A Study of LY2189102 in Patients With Type 2 Diabetes: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of LY2189102 in Patients With Type 2 Diabetes (NCT00942188), a randomized phase 2 study. The primary outcome is Change From Baseline in the Glycosylated Hemoglobin (HbA1c) at 12 Weeks.

2. Clinical Question

The registry describes a phase 2 study intended to evaluate safety, tolerability, and efficacy. The posted primary results are changes from baseline within each group, together with least-squares means and standard errors. The pairwise comparisons discussed in the statistical interpretation are recalculated, unadjusted comparisons with placebo; they are not presented as the trial’s own adjusted pairwise analyses. The registry record does not report the protocol’s original sample-size justification or the planned statistical testing strategy for the primary comparison.

3. Trial Design

This was a randomized, triple-masked, parallel-design phase 2 study of LY2189102 and placebo in people with type 2 diabetes. The official title describes participants as stable on diet and exercise, with or without metformin monotherapy. The registry reports total enrollment of 106 and a completed study. The study start and primary completion dates are listed in the registry record, but those dates do not explain how the analysis plan was developed or implemented.

Four groups appear in the primary outcome results: 0.6 mg LY2189102, 18 mg LY2189102, 180 mg LY2189102, and placebo. The primary outcome analysis included 21 participants in the 0.6 mg group, 16 in the 18 mg group, 19 in the 180 mg group, and 23 in the placebo group. These are the analysis counts for the posted primary result, not a description of all enrolled participants. The registry defines the primary analysis population as randomized participants who received at least 11 doses of study drug, analyzed according to assigned treatment.

The primary outcome model is described as an analysis of covariance, with treatment and site as class variables and baseline HbA1c as a continuous covariate. The reported group values are least-squares means with standard errors. The registry does not report details such as the randomization procedure, the number of sites, the intended allocation ratio, or the handling of participants who did not meet the compliant-set definition. Those details 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.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Compliant set. All randomized participants receiving at least 11 doses of study drug were analyzed according to the treatment subjects were assigned.

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.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in the Glycosylated Hemoglobin (HbA1c) at 12 Weeks, measured over Baseline, 12 weeks.

The primary endpoint is the change from baseline in glycosylated hemoglobin, or HbA1c, at 12 weeks. The registry defines change as the week 12 HbA1c value minus the baseline value and expresses the measure as percentage of glycosylated hemoglobin. A negative change therefore indicates that the measured value at week 12 was lower than the baseline value within that group; it does not by itself establish a difference between treatment groups.

HbA1c is used in clinical research as a measure of glycemia over time, rather than as a single-time-point glucose measurement. That general role helps explain why a trial might select it as an outcome for a study of type 2 diabetes. The registry’s stated primary objective is to evaluate the safety, tolerability, and efficacy of LY2189102; the primary endpoint addresses the efficacy question through change in HbA1c.

The registry reports least-squares means from an ANCOVA model that includes treatment and site, with baseline HbA1c as a covariate. In general, an adjusted mean estimates a group’s outcome while accounting for the covariates included in the model. The primary results list standard errors as the measure of dispersion. The registry does not report a clinical threshold for interpreting the size of an HbA1c change, so the numerical differences should be read as statistical estimates rather than as evidence that a particular change is clinically important.

7. Results Posted in the Registry

• 0.6 mg LY2189102: mean -0.46 versus -0.18 on control; difference -0.27 (95% CI -0.66 to 0.11), standardized effect d = -0.42; z-test p = 0.162.
• 18 mg LY2189102: mean -0.56 versus -0.18 on control; difference -0.38 (95% CI -0.77 to 0.02), standardized effect d = -0.61; z-test p = 0.061.
• 180 mg LY2189102: mean -0.43 versus -0.18 on control; difference -0.24 (95% CI -0.62 to 0.13), standardized effect d = -0.40; z-test p = 0.199.

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 From Baseline in Fasting Glucose at 12 Weeks

• 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:
  • 0.6 mg LY2189102: mean -0.87 versus -0.02 on control; difference -0.85 (95% CI -2.13 to 0.42), standardized effect d = -0.40; z-test p = 0.190.
  • 18 mg LY2189102: mean -1.27 versus -0.02 on control; difference -1.25 (95% CI -2.60 to 0.10), standardized effect d = -0.60; z-test p = 0.069.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 0.6 mg LY2189102 and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 18 mg LY2189102 and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in Insulin Sensitivity (Fasting Insulin) at 12 Weeks

• 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:
  • 0.6 mg LY2189102: mean -1.59 versus 1.41 on control; difference -2.99 (95% CI -11.07 to 5.08), standardized effect d = -0.23; z-test p = 0.467.
  • 18 mg LY2189102: mean -0.92 versus 1.41 on control; difference -2.32 (95% CI -10.93 to 6.28), standardized effect d = -0.18; z-test p = 0.597.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 0.6 mg LY2189102 and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 18 mg LY2189102 and the control. The interval gives the range of effects that remain compatible with the data.

Pharmacokinetics (PK) Maximum Serum Concentration (Cmax) of LY2189102 at End of Dosing (12 Weeks)

• 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 deviations.
• Result:
  • 18 mg LY2189102: mean 6,095 versus 269.39 on control; difference 5,825 (95% CI 4,735 to 6,916), standardized effect d = 4.02; z-test p = <0.001.
  • 180 mg LY2189102: mean 39,995 versus 269.39 on control; difference 39,725 (95% CI 31,685 to 47,765), standardized effect d = 3.10; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for 18 mg LY2189102 than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for 180 mg LY2189102 than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The registry posts several secondary outcomes covering fasting glucose, fasting insulin as an indicator of insulin sensitivity, beta-cell function assessed using a mixed meal tolerance test, HbA1c at other time points, and pharmacokinetic measures. The available quantitative secondary results include fasting glucose, fasting insulin, and LY2189102 maximum serum concentration. The posted results therefore span both clinical measurements and drug-exposure measurements, rather than representing a single uniform family of outcomes.

The general pattern is mixed. The fasting glucose and insulin sensitivity comparisons do not provide a consistent, precise picture of differences from placebo in the recalculated results. The pharmacokinetic summaries show much higher measured maximum serum concentrations in the higher-dose groups than in the 0.6 mg group. Pharmacokinetic exposure is a different type of outcome from HbA1c, so that pattern does not directly settle the primary clinical question. The other named secondary outcomes are not accompanied by numerical results in the record; those results are not reported in the registry record.

Secondary outcomes can help characterize a study, but they generally carry less weight when many outcomes or comparisons are examined without a reported multiplicity strategy. In general, repeated testing increases the chance of apparently notable results arising by chance. The registry record does not report whether secondary hypotheses were prespecified in a hierarchy, whether p-values were adjusted, or which outcomes were intended to be confirmatory. The secondary findings should therefore be read as exploratory context for the primary HbA1c result, rather than as independent confirmation of it. No single secondary pattern resolves the uncertainty in the primary comparisons.

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

• Change From Baseline in Fasting Glucose at 12 Weeks
• Change From Baseline in Insulin Sensitivity (Fasting Insulin) at 12 Weeks
• Number of Participants With a Change From Baseline in Beta-Cell Function Measured by Glucose and Insulin Changes With the Mixed Meal Tolerance Test (MMTT) at 12 Weeks
• Change From Baseline in the Glycosylated Hemoglobin (HbA1c) at Week 10 and Week 12
• Pharmacokinetics (PK) Maximum Serum Concentration (Cmax) of LY2189102 at End of Dosing (12 Weeks)
• PK: Area Under the Concentration Time Curve for Dosing Interval (Tau) at Steady State (AUCτ,SS) at End of Dosing (12 Weeks)
• Pharmacokinetics Measured by Serum Concentration at End of Dosing (12 Weeks)

9. Statistical Interpretation

10. Statistical Methods Explained

The registry describes the primary endpoint as a least-squares mean change and says it was analyzed using ANCOVA. ANCOVA is a general method for comparing average outcomes across groups while including one or more covariates. In this study’s stated model, treatment and site are class variables, and baseline HbA1c is a continuous covariate. Including baseline HbA1c allows the model to account for participants’ starting measurements when estimating group means. The registry does not report further modeling details, such as how site was handled if there were sparse observations.

What does a least-squares mean represent?

In general, a least-squares mean is a model-based group estimate, rather than simply the arithmetic average of the observed values. It is calculated within the specified model and can reflect adjustment for its included covariates. Here, the posted least-squares means are accompanied by standard errors. A standard error describes the sampling uncertainty of an estimated mean; it is not the spread of individual participant outcomes. The registry does not post standard deviations for the primary endpoint.

How should the recalculated comparisons be understood?

The pairwise figures discussed for the primary endpoint are unadjusted recalculations from posted summary statistics. They compare each active group’s posted mean change with the placebo mean change. Because the inputs are group summaries rather than participant-level data, these comparisons do not reproduce the ANCOVA model described for the primary endpoint. The recalculations use an approximate pooled standard deviation derived from the posted standard errors and group sizes. That approximation is another reason to distinguish these comparisons from the trial’s own model-based analysis.

In general, a confidence interval describes a range of estimates compatible with the data and the assumptions of the analysis, at a stated confidence level. A narrow interval indicates greater precision than a wide one, but neither the interval nor its width determines whether a difference is important to patients. For the recalculated primary comparisons, the reported intervals include zero. The registry does not report a confidence level for those recalculated intervals, so no confidence percentage is assigned to them.

What does a p-value convey?

In general, a p-value measures how unusual data at least as extreme as those observed would be under a specified null model. It is not the probability that the null hypothesis is true, and it does not measure the size or importance of an effect. The recalculated p-values for the primary comparisons are unadjusted. The registry does not report the p-values for its own primary ANCOVA comparisons, nor does it state whether the primary analysis used a one-sided or two-sided test. The recalculated values therefore have a narrower role than an analysis prespecified and reported by the trial sponsor.

Why can over-dispersion matter?

In general, over-dispersion means that outcomes vary more than a statistical model assumes. It can make standard errors too small if the model does not account for the extra variability, which can in turn make intervals appear more precise than warranted. The primary outcome is continuous, and the registry does not report an over-dispersion assessment or a variance-modeling strategy. Over-dispersion is therefore a general statistical consideration, not a reported feature of this trial’s primary analysis.

The registry defines the primary population as a compliant set of randomized participants who received at least 11 doses, analyzed according to assigned treatment. This is not the same as a description of every randomized participant. The record does not explain how missing week 12 measurements were handled, whether any imputation was used, or whether another analysis population was examined. It also does not report the original sample-size assumptions, a formal interim-analysis plan, or sensitivity analyses. Those aspects of the statistical plan are not reported in the registry record.

11. Confidence Intervals and Precision

Precision concerns how tightly the data constrain an estimate. A confidence interval is one way of expressing that uncertainty: a narrower interval generally indicates a more precise estimate, while a wider interval leaves more plausible values. General interpretation also depends on the analysis assumptions and the confidence level. For the primary recalculated comparisons, the registry-derived intervals extend across zero. They therefore do not pin down a single direction for the difference with placebo. The registry does not report a confidence level for these recalculated intervals.

The recalculated mean differences were -0.274 for 0.6 mg, -0.378 for 18 mg, and -0.245 for 180 mg LY2189102 versus placebo. Their intervals are broad enough to include zero and values on the opposite side of zero. The point estimates alone would not convey that uncertainty. The group counts used in the primary outcome analysis were 21, 16, 19, and 23, respectively, and the standard errors for the group estimates were 0.145, 0.153, 0.138, and 0.132. These standard errors describe uncertainty in the group mean estimates, not participant-to-participant variation.

The registry also reports ANCOVA intervals for selected secondary outcomes, including 95% intervals for the fasting glucose and fasting insulin analyses. Those analyses illustrate that a model-based interval may differ from a simple recalculated interval because the methods and estimates are not identical. Precision should not be confused with importance: even a comparatively precise estimate can be small, and a wide interval does not prove that the true difference is zero. For this study, the primary recalculated comparisons leave substantial uncertainty about the size and direction of the treatment-placebo differences.

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 express the required number of participants per arm for continuous outcomes. They are not total event counts; the event-count convention applies to time-to-event outcomes, and the listed planning examples concern continuous measures. The calculations assume a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. They use the observed effect as a reference and show planning for 100%, 75%, and 50% of that observed effect. The trial’s original sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the illustrative number of participants per arm that the calculation estimates would be needed for an 80% chance of detecting the specified effect under those assumptions. The 90% power column gives the corresponding number for a 90% chance. In general, a smaller effect is harder to distinguish from random variation, so the planning illustrations require more participants per arm when they target a smaller fraction of the observed effect. These figures are planning illustrations, not observed power.

The illustrations use effects estimated from this trial’s posted results. Such estimates can be unstable, especially when the observed groups are small, and they do not establish that the same effect would occur in another study. Some outcomes can yield very small calculated sample sizes when the observed contrast is large relative to the estimated variability. That arithmetic should not be mistaken for a sound design recommendation by itself. The original design might have relied on different assumptions, but those are not reported in the registry record. The sample-size figures should therefore be read as conditional scenarios rather than as the trial’s actual enrollment target or proof that the study was adequately powered.

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 = -0.274; pooled standard deviation σ = 0.648.
2. n = 2 × (1.96 + 0.842)² × 0.648² / -0.274² = 87.8, rounded up to 88 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 <- -0.274                      # observed difference in means
sigma <- 0.647875019179001                     # 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(942188)
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 = 88 (80% power), 118 (90% power)
 75% of observed effect: n per arm = 157 (80% power), 209 (90% power)
 50% of observed effect: n per arm = 352 (80% power), 470 (90% power)
power.t.test: 88.7 
Simulated power at n = 88 per arm: 0.798 (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. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when a study evaluates multiple outcomes, treatment groups, time points, or contrasts. In general, the more statistical tests performed, the greater the chance that one or more results appear notable by chance if each is judged separately. This study has three LY2189102 dose groups compared with placebo and a set of secondary outcomes that include clinical measures at different time points as well as pharmacokinetic measures. That creates several potential comparisons, although the registry record does not establish which were formally tested or designated confirmatory.

The registry record does not report a multiplicity adjustment, a testing hierarchy, or a prespecified gatekeeping strategy. The primary recalculated p-values described in the interpretation are unadjusted and are not sponsor-reported ANCOVA p-values. The record also does not report primary pairwise p-values. These limitations mean that the available figures do not establish how the trial planned to control the overall chance of false-positive findings across its analyses. Unadjusted secondary results should consequently be interpreted cautiously.

The record describes the primary analysis population as randomized participants who received at least 11 doses, analyzed according to assigned treatment. It does not report the number of participants excluded from that population, the amount or pattern of missing outcome data, or the method used to handle missing values. It is not reported whether the primary endpoint was also analyzed in all randomized participants, or whether sensitivity analyses tested the effect of missing data assumptions. The original sample-size justification, interim-analysis plan, and broader statistical analysis plan are also not reported in the registry record. These absences limit assessment of how closely the posted analyses follow the intended design and how robust the findings are to alternative assumptions.

15. 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: chest pain (3.8%), migraine (3.8%), asthma (3.8%), status asthmaticus (3.8%).

The serious adverse event summaries report the number of participants at risk and the number affected in each group. In the 0.6 mg group, 1 of 26 participants was recorded as affected; in the 18 mg group, 1 of 26 was affected. In the 180 mg group and placebo group, 0 of 27 participants in each group were recorded as affected. These are descriptive counts; the registry record does not provide a comparative statistical analysis of serious adverse events.

The listed serious-event terms are chest pain, migraine, asthma, and status asthmaticus, each reported as 3.8%. The summary does not assign these terms to treatment groups, so the percentages should not be used to infer a group-specific pattern. The registry’s death counts are not reported in the registry record. These summaries do not provide enough detail to assess timing, duration, recurrence, or causal attribution, and they should not be interpreted as a complete account of safety. The study’s stated purpose included safety and tolerability, but the figures are limited to the posted serious-event summary and should be read descriptively.

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

The primary outcome results describe average HbA1c change over 12 weeks in the analysis population defined by the registry. The group least-squares means were negative in all four groups, including placebo. The unadjusted recalculated comparisons between each LY2189102 group and placebo also had negative point estimates, but their intervals included zero. The results therefore do not precisely establish the size or direction of the between-group differences.

This does not mean that the treatments had no effect. A wide interval that includes zero is compatible with no difference, but can also be compatible with differences in either direction. Conversely, a negative point estimate is not by itself evidence of a reliable treatment effect. The registry does not provide sponsor-reported primary pairwise ANCOVA results, a primary p-value, or a reported clinical threshold for interpreting the magnitude of change. The recalculated comparisons are approximate and unadjusted, so they should not be treated as definitive confirmatory tests.

The secondary results add context, but they do not remove this uncertainty. They cover different kinds of measurements, and the registry does not report a strategy for accounting for the number of secondary analyses. Pharmacokinetic findings describe measured drug concentrations, not the primary clinical endpoint. Safety summaries are descriptive and do not establish comparative safety.

In general, a trial result is most informative when the outcome, analysis population, statistical model, missing-data approach, and testing strategy are all clear. Some of those details are available for the primary endpoint, but the record does not report several other elements of the analysis plan. The posted data support a cautious account of the observed estimates and their uncertainty; they do not justify a broad claim about whether LY2189102 works or does not work.

17. Why This Trial Matters Statistically

This trial illustrates several important statistical distinctions in clinical research. First, an observed change within a treatment group is not the same as a treatment-versus-placebo contrast. Each group had a negative posted mean change in HbA1c, but the comparative question concerns the difference in change between groups. The primary results are easiest to interpret when the within-group estimates and between-group estimates are kept separate.

Second, the reported primary method and the available recalculations are not interchangeable. The registry describes an ANCOVA model that includes treatment, site, and baseline HbA1c. The recalculated pairwise estimates use posted summary statistics and are unadjusted. This distinction matters because adjustment, model assumptions, and available information can affect estimates and uncertainty. The registry’s lack of sponsor-reported primary pairwise results also limits the ability to evaluate the intended comparative analysis from the posted record alone.

Third, intervals and sample sizes matter alongside point estimates. The primary recalculated intervals include zero, and the analysis counts were modest. The planning illustrations show how sample requirements depend on assumed effect size, but they are based on observed effects rather than on the trial’s original design rationale. They cannot retrospectively establish the adequacy of the trial’s sample size.

Finally, multiple doses and multiple secondary outcomes create interpretive challenges when a multiplicity strategy is not reported. The record offers a useful case study in separating primary from secondary evidence, distinguishing statistical precision from clinical importance, and treating missing analysis details as genuine uncertainty rather than filling them with assumptions.

18. 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.

Several limitations specific to this trial affect interpretation of the posted results. The primary analysis was restricted to a compliant set of randomized participants who received at least 11 doses. The registry does not report how many randomized participants were not included in that set or whether the resulting estimates were compared with results from a broader analysis population. The analysis counts for the primary endpoint are smaller than total enrollment, but the record does not describe the participant flow that led to those counts.

The primary endpoint’s reported group estimates come from an ANCOVA model, but the registry does not post sponsor-reported pairwise ANCOVA results or a primary p-value. The available recalculated comparisons are unadjusted and approximate. They provide a useful statistical comparison of the posted summaries, but they are not a replacement for participant-level model outputs or the sponsor’s intended primary analysis. The recalculated intervals also have no confidence level stated in the record.

The registry does not report the original sample-size justification, the planned handling of missing data, interim analyses, or a multiplicity strategy. It also does not report clinical thresholds for interpreting the magnitude of HbA1c change. Secondary outcome reporting is incomplete relative to the listed outcome descriptions: several outcomes are named, but numerical results for them are not reported in the registry record. The serious adverse-event summary lacks group attribution for the listed event terms and does not report deaths in the registry record. These limitations constrain conclusions about precision, robustness, secondary evidence, and safety.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: A Study of LY2189102 in Patients With Type 2 Diabetes — NCT00942188.
• Registry record last updated 2019-09-18; status last verified 2019-09.
• Results first posted 2018-03-13.
• 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.

22. Record Summary

The registry record describes a completed, randomized, triple-masked, parallel-design phase 2 study of LY2189102 versus placebo in people with type 2 diabetes. Total enrollment was 106. The primary endpoint was change from baseline in HbA1c at 12 weeks, analyzed in a compliant set of randomized participants who received at least 11 doses.

The posted least-squares mean changes were -0.457, -0.561, and -0.428 for the 0.6 mg, 18 mg, and 180 mg groups, respectively, and -0.183 for placebo. Recalculated unadjusted comparisons with placebo have intervals that include zero. The registry does not report primary pairwise ANCOVA results, the original sample-size justification, missing-data methods, or a multiplicity strategy. Secondary and serious adverse-event summaries provide additional descriptive information, with important analysis details not reported in the registry record.