The Women's Recovery Group Study: Stage I Trial: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for The Women's Recovery Group Study: Stage I Trial (NCT00230100), a randomized phase 1 study. The primary outcome is Change in Mean Days of Any Substance Use for Women.

2. Clinical Question

The study asked whether a structured, women-specific recovery group could be developed and evaluated alongside a standard mixed-gender counseling group for people with substance use disorders. The primary outcome focused on women’s change from baseline in mean days of any substance use per month. The registry describes comparisons during the in-treatment phase and the post-treatment phase, rather than one overall follow-up contrast.

The outcome included days with drug and/or alcohol use. It was assessed at baseline and at repeated monthly follow-ups, with assessments described through month 6 and again at month 9. The registry states that the in-treatment and post-treatment time frames were each compared with baseline. It does not report a single pooled estimate or a result for each period in the information available for this analysis.

3. Trial Design

This was a randomized, parallel-group Phase 1 trial with no masking. The registry lists 46 participants as enrolled and the study status as completed. The study start is recorded as 2003-03 and primary completion as 2005-10. Mclean Hospital is listed as the sponsor.

The two behavioral interventions were the Women's Recovery Group and mixed-gender Group Drug Counseling. The Women's Recovery Group was described as a manual-based, structured relapse-prevention group for women, delivered over 12 sessions. Group Drug Counseling was described as standard 12-week, 90-minute mixed-gender group therapy. The registry summary identifies development of a gender-specific group as the study purpose. The full intervention descriptions are not reported in the registry record.

The primary outcome analysis included women only. The registry describes repeated assessments of substance use: baseline assessment covered the 60 days before the baseline interview, followed by monthly assessments for months 1 through 6 and an assessment at month 9. Months 1–3 were designated in-treatment assessments; months 4–6 and month 9 were post-treatment follow-up assessments. The primary outcome description says that the analysis compared both phases with baseline.

Randomization procedures, allocation concealment, the method used to assign participants, and the number randomized to each arm are not reported in the registry record. The record also does not report the planned sample-size justification, protocol deviations, or whether any interim analyses were conducted. Although the study is labeled Phase 1, that designation alone does not establish a particular statistical objective or design feature beyond what is explicitly described.

The registry lists eight outcome measures and five analyses. The primary outcome is a continuous measure summarized as a mean, with standard error identified as its dispersion measure. Numerical outcome estimates and uncertainty intervals 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.

Before assignment: Groups were conducted in an semi-open format where enrollment continued until a maximum of 6-8 subjects were entered per group and then enrollment was closed until the end of the sequence.

Overall Study

Analysis population for the primary outcome, as defined in the registry: Only women were included in this 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 Change in Mean Days of Any Substance Use for Women, measured over In-treatment phase (month 1-3), Post-treatment phase (month 4-6, 9).

The primary endpoint was change from baseline in the mean number of days per month with any substance use among women. “Any” use included drug and/or alcohol use. The outcome was measured using the Timeline Follow-Back: the baseline assessment covered the 60 days before the baseline interview, and subsequent assessments were conducted monthly through month 6 and again at month 9.

The endpoint was organized across two phases: months 1–3 during treatment, and months 4–6 plus month 9 after treatment. The registry describes comparisons of each phase with baseline. It does not give a single numerical result for either phase, or explain how the repeated follow-up measurements were combined into the reported phase comparisons.

As a general statistical matter, days of use is a continuous outcome that can describe change in the frequency of use over time. A mean gives an average across participants, while a standard error describes the estimated precision of that mean. A standard error is not the same as the spread of individual participants’ outcomes. Repeated measurements can also show whether average outcomes change over time, while accounting for the fact that measurements from the same participant are related.

The registry identifies mean days of use as the primary outcome, but the posted record does not include the group means, estimated changes, between-group contrasts, standard errors, confidence intervals, or p-values. The size and precision of the observed changes are therefore not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome description says that a general mixed model analysis of variance (MMANOVA) was used. It describes the model as estimating means per group over the relevant time period and accounting for covariance between repeated measurements. The registry record does not report the model formula, covariance structure, adjustment variables, estimation method, or the exact contrasts used.

Why account for repeated measurements?

As a general statistical concept, repeated observations from one participant are usually related: a person’s measurements at different visits may resemble one another more than measurements from different people do. Treating every visit as if it came from a different participant can misstate uncertainty. A repeated-measures model represents the within-participant relationship, often called covariance, while estimating average patterns over time.

The primary outcome was assessed at baseline, monthly during months 1–6, and at month 9. The record describes months 1–3 as in-treatment and months 4–6 and month 9 as post-treatment. It says both phases were compared with baseline, but does not specify whether the analysis estimated a separate contrast for each visit, an average across visits in a phase, or another summary. The primary outcome is therefore not reducible from the record to one clearly defined numerical contrast.

What does a mean and standard error communicate?

As a general explanation, the mean is an average outcome for a group or set of observations. The standard error describes the estimated precision of an estimate, rather than the range of individual participant values. Smaller standard errors generally indicate more precise estimates under the model assumptions. They do not, on their own, show whether an effect is clinically important or whether a treatment caused a change.

A confidence interval is a general way to express estimation uncertainty. It gives a range of values compatible with the data and statistical model under a stated confidence procedure. The registry record does not report confidence intervals for the primary or secondary outcomes. Without an estimate and an uncertainty interval, the amount of precision cannot be assessed.

How should the comparison be interpreted?

In a randomized trial, a between-group contrast can address whether outcomes differ between assigned groups, subject to the design and analysis assumptions. A change from baseline within one group answers a different question: it describes change over time in that group. A within-group change alone does not establish that one intervention differs from the other. The registry description says that each phase was compared with baseline, but the numerical results and the specific between-group contrasts are not reported in the registry record.

The study is described as randomized and parallel, but details of the randomization method, concealment, and analysis population are not reported. Those details can matter when assessing possible bias and how closely the analysis reflects the randomized comparison. The primary outcome population is explicitly described as women only; handling of participants who did not complete all assessments is not reported.

What can planning calculations say?

The registry’s sample-size assumptions describe a planning illustration based on the observed effect, using a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The illustration defines the effect to detect as a stated fraction of the observed effect. Such calculations are prospective planning scenarios, not observed trial outcomes and not evidence that the study had a particular probability of detecting an effect. The specific effect fractions and participant counts for the illustrations are not reported in the registry record.

The sample-size assumptions do not establish the trial’s original design rationale. The planned sample-size justification and the assumptions used for the trial’s own design are not reported in the registry record. No observed-power claim can be made from the planning description.

Why might outcome distributions matter?

As a general statistical point, counts of days can have a distribution that differs from a symmetric, bell-shaped pattern. Over-dispersion means that observed variability is greater than a model expects; if present and not handled appropriately, uncertainty estimates may be misleading. The registry record does not report a distributional assessment or a separate model for over-dispersion. It does identify a general mixed model analysis of variance, so no additional modeling choices should be inferred.

The record lists eight outcome measures and five analyses, but does not provide the complete statistical analysis plan or numerical test results. The model description therefore supports a broad account of repeated-measures analysis, not a reconstruction of the exact analysis or its findings.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists eight outcome measures and five analyses. It names the primary outcome as change in mean days of any substance use for women, and lists secondary outcomes concerning mean drinks per drinking day and the Addiction Severity Index Alcohol Composite Score for women. The full set of outcomes and the analyses associated with each are not detailed in the registry record.

When multiple outcomes, time points, or comparisons are examined, the chance of at least one apparently unusual result can increase. As a general statistical principle, multiplicity procedures can control or describe that issue, but the appropriate approach depends on which comparisons were planned and how they relate to the study’s objectives. Whether any adjustment was made, and how primary and secondary comparisons were prioritized, are not reported in the registry record.

The primary outcome description includes multiple time points and two phases. The registry indicates that the outcome was not reduced to one comparison. It does not report a numerical result for each assessment or phase, nor does it identify a single estimate as the primary inferential contrast. That limits the ability to assess consistency across time or to distinguish a planned comparison from an exploratory one.

The registry describes baseline and repeated follow-up assessments, but does not report missing-data counts, reasons for missing assessments, or the method used to handle missing outcomes. It also does not report whether the analysis included all randomized participants, only participants with observed data, or another analysis population. The primary outcome analysis is described as including women, but further population details are not reported.

These omissions do not establish that missing observations or multiplicity affected the findings. They mean that the registry record does not provide enough information to evaluate those aspects of the analysis.

11. 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 0% reporting threshold.

For the Women's Recovery Group, the registry lists 29 participants at risk for serious adverse events and 29 at risk for other adverse events. It records 0 serious adverse events and 0 other adverse events. For mixed-gender Group Drug Counseling, it lists 17 participants at risk for each category, with 0 serious adverse events and 0 other adverse events recorded.

These are event counts in the registry record. They should be read alongside the stated numbers at risk and the fact that the record does not provide further detail about event definitions, collection procedures, observation periods, or whether all participants were assessed in the same way. The listed counts do not quantify the likelihood of future events or establish that the interventions have no risks.

Death counts are not reported in the registry record. The record also lists no top serious adverse-event terms. The absence of listed terms does not add detail about what events were monitored or how they were classified. These figures are descriptive and do not provide a formal comparison of safety between groups.

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

The record supports a description of the trial’s randomized, parallel-group design, its two behavioral interventions, and its planned focus on women’s change in days of substance use. It also reports the measurement schedule and describes the use of a repeated-measures model. The available record does not provide the numerical primary outcome results, so it cannot quantify how much participants’ use changed or whether change differed between groups.

That missing information is central to interpretation. Without effect estimates and uncertainty measures, a reader cannot assess the direction, size, or precision of the primary outcome findings. Nor can the listed design details substitute for outcome results. The record’s lack of a numerical result should not be interpreted as a finding of no difference.

The trial’s purpose was to develop a gender-specific, 12-session, manual-based relapse-prevention group for women with substance use disorders. The comparison was mixed-gender Group Drug Counseling, described as a standard 12-week, 90-minute group therapy. These descriptions characterize the interventions; they do not establish that one was more effective or safer than the other.

The adverse-event entries record zero serious and zero other adverse events among the stated numbers at risk in both groups. Those counts are descriptive, and death counts are not reported. They do not prove the absence of risk or allow a detailed assessment of comparative safety.

Overall, the registry record identifies the question and outlines how the primary outcome was assessed, but the posted numerical results are insufficient to answer the comparative-effect question. Any stronger conclusion about benefit, lack of benefit, or clinical importance would go beyond what is reported.

13. Why This Trial Matters Statistically

This trial is statistically notable for a design that evaluates a women-specific group intervention against mixed-gender group counseling while measuring change repeatedly over time. The primary outcome is not a single end-of-study measurement: the registry describes baseline assessment, monthly follow-up through month 6, and an additional assessment at month 9. The stated analysis therefore needed to address both group means and the relationship among repeated assessments.

The endpoint also distinguishes in-treatment and post-treatment periods. That distinction can be useful when a study asks whether changes observed during an intervention persist in follow-up. Statistically, however, estimates for several visits or periods can answer different questions. Clear reporting of the planned contrasts and their uncertainty is needed to make those distinctions interpretable. The registry record describes the phases but does not report the numerical estimates.

The study is labeled Phase 1 and its stated purpose was development of a gender-specific group. This places the intervention-development aim in view, while the randomized comparison provides a framework for evaluating outcomes across two groups. The record does not report the original sample-size justification or enough result detail to assess the precision of the comparison.

More broadly, the record illustrates why design descriptions and outcome reporting serve different roles. Randomization and repeated-measures methods describe how a comparison was structured and analyzed; effect estimates and uncertainty are needed to understand what the data show. Here, the methods are described at a broad level, but the primary and secondary numerical results are not reported in the registry record.

14. 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 main limitation for statistical interpretation is that numerical outcome results are not reported in the registry record. The primary outcome description gives the measure, assessment schedule, phases, and general model, but not group means, changes, contrasts, standard errors, confidence intervals, or p-values. Secondary outcome results are also not reported.

The primary outcome involves multiple assessment times and two phases, and the registry notes that it was not reduced to one comparison. The specific estimand or contrast for each phase is not described in enough detail to reconstruct the analysis. The record does not state whether results were estimated separately by visit, averaged within a phase, or expressed in another way.

Additional design and analysis details are not reported in the registry record, including the randomization procedure, allocation concealment, the complete statistical analysis plan, handling of missing outcomes, and the analysis population beyond the statement that women were included in the primary analysis. The original sample-size justification, interim analyses, and any multiplicity adjustment are also not reported.

Intervention descriptions are abbreviated in the registry record, so details beyond the stated format and broad purpose are not available. The record does not provide participant characteristics or further information about adherence and completion. These gaps restrict assessment of the study population, implementation, and generalizability. They do not demonstrate that a particular bias occurred; they limit what can be assessed from the record.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: The Women's Recovery Group Study: Stage I Trial — NCT00230100.
• Registry record last updated 2023-11-01; status last verified 2023-10.
• Results first posted 2017-02-08.
• 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.

18. Record Summary

NCT00230100 is listed as a completed, randomized, unmasked, parallel-group Phase 1 study sponsored by Mclean Hospital. It enrolled 46 participants, with a recorded start of 2003-03 and primary completion of 2005-10. The two behavioral interventions were the Women's Recovery Group and mixed-gender Group Drug Counseling.

The primary outcome was women’s change from baseline in mean days of any substance use per month, assessed repeatedly during treatment and follow-up. The registry describes a general mixed model analysis of variance that modeled group means over time and covariance between repeated assessments. Numerical outcome estimates and their precision are not reported in the registry record.

The adverse-event entries record 0 serious and 0 other adverse events in both groups, among 29 at risk in the Women's Recovery Group and 17 at risk in Group Drug Counseling. Death counts are not reported. The registry lists eight outcome measures and five analyses, but does not report multiplicity handling, missing-data methods, or the original sample-size justification.