-Japanese participants. These differences complicate any informal comparison across all arms. The registry does not report the detailed allocation process, progression rules, or a statistical analysis plan, so the intended structure of comparisons cannot be fully assessed.

The posted primary endpoint is specifically limited to SAEs considered related by the investigator. The record does not report independent adjudication of relatedness, participant-level event details, or the reasoning behind attribution. Separate adverse-event counts are reported regardless of causality, but they do not provide a complete account of event severity, timing, or recurrence in the summaries.

No inferential comparison, confidence interval, or numerical pharmacokinetic result is reported. The registry does not report missing-data handling beyond defining the primary population as all enrolled participants whether or not they completed protocol requirements. The study is listed as terminated, but the reason is not reported in the registry record. These omissions constrain interpretation of completeness, precision, and the rationale for the final observed data.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Study of LY2944876 in Healthy Japanese and Non-Japanese Participants — NCT02188303.
• Registry record last updated 2021-05-27; status last verified 2021-05.
• Results first posted 2021-04-14.
• 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.

19. Record Summary

This Phase 1 study evaluated single and multiple doses of LY2944876 in healthy Japanese and non-Japanese participants. It was randomized, double-blind, and sequential, with 48 participants enrolled. The registry lists the status as terminated; the reason is not reported in the registry record.

The primary outcome was the number of participants with one or more SAEs considered by the investigator to be related to study-drug administration, through study completion up to Day 40. The posted count was 0.0 in each listed arm. Non-serious adverse events were reported separately, regardless of causality. The registry also lists AUC(0-168h) and Cmax as secondary outcomes, but their numerical results are not reported in the registry record.

No analysis results or statistical comparison for the primary endpoint are reported. The posted counts are descriptive and do not establish a comparative effect, eliminate the possibility of rare events, or address clinical benefit.