Exenatide in Extreme Pediatric Obesity: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Exenatide in Extreme Pediatric Obesity (NCT01237197), a randomized phase 2 study. The primary outcome is Percent Change From Baseline in Body Mass Index at 3-months.

2. Clinical Question

3. Trial Design

This was a randomized, parallel-group phase 2 trial sponsored by the University of Minnesota. The registry lists quadruple masking and an enrollment of 26. The brief summary describes a double-blind, placebo-controlled pilot trial, while the registry's masking classification is quadruple. The record does not explain the masking roles or how masking was maintained.

The trial's stated primary objective was to generate preliminary data on exenatide's ability to reduce BMI and improve cardiovascular disease and type 2 diabetes risk factors in extremely obese adolescents. The primary outcome posted is percent change from baseline in BMI at 3 months. The intervention descriptions also outline open-label exenatide after the initial placebo period, so the treatment schedules extend beyond the primary outcome time point. The registry describes the study as a three-month pilot in its summary, while its arm descriptions include schedules lasting five and six months; the record does not reconcile these descriptions.

The registry lists the study as completed, with start and primary completion dates of 2010-10 and 2012-05. The outcome result counts differ from overall enrollment: 12 participants are listed for exenatide and 10 for placebo for the primary outcome. The adverse-event groups each list 13 participants at risk. The registry record does not explain these count differences, the analysis population, or the treatment of participants without endpoint data. No further details about the allocation procedure or the trial's original statistical design assumptions are 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.

Randomization Period

Open Label Period

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 Percent Change From Baseline in Body Mass Index at 3-months, measured over Baseline and 3-months.

The primary endpoint is percent change from baseline in body mass index at 3 months. BMI is a continuous measure, and the registry reports a mean and standard deviation for each group. Its description says that the outcome is measured as BMI reduction, so negative percent-change values correspond to reductions from baseline under the stated measure.

A continuous endpoint retains information about the magnitude of change rather than reducing each participant's result to a category. Comparing group means therefore describes average change in the randomized groups. It does not show how much individual participants varied, whether every participant changed in the same direction, or how changes in BMI relate to other outcomes. The posted results include no secondary outcome measures, so the BMI result alone does not describe the cardiovascular disease or type 2 diabetes risk factors mentioned in the trial objective.

The endpoint is specified at 3 months, even though the intervention descriptions include treatment schedules extending beyond that time. The registry record does not report additional details about endpoint assessment, the analysis population, or how missing endpoint measurements were handled.

7. Results Posted in the Registry

• Exenatide: mean -2.90 versus -0.15 on control; difference -2.75 (95% CI -4.98 to -0.52), standardized effect d = -1.09; z-test p = 0.016.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous: percent change in BMI from baseline at 3 months. The registry reports a mean for each group and uses a mean difference for the between-group contrast. A mean represents the average observed value in a group. Here, the group means are -2.9 for exenatide and -0.15 for placebo injection. The reported contrast is -2.75, with the exenatide mean compared with the placebo mean. A negative contrast is consistent with a larger average reduction in the exenatide group for this outcome's stated direction.

What does the standard deviation describe?

The standard deviation describes how spread out participant measurements are around a group's mean. The posted standard deviations are 1.8 for exenatide and 3.2 for placebo injection. A standard deviation is not the uncertainty interval for the mean difference, and it does not show the range of all participant values. It gives a summary of within-group variability. When groups are small, a mean and standard deviation cannot show the full shape of the observations; participant-level distributions are not reported in the registry record.

What does the mean difference describe?

A mean difference compares group averages on the same measurement scale. The reported estimate is -2.75 for exenatide relative to placebo injection. It describes the average contrast in percent change, not a percentage of participants who responded, and not a change in absolute BMI units. The registry also reports a pooled standard deviation of 2.528 and a standardized effect size of -1.088. A standardized effect expresses a contrast relative to a measure of variability, which can help describe its scale independently of the original measurement units. It does not replace the outcome-scale estimate or its confidence interval.

How should the interval be understood?

A confidence interval is a range of values compatible with the observed data and the statistical procedure used, under that procedure's assumptions. It conveys uncertainty about an estimate; it is not a range containing a known proportion of individual participant outcomes. The reported interval for the mean difference extends from -4.98 to an upper limit below zero. The confidence level and the detailed procedure used to construct the interval are not reported in the registry record. The exenatide group also has a reported interval from -5.02 to -0.37; an interval for the placebo group is not reported.

What does the p-value add?

The unadjusted p-value is 0.016. A p-value describes how incompatible the observed data are with a specified null model, assuming that model and the analysis assumptions hold. It is not the probability that the null hypothesis is true, nor a measure of the size or clinical importance of the difference. The record labels the result unadjusted, and no adjustment for multiple comparisons is reported. The registry does not give enough detail to identify the full analysis procedure underlying the p-value.

Why can over-dispersion matter?

General statistical explanation: over-dispersion refers to variability greater than a statistical model expects. If a model underestimates variability, its uncertainty estimates can be too narrow and its tests can appear more decisive than warranted. This is a general issue, not a finding established by the posted summaries. The outcome is continuous and the registry reports standard deviations, but it does not report a model-based assessment of over-dispersion or other distributional diagnostics.

What can be inferred from the posted analysis?

The registry reports one outcome measure and no additional analysis results. Its mean difference and uncertainty interval give a group-level summary at the stated time point, but they do not reveal participant-level patterns, adjustment for baseline characteristics, or sensitivity to missing data. Those methods are not reported in the registry record. The comparison is best read as a preliminary estimate from the posted small-group results, rather than as a complete account of the trial's statistical plan.

10. Confidence Intervals and Precision

The reported mean difference is -2.75, with an interval from -4.98 to an upper limit below zero. The interval is entirely on the negative side of zero, consistent with the direction of the reported contrast and the group means. Its width also shows that the estimate is not pinpoint precise: a range of effects remains compatible with the result under the procedure used. The confidence level and interval-construction method are not reported in the registry record.

For exenatide, the reported mean is -2.9 and the interval extends from -5.02 to -0.37. The placebo mean is -0.15 with a standard deviation of 3.2, but no interval for that group mean is reported. The group standard deviations, 1.8 for exenatide and 3.2 for placebo injection, describe observed spread rather than precision of the between-group contrast.

The primary outcome counts are 12 for exenatide and 10 for placebo injection. With these small numbers, the group summary can be influenced by individual observations. The record does not provide participant-level data, an explanation for the outcome counts, or details on missing-data handling, so the impact of those features on precision cannot be assessed from the registry results alone.

An interval describes statistical uncertainty under its method and assumptions. It does not cover every source of uncertainty, such as questions about generalizability, analysis choices that are not documented, or differences between the registry descriptions of study duration. The result is therefore most informative as a preliminary estimate at the 3-month endpoint.

11. 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 figures are planning illustrations based on the observed mean difference, not the original trial's design calculation. They are participants per arm, not total events. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. Each row uses the stated fraction of the observed effect as the effect to detect.

For planning around 100% of the observed effect, the illustration gives 14 participants per arm for 80% power and 18 participants per arm for 90% power. For planning around 75% of the observed effect, it gives 24 participants per arm for 80% power and 32 participants per arm for 90% power. For planning around 50% of the observed effect, it gives 54 participants per arm for 80% power and 72 participants per arm for 90% power.

Power is the probability, under specified assumptions and a particular true effect, that a study will detect an effect at the chosen significance threshold. The 80% and 90% columns show different planning targets: the latter seeks a higher probability of detecting the assumed effect, and therefore requires more participants in these illustrations. Smaller effects also need more participants to detect with the same power target. These figures are planning illustrations, not observed power for the completed trial. The original trial's sample-size justification and design assumptions are not reported in the registry record.

12. 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 = -2.750; pooled standard deviation σ = 2.528.
2. n = 2 × (1.96 + 0.842)² × 2.528² / -2.750² = 13.3, rounded up to 14 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 <- -2.75                      # observed difference in means
sigma <- 2.52784493195291                     # 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(1237197)
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 = 14 (80% power), 18 (90% power)
 75% of observed effect: n per arm = 24 (80% power), 32 (90% power)
 50% of observed effect: n per arm = 54 (80% power), 72 (90% power)
power.t.test: 14.3 
Simulated power at n = 14 per arm: 0.794 (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.

13. Multiplicity, Missing Data and Analysis Populations

The registry posts one outcome measure and no secondary outcome measures. It lists no analysis results beyond the primary comparison. The unadjusted p-value is 0.016, and no multiplicity adjustment is reported in the registry record. When several outcomes, time points, or comparisons are tested, the chance of at least one apparently notable result can increase; statistical methods can account for that, but the record does not say whether any broader testing plan was used. With no secondary results posted, the scope of any outcome-selection or multiplicity plan cannot be evaluated.

Missing-data handling is not reported in the registry record. The primary outcome summaries list 12 participants for exenatide and 10 for placebo injection, compared with overall enrollment of 26. The adverse-event summaries list 13 participants at risk in each group. These reported counts should not be treated as an explanation of the endpoint counts; the registry does not state why they differ or whether endpoint values were missing.

The analysis population is not reported in the registry record. It is therefore unclear from the posted results whether the endpoint analysis included all randomized participants, only participants with an observed measurement, or another defined group. The registry also does not report whether the analysis adjusted for baseline BMI or other characteristics, how protocol deviations were handled, or whether sensitivity analyses were performed.

These are reporting limitations, not proof that the trial did not use such procedures. Without the methods, readers cannot determine how missing observations, the analysis set, or multiple testing may have affected the reported estimate and its uncertainty.

14. 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 adverse-event record lists 13 participants at risk in each group. For serious adverse events, 0 affected participants are reported in the exenatide group and 0 in the placebo injection group. No serious adverse-event terms are listed. The record does not report death counts, so deaths are not reported in the registry record.

For other adverse events, 12 affected participants are listed in each group, with 13 at risk in each. These are counts of affected participants as presented in the registry; they do not indicate how many events each participant experienced or describe their severity, timing, or relationship to study treatment. No further detail about the other adverse events is included in the posted results.

These summaries are descriptive and based on small groups. A zero count for serious adverse events in these summaries does not establish that a treatment is free of risk or characterize uncommon events. The registry record does not provide additional event details or a formal comparative safety analysis.

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

The posted primary result describes average percent change in BMI at 3 months in the randomized groups. The exenatide mean was -2.9 and the placebo injection mean was -0.15; the reported mean difference was -2.75. The interval for the difference lies below zero, and the unadjusted p-value is 0.016. Together, these summaries describe a greater average BMI reduction in the exenatide group in this particular comparison, while retaining uncertainty about the size of that contrast.

This result does not establish the size of an effect in a broader population of adolescents, since the primary outcome summaries include 12 participants in one group and 10 in the other. The registry does not explain these counts or report missing-data methods and analysis populations. It also does not post participant-level results, secondary outcomes, or a later comparative endpoint.

The trial objective mentions improvement in cardiovascular disease and type 2 diabetes risk factors, but no results for those outcomes are posted. The BMI finding therefore cannot be used to infer changes in those risk factors. It also does not answer questions about outcomes beyond the 3-month endpoint. Although the intervention descriptions include open-label treatment after the initial randomized comparison, the registry record does not post later comparative results.

Statistical evidence is not the same as a clinical judgment about the importance of an effect. The registry reports a continuous outcome, a group contrast, an interval, and an unadjusted p-value, but does not state a threshold for a clinically important BMI change. The result should be understood as a preliminary estimate from a pilot trial rather than a complete assessment of benefit, harm, or longer-term outcomes.

16. Why This Trial Matters Statistically

This trial is statistically informative as a small randomized comparison of a continuous BMI outcome in adolescents with extreme obesity. Randomization and masking are important design features for reducing some forms of bias, while the parallel-group structure allows a direct comparison at the primary 3-month endpoint. The posted means and mean difference make the scale and direction of the group-level result explicit.

The record also illustrates why a point estimate should be read with its uncertainty. The reported contrast is -2.75, and its interval remains below zero but spans a range of possible effect sizes. The small endpoint counts and differences between outcome counts, enrollment, and adverse-event counts make transparent reporting of analysis populations and missing-data handling especially useful; those details are not reported in the registry record.

The objective refers to multiple potential areas of interest, but only one outcome measure is posted. That separation matters: the BMI estimate cannot stand in for unreported cardiovascular disease or type 2 diabetes risk-factor results. Likewise, the sample-size illustrations based on the observed effect are not evidence of the trial's original planning or its achieved power.

As a pilot study, this record offers a preliminary estimate and highlights questions for interpretation, including the precision of the contrast, the endpoint counts, and the absence of posted analysis details. It does not supply all the information needed to judge how robust the result is to alternative analysis choices or how it applies beyond the studied sample.

17. 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 endpoint summaries include 12 participants in the exenatide arm and 10 in the placebo injection arm, while overall enrollment is 26. The adverse-event record lists 13 participants at risk in each group. The registry record does not explain these differences, so the endpoint analysis population and the availability of outcome data cannot be established from the posted results.

The study summary describes a three-month pilot, but arm descriptions include schedules extending to five months for exenatide and six months for placebo followed by open-label exenatide. The primary endpoint is at 3 months. The record does not reconcile the duration descriptions, and no later comparative outcome is posted.

The registry does not report the original sample-size justification, detailed statistical plan, confidence level for the reported intervals, missing-data methods, or analysis population. It also does not post secondary outcome results despite the broader objectives described in the summary. The absence of these details limits assessment of multiplicity, model choices, and the effect of missing observations.

The result comes from a small pilot trial and may not represent outcomes in other populations or settings. The registry record does not provide participant-level data or enough detail to assess how individual observations influenced the group means. These limitations concern interpretation of the available results; they do not show that unreported procedures were not conducted.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Exenatide in Extreme Pediatric Obesity — NCT01237197.
• Registry record last updated 2014-09-12; status last verified 2014-09.
• Results first posted 2014-09-12.
• 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.

21. Record Summary

NCT01237197 is a completed, randomized, quadruple-masked, parallel-group phase 2 trial sponsored by the University of Minnesota. It enrolled 26 participants and studied exenatide versus placebo in adolescents described as extremely obese. The primary endpoint was percent change from baseline in BMI at 3 months.

The posted means were -2.9 for exenatide and -0.15 for placebo injection, with a reported mean difference of -2.75 and an unadjusted p-value of 0.016. Endpoint counts were 12 and 10, respectively. The registry reports no secondary outcome measures or additional analyses. Details about missing-data handling, analysis populations, multiplicity, and the original sample-size justification are not reported in the registry record.