Building Recovery By Improving Goals, Habits, and Thoughts: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Building Recovery By Improving Goals, Habits, and Thoughts (NCT01191788), a non-randomized na study. The primary outcome is Depressive Symptoms as Measured by the Beck Depression Inventory II.

2. Clinical Question

3. Trial Design

The registry describes a completed, parallel, non-randomized study sponsored by RAND. The study start is recorded as 2006-08 and primary completion as 2009-07. Masking is listed as none. The record gives enrollment as 299. Separately, the brief summary says that 360 clients would receive one of two conditions. These enrollment statements are not reconciled in the registry record, so it is not clear from these entries how many participants entered each arm or contributed to the primary outcome analysis.

One arm received group CBT for depression in addition to usual residential alcohol and other drug treatment. The arm description specifies up to 16 group sessions. The comparator was treatment as usual. The brief summary states that trained alcohol and other drug counselors would lead the CBT groups and that data would be analyzed using an intent-to-treat model. This describes the proposed analysis approach, not a reported analysis: the registry lists zero analyses.

Non-randomized allocation is an important design feature. Without random assignment, observed group differences may reflect pre-existing differences between participants or other factors associated with receiving each condition, as well as any relationship with the intervention. The record does not report how participants were allocated, what factors governed allocation, or whether statistical adjustment for group differences was planned. No masking also means that blinding is not part of the recorded design.

The registry lists two outcome measures. The primary outcome is depressive symptoms measured by the BDI-II at 3 Months Post Treatment; the secondary outcome is mental health functioning measured by the SF-12 MCS. Although the study status is completed, outcome estimates and analysis details are not reported in the registry record. Completion status alone does not establish what the study found.

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:

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 Depressive Symptoms as Measured by the Beck Depression Inventory II, measured over 3 Months Post Treatment.

The primary endpoint is depressive symptoms measured by the Beck Depression Inventory II (BDI-II) at 3 Months Post Treatment. The BDI-II is described as a 21-question, self-administered measure. Its scores range from 0 to 63, with higher scores indicating more severe depressive symptoms. The endpoint is specified as a mean score, with standard deviation as the measure of dispersion.

A continuous score can describe a range of symptom severity rather than reducing responses to a simple event/no-event outcome. Comparing mean scores can therefore address whether the groups differed on average at the stated follow-up. The standard deviation describes how spread out individual scores are around a group mean; it is not itself an estimate of the treatment-group difference.

The registry record does not provide the group means, standard deviations, number assessed at follow-up, or an estimated difference. It also does not report a confidence interval or p-value for the primary endpoint. Thus, the outcome definition is available, but the posted record does not allow readers to assess the observed magnitude or precision of a group contrast.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies the primary measure as a continuous outcome summarized by a mean and standard deviation. It describes a proposed intent-to-treat analysis and a parallel non-randomized allocation. These details establish some features of the intended comparison, but the registry does not report the actual statistical model, estimates, uncertainty intervals, or hypothesis tests. The entries below explain the relevant statistical concepts in general; they should not be taken as a description of unreported procedures used in this study.

What does a mean comparison describe?

For a continuous outcome such as BDI-II score, a group mean represents the average score among the participants included in that summary. A contrast between group means describes the average separation between the groups on the measured scale. The standard deviation describes variability among individual scores within a group. It does not describe the precision of the group mean or the uncertainty in a between-group contrast by itself.

To interpret a mean contrast, readers generally need the group summaries and a measure of uncertainty. A confidence interval gives a range of values compatible with the data and the assumptions of the analysis; it communicates precision as well as the estimated direction and magnitude. A p-value addresses compatibility with a specified null hypothesis under the analysis assumptions, but does not measure clinical importance or the probability that a hypothesis is true. Neither kind of inferential result is reported for the primary outcome in the registry record.

Why does allocation matter?

Random allocation is intended to make treatment assignment independent of participant characteristics, on average, which supports a more direct interpretation of between-group differences. This study is listed as non-randomized. In such a design, group membership may be related to characteristics that also influence depressive symptoms. For example, selection into a condition or differences in circumstances could contribute to an observed score contrast. This is a general concern, not evidence that any particular imbalance occurred in this study.

Statistical adjustment can sometimes account for measured differences, but it cannot automatically remove bias from unmeasured factors or a poorly specified model. The registry record does not report which baseline variables were measured for adjustment, whether adjustment was planned, or what model was used. It is therefore not possible to assess the adequacy of confounding control from the posted record.

What does intent-to-treat mean?

In general, an intent-to-treat approach analyzes participants according to their assigned or original study group, regardless of how much intervention they received. It can preserve the comparability created by randomization when allocation is randomized. In a non-randomized study, it does not itself remove differences associated with how groups were formed. The brief summary says that an intent-to-treat model would be used, but the registry does not report how this approach was defined or implemented. It does not identify the participants included in the primary analysis.

How should follow-up timing be read?

The primary endpoint is measured at 3 Months Post Treatment. A score at a specified follow-up is a measurement at that time, not a report of change from baseline unless an analysis explicitly compares baseline and follow-up values. The record does not report baseline scores, change scores, or an adjusted endpoint comparison. It therefore does not establish whether the planned analysis would compare follow-up means, changes, or another summary.

What can a planning illustration tell readers?

The stated sample-size assumptions describe a planning illustration based on an observed effect: a two-sided significance level of 0.05, equal allocation between arms, a normal approximation, and detection of a stated fraction of the observed effect. Such calculations are planning exercises, not observed trial findings. They depend on the effect used for planning and on statistical assumptions. The record does not give a reported primary-outcome effect from which readers could assess the illustration, and the illustration should not be interpreted as observed power or as evidence that the study detected an effect.

More generally, a planning calculation estimates the sample size needed to detect a specified effect under stated assumptions. It does not establish that the effect is real, important, or precisely estimated in the completed study. Nor can a planning result replace an observed effect estimate and its confidence interval. The registry record does not report a sample-size justification from the trial's own design.

Finally, all these concepts depend on the data and analysis actually used. Because outcome summaries, analytic methods, and uncertainty measures are not reported, the statistical interpretation must remain limited to the registered design and outcome definitions.

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("Group CBT", "Comparison")
n   <- c(120, 140)
m   <- c(14.83, 21.82)
sp  <- c(11.23, 12.74)
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  Group CBT  120  14.830  11.230  12.800  16.860
CARM  Comparison  140  21.820  12.740  19.691  23.949

11. Multiplicity, Missing Data and Analysis Populations

The registry lists two outcome measures: the BDI-II primary endpoint and the SF-12 MCS secondary outcome. It also lists zero analyses. No outcome-specific estimates or tests are reported, and a statistical plan for managing multiple outcomes or multiple tests is not reported in the registry record. Without such information, it is not possible to determine whether any multiplicity adjustment was planned or applied, or how the primary and secondary outcomes were to be interpreted together.

The brief summary describes an intent-to-treat model, but does not state which participants would be included in each analysis, how the analysis population would be defined, or whether participants who did not complete the intervention would remain in their original group for analysis. The registry does not report the number of participants assessed at follow-up, missing BDI-II or SF-12 MCS values, reasons for missingness, or a method for handling missing data. These details are important because incomplete follow-up can affect both the analyzed population and the estimated group means.

It is also not reported whether the primary endpoint analysis would adjust for baseline scores, site or counselor effects, or other participant characteristics. The record describes a single public sector treatment organization, but does not provide further details about clustering or a plan to account for it. These analysis choices should not be inferred from the outcome definitions or from the stated intent-to-treat approach. The registry record supplies too little information to evaluate the analysis population, missing-data assumptions, or multiplicity control.

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 0% reporting threshold.

The registry records serious adverse events for the Group CBT arm among 140 participants at risk, with 0 affected. For the Comparison arm, 159 participants are listed at risk, with 0 affected. The registry also lists 0 other adverse events affected in each arm, using the same at-risk counts. These are the adverse-event figures recorded for the groups; they do not provide detail about event types or follow-up procedures.

The deaths entries are null, and the serious-event terms list is empty. Deaths and event terms are therefore not reported in the registry record. A zero in the affected count means that no affected participants are entered in that registry field; it should not be expanded into a claim about every possible harm or about safety beyond the recorded categories and reporting.

These figures do not establish that the intervention caused or prevented adverse events. The non-randomized design also limits direct comparisons between the arms. The registry record does not provide further information about how adverse events were collected, how long participants were monitored for them, or how events were classified.

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

The registry establishes that a completed, non-randomized, parallel study compared usual residential alcohol and other drug treatment plus group CBT for depression with treatment as usual. It identifies the BDI-II score at 3 Months Post Treatment as the primary endpoint and the SF-12 MCS as a secondary outcome. It also reports the arm descriptions and adverse-event counts.

Those details do not amount to evidence of an outcome difference. The primary and secondary results are not reported in the registry record. There is no posted estimate of the group contrast, no measure of its precision, and no reported analysis to evaluate. Consequently, the record cannot show whether scores differed, by how much they differed, or whether any observed contrast was compatible with a range of effects.

Even if a mean difference were available, a non-randomized comparison would need cautious interpretation. Differences in participant characteristics or the process by which participants entered each arm could contribute to the observed contrast. The registry does not describe allocation procedures or adjustment methods, so readers cannot judge whether these concerns were addressed.

The listed adverse-event figures should also be read narrowly. They record zero affected participants in the reported serious and other adverse-event fields for each group, while deaths are not reported. They do not provide a complete account of how safety was monitored or what other events may have occurred outside those fields.

Accordingly, the record supports a description of the study question and design, but not a conclusion about whether adding group CBT was associated with better or worse depressive symptoms, mental health functioning, or safety outcomes. Those conclusions would require results and analytic details that are not reported in the registry record.

14. Why This Trial Matters Statistically

This study raises a statistical question that is common in service settings: how to evaluate a behavioral intervention delivered within routine treatment when participants are not randomly allocated. The contrast is between an added group CBT course and treatment as usual in residential alcohol and other drug care. The registered primary endpoint is a continuous symptom measure, making the mean and its variability central to interpretation.

Its non-randomized design makes the distinction between association and causal effect especially important. A difference between groups could reflect the intervention, but could also reflect characteristics related to treatment selection or other factors. Statistical adjustment may help with measured differences, though the registry does not report whether or how it was used. The design information alone therefore cannot establish that a group contrast would be attributable to CBT.

The trial also illustrates why completion status and a clear outcome definition are not enough for statistical interpretation. Without group summaries, effect estimates, uncertainty intervals, or analysis details, readers cannot judge magnitude, precision, or robustness. The gap between the enrollment entry of 299 and the brief-summary statement that 360 clients would receive a condition is another reason to seek a reconciled account of participant flow and analysis populations.

Finally, a planning illustration and an observed result answer different questions. Planning assumptions concern the ability to detect a specified effect under stated conditions; observed estimates describe the data collected. Keeping those concepts separate is essential, particularly when the registry does not report the outcome analysis. The record's value is in documenting the study question and planned comparison, while its statistical conclusions remain limited by the absence of posted results.

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 principal limitation for interpreting this trial from the registry record is that outcome results are not reported. There are no primary or secondary outcome summaries, effect estimates, confidence intervals, or p-values. Although the study status is completed, the posted record does not show what was observed or how precisely it was estimated.

Allocation was non-randomized and masking was listed as none. The record does not explain how participants were assigned to the groups, whether allocation depended on participant or service characteristics, or whether potential baseline differences were addressed. This limits the interpretation of any group contrast as an intervention effect.

The participant counts also need clarification. The registry lists enrollment of 299, while the brief summary says 360 clients would receive one of the two conditions. The record does not explain the relationship between these figures, report arm-specific enrollment beyond the adverse-event at-risk counts, or state how many participants contributed to the primary endpoint.

Further limitations include the absence of reported baseline outcome values, follow-up completion, missing-data procedures, covariate adjustment, and a detailed statistical analysis plan. Although intent-to-treat analysis is described in the brief summary, its implementation is not reported, and the registry lists zero analyses. The record also does not report how multiple outcomes were handled, how adverse events were collected, or any cost-effectiveness findings mentioned in the study summary. These gaps preclude a complete assessment of statistical validity, precision, and the study's intended economic evaluation.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Building Recovery By Improving Goals, Habits, and Thoughts — NCT01191788.
• Registry record last updated 2022-10-18; status last verified 2022-09.
• Results first posted 2012-06-25.
• 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

The registry describes a completed, parallel, non-randomized study of group CBT for depression added to usual residential alcohol and other drug treatment versus treatment as usual. RAND is listed as sponsor; masking is recorded as none. The record lists enrollment of 299, while the brief summary describes 360 clients. This difference is not reconciled.

The primary outcome is mean BDI-II score at 3 Months Post Treatment, with standard deviation as the dispersion measure. The secondary outcome is mental health functioning measured by SF-12 MCS. The brief summary describes an intent-to-treat approach and a cost-effectiveness evaluation, but results and analysis details are not reported in the registry record. The registry lists zero analyses. Serious and other adverse-event affected counts are recorded as 0 in both arms; deaths are not reported.