Adding Guided Self-Help Group Therapy to the Alli Weight Loss Program in Treating Binge Eating Disorder: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Adding Guided Self-Help Group Therapy to the Alli Weight Loss Program in Treating Binge Eating Disorder (NCT00601354), a randomized na study. The primary outcome is Weight Loss.

2. Clinical Question

3. Trial Design

This was a randomized, single-masked, parallel-group study sponsored by Stanford University. The registry lists the study as completed, with a start date of 2007-09 and a primary completion date of 2008-11. The phase is recorded as NA. Enrollment was 17.

Participants were assigned to either orlistat/Alli with guided self-help affect regulation group therapy or orlistat/Alli with medication management alone. Both groups received the Alli weight-loss program and medication. The group-therapy arm description specifies 12 weekly sessions. This design makes the treatment contrast the addition of the group intervention to the shared program and medication, although the record does not state exactly which people were masked or how masking was maintained.

The posted primary endpoint is continuous: change in weight in pounds, summarized as a mean with standard deviation, at 3 months from pre-treatment to post-treatment. The primary outcome population is described as intent-to-treat. Binge Frequency is listed as a secondary outcome, and the record lists three outcome measures overall. It does not provide the other outcome measure descriptions in the available record.

The two arm-level primary results are presented as descriptive summaries. The guided self-help arm has n 8, a mean of 6.15 lbs, and a standard deviation of 14.36. The medication-management-alone arm has n 9, a mean of 3.61 lbs, and a standard deviation of 8.11. The registry record does not report a between-group estimate, confidence interval, or p-value. It also does not report a detailed randomization procedure, masking details, or a statistical analysis plan.

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: There was no wash out, run-in, or transition following participant enrollment.Exclusion criteria are described previously. Main exclusion was weight less than 27 kg/m2.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Used intent-to-treat analysis

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 Weight Loss, measured over 3 months: Measured from pre to post treatment.

The primary endpoint is weight loss, described as change in weight in pounds from pre-treatment to post-treatment, with measurement at 3 months. Weight change is a continuous outcome: each participant’s measurement can take a range of values, and the registry summarizes the arm results using a mean and standard deviation. The record identifies the primary analysis population as intent-to-treat.

Weight is a direct measure of the stated weight-loss objective. A pre-to-post change expresses how weight shifted over the treatment period, rather than only giving a measurement at the end. Comparing the arm-level changes could address whether the groups differed in their observed weight outcomes, but the registry record does not report a numerical between-group comparison or inferential test. The two arm means alone do not establish the precision of that contrast.

The posted summaries are 6.15 lbs with standard deviation 14.36 for the guided self-help group and 3.61 lbs with standard deviation 8.11 for the medication-management-alone group. The endpoint description calls the outcome weight loss, but does not give individual observations, a confidence interval, or further detail on the calculation of change. Binge Frequency is listed as a secondary outcome, not as the primary endpoint considered in these summaries.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is continuous, and the registry describes it as a mean with standard deviation. The reported values are arm-level summaries of weight loss in pounds. The means describe the central outcome in each group, while the standard deviations describe the spread of participant outcomes around each group’s mean. A standard deviation is not a confidence interval: it describes variation among observations, whereas a confidence interval describes uncertainty in an estimated quantity, such as a group mean or a between-group contrast.

What does randomization contribute?

Random assignment is intended to make treatment groups comparable, on average, with respect to both measured and unmeasured participant characteristics. In a randomized trial, a group difference can therefore be interpreted as a treatment contrast under the design and analysis assumptions. Randomization does not guarantee that small groups will look alike in every characteristic. The record says the allocation was randomized, but does not describe the sequence-generation procedure, concealment, or stratification. Those implementation details are not reported in the registry record.

The study used a parallel-group design: participants were assigned to a group and the interventions were compared across groups. Both arms included orlistat/Alli and the Alli weight-loss program. The intended contrast was the addition of guided self-help group therapy in one arm. A comparison therefore concerns the therapy as an addition to that shared background, not the isolated effect of group therapy without the medication and program.

What does masking mean in this record?

The registry labels the study single-masked, but does not identify the masked party or explain how masking was achieved. Masking can reduce the influence of expectations on behavior, outcome assessment, or analysis, depending on who is masked. The label alone does not establish which potential sources of bias were addressed. Because group sessions are part of one intervention, the record’s lack of detail is especially relevant to understanding how masking applied in practice; no further assumption about implementation can be made.

How should the mean and standard deviation be read?

The arm summaries are a mean of 6.15 lbs and standard deviation of 14.36 in the guided self-help group, and a mean of 3.61 lbs and standard deviation of 8.11 in the medication-management-alone group. The standard deviations indicate substantial spread in the reported outcome relative to the arm means. In general, when observations vary widely, the mean can give an incomplete picture of the distribution. Individual data or distribution summaries could clarify whether the mean represents a typical participant, but these are not reported in the registry record.

Over-dispersion is a general concern when observed variability is greater than a statistical model expects. If an analysis assumes less variability than the data contain, its uncertainty estimates can be too small and its conclusions too confident. The posted summaries alone do not establish whether a particular model was used or whether over-dispersion was formally assessed. The record does not report model diagnostics, transformations, or robust methods.

What would an inferential comparison add?

A treatment contrast would estimate the difference between the arm outcomes under a stated analysis. A confidence interval would communicate the precision of that estimate by showing a range of values compatible with the data and the model assumptions. A p-value would summarize how unusual the observed data, or more extreme data, would be under a specified null hypothesis. Neither measure is a substitute for considering the size and clinical meaning of an effect. For this trial, the registry record does not report a contrast, confidence interval, p-value, or test specification.

Because the result is continuous, an analysis might use a comparison of means or another method suited to the outcome and design. The registry record does not say which method was used, whether adjustment was planned, or whether the analysis used change scores, endpoint weights with baseline adjustment, or another approach. The stated endpoint is change from pre-treatment to post-treatment, but that description alone does not identify the computational method or its assumptions.

How do the planning assumptions differ from trial results?

The record describes planning illustrations based on the observed effect, using a two-sided significance level of 0.05, equal allocation, and a normal approximation. These are planning assumptions, not evidence that the trial had a particular power or that a target sample size was met. A planning calculation asks how many participants per arm might be needed to detect an assumed effect under stated conditions. Its result depends on the assumed effect and variability as well as the chosen error rate and allocation. Such a calculation is not observed power and cannot replace a confidence interval or the trial’s actual comparative analysis.

Any recalculated comparison based only on arm-level summaries would be a simple, unadjusted re-calculation rather than the sponsor’s prespecified analysis. The registry record does not post such a recalculation, and there is no reported sponsor comparison to reconcile with one. The posted arm summaries remain descriptive; they do not disclose the analysis decisions needed to reproduce a formal test.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("OTC Orlistat + Guided Self-help Affect Regulation", "OTC Orlistat /Medication Management Alone")
n   <- c(8, 9)
m   <- c(6.15, 3.61)
sp  <- c(14.36, 8.11)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  OTC Orlistat + Guided Self-help Affect Regulation  8  6.150  14.360  -5.855  18.155
CARM  OTC Orlistat /Medication Management Alone  9  3.610  8.110  -2.624  9.844

11. Multiplicity, Missing Data and Analysis Populations

The registry lists three outcome measures and identifies Binge Frequency as a secondary outcome. It does not give details for the other listed measures in this record. The primary outcome is weight loss. No inferential results are reported for the primary or secondary outcomes, and the registry lists zero analysis entries. The record therefore does not show whether any multiplicity adjustment was planned or used.

Multiplicity arises when several outcomes, timepoints, or statistical tests are evaluated. Looking across many tests can increase the chance that at least one result appears noteworthy by chance. In general, a prespecified hierarchy or adjustment can address this issue, but the relevant plan is not reported in the registry record. The mere listing of multiple outcomes does not establish how the study team analyzed them.

The primary outcome population is described as intent-to-treat. In general, intent-to-treat analysis aims to analyze participants according to their randomized assignment, regardless of later adherence or treatment received. The phrase does not, by itself, explain who was included in this analysis or how unavailable measurements were handled. The registry record does not report missing-data counts, reasons for missingness, imputation methods, sensitivity analyses, or whether all randomized participants contributed to the primary result.

There are arm-level sample sizes for the posted outcome, but the record does not explain whether those counts represent every randomized participant or only participants with available measurements. Without that information, the degree to which missing outcomes could affect the reported means cannot be assessed. No assumptions about missingness or analysis-population handling should be inferred from the intent-to-treat label alone.

12. 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.

The safety record lists zero serious adverse events among 8 participants at risk in the guided self-help group arm and zero among 9 at risk in the medication-management-alone arm. It also lists zero other adverse events among 8 and 9 participants at risk, respectively. These are the posted counts for the displayed safety categories.

Zero reported events in a small group is not evidence that an event is impossible or that there is no safety risk. It means that no affected participants are recorded for that category in the registry entry. Small denominators provide limited information about uncommon events, and the record does not give event-level descriptions or a follow-up duration specific to safety reporting.

Deaths are recorded as null for both groups. A null entry is not the same as a reported count of zero; deaths are not reported in the registry record. No serious adverse event terms are listed. The posted figures should therefore be read as registry reporting, not as a complete account of all possible harms or as a comparative safety analysis. No adverse-event rate comparison or causal interpretation is reported.

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

The result supports a limited descriptive statement: the registry reports mean weight-loss values for each randomized arm at the 3-month pre-to-post treatment timeframe. The guided self-help plus orlistat/Alli arm has a reported mean of 6.15 lbs, and the medication-management-alone arm has a reported mean of 3.61 lbs. The posted standard deviations are 14.36 and 8.11, respectively. These summaries do not, by themselves, establish a treatment effect.

A comparative conclusion requires more than reading the two means side by side. The record does not report a between-group estimate or its uncertainty. Without that information, readers cannot determine the precision of the contrast from the posted results, or whether the observed arm summaries are compatible with a range of materially different comparative effects. The small arm sizes and wide spread in the outcomes further caution against treating the means as definitive.

The endpoint is weight loss, while the study’s stated purpose also includes reducing binge eating. Binge Frequency appears as a secondary outcome, but no result for it is reported in the record. Thus, the posted primary outcome does not answer the secondary question about binge frequency. Nor does it establish how participants experienced the group intervention or whether they completed the planned sessions.

The findings also do not isolate the effect of guided self-help therapy from the shared orlistat/Alli medication and weight-loss program. The design compares the combined regimen with the shared program and medication alone. Any valid interpretation of the intended contrast would depend on the actual allocation and analysis, details that are not fully documented in the registry record.

These results should not be interpreted as proof that the added therapy is beneficial, ineffective, or equivalent to the comparator. The registry record provides descriptive means and variability but no formal comparative inference. Absence of a reported statistical test is not evidence that the groups were the same, just as a numerical difference between means is not sufficient evidence of a reliable treatment difference.

14. Why This Trial Matters Statistically

This trial is statistically notable because it asks a clear add-on question: whether guided self-help group therapy, delivered alongside the orlistat/Alli program, is associated with a different weight outcome from the same medication and program alone. A shared background treatment helps define the intended contrast. It also means the comparison should not be described as therapy versus no treatment or as medication versus no medication.

The trial illustrates why descriptive summaries and comparative inference serve different purposes. A mean and standard deviation describe each arm, but do not directly quantify the uncertainty in the between-arm contrast. Reporting an estimate with a confidence interval would make the size and precision of the comparison easier to assess. In this record, those inferential results are not reported, so interpretation must remain at the level of arm summaries.

The limited enrollment and the spread of the outcome highlight how unstable estimates can be in small studies. Randomization is valuable, but does not eliminate chance imbalance or make a small dataset precise. This is a general statistical point, not a claim that a particular imbalance occurred in this trial. It also underscores why sample-size planning and observed results should not be conflated. Planning illustrations describe assumptions about a future or intended comparison; they are not a substitute for the trial’s observed uncertainty.

Finally, the record distinguishes the primary endpoint from the stated broader aims. Weight change is reported as the primary measure, while Binge Frequency is listed as secondary without a posted result. That distinction matters when evaluating what the available outcome data address. The trial record is useful for identifying its design and descriptive results, while its missing analysis details limit the strength of conclusions that can be drawn.

15. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The registry record leaves important design and analysis details unspecified. It does not describe the randomization sequence, allocation concealment, the identity of the masked party, or the practical masking procedures. It also does not report the planned statistical model, covariate adjustment, hypothesis test, confidence interval, or analysis plan. These omissions limit reproducibility and make it difficult to assess whether the posted summaries reflect the intended primary analysis.

The enrollment was 17, and the posted primary outcome groups have n 8 and n 9. The record does not explain whether those numbers include all randomized participants or only those with observed outcome data. Although the primary population is labeled intent-to-treat, missing-data counts, reasons, methods, and sensitivity analyses are not reported. The precise analysis population therefore remains uncertain.

The outcome description gives a 3-month pre-to-post timeframe and identifies weight change in pounds, but offers no detail on measurement procedures or the handling of baseline values. There are no participant-level data or distribution summaries beyond the means and standard deviations. The registry also does not report a comparative estimate, confidence interval, or p-value, so precision and statistical compatibility cannot be evaluated from the posted results.

Binge Frequency is listed as a secondary outcome, but no result is reported. The other outcome measures are not detailed in the available record. No multiplicity strategy is described. Safety reporting lists zero affected participants for serious and other adverse events, while deaths are not reported in the registry record. These safety entries do not establish complete ascertainment or comparative risk.

The study’s small enrollment and brief stated treatment timeframe constrain what the posted summaries can establish. The record does not report follow-up beyond the stated 3-month endpoint, adherence, session attendance, or longer-term outcomes. These limitations are specific to the information recorded; they do not establish that unreported procedures or analyses did not occur.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Adding Guided Self-Help Group Therapy to the Alli Weight Loss Program in Treating Binge Eating Disorder — NCT00601354.
• Registry record last updated 2013-09-09; status last verified 2013-06.
• Results first posted 2013-09-09.
• 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.

19. Record Summary

NCT00601354 is a completed, randomized, single-masked, parallel-group study sponsored by Stanford University. The record lists 17 participants and a study period from 2007-09 to primary completion in 2008-11. It compares orlistat/Alli with the Alli program plus guided self-help group therapy against orlistat/Alli and the program alone.

The primary endpoint is weight loss, measured as pre-to-post change in pounds at 3 months and summarized as a mean with standard deviation. The posted means are 6.15 lbs for the guided self-help arm and 3.61 lbs for the medication-management-alone arm. The registry record does not report a comparative estimate, confidence interval, p-value, or detailed analysis plan. Binge Frequency is listed as a secondary outcome without a posted result. Serious and other adverse event counts are zero in both arms; deaths are not reported in the registry record.