This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for The Insomnia Treatment and Problems Study for Veterans (NCT03804788), a randomized na study. The primary outcome is Retention.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT03804788 |
| Phase | NA |
| Condition | Insomnia, Alcohol; Harmful Use |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Double |
| Enrollment | 71 |
| Arms in the primary outcome | 2 |
| Lead sponsor | University of Missouri-Columbia |
| Results posted | Yes |
2. Clinical Question
Population
The trial is framed around returning veterans and addresses insomnia and harmful alcohol use. The registry record does not report detailed eligibility criteria or the demographic and clinical characteristics of enrolled participants.
Intervention
Individual Cognitive Behavioral Therapy for Insomnia (CBT-I), delivered once a week for six weeks. The registry record describes it as a behavioral intervention.
Comparator
Sleep Hygiene, described as a sleep hygiene handout delivered once to all participants. This is also listed as a behavioral intervention.
Primary question
At post-treatment (week 6), how many participants completed all treatment sessions in each arm? This endpoint measures retention, rather than directly measuring improvement in insomnia or alcohol use.
The study’s stated aim is to evaluate improvement of insomnia as a mechanism of improvement in alcohol use outcomes. Its primary endpoint is narrower: treatment completion. The record lists alcohol craving, percentage of days using alcohol to help with sleep, and percentage of days using sleep medication among the secondary outcomes, along with delay discounting, negative affect, and emotion regulation. Results for those outcomes are not reported in the registry record.
Accordingly, the posted primary comparison addresses whether retention differed between the CBT-I and Sleep Hygiene arms. It does not, by itself, answer whether insomnia improved, whether alcohol use changed, or whether any change in insomnia was a mechanism for a change in alcohol use. The registry record does not report detailed eligibility criteria, so the population to which the findings may apply cannot be characterized more specifically from this record.
3. Trial Design
NCT03804788, titled “The Insomnia Treatment and Problems Study for Veterans,” is described as a randomized, double-masked, parallel-arm trial. The official title is “The Impact of Insomnia Treatment on Heavy Alcohol Use Among Returning Veterans.” The study status is completed. The record gives a start date of 2019-04-04, a primary completion date of 2023-09-30, and enrollment of 71. The phase is listed as NA, and the sponsor is University of Missouri-Columbia.
Participants were assigned to CBT-I or Sleep Hygiene. The CBT-I arm is described as individual treatment once a week for six weeks. The Sleep Hygiene arm received a handout once. The posted arm counts are 38 for CBT-I and 33 for Sleep Hygiene. The record does not identify which people or groups were masked, explain how masking was maintained, or describe the randomization procedure. Those details are not reported in the registry record.
The primary outcome is retention, defined as the number of participants who complete all treatment sessions, assessed at post-treatment (week 6). The registry record lists 14 outcome measures and six secondary outcomes. These include delay discounting, negative affect, emotion regulation, alcohol craving, percentage of days using alcohol to help with sleep, and percentage of days using sleep medication. The record does not provide posted results for these secondary outcomes.
The record does not report the protocol’s sample-size justification, planned allocation ratio, planned analysis populations, or a detailed statistical analysis plan. It also does not specify whether any interim analyses were planned. The observed arm counts describe the participants represented in the posted retention results; they do not supply those missing design details.
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
| Stage | CBT-I | Sleep Hygiene |
|---|---|---|
| STARTED | 38 | 33 |
| COMPLETED | 38 | 33 |
| NOT COMPLETED | 0 | 0 |
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.
| Characteristic | Unit | CBT-I | Sleep Hygiene | Total |
|---|---|---|---|---|
| Participants analysed | 38 | 33 | 71 | |
| Age, Continuous | years | 37.1 (SD 7.7) | 38.3 (SD 11.1) | 37.7 (SD 9.3) |
| Sex: Female, Male: Female | Participants | 6 | 8 | 14 |
| Sex: Female, Male: Male | Participants | 32 | 25 | 57 |
| Ethnicity (NIH/OMB): Hispanic or Latino | Participants | 2 | 1 | 3 |
| Ethnicity (NIH/OMB): Not Hispanic or Latino | Participants | 36 | 32 | 68 |
| Ethnicity (NIH/OMB): Unknown or Not Reported | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): American Indian or Alaska Native | Participants | 1 | 0 | 1 |
| Race (NIH/OMB): Asian | Participants | 1 | 0 | 1 |
| Race (NIH/OMB): Native Hawaiian or Other Pacific Islander | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): Black or African American | Participants | 3 | 0 | 3 |
| Race (NIH/OMB): White | Participants | 31 | 27 | 58 |
| Race (NIH/OMB): More than one race | Participants | 2 | 6 | 8 |
| Race (NIH/OMB): Unknown or Not Reported | Participants | 0 | 0 | 0 |
| Region of Enrollment: United States | participants | 38 | 33 | 71 |
6. Primary Endpoint
The registry lists the primary outcome as Retention, measured over Assessed at post-treatment (week 6).
| Element | Registry entry |
|---|---|
| Result type | Count Of Participants |
| Measure of spread | not applicable |
| Unit | Participants |
| Endpoint classification | Binary Endpoint |
The primary endpoint is retention, measured as the number of participants who complete all treatment sessions. It was assessed at post-treatment (week 6). The posted results give counts of 33 participants completing treatment in each arm, with 38 participants in CBT-I and 33 in Sleep Hygiene.
Retention is a process outcome: it describes whether participants stayed through the treatment sessions, rather than whether their insomnia or alcohol use changed. In general, completion is useful for understanding engagement with an intervention and how many participants received the intended course of sessions. It can also help interpret later outcome measurements, because participants who do not complete treatment may have fewer opportunities for post-treatment assessment. Those general considerations do not establish why the investigators selected retention as the primary endpoint; the endpoint rationale is not reported in the registry record.
The outcome is directly interpretable as a count of completers, but counts alone do not describe the reasons for non-completion or the experience of participants who completed treatment. The registry record does not report reasons for missing sessions, a definition of completion beyond completing all treatment sessions, or outcome data for insomnia and alcohol use alongside the primary retention result. Retention therefore answers a specific implementation question and should not be treated as a substitute for the study’s stated interest in alcohol-related outcomes.
7. Results Posted in the Registry
- Sleep Hygiene: 100.0% (33/33) versus 86.8% (33/38) on control; risk difference 13.2 percentage points (95% CI 2.4 to 23.9), risk ratio 1.15 (1.02–1.30); unadjusted two-proportion z-test p = 0.031.
Risk difference: Sleep Hygiene
95% CI: 2.4 to 23.9 percentage points
Recalculated from the posted summary statistics
8. Statistical Interpretation
The posted retention counts are 33 of 38 participants in CBT-I and 33 of 33 in Sleep Hygiene. The registry comparison reports a risk difference of 0.132 for Sleep Hygiene relative to CBT-I, with a confidence interval from 0.024 to 0.239. The reported risk ratio is 1.152, with a confidence interval from 1.017 to 1.303. The unadjusted p-value is 0.031.
For this binary endpoint, a risk difference expresses the contrast between the arms in the probability of completing all treatment sessions. The positive reported estimate is oriented toward a higher completion probability in Sleep Hygiene than in CBT-I. The interval gives a range of values compatible with the estimated contrast under the statistical method used. It is not a range containing a known true value with certainty, and it does not describe the experience of every participant.
The point estimate and its interval indicate that the observed retention contrast favors the Sleep Hygiene arm on this endpoint. The p-value describes how unusual results at least as incompatible with a no-difference model would be under the assumptions of the test; it does not measure the probability that the null hypothesis is true, nor does it establish the importance of the contrast. The record labels the p-value as unadjusted. A multiplicity-adjusted result is not reported in the registry record.
Interpretation should remain focused on completion. The posted result does not show whether either intervention changed insomnia symptoms, alcohol use, or the proposed relationship between insomnia improvement and alcohol outcomes. Although the study’s stated aim concerns improvement in alcohol use outcomes, the posted primary result is retention, and results for the listed secondary outcomes are not reported in the registry record.
The record does not explain why participants did not complete all sessions in CBT-I, or whether non-completion reflected treatment burden, scheduling, participant choice, or other circumstances. It also does not report the analysis population or handling of missing outcome information. These omissions limit interpretation of how representative the retention counts are of all randomized participants and why the arm counts differ.
Finally, the comparison is specific to the interventions as described: individual CBT-I delivered weekly for six weeks versus a single sleep hygiene handout. It is not a comparison of all possible insomnia treatments or all possible sleep hygiene programs. The result characterizes the posted retention outcome for these trial arms; it should not be extended to unreported clinical outcomes or to people outside the population described by the registry record.
9. Statistical Methods Explained
What does the primary endpoint count?
The endpoint is a binary participant outcome summarized as a count: whether each participant completed all treatment sessions by post-treatment (week 6). A count is straightforward to interpret, but it does not convey reasons for completion or non-completion. The posted counts are 33 in each arm, with arm sizes of 38 for CBT-I and 33 for Sleep Hygiene. The registry record does not report the individual-level data or any additional breakdown of completion.
How should a risk difference be read?
A risk difference compares the event probabilities between two groups by subtracting one group’s probability from the other’s. Here, the event is retention, not an adverse event. The registry reports a risk difference of 0.132 for Sleep Hygiene relative to CBT-I. Its positive direction corresponds to a higher retention probability in Sleep Hygiene. In general, the risk difference retains the absolute scale of the event probability and is often readily connected to the outcome being counted.
The record also reports a risk ratio of 1.152. A risk ratio compares the probability of the event in one group with the probability in another, rather than expressing the contrast as an absolute difference. These measures present the same binary outcome on different scales. Neither measure, by itself, explains why the outcome differed or establishes a treatment effect on insomnia or alcohol use.
What does the confidence interval add?
A confidence interval represents the uncertainty around an estimate under a statistical method and its assumptions. For the reported risk difference, the interval runs from 0.024 to 0.239. For the risk ratio, the interval runs from 1.017 to 1.303. The interval is not a guarantee that the true value lies within its endpoints. Its width reflects precision: narrower intervals indicate more precise estimates than wider intervals, all else being equal. The interval should be read alongside the estimate and the limitations of the design and reporting.
How should the p-value be understood?
The unadjusted p-value is 0.031. In general, a p-value measures how compatible the observed data are with a specified null model, given the model assumptions. It is not the probability that the null model is true, and it does not express the size or practical importance of a difference. The registry record does not report a multiplicity adjustment for this p-value or describe a full analysis plan, so the result should be interpreted as the unadjusted comparison posted for the primary endpoint.
What information about the analysis is missing?
The record does not report whether the comparison was adjusted for any baseline variables, which analysis population was used, or how missing endpoint data were handled. It does not report the detailed statistical test or method used to produce the confidence intervals. Those details are not reported in the registry record; the posted estimates should not be used to infer the undisclosed methods.
The record lists a planning illustration based on the observed effect, with a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. The illustrated effect to detect is described as a stated fraction of the observed effect. Such calculations are planning illustrations, not observed power and not evidence about the probability that this completed trial detected a true effect. The registry record does not report the trial’s own sample-size justification, so the planning illustration should not be mistaken for the original design rationale.
General statistical methods also depend on assumptions about the outcome, allocation, and data structure. For a binary outcome, the event definition and treatment of participants with missing status matter. The record gives a completion definition and arm counts, but it does not report a missing-data method or a sensitivity analysis. The record also does not describe interim analyses. These absent details matter when judging how robustly the posted estimate represents the randomized comparison.
10. Confidence Intervals and Precision
The risk-difference estimate for retention is 0.132, with a confidence interval from 0.024 to 0.239. The risk-ratio estimate is 1.152, with a confidence interval from 1.017 to 1.303. The unadjusted p-value is 0.031. These figures describe the estimated contrast and its statistical uncertainty for the posted primary endpoint.
A confidence interval is useful because a point estimate alone can appear more definitive than the data warrant. The endpoints show a range of values compatible with the data under the method’s assumptions, rather than a set of values known to contain the true effect. A confidence interval also does not account automatically for every source of uncertainty, including missing outcomes, outcome selection, or limits in the trial record’s reporting.
The interval for the risk difference is entirely above zero, and the interval for the risk ratio is entirely above one. In general, zero is the no-difference value for a risk difference, while one is the no-difference value for a risk ratio. This is consistent with the reported direction of higher retention in Sleep Hygiene. The intervals nevertheless allow a range of contrast sizes, and their bounds should not be interpreted as clinically important thresholds. The registry record does not define such a threshold.
Precision depends in part on the amount of information in the data and on the variability of the outcome. With a binary endpoint, the number of participants and the number of events contribute to that information. The record gives arm sizes and completion counts, but does not report a prospective sample-size justification or a target precision. The available interval concerns retention only; precision for insomnia and alcohol-use outcomes cannot be assessed from the posted primary result. No results for the listed secondary outcomes are reported in the registry record.
11. Multiplicity, Missing Data and Analysis Populations
The registry record lists 14 outcome measures and identifies six secondary outcomes: delay discounting, negative affect, emotion regulation, alcohol craving, percentage of days using alcohol to help with sleep, and percentage of days using sleep medication. It does not report results for those secondary outcomes. Although the retention comparison has an unadjusted p-value of 0.031, a multiplicity procedure or adjusted p-value is not reported in the registry record.
In general, evaluating multiple outcomes or multiple comparisons can increase the chance of obtaining at least one apparently notable result by chance. Statistical plans may address this through prespecified outcome hierarchies or adjustment methods, but the registry record does not report whether such procedures were planned or used. The count of listed outcome measures does not establish how many analyses were conducted. The record reports zero analyses, and the details of any analysis conducted outside the posted registry information are not reported in the registry record.
Missing-data handling is also important. The primary outcome is defined as completion of all treatment sessions, but the record does not explain whether completion status was available for every randomized participant, how an unknown status was classified, or whether any sensitivity analyses were performed. It does not describe the analysis population, such as whether all randomized participants were included in the comparison. Those details are not reported in the registry record.
These gaps do not change the posted counts or estimates, but they limit assessment of how the analysis addressed missing information and multiple outcomes. The primary comparison is therefore best read as the registry’s unadjusted retention result, with no assumption about unreported analysis choices. The listed secondary outcomes cannot be used to draw conclusions about insomnia improvement, alcohol use, or the proposed mechanism without posted results and their analysis details.
12. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| CBT-I | 0 | 38 | 0.0% |
| Sleep Hygiene | 0 | 33 | 0.0% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| CBT-I | 0 of 38 |
| Sleep Hygiene | 0 of 33 |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 1% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| CBT-I | 1 of 38 |
| Sleep Hygiene | 0 of 33 |
Most frequent non-serious adverse event terms
| Event term | Organ system | CBT-I | Sleep Hygiene |
|---|---|---|---|
| Unanticipated Problem Involving Risk | Psychiatric disorders | 1 of 38 | 0 of 33 |
The registry record lists serious adverse events for 38 participants at risk in CBT-I and 33 at risk in Sleep Hygiene. It reports zero affected by serious adverse events in each arm. No top serious adverse event terms are listed. The record also reports zero deaths in both arms.
For other adverse events, 1 participant is listed as affected among 38 at risk in CBT-I, and 0 are listed as affected among 33 at risk in Sleep Hygiene. These are the registry’s posted counts. The record does not provide event descriptions for the other adverse event, severity, timing, or an assessment of whether it was related to an intervention.
Zero recorded serious adverse events does not establish that no events could occur, nor does it establish that the arms have identical safety profiles. The counts describe what is reported for the trial and should be read in light of the number of participants at risk and the registry’s reporting. Further detail about event definitions, ascertainment, and attribution is not reported in the registry record. These figures are descriptive and do not, on their own, establish a causal safety comparison.
13. What the Result Does, and Does Not, Mean
The primary result concerns retention: the number of participants who completed all treatment sessions by week 6. The registry reports 33 completers in each arm, with 38 participants in CBT-I and 33 in Sleep Hygiene. The estimated risk difference is 0.132 in the direction of higher retention in Sleep Hygiene, and the reported confidence interval is 0.024 to 0.239. This is evidence about completion in the two trial arms as described.
It does not establish that the handout improved insomnia, reduced harmful alcohol use, or changed any other clinical outcome. The study’s stated aim concerns improvement of insomnia as a mechanism for improvement in alcohol use outcomes, but the posted primary endpoint is retention. The registry record lists alcohol-related secondary outcomes but does not report their results. The proposed mechanism therefore cannot be assessed from the primary retention comparison.
The result also does not establish why some participants did not complete all CBT-I sessions or whether the retention pattern was caused by the intervention rather than other factors. Reasons for non-completion, baseline characteristics, analysis population, and missing-data handling are not reported in the registry record. These limits make it difficult to identify what drove the observed difference or how it might relate to participant characteristics and treatment experience.
General statistical interpretation requires separating an estimate from its uncertainty and from its practical meaning. The confidence interval describes uncertainty under the analysis assumptions; it is not a guarantee about the effect in every setting. The unadjusted p-value is not a measure of clinical importance. The record does not define a meaningful retention threshold or provide a basis for judging the effect on outcomes beyond completion.
Finally, this was a comparison of a six-week individual CBT-I course with a single sleep hygiene handout, not a comparison of every form of insomnia care. Any interpretation should stay within the reported endpoint and these trial arms. The record’s completed status does not supply missing clinical outcome results or resolve the limits in the available analysis details.
14. Why This Trial Matters Statistically
Retention is statistically and operationally informative because a treatment’s intended course can only be delivered to participants who remain engaged. Counting completion gives a direct description of whether participants completed all sessions. In this trial, the endpoint is especially distinct from the broader stated interest in insomnia and alcohol outcomes: it reports engagement with treatment, not change in symptoms or behavior.
The comparison also illustrates why estimates should be accompanied by uncertainty measures. The reported risk difference and risk ratio provide two ways to express the retention contrast, while their confidence intervals show that the estimate is not exact. The unadjusted p-value adds a measure of compatibility with a no-difference model under the method’s assumptions, but does not establish clinical importance or explain the reasons behind completion patterns.
It is also useful to distinguish a primary outcome from a study’s wider scientific aim. The record lists secondary outcomes relevant to alcohol use, sleep-related behavior, and psychological constructs, but does not report their results. A retention result cannot stand in for those measures. The gap between a mechanism-focused aim and the posted primary endpoint is important when deciding which conclusions are supported by the registry record.
More broadly, the trial record shows how reporting detail affects statistical interpretation. The randomized, double-masked, parallel design and arm counts are described, but the identity of masked parties, analysis population, missing-data approach, and multiplicity plan are not. Recognizing those unknowns helps readers avoid treating a single posted comparison as a complete account of every design and analysis decision.
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 primary result is limited to retention at post-treatment (week 6). The registry record does not report results for the listed secondary outcomes, including alcohol craving, percentage of days using alcohol to help with sleep, and percentage of days using sleep medication. Consequently, the primary result cannot establish whether insomnia or alcohol outcomes changed or whether insomnia improvement was a mechanism for any alcohol-related change.
Important population details are not reported in the registry record. The titles frame the study around returning veterans, and the conditions include insomnia and harmful alcohol use, but detailed eligibility criteria and participant characteristics are absent. The applicability of the result to more specifically defined groups therefore cannot be assessed from the record.
The record does not report why participants did not complete all sessions, the analysis population, or how missing outcome data were handled. It also does not identify the masked parties or provide details of the randomization process. These omissions limit assessment of potential bias and of how closely the posted counts represent the randomized comparison.
The intervention contrast is specific: individual CBT-I once a week for six weeks versus a sleep hygiene handout delivered once. The posted result should not be generalized to other treatment schedules or forms of sleep hygiene without additional evidence. The registry record does not report the trial’s sample-size justification, a detailed statistical analysis plan, interim analyses, or a multiplicity procedure. Those missing details constrain interpretation of the precision and the status of the unadjusted comparison.
16. Related Tutorials
17. Related Statistical Calculators
18. Sources
- ClinicalTrials.gov: The Insomnia Treatment and Problems Study for Veterans — NCT03804788.
- Registry record last updated 2026-09-11; status last verified 2026-09.
- Results first posted 2025-01-15.
- 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.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
19. Record Summary
NCT03804788 is a completed randomized, double-masked, parallel-arm trial sponsored by University of Missouri-Columbia. The record lists enrollment of 71, a start date of 2019-04-04, and primary completion on 2023-09-30. The arms were individual CBT-I once a week for six weeks and a single sleep hygiene handout.
The primary endpoint was retention, defined as completing all treatment sessions at post-treatment (week 6). The posted counts were 33 of 38 for CBT-I and 33 of 33 for Sleep Hygiene. The reported risk difference for Sleep Hygiene relative to CBT-I was 0.132, with a confidence interval from 0.024 to 0.239; the unadjusted p-value was 0.031.
The registry record lists six secondary outcomes but reports no results for them. Details of missing-data handling, analysis populations, multiplicity procedures, and the sample-size justification are not reported in the registry record. The primary result therefore describes retention, not insomnia or alcohol-use outcomes.