A Study to Evaluate a Drug (Dasotraline) on the Safety, Effectiveness and How Well the Body Tolerates it, in Adults With Moderate to Severe Binge Eating Disorder: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Evaluate a Drug (Dasotraline) on the Safety, Effectiveness and How Well the Body Tolerates it, in Adults With Moderate to Severe Binge Eating Disorder (NCT03107026), a randomized phase 3 study. The primary outcome is Change From Baseline in Number of Binge Days.

2. Clinical Question

The clinical question is framed around change in a weekly count rather than whether a participant had any binge episodes at all. The primary measure therefore captures the frequency of days with binge eating over the assessment period. It does not, by itself, describe the number of episodes on a binge day, the duration or intensity of episodes, or whether a participant achieved a sustained period without binge eating.

The study also registered secondary outcomes, including clinician-rated severity, obsessive-compulsive symptoms related to binge eating, binge days and episodes at other study visits, and a four-week cessation measure. These outcomes address related but distinct aspects of the condition. They can add context to the primary endpoint, but they do not replace it. The main comparison remains the change in binge days at Week 12 for each dose against placebo.

3. Trial Design

This was a Phase 3 randomized, parallel-group, placebo-controlled study of dasotraline in adults with moderate to severe binge eating disorder. The official title describes a 12-week, fixed-dose, multicenter, double-blind study. The registry record lists quadruple masking. These descriptions indicate that the record reports both a double-blind design in the official title and quadruple masking in its masking field; further details about who was masked are not reported in the registry record.

Participants were assigned to once-daily placebo, dasotraline 4mg, or dasotraline 6mg. The registry record gives total enrollment as 491. For the primary outcome, the reported group counts were 162 for placebo, 161 for dasotraline 4mg, and 162 for dasotraline 6mg. These are the counts associated with the posted primary outcome and should not be assumed to describe every analysis population or every point in participant follow-up.

The study began on 2017-03-31, reached primary completion on 2018-05-16, and is listed as completed. Sumitomo Pharma America, Inc. is named as the sponsor. The registry identifies the primary outcome population as ITT, but the exact operational definition of that population and the handling of participants with missing outcome data are not reported in the registry record.

Random allocation and a placebo group support a comparative design, while fixed doses allow the two dose groups to be compared separately with placebo. The record does not report the original sample-size justification, the allocation ratio in the protocol, or additional details about how randomization and masking were implemented. Those details should not be inferred from the study’s general design labels.

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.

Before assignment: A total 491 subjects were randomized in this study. Five subjects were randomized but never received any dose of study medication.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: ITT

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 Number of Binge Days, measured over baseline and 12 Weeks.

The primary endpoint is change from baseline in the number of binge days per week at Week 12. A binge day is defined as a day during which at least 1 binge episode occurs. The registry describes the outcome as a least-squares mean, with standard error as the measure of dispersion, and identifies the analysis population as ITT.

Change scores make the Week 12 measure relative to each participant’s baseline rather than treating the final measurement alone as the outcome. A negative change represents fewer binge days per week than at baseline. Comparing the groups’ changes asks whether the measured reduction differs between each dasotraline dose and placebo, not simply whether the average changed within any one group.

This endpoint is useful because it represents the frequency of days affected by binge episodes and can be tracked over the study period. It is not a complete measure of all dimensions of binge eating disorder. In particular, a count of binge days does not convey the number of episodes on each day, and it does not establish how participants experienced the changes or whether changes persisted after the study period. The registry does not report a threshold for a change considered clinically important, so statistical differences should not be equated with a stated clinical-importance threshold.

7. Results Posted in the Registry

• Dasotraline 4mg: mean -3.21 versus -2.92 on control; difference -0.29 (95% CI -0.66 to 0.08), standardized effect d = -0.17; z-test p = 0.127.
• Dasotraline 6mg: mean -3.47 versus -2.92 on control; difference -0.55 (95% CI -0.93 to -0.17), standardized effect d = -0.32; z-test p = 0.005.

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 Binge Eating Clinical Global Impression-Severity( BE-CGI-S )Score

• 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:
  • Dasotraline 4mg: mean -2.13 versus -1.77 on control; difference -0.36 (95% CI -0.68 to -0.04), standardized effect d = -0.25; z-test p = 0.028.
  • Dasotraline 6mg: mean -2.27 versus -1.77 on control; difference -0.50 (95% CI -0.83 to -0.17), standardized effect d = -0.33; z-test p = 0.003.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Dasotraline 4mg 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 lower for Dasotraline 6mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percent of Subjects With a 4-week Cessation From Binge Eating

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Dasotraline 4mg: 33.5% (54/161) versus 30.2% (49/162) on control; risk difference 3.3 percentage points (95% CI -6.9 to 13.5), risk ratio 1.11 (0.81–1.53); unadjusted two-proportion z-test p = 0.525.
  • Dasotraline 6mg: 34.0% (55/162) versus 30.2% (49/162) on control; risk difference 3.7 percentage points (95% CI -6.5 to 13.9), risk ratio 1.12 (0.82–1.54); unadjusted two-proportion z-test p = 0.475.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Dasotraline 4mg 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 Dasotraline 6mg and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in Yale-Brown Obsessive Compulsive Scale Modified for Binge Eating (Y-BOCS-BE) Total Score

• 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:
  • Dasotraline 4mg: mean -14.13 versus -11.83 on control; difference -2.30 (95% CI -4.17 to -0.43), standardized effect d = -0.27; z-test p = 0.016.
  • Dasotraline 6mg: mean -15.23 versus -11.83 on control; difference -3.40 (95% CI -5.30 to -1.50), standardized effect d = -0.39; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Dasotraline 4mg 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 lower for Dasotraline 6mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes cover several related dimensions: clinician-rated severity, binge cessation, obsessive-compulsive symptoms related to binge eating, and counts of binge days or episodes at additional visits. These measures do not all answer the same question. Some assess changes in continuous scores, while cessation is a binary participant outcome. Taken together, the available results can provide context for the primary endpoint, but they should not be treated as interchangeable measures.

In the detailed secondary results, the continuous comparisons generally show more negative changes in the dasotraline groups than in placebo. The sponsor’s reported comparisons for clinician-rated severity and Y-BOCS-BE total score include intervals that lie below zero. By contrast, the sponsor’s logistic-regression comparisons for four-week cessation have confidence intervals that include 1. The pattern is therefore not uniform across types of outcome. These results are secondary and should not displace the primary comparison.

Secondary results carry less weight when many outcomes, visits, groups, or statistical tests are considered and the testing strategy is not reported. With multiple opportunities to observe a nominally notable result, some findings may occur by chance even if there is no underlying difference for the corresponding measure. The registry record does not report whether multiplicity was controlled, so the secondary p-values and intervals should be read as descriptive evidence rather than as a confirmed set of independent findings.

The registry lists other secondary measures assessed at different visits, including changes in binge days and episodes over time and subscale scores. A broader assessment would require the complete outcome results and the prespecified analysis plan. The available secondary findings are relevant to the primary endpoint, but they do not establish that all related measures moved consistently or that any change persisted beyond the study’s 12-week period.

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

• Change From Baseline in Binge Eating Clinical Global Impression-Severity( BE-CGI-S )Score
• Percent of Subjects With a 4-week Cessation From Binge Eating
• Change From Baseline in Yale-Brown Obsessive Compulsive Scale Modified for Binge Eating (Y-BOCS-BE) Total Score
• Change From Baseline in Number of Binge Days Per Week at Weeks 1, 2, 3, 4, 6, 8, and 10
• Change From Baseline in Number of Binge Episodes Per Week at Weeks 1, 2, 3, 4, 6, 8, 10, and 12
• Change From Baseline in Binge-eating Clinical Global Impression-Severity (BE-CGI-S) Score at Weeks 2, 4, 6, 8, and 10
• Change From Baseline in Yale-Brown Obsessive Compulsive Scale Modified for Binge Eating (Y-BOCS-BE) Total Score at Weeks 2, 4, 6, 8, and 10
• Change From Baseline in Yale-Brown Obsessive Compulsive Scale Modified for Binge Eating (Y-BOCS-BE) Subscale Scores (Obsessions and Compulsions) at Weeks 2, 4, 6, 8, 10, and 12

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: it records a change in the number of binge days per week. The registry reports least-squares means for the three groups and standard errors. A least-squares mean is a model-based group mean; it may reflect a statistical model rather than a simple arithmetic average. The registry identifies the sponsor’s method for the primary pairwise comparisons as Mixed Models Analysis, but does not report the complete model specification, covariates, or assumptions. Those details are not reported in the registry record.

What does a group mean describe?

A group mean summarizes the average change among participants included in that outcome analysis. The primary outcome values are -2.92 for placebo, -3.21 for dasotraline 4mg, and -3.47 for dasotraline 6mg. Negative values indicate a decrease from baseline. These within-group changes do not by themselves answer whether the groups differed. The comparative estimate is the mean difference between a dose group and placebo.

What does a standard error describe?

A standard error describes the estimated precision of a mean. It is not the same as the spread of individual participant outcomes. A relatively small standard error can coexist with substantial variation among participants, because the standard error reflects uncertainty in the estimated mean rather than the range of individual experiences. The registry reports standard errors for the primary group means but does not provide the participant-level outcome distribution in the information summarized for this analysis.

How should the pairwise estimates be read?

The sponsor’s reported comparison is a mean difference in final values from a mixed-model analysis. The comparison for dasotraline 4mg versus placebo is -0.29; the comparison for dasotraline 6mg versus placebo is -0.55. A negative contrast indicates a lower value for the dasotraline group relative to placebo under the reported comparison. Since the endpoint is change in binge days, a more negative value corresponds to a greater decrease in the measure. These are comparisons against placebo, not direct evidence from a statistical test comparing the two dose groups with one another.

What does a confidence interval add?

A confidence interval gives a range of values compatible with the data and the analysis assumptions at the stated confidence level. The sponsor reports 95% confidence intervals for the primary comparisons. An interval that includes zero is compatible with no difference between groups; an interval that excludes zero is less compatible with a zero difference under that analysis. The interval does not state the probability that the true effect lies in the particular range, and it does not account for unreported analysis choices or multiplicity adjustments.

How should p-values be interpreted?

A p-value describes how unusual data at least as incompatible with a specified null hypothesis would be if that null hypothesis and the model assumptions held. It is not the probability that the null hypothesis is true, nor does it measure the size or clinical importance of a difference. The sponsor reports p = 0.119 for 4mg versus placebo and p = 0.004 for 6mg versus placebo. The registry record does not report the full testing hierarchy or multiplicity procedure, so these values should not automatically be treated as adjusted for all outcomes and comparisons.

Why are the recalculations approximate?

The unadjusted recalculations use posted group summary statistics to estimate differences and uncertainty. They are not a reconstruction of the sponsor’s full mixed model. For the continuous outcomes, the posted standard errors are used to approximate variability; the record identifies the pooled standard deviation as approximate. A summary-statistic calculation cannot reproduce model adjustments, missing-data procedures, or other details that are absent from the record. The discrepancy flag is particularly important for the 4mg primary comparison: the recalculated p-value is 0.127, while the sponsor reports 0.119. The sponsor’s own analysis takes precedence.

What does the binary secondary measure represent?

The four-week cessation outcome is a participant count, rather than a continuous change score. The sponsor reports logistic regression odds ratios for the dose groups against placebo. An odds ratio compares the odds of the recorded outcome between groups; it is not the same as a risk difference or a ratio of probabilities. The registry record also contains simple unadjusted risk-difference recalculations, but these do not replace the sponsor’s logistic-regression results. Because the reported confidence intervals for the sponsor’s odds ratios include 1, the posted comparisons do not clearly distinguish the odds between each dose group and placebo under those analyses.

What can the methods not establish?

The registry record does not report the complete statistical analysis plan, the model’s covariates, the method used to handle missing values, any interim analyses, or an adjustment plan for multiple testing. It also does not report a clinical-importance threshold for the primary endpoint. General statistical interpretation can explain the meaning of estimates and intervals, but it cannot fill in those unreported protocol details. The outcome results should be understood as the sponsor’s reported analyses alongside transparent, unadjusted recalculations, with the sponsor’s analysis taking precedence when the values differ.

11. Confidence Intervals and Precision

The sponsor’s 95% confidence interval for the 4mg comparison with placebo is -0.66 to 0.08. It includes zero, and its span reflects uncertainty about both the direction and size of the between-group difference. The point estimate is -0.29, but the interval also allows values on the positive side of zero. The reported p-value is 0.119.

For the 6mg comparison, the sponsor’s 95% confidence interval is -0.93 to -0.17, around a point estimate of -0.55. This interval lies below zero, while still covering a range of possible effect sizes. Its width matters: a point estimate alone would give an incomplete account of uncertainty. The reported p-value is 0.004.

A confidence interval is not a guarantee that the true effect lies within its limits, nor does it show the range of individual participant responses. It quantifies uncertainty in an estimated group contrast under the model and assumptions used. The registry record does not give enough detail to assess every modeling assumption or the impact of missing data, and it does not report a multiplicity adjustment. The posted intervals therefore describe precision for the specified comparisons, not certainty about every endpoint or analysis.

The recalculated intervals are -0.663 to 0.083 for 4mg versus placebo and -0.930 to -0.170 for 6mg versus placebo. Their close but not identical values reflect the difference between simple summary-statistic calculations and the sponsor’s mixed-model analysis. Because a discrepancy is flagged, the sponsor’s reported intervals and tests take precedence for interpretation.

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 translate an observed contrast into the approximate number of participants per arm that would be needed under stated planning assumptions. They are not the original design justification for this study; the trial’s own sample-size assumptions are not reported in the registry record. The figures are participants per arm, not total participants, for these continuous and binary outcomes. The event-total convention for time-to-event outcomes does not apply to these outcomes.

The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each illustration considers detecting the stated fraction of the observed effect. The 80% power column represents the planned chance of detecting that assumed effect under those assumptions if it were the true effect; the 90% column represents a higher planned chance of detection. These are design probabilities, not guarantees for an individual study.

For each comparison, planning for a smaller effect requires more participants per arm than planning for the full observed effect. This follows because smaller differences are harder to distinguish from random variation while maintaining the same significance level and planned power. The observed effect is used only as an input to these hypothetical planning calculations, so estimates based on it may be unstable, especially when the original estimate is uncertain. This is not observed power.

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 = -0.290; pooled standard deviation σ = 1.709.
2. n = 2 × (1.96 + 0.842)² × 1.709² / -0.290² = 545.3, rounded up to 546 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 <- -0.29                      # observed difference in means
sigma <- 1.70924223249538                     # 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(3107026)
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 = 546 (80% power), 731 (90% power)
 75% of observed effect: n per arm = 970 (80% power), 1,298 (90% power)
 50% of observed effect: n per arm = 2,182 (80% power), 2,921 (90% power)
power.t.test: 546.3 
Simulated power at n = 546 per arm: 0.796 (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 registry reports the sponsor’s primary comparisons using Mixed Models Analysis. For dasotraline 4mg versus placebo, the sponsor reports a mean difference of -0.29, a 95% confidence interval of -0.66 to 0.08, and p = 0.119. For dasotraline 6mg versus placebo, the sponsor reports -0.55, a 95% confidence interval of -0.93 to -0.17, and p = 0.004.

The simple recalculations use the posted group means and standard errors and produce estimates of -0.29 and -0.55, with unadjusted p-values of 0.127 and 0.005, respectively. The recalculated confidence limits also differ slightly from the sponsor’s reported limits. Such differences can arise because a summary-statistic recalculation does not reproduce the sponsor’s model and analysis procedures. The registry record flags a discrepancy, including for the 4mg primary comparison.

The recalculations are useful as an approximate cross-check, but they are not an alternative sponsor analysis. The sponsor’s own analysis takes precedence for the trial’s reported inference. The registry record does not contain sufficient model detail to explain exactly why the estimates of uncertainty and p-values differ.

15. Multiplicity, Missing Data and Analysis Populations

The registry record lists a primary endpoint and numerous secondary outcomes, including measures at multiple visits. That creates a multiplicity question: when many hypotheses are tested, the chance of at least one apparently notable result can increase. Statistical plans commonly address this by specifying which comparisons are confirmatory and whether or how testing is adjusted. The registry record does not report a multiplicity adjustment, testing hierarchy, or other strategy for controlling the overall error rate. It is therefore not possible to determine from the record whether the sponsor’s reported p-values were adjusted across outcomes or comparisons.

The primary result should be distinguished from secondary findings. The primary endpoint is identified as change in binge days at Week 12, and the sponsor reports comparisons against placebo. Secondary measures can contribute supporting context, but nominal p-values on those measures do not have the same interpretive status as a prespecified primary test when the multiplicity plan is unavailable.

Missing-data methods are also not reported in the registry record. The primary population is labeled ITT, but the record does not give the exact analysis-set definition, the number of participants with missing Week 12 values, or how missing measurements were handled in the model. A mixed-model method is named, but that label alone does not establish the assumptions made about missing observations or the steps taken to assess them.

The registry does not report interim analyses or stopping rules. It also does not report the complete statistical analysis plan or the original sample-size justification. These omissions limit the ability to assess the prespecification and robustness of the analyses. They do not show that particular procedures were or were not used; they mean that those details are not reported in the registry record.

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: palpitations (0.6%), hiatus hernia (0.6%), inguinal hernia (0.6%), psychotic disorder (0.6%), cholecystitis (0.6%).

The registry reports serious adverse events for 1 of 163 participants at risk in the placebo group, 3 of 161 in the dasotraline 4mg group, and 1 of 162 in the dasotraline 6mg group. It reports no deaths in the three groups. The record also lists non-serious adverse events affecting 70 participants at risk in the placebo group, 105 in the 4mg group, and 113 in the 6mg group. These are counts, and the at-risk group sizes are stated separately.

The serious-event figures are descriptive. They do not establish that an event was caused by the assigned treatment, and they do not by themselves support a comparison of overall safety. The registry lists palpitations, hiatus hernia, inguinal hernia, psychotic disorder, and cholecystitis among the top serious-event terms, each reported as 0.6%. The record does not provide enough detail in these figures to assess event timing, duration, severity beyond the serious classification, or the sponsor’s attribution of causality. Safety findings should be read alongside the study’s limited 12-week observation period and the full clinical record, not as a standalone conclusion.

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

The posted results describe average changes in weekly binge days during a 12-week randomized study. The sponsor-reported comparison for dasotraline 4mg versus placebo is imprecise enough to include no difference in its 95% confidence interval. The sponsor-reported comparison for dasotraline 6mg versus placebo has a confidence interval below zero. These statements describe the posted estimates and their uncertainty; they do not establish what would happen for every participant.

A group average does not describe the distribution of individual responses. Some participants may have had larger changes, smaller changes, no change, or changes in the opposite direction. The registry outcome does not report individual trajectories. Nor does a change in binge days alone establish a change in every aspect of binge eating disorder, functioning, or quality of life.

The comparisons do not establish a direct difference between dasotraline 4mg and dasotraline 6mg, because the reported primary tests compare each dose with placebo. The registry record also does not report a clinical-importance threshold for the endpoint. Statistical evidence about a group contrast should not be treated as proof that the size of the contrast is meaningful to every participant.

Interpretation is further bounded by the absence of registry entries about missing-data handling, multiplicity, and the full model specification. Secondary outcomes offer additional context but are subject to the same reporting limits, with the added concern of multiple testing. The safety counts describe reported events during the study and do not establish causality. These registry results are a record of specified study outcomes and analyses, not medical advice or a basis for an individual treatment decision.

18. Why This Trial Matters Statistically

This trial illustrates why the estimate, its uncertainty, and the analysis method all matter. The two dose-versus-placebo point estimates differ in magnitude, and their confidence intervals convey different levels of compatibility with a zero contrast. Looking only at group means would miss the central comparative question; looking only at p-values would omit the size and precision of the estimated differences.

It also illustrates the distinction between a sponsor’s model-based analysis and a simple recalculation from posted summary values. The primary estimates are similar, but the recalculated uncertainty and p-values are not identical. When the registry flags a discrepancy, the sponsor’s analysis takes precedence, while the recalculation remains an approximate check rather than a replacement.

The study also demonstrates why secondary results need a defined interpretive hierarchy. Multiple outcomes and visits can give a richer picture, but without a reported multiplicity strategy, isolated nominal findings deserve caution. Finally, a registry record can identify the primary outcome and report results while leaving key methods—such as missing-data handling and model details—not reported. Recognizing those limits is part of sound statistical interpretation, not a reason to infer what the record does not say.

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.

The primary outcome is a weekly count of days with at least 1 binge episode, so it does not capture episode frequency within a day or all dimensions of the condition. The registry record does not state a clinical-importance threshold for a change in this endpoint, limiting interpretation of the practical importance of the estimated differences.

The sponsor’s mixed-model details are incomplete in the registry record. The covariates, model specification, assumptions, missing-data handling, and sensitivity analyses are not reported. The record identifies the primary population as ITT but does not provide its operational definition. This limits independent assessment of how participants with incomplete follow-up contributed to the estimates.

The simple recalculations are approximate and unadjusted. They do not reproduce the sponsor’s model, and the registry flags a discrepancy between recalculated and sponsor-reported results. The sponsor’s reported analysis therefore takes precedence. The record does not report whether multiplicity was addressed despite numerous secondary outcomes and repeated visits, which makes the secondary findings less definitive.

Follow-up for the study was 12 weeks, so these results do not describe outcomes beyond that period. The registry record also does not report the original sample-size justification or interim-analysis plan. Safety counts are descriptive and do not establish causality. These limitations are specific to what is reported for this study and constrain how broadly its estimates can be interpreted.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Study to Evaluate a Drug (Dasotraline) on the Safety, Effectiveness and How Well the Body Tolerates it, in Adults With Moderate to Severe Binge Eating Disorder — NCT03107026.
• Registry record last updated 2020-07-13; status last verified 2020-06.
• Results first posted 2020-07-13.
• 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.

23. Record Summary

The registry record describes a completed Phase 3 randomized, parallel-group, placebo-controlled study of once-daily dasotraline 4mg or 6mg in adults with moderate to severe binge eating disorder. The official title specifies a 12-week study. Total enrollment was 491.

The primary outcome was change from baseline in weekly binge days at Week 12, analyzed in the ITT population. The sponsor reported a mean difference of -0.29 for 4mg versus placebo and -0.55 for 6mg versus placebo. The first sponsor-reported 95% confidence interval includes zero; the second lies below zero. The registry also contains secondary outcome findings and adverse-event counts, which require cautious interpretation given unreported multiplicity and analysis details.

The registry record does not report the full statistical analysis plan, missing-data procedures, or original sample-size justification. A discrepancy is flagged between the sponsor’s primary analysis and simple recalculations; the sponsor’s analysis takes precedence.