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 Effect of LY2189265 on Insulin Secretion in Response to Intravenous Glucose (NCT01300260), a randomized phase 1 study. The primary outcome is Maximum Insulin Concentration (Cmax) - First Phase Response.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT01300260 |
| Phase | Phase 1 |
| Condition | Diabetes Mellitus, Type 2 |
| Allocation | Randomized |
| Design model | Crossover |
| Masking | Triple |
| Enrollment | 32 |
| Arms in the primary outcome | 4 |
| Lead sponsor | Eli Lilly and Company |
| Results posted | Yes |
2. Clinical Question
Population
The primary endpoint population included healthy participants and participants with type 2 diabetes mellitus who received at least 1 dose of LY2189265 or placebo and had evaluable first-phase INSCmax(0-10) data. The registry reports endpoint groups for healthy participants and for participants with type 2 diabetes mellitus. The broader study enrollment was 32.
Intervention
LY2189265, also identified in the arm descriptions as dulaglutide, was given as a single 1.5 mg subcutaneous injection on Day 1 of a treatment period. The endpoint was assessed on Day 3 after the study’s insulin infusion and intravenous dextrose bolus.
Comparator
Placebo was given as a single subcutaneous injection on Day 1 of the other treatment period. Participants were assigned to LY2189265 followed by placebo or placebo followed by LY2189265, consistent with the randomized crossover design.
Primary question
Within each reported population, how did the geometric mean maximum plasma insulin concentration during the first 10 minutes after the first dextrose bolus compare following LY2189265 versus placebo? The registry reports mixed-model ratios, confidence intervals and p-values for the healthy-participant and type 2 diabetes mellitus comparisons.
The biological question is whether the measured insulin response to an experimentally administered glucose stimulus differs between the two treatment periods. This is a laboratory endpoint, not a direct measure of longer-term glucose control or a clinical outcome. The registry’s brief summary describes the study purpose as measuring the effect of LY2189265 on insulin levels in response to glucose intake; the recorded procedure used an intravenous dextrose bolus after an insulin infusion.
The comparisons are reported separately for healthy participants and participants with type 2 diabetes mellitus. That distinction matters because these are different populations, and the registry presents separate endpoint summaries and model-based comparisons for them. The record does not report a single pooled estimate across both populations.
3. Trial Design
The registry describes a randomized, triple-masked, crossover Phase 1 study. Its status is completed, and enrollment is recorded as 32. The condition listed is diabetes mellitus, type 2; however, the primary endpoint description and arm titles also include healthy participants. The record does not explain how the condition listing relates to the inclusion of healthy participants.
In a crossover design, participants receive treatments in different periods, so each participant may contribute observations under more than one treatment. Here, the listed sequences are LY2189265 followed by placebo and placebo followed by LY2189265. The randomized assignment concerns which treatment came first. The registry does not report the masking roles, the length of any interval between periods, or whether the analysis adjusted for period, sequence, or possible carryover effects.
On Day 1 of each period, participants received a single subcutaneous injection of LY2189265 or placebo. On Day 3, they underwent a 6-hour insulin infusion followed by an intravenous dextrose 50% bolus. The primary measurement was the maximum plasma insulin concentration during the 0-10 minutes after that first dextrose bolus, corrected for baseline. The description also records a later dextrose bolus, a 20% dextrose infusion and a glucagon bolus, but these later procedures are not the primary endpoint assessed in this analysis.
Endpoint summaries are displayed separately for healthy participants and participants with type 2 diabetes mellitus. The endpoint analysis counts differ between treatment groups within the type 2 diabetes mellitus population; the registry does not explain the difference. The enrollment figure should therefore not be treated as the endpoint denominator or as the count for any one reported comparison. The specific sample-size justification and detailed design assumptions 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.
Period 1 of Study: First Intervention
| Stage | LY2189265 First, Then Placebo | Placebo First, Then LY2189265 |
|---|---|---|
| STARTED | 15 | 17 |
| Received at Least 1 Dose of Study Drug | 15 | 17 |
| COMPLETED | 14 | 16 |
| NOT COMPLETED | 1 | 1 |
Reasons for not completing this period:
| Reason | LY2189265 First, Then Placebo | Placebo First, Then LY2189265 |
|---|---|---|
| Adverse Event | 0 | 1 |
| Withdrawal by Subject | 1 | 0 |
Washout Period of at Least 28 Days
| Stage | LY2189265 First, Then Placebo | Placebo First, Then LY2189265 |
|---|---|---|
| STARTED | 14 | 16 |
| COMPLETED | 14 | 16 |
| NOT COMPLETED | 0 | 0 |
Period 2 of Study: Second Intervention
| Stage | LY2189265 First, Then Placebo | Placebo First, Then LY2189265 |
|---|---|---|
| STARTED | 14 | 16 |
| COMPLETED | 14 | 15 |
| NOT COMPLETED | 0 | 1 |
Reasons for not completing this period:
| Reason | LY2189265 First, Then Placebo | Placebo First, Then LY2189265 |
|---|---|---|
| Adverse Event | 0 | 1 |
Analysis population for the primary outcome, as defined in the registry: All participants (healthy and with type 2 diabetes mellitus \[T2DM\]) who received at least 1 dose of study drug (LY2189265 or Placebo) with evaluable INSCmax(0-10) first response phase 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: Healthy participants or participants with type 2 diabetes mellitus (T2DM) who received at least one dose of study drug (LY2189265 or Placebo).
| Characteristic | Unit | Healthy Participants | Participants With Type 2 Diabetes Mellitus (T2DM) | Total |
|---|---|---|---|---|
| Participants analysed | 10 | 22 | 32 | |
| Age, Continuous | years | 51.9 (SD 5.0) | 56.3 (SD 6.1) | 54.9 (SD 6.1) |
| Sex: Female, Male: Female | Participants | 3 | 7 | 10 |
| Sex: Female, Male: Male | Participants | 7 | 15 | 22 |
| Ethnicity (NIH/OMB): Hispanic or Latino | Participants | 0 | 0 | 0 |
| Ethnicity (NIH/OMB): Not Hispanic or Latino | Participants | 10 | 22 | 32 |
| Ethnicity (NIH/OMB): Unknown or Not Reported | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): American Indian or Alaska Native | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): Asian | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): Native Hawaiian or Other Pacific Islander | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): Black or African American | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): White | Participants | 10 | 22 | 32 |
| Race (NIH/OMB): More than one race | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): Unknown or Not Reported | Participants | 0 | 0 | 0 |
| Region of Enrollment: Germany | participants | 10 | 22 | 32 |
6. Primary Endpoint
The registry lists the primary outcome as Maximum Insulin Concentration (Cmax) - First Phase Response, measured over 0-10 minutes after dextrose bolus on Day 3 postdose.
| Element | Registry entry |
|---|---|
| Result type | Geometric Mean |
| Measure of spread | 95% Confidence Interval |
| Unit | picomole per liter (pmol/L) |
| Endpoint classification | not reduced to a single comparison |
The primary endpoint is maximum insulin concentration (Cmax) during the first-phase response, measured in picomoles per liter. It covers the 0-10 minutes after the first intravenous dextrose 50% bolus on Day 3 of a treatment period. The concentration was corrected for baseline, defined as the mean insulin concentration measured between -30 and 0 minutes relative to the bolus. The endpoint population was restricted to participants who received at least 1 dose of study drug and had evaluable first-response-phase data.
This measure captures the early insulin response following a standardized glucose stimulus. A maximum concentration provides a summary of the peak response within the specified time window, while baseline correction accounts for insulin concentrations measured immediately before the stimulus. These features make the endpoint suitable for comparing short-term physiological responses under the two treatment conditions. That is a general explanation of the endpoint’s statistical and physiological role, not a claim about clinical benefit.
The registry reports geometric means and 95% confidence intervals for each treatment group, with separate mixed-model ratios for healthy participants and participants with type 2 diabetes mellitus. A geometric summary is appropriate for positive measurements that may be skewed; it describes the central level on a multiplicative rather than additive scale. The endpoint does not measure long-term outcomes, and the registry does not report a clinically meaningful threshold for interpreting the size of a difference.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
For healthy participants, the registry reports a geometric least-squares mean ratio of 2.96 for LY2189265 relative to placebo. Its 95% confidence interval is 2.41 to 3.64, and the reported p-value is <0.001. For participants with type 2 diabetes mellitus, the reported ratio is 5.40, with a 95% confidence interval of 4.09 to 7.13 and a p-value of <0.001. Both comparisons are from mixed models and concern the baseline-corrected first-phase insulin Cmax endpoint.
Each ratio is a relative comparison on the geometric scale within its stated population. The reported values are above 1, and both confidence intervals lie above 1. In plain statistical terms, the model estimates a higher geometric mean endpoint under LY2189265 than under placebo in each reported population. The p-values indicate that the model-based comparisons are inconsistent with an equal-treatment ratio under the test’s assumptions. They do not by themselves describe the size or clinical importance of the response.
The arm summaries give additional context. Among healthy participants, the geometric mean is 233.0 pmol/L under placebo and 689.0 pmol/L under LY2189265. Among participants with type 2 diabetes mellitus, the corresponding summaries are 74.3 pmol/L and 401.0 pmol/L. The confidence intervals around these arm estimates are broad, especially for the LY2189265 groups. A confidence interval describes uncertainty in an estimated quantity under the analysis; it is not a range containing every participant’s measurement, nor does it establish that the true value has a particular probability of lying within the specific interval.
The population-specific ratios should not be compared as if the study had formally tested whether treatment effects differ between populations. The registry reports separate model comparisons, but no treatment-by-population interaction test or direct contrast between those ratios is reported. Differences in baseline response, variability, eligibility or analysis populations could affect cross-population comparisons. The record does not provide enough detail to separate those possibilities.
The registry is a Phase 1 study using a controlled physiological stimulus and a short-term laboratory endpoint. Its results describe the recorded insulin response in the analyzed participants under this procedure. They do not establish an effect on longer-term glycemic measures, complications, symptoms, or other clinical outcomes. No clinical threshold for a meaningful Cmax change is reported, so statistical evidence of a difference should not be translated into a claim about clinical importance.
9. Statistical Methods Explained
The registry reports geometric least-squares means and a mixed-model comparison for each population. A least-squares mean is a model-based estimate of the average response under the fitted model, rather than simply a raw arithmetic average. The ratio compares the modeled geometric mean under LY2189265 with the modeled geometric mean under placebo. Because the comparison is expressed as a ratio, 1 represents equal modeled values; a ratio above 1 indicates a larger modeled value for the treatment named first in the comparison.
The geometric mean is useful when a positive outcome is better represented on a multiplicative scale or has a right-skewed distribution. Conceptually, it is based on averaging values after taking logarithms and then returning to the original scale. This general statistical explanation does not establish the exact transformation or model specification used in this trial; the detailed model formula and diagnostics are not reported in the registry record. Geometric summaries are not interchangeable with arithmetic means, and a ratio does not express an absolute difference in pmol/L.
A 95% confidence interval gives a range of estimates compatible with the observed data and the model’s assumptions under repeated sampling. It communicates precision as well as direction. Narrower intervals generally indicate greater precision than wider intervals, though precision alone does not establish clinical relevance. The healthy-participant comparison is reported as 2.96 with a 95% confidence interval from 2.41 to 3.64. The type 2 diabetes mellitus comparison is 5.40 with a 95% confidence interval from 4.09 to 7.13. Both intervals exclude 1, the value corresponding to equal modeled geometric means.
The reported p-value is a measure of how incompatible the observed result is with a specified null hypothesis, assuming the model and other test conditions hold. A p-value is not the probability that the null hypothesis is true, nor does it measure the probability that the result is due to chance in ordinary language. The registry reports p < 0.001 for each population comparison. This threshold does not reveal the exact p-value, and it does not substitute for evaluating the estimate, confidence interval, design, and endpoint meaning.
The mixed-model approach is particularly relevant to crossover data because observations from the same participant are related rather than independent. In general, a model can account for such within-participant structure and for other planned design factors. The registry labels the method as mixed models analysis but does not report the model terms, covariance structure, transformation details, handling of period or sequence, or treatment of missing endpoint observations. It is therefore not possible to determine from the record precisely how those features were handled.
Over-dispersion is a general issue when the observed variability is greater than assumed by a statistical model: standard errors may then be too small and confidence intervals too narrow if the extra variability is ignored. The registry does not identify an over-dispersion assessment for this continuous endpoint, and such a concern should not be asserted as a finding. More generally, model diagnostics and assumptions are important to judging the reliability of model-based intervals and tests; those details are not reported in the registry record.
For each population, the registry also gives treatment-specific geometric means and 95% confidence intervals. These descriptive summaries are not themselves the mixed-model test. The model-based ratio incorporates the analysis method, while dividing or comparing displayed arm summaries would not necessarily reproduce it. With a crossover design, participants’ paired responses and model structure can matter. The record’s reported analysis should therefore be distinguished from any simple re-calculation based only on posted summary statistics.
Sample-size illustrations, when based on an observed effect, are planning exercises rather than evidence about the design quality or the probability that the completed trial detected an effect. They depend on assumptions such as the chosen effect to detect, significance level, allocation and approximation method. The stated assumptions for any planning illustration do not establish that those values were used to design this study. The trial’s own sample-size justification and power calculation are not reported in the registry record; no planning illustration should be described as observed power.
These methods describe different parts of the evidence: the endpoint defines what was measured, the arm summaries show the treatment-specific estimates, and the mixed-model ratios and confidence intervals quantify the reported comparisons. None removes limitations arising from the small, specialized study context, incomplete model detail, or restricted endpoint. Statistical significance is evidence about compatibility with a null comparison under the model, not a verdict about clinical value.
10. Analyses Reported by the Sponsor
| Method | Estimate | 95% CI | P-value |
|---|---|---|---|
| Mixed Models Analysis | Geometric least squares (LS) mean ratio 2.96 | 2.41 to 3.64 | < 0.001 |
| Mixed Models Analysis | Geometric least squares (LS) means ratio 5.40 | 4.09 to 7.13 | < 0.001 |
The registry’s primary comparative results are the sponsor-reported mixed-model analyses. They give geometric least-squares mean ratios of 2.96 in healthy participants and 5.40 in participants with type 2 diabetes mellitus, with their respective 95% confidence intervals and p-values. These are model-based comparisons, not simple ratios calculated directly from the displayed arm summaries.
A recalculation from posted summary statistics, if presented alongside the registry analysis, is an unadjusted check and may not reproduce a mixed-model estimate from crossover data. It may not account for the participant-level pairing or the model’s treatment of design features. The registry record does not report a discrepancy between the sponsor analysis and a recalculation. Accordingly, the sponsor’s reported analysis remains the relevant model-based result; the record does not indicate a conflict that would call for treating a recalculated value as primary.
The detailed model specification is not reported in the registry record, so readers cannot independently assess every modeling choice from the available description. The sponsor analysis should be interpreted with that qualification and with the limits of the endpoint and population in mind.
11. Multiplicity, Missing Data and Analysis Populations
The registry reports one primary endpoint and one secondary outcome, Insulin Maximum Concentration (Cmax), with six outcome measures and 12 analyses recorded overall. It does not report a multiplicity adjustment, a hierarchy of hypotheses, or which comparisons were designated confirmatory. When multiple outcomes or analyses are examined, the chance of at least one small p-value can increase; that is a general statistical consideration, not a claim that the reported findings are false. Without an analysis plan or adjustment details in the registry record, the reported p-values should be read as the results of the stated comparisons rather than as evidence that all possible testing was controlled.
The primary endpoint description defines an analysis population consisting of participants who received at least 1 dose and had evaluable endpoint data. The record reports endpoint analysis counts by treatment and population, but does not fully explain exclusions, missing measurements, or the handling of incomplete crossover data. It also does not report whether the primary analysis used an intention-to-treat, per-protocol, or other named population beyond the endpoint-specific description. The number and reasons for participants without evaluable endpoint data are not reported in the registry record.
The registry’s mixed-model label does not by itself reveal how missing observations were handled or what assumptions were made about missingness. In general, missing-data assumptions can affect estimates when the probability of missingness is related to observed or unobserved outcomes. The record does not report sensitivity analyses addressing missing data, nor does it describe imputation.
The reported comparisons are separate for healthy participants and participants with type 2 diabetes mellitus. A formal test of whether the treatment comparison differs between those populations is not reported. Nor are subgroup-specific multiplicity procedures or a prespecified testing sequence reported. These omissions limit interpretation of the collection of analyses but do not change the numerical results stated for the two reported comparisons.
12. 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 |
|---|---|---|---|
| Healthy Participants: Placebo | 0 | 10 | 0.0% |
| Healthy Participants: LY2189265 | 0 | 10 | 0.0% |
| Participants With Type 2 Diabetes Mellitus (T2DM): Placebo | 0 | 21 | 0.0% |
| Participants With Type 2 Diabetes Mellitus (T2DM): LY2189265 | 0 | 21 | 0.0% |
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 |
|---|---|
| Healthy Participants: Placebo | 2 of 10 |
| Healthy Participants: LY2189265 | 6 of 10 |
| Participants With Type 2 Diabetes Mellitus (T2DM): Placebo | 9 of 21 |
| Participants With Type 2 Diabetes Mellitus (T2DM): LY2189265 | 11 of 21 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Healthy Participants: Placebo | Healthy Participants: LY2189265 | Participants With Type 2 Diabetes Mellitus (T2DM): Placebo | Participants With Type 2 Diabetes Mellitus (T2DM): LY2189265 |
|---|---|---|---|---|---|
| Vomiting | Gastrointestinal disorders | 1 of 10 | 1 of 10 | 0 of 21 | 4 of 21 |
| Headache | Nervous system disorders | 0 of 10 | 0 of 10 | 3 of 21 | 2 of 21 |
| Nausea | Gastrointestinal disorders | 1 of 10 | 0 of 10 | 1 of 21 | 2 of 21 |
| Injection site phlebitis | General disorders | 1 of 10 | 0 of 10 | 2 of 21 | 1 of 21 |
| Hypoglycaemia | Metabolism and nutrition disorders | 0 of 10 | 4 of 10 | 0 of 21 | 0 of 21 |
| Decreased appetite | Metabolism and nutrition disorders | 0 of 10 | 0 of 10 | 1 of 21 | 2 of 21 |
| Abdominal distension | Gastrointestinal disorders | 0 of 10 | 1 of 10 | 1 of 21 | 0 of 21 |
| Injection site oedema | General disorders | 0 of 10 | 1 of 10 | 1 of 21 | 0 of 21 |
| Injection site thrombosis | General disorders | 0 of 10 | 1 of 10 | 1 of 21 | 0 of 21 |
| Malaise | General disorders | 0 of 10 | 1 of 10 | 0 of 21 | 1 of 21 |
The registry reports zero participants with serious adverse events in each of the four safety groups: healthy participants receiving placebo, healthy participants receiving LY2189265, participants with type 2 diabetes mellitus receiving placebo, and participants with type 2 diabetes mellitus receiving LY2189265. These are observed serious-adverse-event counts for the groups and periods recorded; they are not proof that serious events cannot occur or that the treatments have equivalent safety.
Other adverse events are reported for 2 participants in the healthy-participant placebo group and 6 in the healthy-participant LY2189265 group. For participants with type 2 diabetes mellitus, the corresponding counts are 9 for placebo and 11 for LY2189265. These counts describe participants affected, not event totals or rates. No serious adverse-event terms are listed in the record. Death counts are not reported in the registry record.
The safety group denominators are reported as 10, 10, 21 and 21, respectively. They should be read as the group-specific counts at risk in the safety record, not assumed to match the endpoint analysis counts. In a crossover study, adverse-event exposure can also relate to treatment periods; the registry summary does not provide enough detail to reconstruct event timing or compare exposure-adjusted risks. The figures are descriptive and do not establish a causal safety difference.
13. What the Result Does, and Does Not, Mean
The registry results show higher model-estimated geometric mean first-phase insulin Cmax under LY2189265 than under placebo in both reported populations. The healthy-participant ratio is 2.96, and the ratio among participants with type 2 diabetes mellitus is 5.40. The 95% confidence intervals are 2.41 to 3.64 and 4.09 to 7.13, respectively, and both reported p-values are <0.001. These estimates describe the short-term response to a controlled intravenous dextrose stimulus.
They do not show that the same relative response would occur in other populations or under ordinary eating conditions. The measured outcome is an early laboratory response after a specified insulin infusion and dextrose challenge. It is not a measure of sustained glucose regulation, diabetes complications, quality of life, or other patient-centered outcomes. No relationship between this endpoint and a clinically important benefit is reported in the registry record.
The results also do not establish that the treatment effect differs between healthy participants and participants with type 2 diabetes mellitus. Separate significant comparisons are not a test of the difference between those comparisons. The registry does not report a formal interaction analysis. Nor can the arm summaries alone establish how much of any apparent cross-population contrast reflects baseline physiology, participant selection, variability, or model features.
Statistical significance does not mean that an effect is important to patients, and a confidence interval does not describe the range of responses among individual participants. The record’s small Phase 1 setting, specialized procedure, endpoint eligibility requirements, and lack of detailed model and missing-data information all constrain generalization. The appropriate conclusion is about the measured endpoint in these analyzed groups, not a broader claim about clinical effectiveness or treatment choice.
14. Why This Trial Matters Statistically
This study is statistically informative because it uses a crossover design to compare a physiological response under LY2189265 and placebo. In general, crossover studies can make within-person comparisons, which can reduce the influence of stable differences between participants. The strength of that feature depends on appropriate design and analysis, including attention to period and sequence effects. Although the registry identifies the design and reports mixed-model analyses, it does not provide enough model detail to assess those elements fully.
The endpoint also illustrates why scale matters. The registry reports geometric means and treatment ratios rather than only arithmetic differences. This represents the comparison multiplicatively and can be useful for positive, skewed measurements. At the same time, a ratio does not communicate an absolute change in pmol/L, and the geometric means and their intervals are needed to understand the scale of the observed concentrations.
Separating healthy participants from participants with type 2 diabetes mellitus is important for transparent interpretation. The reported response estimates differ across these populations, but the absence of a formal between-population test means those separate results should not be taken as proof of effect modification. This is a useful distinction between describing subgroup results and testing whether subgroups differ.
Finally, the endpoint is a mechanistic, short-term measure. It can inform understanding of insulin secretion in response to a controlled glucose challenge, but it is not itself a clinical outcome. Reading the result alongside the design, analysis population, confidence intervals, safety counts and missing reporting helps keep the inference proportional to what the study measured.
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 registry does not provide the full protocol or detailed statistical analysis plan. The exact mixed-model specification, participant-level covariance structure, transformation details, period and sequence terms, and handling of possible carryover are not reported in the registry record. These omissions make it difficult to independently assess the assumptions behind the reported confidence intervals and tests.
Enrollment is recorded as 32, but endpoint analysis counts vary by treatment and population. The record does not explain the reasons for those differences, provide a full participant flow, or report the missing-data mechanism and sensitivity analyses. Safety denominators also do not always match endpoint counts. These figures refer to different recorded analysis contexts and should not be treated as interchangeable.
The registry includes healthy participants as well as participants with type 2 diabetes mellitus, while the listed condition is diabetes mellitus, type 2. The record does not explain this listing or report enough eligibility detail to assess representativeness. Generalization beyond the analyzed groups is consequently limited. The use of a controlled infusion and dextrose challenge also differs from usual daily conditions.
The primary outcome is a short-window, baseline-corrected laboratory measurement. A clinical threshold for meaningful change is not reported, and longer-term clinical outcomes are not described as primary results. The registry also does not report multiplicity procedures, a formal comparison between the two populations, or the sample-size justification. These limitations do not erase the reported model results, but they restrict the conclusions that can be drawn from them.
16. Related Tutorials
17. Related Statistical Calculators
18. Sources
- ClinicalTrials.gov: Effect of LY2189265 on Insulin Secretion in Response to Intravenous Glucose — NCT01300260.
- 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.
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.
19. Record Summary
This completed randomized, triple-masked, crossover Phase 1 study evaluated LY2189265 and placebo in healthy participants and participants with type 2 diabetes mellitus. Enrollment was 32. The primary endpoint was baseline-corrected maximum plasma insulin concentration during the 0-10 minutes after an intravenous dextrose bolus on Day 3 of a treatment period.
The registry reports mixed-model geometric least-squares mean ratios of 2.96 in healthy participants and 5.40 in participants with type 2 diabetes mellitus. Both 95% confidence intervals exclude 1, and both p-values are <0.001. The findings concern a short-term physiological endpoint under a controlled challenge, not longer-term clinical outcomes. Model details, missing-data handling, multiplicity procedures and a formal test comparing treatment effects between populations are not reported in the registry record.