Naltrexone for Antipsychotic-Induced Weight Gain: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Naltrexone for Antipsychotic-Induced Weight Gain (NCT01866098), a randomized na study. The primary outcome is Change in Weight From Baseline.

2. Clinical Question

The registry describes the study as designed to examine naltrexone's effect on weight loss among people taking antipsychotic medication. It identifies weight change as the primary outcome and also lists changes in fasting glucose, HbA1c, insulin, total cholesterol, HDL, and LDL as secondary outcomes. The record contains posted results for the primary outcome and for three secondary outcomes.

The question is comparative: the relevant evidence is not just whether weight changed within each group, but how the reported changes in each naltrexone group compare with the placebo result, and how uncertain those comparisons are. The registry gives arm-level least-squares mean changes and standard errors, along with a mixed models analysis across the groups. The posted estimates and intervals describe the results for this trial; they do not establish what would happen in other populations or settings.

3. Trial Design

The registry record describes a randomized, quadruple-masked, parallel-group study sponsored by Yale University. It lists an enrollment of 144 and a completed status. The study began in 2013-05, and the primary completion date is 2019-04-07. The phase is recorded as NA; a phase is not reported in the registry record.

Participants were assigned to placebo, naltrexone 25mg, or naltrexone 50mg. The listed regimens were oral capsules taken once daily for 52 weeks. The record identifies the study population through diagnoses including schizophrenia, schizoaffective disorder, schizophreniform disorder, bipolar disorder, and severe major depression with psychotic features, and describes the clinical context as antipsychotic treatment. Details of the randomization sequence, allocation concealment, and which individuals were masked are not reported in the registry record.

For the primary outcome, the analysis population comprised participants who were randomized, received at least 1 dose of naltrexone or placebo, and had at least 1 assessment after baseline. The registry reports arm-level analyses for 51 placebo participants, 47 in the naltrexone 25mg group, and 46 in the naltrexone 50mg group. These are the reported analysis group sizes, not a description of participant flow; the numbers screened, excluded, or missing outcome measurements are not reported in the registry record.

The primary outcome was change in weight from baseline at 52 weeks. The secondary outcomes listed include metabolic measures, but results are posted for only some of those outcomes. The original sample-size justification, planned analysis details beyond the posted method labels, and any interim analyses 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: Analysis population consists of participants who were randomized, received at least 1 dose of the trial compound (naltrexone or placebo), and had at least 1 assessment after baseline.

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 in Weight From Baseline, measured over Baseline and 52 weeks.

The primary endpoint is change in weight from baseline to the study endpoint at 52 weeks, measured in kilograms. The registry describes weight as measured at each assessment and change as determined at the study endpoint. It reports least-squares mean changes, with standard errors, for placebo and each naltrexone dose.

Change from baseline focuses the outcome on how weight at the endpoint differs from the participant's starting measurement, rather than only comparing endpoint weights. The least-squares mean is a model-based estimate of the group mean; it can reflect the fitted analysis rather than simply being the arithmetic average of observed endpoint changes. The registry does not describe the model's covariates or other specification details.

Weight is the direct outcome relevant to the study's stated purpose of examining weight change in people treated with antipsychotic medications. Comparisons with placebo provide a reference for interpreting changes that may occur over the study period apart from assignment to either naltrexone dose. The outcome does not, by itself, explain why any change occurred, and the registry record does not provide enough information to assess how missing measurements were handled beyond the stated analysis-population definition.

7. Results Posted in the Registry

• Naltrexone 25mg: mean 0.69 versus -0.16 on control; difference 0.85 (95% CI -4.73 to 6.43), standardized effect d = 0.06; z-test p = 0.765.
• Naltrexone 50mg: mean -0.95 versus -0.16 on control; difference -0.79 (95% CI -6.13 to 4.55), standardized effect d = -0.06; z-test p = 0.772.

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.

Changes in Fasting Glucose From Baseline

• 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:
  • Naltrexone 25mg: mean 4.60 versus 8.20 on control; difference -3.60 (95% CI -11.68 to 4.48), standardized effect d = -0.18; z-test p = 0.383.
  • Naltrexone 50mg: mean -0.40 versus 8.20 on control; difference -8.60 (95% CI -16.23 to -0.97), standardized effect d = -0.45; z-test p = 0.027.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Naltrexone 25mg and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Naltrexone 50mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Changes in Glycosylated Hemoglobin (HbA1c) From Baseline

• 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:
  • Naltrexone 25mg: mean -0.06 versus -0.01 on control; difference -0.05 (95% CI -0.42 to 0.31), standardized effect d = -0.06; z-test p = 0.772.
  • Naltrexone 50mg: mean 0.06 versus -0.01 on control; difference 0.07 (95% CI -0.73 to 0.86), standardized effect d = 0.04; z-test p = 0.869.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Naltrexone 25mg 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 Naltrexone 50mg and the control. The interval gives the range of effects that remain compatible with the data.

Changes in Insulin From Baseline

• 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:
  • Naltrexone 25mg: mean 0.45 versus 6.45 on control; difference -6.00 (95% CI -21.52 to 9.52), standardized effect d = -0.15; z-test p = 0.449.
  • Naltrexone 50mg: mean 2.16 versus 6.45 on control; difference -4.29 (95% CI -18.79 to 10.21), standardized effect d = -0.12; z-test p = 0.562.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Naltrexone 25mg 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 Naltrexone 50mg and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists six secondary outcomes concerning fasting glucose, HbA1c, insulin, total cholesterol, HDL, and LDL. Results are posted for fasting glucose, HbA1c, and insulin; results for total cholesterol, HDL, and LDL are not reported in the registry record. For the posted outcomes, the record includes arm-level estimates, standard errors, unadjusted recalculated pairwise comparisons, and an overall mixed models p-value.

Across these posted outcomes, the pattern is not uniformly aligned in direction or strength. Most recalculated dose-versus-placebo intervals include zero, and the overall mixed models p-values do not indicate a consistent pattern of separation across outcomes. The fasting glucose result for naltrexone 50mg has an unadjusted recalculated interval that does not include zero, while the overall mixed models result for that secondary outcome is p = 0.19. This contrast illustrates why an isolated pairwise calculation should not be treated as a definitive finding when considered alongside the outcome-level analysis.

These secondary findings are contextual rather than replacements for the primary weight result. They concern different measures and have their own uncertainty. Several outcomes and dose comparisons were examined, and the registry does not report a multiplicity adjustment plan. When multiple tests are interpreted without adjustment, an apparently notable result can arise by chance more often than in a single prespecified test. The secondary results therefore warrant less weight than a clearly prespecified, fully reported primary analysis, and should be treated as exploratory rather than conclusive evidence of a broad metabolic pattern.

Because the record posts only part of the listed secondary outcome set, it is not possible to assess the full pattern across all outcomes from the registry record. The absence of posted results for an outcome is not evidence that no change occurred.

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

• Changes in Fasting Glucose From Baseline
• Changes in Glycosylated Hemoglobin (HbA1c) From Baseline
• Changes in Insulin From Baseline
• Changes in Total Cholesterol From Baseline
• Changes in HDL From Baseline
• Changes in LDL From Baseline

9. Statistical Interpretation

10. Statistical Methods Explained

The registry identifies a mixed models analysis for the primary outcome and reports least-squares means with standard errors. A mixed model is a statistical framework that can represent relationships among repeated or otherwise related measurements. In general, such models can use available observations while accounting for the structure specified by the analyst. The registry record does not report the exact model specification, covariates, covariance structure, or missing-data assumptions, so those details cannot be evaluated from the record.

A least-squares mean is an estimate from a fitted model, rather than necessarily a raw average. It is commonly used to summarize group outcomes after accounting for terms included in the model. Interpretation depends on the model's specification and the population represented by its analysis. The registry lists the primary population as randomized participants who received at least 1 dose and had at least 1 post-baseline assessment. It does not describe an intention-to-treat analysis of all randomized participants or provide a fuller participant-flow account.

A standard error describes the uncertainty in an estimated mean. It is not the same as a standard deviation, which describes variation among individual measurements. Smaller standard errors generally indicate more precise estimates, while larger ones indicate greater uncertainty. The primary arm-level standard errors are 1.78 kg for placebo, 2.22 kg for naltrexone 25mg, and 2.06 kg for naltrexone 50mg. These quantify uncertainty around the reported least-squares means under the reported analysis; they do not describe the spread of individual participants' weight changes.

The overall reported p-value is 0.83 from a mixed models analysis across the three groups. A p-value describes how incompatible the observed data are with a specified null hypothesis under the assumptions of the test. It is not the probability that the null hypothesis is true, and it does not measure the size or clinical importance of a difference. The registry does not state the exact null formulation or all test details. The overall result should not be interpreted as a direct test of each dose against placebo.

The pairwise comparisons accompanying the arm summaries are simple unadjusted recalculations. They estimate each naltrexone-placebo mean difference and provide confidence intervals and unadjusted p-values. The calculations approximate standard deviations from the arm-level standard errors, rather than using individual participant observations. Consequently, these contrasts are useful as a transparent summary of the posted numbers, but they may not reproduce the sponsor's mixed-model estimates, standard errors, or inferential tests. There is no discrepancy flag for the primary outcome; where a discrepancy between a recalculation and the sponsor's own analysis is present, the sponsor's analysis takes precedence.

In general, a confidence interval gives a range of values compatible with the data and analysis procedure at its stated confidence level. Its width conveys precision: wider intervals leave more uncertainty about the underlying group difference. An interval that crosses zero includes both a difference in one direction and a difference in the other direction, as well as no difference. That does not prove that the groups are the same. The intervals for both recalculated primary comparisons cross zero and are wide, so they do not tightly determine the direction or magnitude of the difference.

The sample-size illustrations are separate from the original trial design. They use the observed effect as a planning reference and display what sample sizes would correspond to specified fractions of that effect under stated assumptions. Those assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The original trial's sample-size assumptions and justification are not reported in the registry record. These illustrations are not evidence about the trial's achieved power.

Multiplicity arises when many outcomes or comparisons are examined. Without an adjustment plan, the chance of at least one apparently notable result by chance can rise as the number of tests grows. The registry lists multiple secondary outcomes and posts results for only some; its record does not describe a multiplicity adjustment strategy. Thus, individual secondary p-values should be treated cautiously, particularly when they are unadjusted and are considered alongside several outcomes.

Missing-data handling is another important part of interpretation. The eligibility rule for the primary analysis requires a post-baseline assessment, but the record does not say how missing follow-up measurements were modeled, imputed, or otherwise handled. It also does not report reasons for missingness or sensitivity analyses. Those omissions limit assessment of whether the fitted analysis could be affected by incomplete follow-up.

11. Confidence Intervals and Precision

Precision is best assessed from the confidence intervals, not from the point estimates alone. The recalculated mean difference for naltrexone 25mg versus placebo is 0.85 kg, with a 95% confidence interval from -4.727 to 6.427. For naltrexone 50mg versus placebo, it is -0.79 kg, with a 95% confidence interval from -6.126 to 4.546. Both intervals include zero and values in either direction, leaving substantial uncertainty about the underlying contrast.

The intervals are based on unadjusted recalculations from posted arm summaries, with variability approximated from the reported standard errors. They are not confidence intervals from the sponsor's mixed models analysis. The registry does not report a confidence interval for its overall mixed models test, and the arm-level standard errors alone do not substitute for an interval around the sponsor's dose-versus-placebo contrasts.

In general, a narrower interval indicates a more precise estimate, while a wider interval indicates that a broader range of effects remains compatible with the data and analysis. Precision is different from whether an estimate is clinically important. The registry does not report a threshold for a clinically meaningful difference in weight, so these intervals cannot be classified against such a threshold using the record alone.

The results should not be read as proving equivalence or no effect. Rather, the recalculated intervals show that the posted summaries leave room for differences in either direction. Participant-level data, fuller model details, and the sponsor's direct contrast estimates and intervals are not reported in the registry record, limiting further assessment of precision.

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 are planning calculations based on the observed effects, not a reconstruction of the trial's original design. The listed assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The planning scenarios use the full observed effect and smaller fractions of it, including 75% and 50% of the observed effect.

For these continuous outcomes, the figures are participants per arm, not a total across both comparison groups and not total events. The 80% power column indicates the illustrated number of participants per arm for a design that would have an 80% chance of detecting the specified effect under the assumptions, if that effect and model assumptions were correct. The 90% power column represents a higher target chance of detection under those same assumptions. Achieving a higher target power generally requires more participants for a given effect.

The table and curve should be read as sensitivity illustrations: the required sample size depends on the assumed effect size, and smaller effects need more participants to detect with the same power target. The figures are not observed power and do not describe the probability that this completed trial detected an effect. They also do not establish what sample size the investigators planned. The original trial's sample-size justification and design assumptions are not reported in the registry record.

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 = 0.850; pooled standard deviation σ = 13.970.
2. n = 2 × (1.96 + 0.842)² × 13.970² / 0.850² = 4,240.1, rounded up to 4,241 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 <- 0.85                      # observed difference in means
sigma <- 13.9696921941752                     # 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(1866098)
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 = 4,241 (80% power), 5,677 (90% power)
 75% of observed effect: n per arm = 7,538 (80% power), 10,092 (90% power)
 50% of observed effect: n per arm = 16,961 (80% power), 22,706 (90% power)
power.t.test: 4241 
Simulated power at n = 4,241 per arm: 0.799 (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. Analyses Reported by the Sponsor

The sponsor's reported primary analysis is a mixed models analysis across placebo and both naltrexone groups, with p = 0.83. This is the registry's own inferential result for the primary outcome and should be kept distinct from the simple dose-versus-placebo recalculations. The record does not give the sponsor's pairwise contrast estimates or their confidence intervals.

The recalculated comparisons use the posted arm means and standard errors to form unadjusted mean differences. They estimate 0.85 kg for naltrexone 25mg versus placebo and -0.79 kg for naltrexone 50mg versus placebo. The corresponding recalculated p-values are 0.765 and 0.772. Because the recalculation approximates variability and does not reproduce the mixed model, the estimates and tests are not interchangeable with the sponsor's analysis.

The discrepancy indicator is false for this outcome, so no discrepancy between the recalculation and sponsor analysis is flagged in the registry-derived results. If a discrepancy were present, the sponsor's own analysis would take precedence. The overall mixed models test and recalculated pairwise contrasts answer different questions, and neither should be presented as a substitute for the other.

15. Multiplicity, Missing Data and Analysis Populations

The registry reports one primary outcome and lists several secondary outcomes. It also gives an overall mixed models test for each outcome with posted results and includes recalculated dose-versus-placebo comparisons. Testing multiple outcomes and comparisons creates a multiplicity concern: even when no underlying difference exists, a larger collection of tests increases the chance of at least one result appearing notable by chance. The registry does not report whether a formal multiplicity adjustment was planned or applied, how the primary and secondary tests were ordered, or which comparisons were prespecified. Individual unadjusted secondary results should therefore be interpreted cautiously.

The primary analysis population is described as randomized participants who received at least 1 dose of trial compound and had at least 1 post-baseline assessment. This definition excludes randomized participants without a post-baseline assessment from the stated analysis population, but the record does not provide participant flow or explain how many randomized participants were excluded for that reason. The registry reports arm-level analysis counts, but does not give reasons for missing assessments or outcomes.

Missing-data methods are not reported in the registry record. In general, missingness can affect estimates if participants with unavailable measurements differ systematically from those with observed measurements. A mixed model may accommodate incomplete repeated measurements under particular assumptions, but the registry does not provide the model specification or assumptions needed to assess that issue. Imputation procedures, sensitivity analyses, and the extent of missing endpoint data are also not reported.

The record therefore permits description of the stated analysis population and posted estimates, but not a complete assessment of multiplicity control or robustness to missing data. These are reporting limitations, not evidence that any particular analysis choice was made.

16. Safety Results

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

Deaths

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: cocaine overdose (2.1%).

The serious adverse event figures are reported separately by group. The registry lists 0 serious adverse events in the placebo group, 1 in the naltrexone 25mg group, and 0 in the naltrexone 50mg group. Deaths are reported as 0, 1, and 0, respectively. The record also lists the serious adverse event term Cocaine Overdose at 2.1%; it does not assign that term to a particular group in the posted summary.

Other adverse events are reported for 35 of 51 participants in the placebo group, 33 of 47 in the naltrexone 25mg group, and 35 of 46 in the naltrexone 50mg group. These are registry counts, not estimates of causation. The record does not provide enough detail to determine whether events were considered related to study treatment, their timing, severity beyond the serious-event classification, or how event reporting was collected. Group counts should be read descriptively and do not establish that treatment caused or prevented an event. The record does not provide further details about the death or its relationship to study treatment.

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

The posted primary outcome describes estimated mean weight change through 52 weeks in the placebo and two naltrexone groups among the defined analysis population. The overall sponsor-reported mixed models test is p = 0.83. The unadjusted recalculated contrasts are imprecise, with confidence intervals that include zero and extend in both directions. Together, these results do not precisely determine the size or direction of a dose-versus-placebo difference in this trial.

That interpretation is not the same as concluding that naltrexone and placebo are equivalent, or that there was no effect. A non-small p-value is not proof of no difference, and the registry does not report an equivalence margin or a threshold for a clinically meaningful weight change. The intervals leave uncertainty, so the point estimates should not be treated as exact descriptions of what would occur in a broader population.

The evidence is also limited to the population and regimen described in the registry: people with the listed psychiatric conditions receiving antipsychotic medication, assigned to one of the listed daily capsules for 52 weeks. The record does not establish that the results apply to different populations, doses, durations, or settings. The listed enrollment is not a substitute for the primary analysis population, and participant flow and missing-data handling are not fully reported.

Secondary metabolic outcomes provide additional measures but have incomplete posted coverage and raise multiplicity concerns. Their results should not be used to claim a broad benefit or harm pattern. Safety counts are descriptive, with limited event detail and no clear causal attribution in the registry summary. Overall, the record supports a cautious account of the estimates and their uncertainty, not a definitive clinical conclusion.

18. Why This Trial Matters Statistically

This trial is statistically informative as an example of why estimated effects, uncertainty, and analysis methods need to be read together. The registry provides arm-level least-squares means and standard errors, an overall mixed models p-value, and enough summary information for approximate unadjusted pairwise calculations. Those quantities answer related but distinct questions and should not be blended into a single claim.

The primary estimates and their intervals demonstrate the difference between a point estimate and precision. A result close to zero does not prove equivalence, while a confidence interval spanning a wide range makes clear that the evidence does not tightly locate the underlying contrast. The reported overall analysis and the recalculated pairwise comparisons also illustrate how conclusions depend on the test and comparison being discussed.

The record highlights the importance of complete statistical reporting. Details such as model specification, missing-data handling, multiplicity procedures, and original sample-size justification affect how confidently results can be interpreted. Their absence does not invalidate the posted results, but it restricts independent assessment of their assumptions and robustness.

Finally, the sample-size illustrations distinguish planning from retrospective claims. They show how assumptions about effect size and power targets change planning requirements, but they are not observed power and cannot explain the design choices made for this completed study. The broader statistical lesson is to separate what the data estimate, how uncertain that estimate is, and what the registry does not document.

19. 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 registry record constrain interpretation. The primary analysis is defined by receipt of at least 1 dose and availability of at least 1 post-baseline assessment. Participant flow, reasons for exclusion, missing endpoint measurements, and the handling of missing data are not reported in the registry record. The reported analysis counts therefore cannot by themselves show how complete follow-up was or whether missingness could affect the estimates.

The sponsor's primary result is reported as an overall mixed models p-value without model details or sponsor-reported pairwise effect estimates and confidence intervals. The recalculated pairwise results are approximate, unadjusted comparisons from summary statistics, not a reanalysis of participant-level data. Model covariates, repeated-measure structure, and assumptions are not reported, limiting comparison between the sponsor analysis and the recalculation.

The registry does not report the original sample-size justification, interim analyses, a multiplicity plan, or a threshold for clinically meaningful weight change. These omissions limit assessment of how the study was planned and how the primary and secondary evidence should be prioritized. Although six secondary outcomes are listed, results for only three are posted; the other three are not reported in the registry record.

Safety information is also limited to group counts and a listed serious event term, without enough detail to assess timing or treatment relationship. The registry's enrollment figure and completed status do not resolve these reporting gaps. These limitations concern what can be concluded from the available record; they do not establish that particular procedures were or were not used.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Naltrexone for Antipsychotic-Induced Weight Gain — NCT01866098.
• Registry record last updated 2021-10-01; status last verified 2021-09.
• Results first posted 2020-04-08.
• 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.

23. Record Summary

The registry describes a completed randomized, quadruple-masked, parallel-group trial sponsored by Yale University, comparing daily oral naltrexone 25mg and 50mg with placebo for 52 weeks. The primary outcome was change in weight from baseline, with an analysis population requiring randomization, at least 1 dose, and at least 1 post-baseline assessment.

The reported overall primary mixed models result is p = 0.83. Approximate unadjusted recalculations yield imprecise dose-versus-placebo comparisons, with intervals that include zero. Results for three listed secondary outcomes are posted, while results for three other listed secondary measures are not reported in the registry record. Details on missing data, multiplicity, model specification, and original sample-size justification are not reported, limiting assessment of robustness and broader interpretation.