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 Digital Interventions to Treat Hazardous Drinking (NCT04890652), a na na study. The primary outcome is Change in Alcohol Use (Quantity).
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT04890652 |
| Phase | NA |
| Condition | Hazardous Drinking, Stress |
| Allocation | Not applicable (single group) |
| Design model | Single Group |
| Masking | None (open label) |
| Enrollment | 33 |
| Arms in the primary outcome | n/a |
| Lead sponsor | Yale University |
| Results posted | Yes |
2. Clinical Question
Population
The study concerns risky social drinkers with hazardous drinking and stress. Its stated aim also includes examining whether stress, including COVID-19-related stress, is associated with alcohol-misuse risk and intervention outcomes. The registry record reports enrollment of 33 participants, but does not provide further eligibility details or a fuller description of the analyzed population.
Intervention
All participants were assigned to the same behavioral digital intervention program lasting four weeks. The registry record describes the study as a feasibility study intended to assess the intervention's preliminary efficacy in reducing stress and alcohol use. It does not report further details about the intervention's content or delivery.
Comparator
There is no separate control group in this single-group study. Because all participants received the same program, the study does not provide a randomized, like-for-like comparison between the intervention and another treatment, usual care, or no intervention. Changes over time therefore cannot be attributed to the intervention by comparison with a concurrent control group.
Primary question
The primary outcome is change in the average number of alcoholic drinks consumed per week, measured at baseline, immediately after the intervention, and at follow-up 30 days later. The registry record identifies the Timeline Follow Back as the measure. However, it does not report numerical outcome values or an analysis of change, so the amount and precision of any observed change cannot be established from the record.
3. Trial Design
This is a completed, single-group behavioral study sponsored by Yale University. The registry lists enrollment of 33 participants and describes the intervention group as risky drinkers, with all participants receiving the same four-week digital program. The allocation field is listed as NA and masking as none. The record does not describe a randomized assignment or a separate comparison group, so the design is not suited to a direct estimate of how outcomes would have differed under another treatment or no intervention.
The study's stated purpose is feasibility and preliminary evaluation of an intervention intended to reduce stress and alcohol use. It also aims to examine the relationship of stress, including COVID-19-related stress, to alcohol-misuse risk and intervention outcomes in risky social drinkers. These aims describe what the study set out to examine; they do not establish that the registry reports findings for each aim.
The listed primary outcome is change in alcohol-use quantity, expressed as drinks per week and measured at baseline, immediately post-intervention, and 30-day follow-up. The registry identifies two outcome measures and two analyses, but does not report the analysis methods, outcome estimates, or the results for the other outcome measure. The protocol, detailed eligibility criteria, and statistical analysis plan are not reported in the registry record.
The registry lists the study as completed, with a start date of 2021-10-13 and primary completion date of 2023-08-23. Completion status alone does not indicate whether the intended analyses were conducted or whether results were submitted. Numerical results for the primary outcome 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: Out of the 33 enrolled participants, six participants did not start the study due to scheduling difficulties (N=2), no shows (N=3), and obtaining a new job (N=1).
Overall Study
| Stage | Digital Intervention (4-week) |
|---|---|
| STARTED | 27 |
| COMPLETED | 25 |
| NOT COMPLETED | 2 |
Reasons for not completing this period:
| Reason | Digital Intervention (4-week) |
|---|---|
| Withdrawal by Subject | 2 |
Analysis population for the primary outcome, as defined in the registry: Two participants (N=2) discontinued participation in the study following the baseline assessment; One participant withdrew during the second week of the intervention due to scheduling difficulties from a personal busy schedule, and the other participant withdrew in week 4 of the intervention due to non-compliance issues (e.g., repeated instances of not showing up).
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 | Digital Intervention (4-week) |
|---|---|---|
| Participants analysed | 27 | |
| Age, Continuous | years | 34.9 (SD 8.4) |
| Sex: Female, Male: Female | Participants | 20 |
| Sex: Female, Male: Male | Participants | 7 |
| Ethnicity (NIH/OMB): Hispanic or Latino | Participants | 5 |
| Ethnicity (NIH/OMB): Not Hispanic or Latino | Participants | 22 |
| Ethnicity (NIH/OMB): Unknown or Not Reported | Participants | 0 |
| Race (NIH/OMB): American Indian or Alaska Native | Participants | 0 |
| Race (NIH/OMB): Asian | Participants | 4 |
| Race (NIH/OMB): Native Hawaiian or Other Pacific Islander | Participants | 0 |
| Race (NIH/OMB): Black or African American | Participants | 3 |
| Race (NIH/OMB): White | Participants | 17 |
| Race (NIH/OMB): More than one race | Participants | 2 |
| Race (NIH/OMB): Unknown or Not Reported | Participants | 1 |
| Region of Enrollment: United States | participants | 27 |
6. Primary Endpoint
The registry lists the primary outcome as Change in Alcohol Use (Quantity), measured over baseline, immediately post-intervention, and follow-up (30 days).
| Element | Registry entry |
|---|---|
| Result type | Mean |
| Measure of spread | Standard Deviation |
| Unit | drinks per week |
| Endpoint classification | Continuous Endpoint |
The primary endpoint is the average number of alcoholic beverages consumed per week, measured with the Timeline Follow Back. The record describes measurement at baseline, immediately after the four-week intervention, and at follow-up 30 days later. It specifies a mean and standard deviation as the summary approach and gives drinks per week as the unit.
A measure of weekly drinking quantity can describe change in reported alcohol consumption over time. Repeated measurement allows the study to observe whether participants' reported drinking differs after the intervention from their baseline reports, and whether a difference is still present at follow-up. These are general uses of repeated continuous outcomes; they do not establish what happened in this study.
The registry record does not report the mean or standard deviation at any assessment, the number of participants contributing data at each time point, or a numerical estimate of change. It also does not report a confidence interval or a test result for the endpoint. Accordingly, the endpoint definition is available, but its observed trajectory and statistical precision cannot be described from the registry record. Self-reported measurement and the absence of a concurrent comparison group are important when interpreting any change that may be reported elsewhere.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The registry record defines a primary measure of alcohol-use quantity, but does not report the numerical results for that outcome. There is no posted mean or standard deviation at baseline, immediately post-intervention, or 30-day follow-up, and no reported estimate of change between assessments. A direction, magnitude, or precision of change therefore cannot be inferred from the endpoint description alone.
The study's design also shapes what an observed change could mean. Since all participants received the same four-week program and there was no separate control group, a before-and-after pattern would describe change among participants over time. It would not, by itself, separate a possible intervention effect from other explanations such as natural variation, changes in circumstances, repeated measurement, or selective follow-up. These are general considerations for single-group studies, not claims that any particular explanation occurred in this study.
The stated study aims include feasibility, preliminary efficacy, and examining stress in relation to alcohol-misuse risk and intervention outcomes. The record does not provide numerical findings for feasibility, stress, or the additional outcome measure. It also does not report estimates for any association between stress and drinking outcomes. The aims should therefore not be read as results.
The record describes two participants (N=2) discontinuing after baseline. One participant withdrew during the second week because of scheduling difficulties from a personal busy schedule; another withdrew in week 4. The explanation for the latter withdrawal is incomplete in the registry record. The record does not say how missing outcome observations were handled or how many participants contributed data to each assessment. This matters because the people with observed follow-up data may not fully represent everyone enrolled.
No confidence interval, hypothesis test, or model estimate for the primary endpoint is reported in the registry record. Without an estimate and its uncertainty, readers cannot judge whether a change was small or large, or how precisely it was measured. The absence of reported numerical results is not evidence that there was no change; it means the change cannot be evaluated from this registry record.
9. Statistical Methods Explained
Statistical methods are useful for describing the size and uncertainty of an observed pattern, but the registry record does not report the analysis used for the primary endpoint. It identifies the endpoint as a continuous measure summarized by a mean and standard deviation, and lists two analyses overall. It does not specify the model, comparison of time points, covariate adjustment, confidence intervals, or hypothesis tests. The methods below explain general concepts relevant to this kind of outcome; they should not be taken as a description of analyses actually performed in this study.
What does a mean describe?
For a continuous measure such as drinks per week, the mean is an average across the observations included in an analysis. A mean can offer a concise description of reported drinking quantity at a particular assessment. It does not show the full spread of individual responses, and it can be affected by unusually high or low observations. The registry's endpoint description names the mean as the parameter, but gives no mean values for any assessment.
The standard deviation describes how dispersed individual observations are around the mean. A larger standard deviation indicates more variability among the measured values, while a smaller one indicates that values are more closely clustered. It is not the same as the uncertainty in the estimated mean. The registry record identifies standard deviation as the measure of dispersion but does not report its values.
What would a change estimate mean?
A change estimate would summarize how the outcome differs between two assessments, or how it changes across the listed assessments. Since the same participants may be measured more than once, an analysis can account for the relationship between repeated observations on a participant. Different approaches make different assumptions about the pattern of change and the use of incomplete observations. The record does not say which approach was used, so it is not possible to determine how the reported analyses, if any, treated repeated measures.
In general, a confidence interval gives a range of values compatible with the data and the assumptions of the analysis. It conveys precision as well as the estimated direction and size of an effect. A narrow interval indicates greater precision than a wide interval, but neither guarantees that an estimate is free from bias. No confidence interval for the primary alcohol-use outcome is reported in the registry record.
A hypothesis test can assess how compatible data are with a specified null hypothesis under a statistical model. A p-value is not the probability that the null hypothesis is true, nor does it measure the practical importance of an observed difference. Interpretation should consider the estimate and its uncertainty, rather than treating a threshold as a complete account of the result. The registry record does not report a p-value or identify a testing procedure for the primary endpoint.
Why does the design matter?
In a randomized comparison, allocation can support a comparison between groups, subject to the trial's conduct and analysis. This study is listed as single-group, with no like-for-like control arm. A comparison of post-intervention measurements with baseline can describe within-participant change, but it does not supply the counterfactual outcome: what would have happened to those same participants over the same period without the intervention. This limitation applies regardless of the statistical technique used to summarize change.
The intervention is behavioral and the principal endpoint is based on the Timeline Follow Back. Repeated self-reported measures can be useful for tracking an outcome, but answers may be affected by recall and reporting. These are general measurement considerations; the registry record does not quantify their effect in this study.
How should planning calculations be read?
A sample-size calculation is a planning exercise based on assumptions about the effect to detect, outcome variability, significance level, allocation, and analysis. It is not an observed result and does not show that a study had a particular probability of finding a result after it was completed. The record describes a planning illustration based on a fraction of an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. Such an illustration is not the study's own design justification. In particular, a hypothetical two-arm planning setup does not turn this single-group study into a randomized comparison. No protocol sample-size justification is reported in the registry record.
Over-dispersion is a general concern when observed variability is greater than a statistical model assumes. If a model understates variability, its standard errors may be too small and its intervals or tests may appear more precise than warranted. Whether over-dispersion is relevant depends on the outcome and model; the record does not describe a model or report a diagnostic assessment, so no study-specific conclusion can be drawn.
10. Multiplicity, Missing Data and Analysis Populations
The registry lists two outcome measures and two analyses, but does not report their full definitions, statistical hypotheses, or analysis procedures. It does not say whether one outcome was designated as primary for inference, how the two analyses relate to the outcomes, or whether any adjustment for multiple testing was planned or used. The multiplicity approach is not reported in the registry record.
Multiplicity is a general concern when several outcomes, time points, or statistical comparisons are examined. As the number of opportunities to find a result increases, the chance of at least one apparently notable finding can also increase under some testing strategies. Adjustment methods can address particular testing goals, but their choice depends on the prespecified questions and analysis plan. The available record does not support a conclusion about whether multiplicity affected the reported analyses.
The endpoint is scheduled for baseline, immediately post-intervention, and 30-day follow-up. The record describes two participants (N=2) discontinuing after baseline. One withdrew during week 2 because of scheduling difficulties from a personal busy schedule, and the other withdrew in week 4; the reason for the latter withdrawal is not fully stated. The record does not give the number assessed at each time point, explain whether discontinuing participants provided any later measures, or describe how missing data were handled.
Analysis populations are also not reported in the registry record. It is not stated whether analyses included all enrolled participants, only participants with available measurements, or another defined group. Without that information, together with the outcome counts at each assessment, readers cannot assess the extent of missingness or the population represented by any estimate. No imputation method or sensitivity analysis for missing data is reported.
11. 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 |
|---|---|---|---|
| Digital Intervention | 0 | 27 | 0.0% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| Digital Intervention | 0 of 27 |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 0% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Digital Intervention | 3 of 27 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Digital Intervention |
|---|---|---|
| General disorders and administration site conditions - Other, specify | Infections and infestations | 1 of 27 |
| General disorders and administration site conditions - Other, specify | General disorders | 1 of 27 |
| General disorders and administration site conditions - Other, specify | Nervous system disorders | 1 of 27 |
The registry reports one group titled Digital Intervention. Among the 27 participants listed as at risk for serious adverse events, 0 were reported as affected by a serious adverse event. The record lists no serious adverse-event terms. It also reports 3 participants with other adverse events among 27 at risk, and 0 deaths.
These figures describe what is recorded for the listed group and the registry's stated at-risk counts. They do not establish that no unrecorded events occurred, and they do not describe comparative safety against another group. Because this was a single-group study, there is no separate control-group rate in the record for comparison. The registry does not provide details about the three other adverse events in the registry record for this summary.
Serious adverse events are distinct from other adverse events; the counts should not be combined or interpreted as measures of the same category. The record does not report event timing, severity details for the other events, or an assessment of whether events were related to the intervention. These safety figures are descriptive and should be read within those limits.
12. What the Result Does, and Does Not, Mean
The record establishes that a four-week digital intervention was studied in a single group of risky drinkers, with alcohol-use quantity designated as the primary outcome. It also describes the intended focus on stress and feasibility. These details explain the study question and its design, but the registry record does not report the numerical primary outcome results needed to judge the observed change in weekly drinking.
Even if a within-participant change were reported, this design would not establish how much of that change was caused by the intervention. Without a concurrent control group, there is no direct comparison that separates the intervention from other influences over time. This is a general limitation of single-group before-and-after evidence, rather than a judgment about the actual pattern in this study.
The record's enrollment count is 33, and it describes two participants (N=2) discontinuing after baseline. It does not report endpoint values, numbers analyzed at each time point, confidence intervals, or a statistical test for the primary outcome. Therefore, neither the size of any change nor its precision can be assessed from the registry record. The stated aims regarding stress and the second outcome measure likewise should not be interpreted as findings without reported results.
The safety record reports 0 serious adverse events among 27 at risk and 0 deaths, as well as 3 other adverse events among 27 at risk. These are descriptive registry figures and do not provide a comparative safety assessment or details about the other events.
Overall, the registry record supports a description of the study's intent, design, endpoint, and recorded safety counts. It does not support a conclusion about whether alcohol use or stress changed, how large any change may have been, or whether any change was attributable to the intervention.
13. Why This Trial Matters Statistically
This study raises a question that is statistically important in behavioral research: how to evaluate change in a continuous, self-reported outcome measured repeatedly in a small feasibility study. The endpoint is defined as average drinks per week at baseline, immediately after the intervention, and 30-day follow-up. Those time points could describe both immediate and later patterns, but the registry record does not report the measurements or their uncertainty.
The single-group design is central to interpretation. Repeated measurements can reveal how participants' reported outcomes vary over time, yet without a separate control group they cannot distinguish intervention-associated change from other time-related influences. Statistical modeling can describe a pattern more carefully, but no model can create the missing randomized comparison.
Missing follow-up information is another important issue. The record describes two discontinuations after baseline but does not report the number contributing data at each assessment or the method used to handle missing values. This prevents readers from judging whether reported estimates, if available elsewhere, represent everyone enrolled or a subset with observed data. In small studies, each participant's available observations can be particularly consequential, though the registry record does not quantify that impact.
The stated feasibility purpose also matters: feasibility questions differ from definitive comparative-effectiveness questions. A feasibility study may inform whether an intervention and its assessments can be implemented, while an efficacy claim requires appropriate outcome evidence and a design that supports the relevant comparison. The registry states an aim of preliminary efficacy, but does not report numerical findings with which to evaluate it.
For statistical readers, the main lesson is to keep design, endpoint, missingness, and precision in view together. Here, the registry gives a defined outcome and a study structure, but not the outcome estimates or analysis details needed to assess change. Recognizing that boundary is essential to avoid treating aims or design descriptions as evidence of results.
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 registry record does not report numerical results for the primary endpoint. It gives no mean or standard deviation at baseline, immediately post-intervention, or 30-day follow-up, and no estimate of change, confidence interval, or test result. Thus, the primary outcome cannot be quantitatively interpreted from this record.
The study is single-group, and all participants received the same four-week intervention. There is no separate control group for a like-for-like comparison. Any observed change over time would therefore be difficult to distinguish from other influences, including changes in circumstances or natural variation. This design limitation remains even if a within-participant statistical analysis is performed.
The record describes two participants (N=2) discontinuing after baseline. One withdrew during the second week because of scheduling difficulties from a personal busy schedule; the other withdrew in week 4, and the reason is incomplete in the registry record. The number of participants with endpoint data at each assessment, the analysis population, and the missing-data approach are not reported.
The record identifies the Timeline Follow Back for alcohol quantity but does not provide details of the assessment procedures or any validation information. Alcohol-use quantity is reported by participants, so recall and reporting are general considerations. The registry also states aims concerning stress and COVID-19-related stress, but does not report the corresponding measures or numerical findings in the registry record for this summary.
Finally, the protocol, sample-size justification, statistical analysis plan, and multiplicity approach are not reported in the registry record. The planning illustration described in the record is not the study's design justification and uses a hypothetical two-arm setup, unlike the single-group study. These omissions limit assessment of the analysis plan and the certainty of any study conclusions.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: Digital Interventions to Treat Hazardous Drinking — NCT04890652.
- Registry record last updated 2024-09-19; status last verified 2024-08.
- Results first posted 2024-09-19.
- 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.
18. Record Summary
NCT04890652 is a completed, single-group behavioral study sponsored by Yale University, with enrollment of 33 participants. All participants were described as risky drinkers and received the same four-week digital intervention. The study aimed to assess feasibility and preliminary efficacy for reducing stress and alcohol use, and to examine stress in relation to alcohol-misuse risk and intervention outcomes.
The primary endpoint is mean drinks per week measured by the Timeline Follow Back at baseline, immediately post-intervention, and 30-day follow-up. The registry record does not report numerical results for this endpoint, analysis details, or results for the other outcome measure. It describes two participants (N=2) discontinuing after baseline.
Safety records list 0 serious adverse events among 27 at risk, 3 other adverse events among 27 at risk, and 0 deaths. As a single-group study without a like-for-like control, it cannot provide a randomized comparison of outcomes. The registry record therefore describes the study design and aims, but does not permit assessment of the magnitude or precision of primary outcome change.