The RESTING Insomnia Study: Randomized Controlled Study on Effectiveness of Stepped-Care Sleep Therapy: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for The RESTING Insomnia Study: Randomized Controlled Study on Effectiveness of Stepped-Care Sleep Therapy (NCT03532282), a randomized na study. The primary outcome is Insomnia Severity Index (ISI).

2. Clinical Question

The RESTING Insomnia Study asks whether two primary-care-friendly ways of delivering cognitive behavioral therapy for insomnia differ in their effects on insomnia severity among middle-aged and older adults. One approach delivers therapy online only. The other offers online therapy, therapist-led therapy, or a sequence of both. The primary measure is the Insomnia Severity Index (ISI), assessed at baseline and at months 2, 4, 6, 9, and 12.

3. Trial Design

The RESTING Insomnia Study is a randomized, double-masked, parallel-group controlled study. The registry lists an enrollment of 388. It identifies Stanford University as the sponsor and the study status as completed. The listed study start date is 2019-02-01, and the primary completion date is 2023-01-12.

The trial compares two behavioral interventions. In the online-only group, cognitive behavioral therapy for insomnia is delivered online. In the stepped-care group, therapy may be delivered online, led by a therapist, or delivered sequentially using both. The registry record does not give further detail about how participants were assigned to particular forms of stepped care or the rules used to move between them.

Random allocation is intended to support a fair comparison by reducing systematic differences between groups at the start of a trial. A parallel design means participants are assigned to a group and the groups are compared over the study period. The registry describes masking as double, but the specific people who were masked and how masking was maintained are not reported in the registry record.

The listed primary outcome is the Insomnia Severity Index, measured at baseline and at months 2, 4, 6, 9, and 12. The primary outcome population is described as the intent-to-treat sample, with values drawn from participants who have data at the relevant time point. The registry also lists PROMIS Sleep Related Impairment and PHQ-4 as secondary outcomes. It reports four outcome measures and four analyses, but further detail about the analysis procedures is 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: 388 participants signed consent. 254 were eligible and 245 were randomized to a study arm

Overall Study

Analysis population for the primary outcome, as defined in the registry: Intent to treat sample; values for participants with available data at the respective time point

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 Insomnia Severity Index (ISI), measured over at baseline and at months 2, 4, 6, 9, & 12.

The primary endpoint is the Insomnia Severity Index (ISI), a patient-reported measure of insomnia severity. It is a 7-item questionnaire. Each item is rated on a 0 to 4 scale, and the total score is the sum of the item scores. The resulting score ranges between 0 and 28; a higher score corresponds with greater insomnia severity.

The registry describes 10 as a cutoff for identifying people in the community who are likely to meet criteria for insomnia disorder, and 8 as a cutoff for defining remission. These thresholds help give the scale a clinical interpretation, but they do not replace analysis of the score itself. A group mean describes the average score for the participants with available data at a time point; the standard deviation describes how spread out individual scores are around that mean.

Repeated assessments at baseline and at months 2, 4, 6, 9, and 12 can describe the course of reported insomnia severity over time. To assess a treatment-group comparison, readers need the outcome values and the statistical comparison between groups. Those primary outcome results are not reported in the registry record, so the relative pattern of ISI scores cannot be characterized from the information recorded.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies the primary outcome as a continuous measure summarized by its mean and standard deviation. It also provides assumptions for a planning illustration based on an observed effect. The actual outcome estimates, statistical comparison, and analysis model are not reported in the registry record. The general explanations below describe how such methods are interpreted; they do not identify methods used by this trial beyond what the registry states.

What does a mean describe?

For a continuous measure such as the ISI, a mean is the arithmetic average of the scores in a group at a given assessment. It gives a concise description of the group’s central score, but it does not show how much participants differ from one another. Two groups can have similar means while having different distributions of individual scores, or different means while their individual scores overlap substantially. The means and their uncertainty need to be considered together.

What does a standard deviation describe?

A standard deviation describes the spread of scores around a group mean. A smaller standard deviation indicates that scores are more concentrated around that mean; a larger one indicates more variation among participants. It is not the same as the uncertainty in the estimated mean. The standard error and a confidence interval concern the precision of an estimate, whereas the standard deviation describes variability among observed scores. The registry lists standard deviation as the measure of dispersion for the primary outcome, but does not report the ISI standard deviations.

How should repeated measurements be understood?

The ISI is scheduled at baseline and at months 2, 4, 6, 9, and 12. Repeated measurement can describe whether average scores change over time and whether the pattern differs between groups. Measurements from the same participant are related, so they should not be treated as if they came from unrelated people. A longitudinal analysis can account for that relationship, but the model used for this trial is not reported in the registry record. The schedule alone does not show how the investigators analyzed time or whether the primary comparison concerned a particular assessment or an overall pattern.

What does a confidence interval add?

In general, a confidence interval expresses uncertainty around an estimated effect. It gives a range of values compatible with the data and the assumptions of the analysis. A narrower interval indicates greater precision than a wider interval. It does not show the range of individual participant responses, and it does not guarantee that the true effect lies within the interval. No confidence interval for the primary comparison is reported in the registry record, so its precision cannot be assessed.

What do the planning assumptions mean?

The registry describes a planning illustration using a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. It says the effect to detect is a stated fraction of the observed effect. These are assumptions for a planning calculation, not evidence about the trial’s observed effect or its statistical power after completion. The record does not provide the planning estimates themselves, and does not report the sample-size justification used for the trial’s design. The planning assumptions should therefore not be mistaken for the trial’s analysis plan.

More generally, sample-size calculations estimate how much information a future study may need under specified assumptions. Their outputs depend on those assumptions, including the effect targeted and the statistical method. They are not a retrospective measure of whether a completed study “had enough power” to detect its actual result. The registry’s stated planning approach does not establish what effect was observed, because the primary outcome results are not reported.

Why can variability affect an analysis?

When scores vary considerably among participants, a group mean may be estimated less precisely than when scores are more tightly clustered, all else being equal. The standard deviation helps describe that variability. General statistical methods may also need to account for features such as repeated measurements, skewed outcomes, or over-dispersion when those features are present. Over-dispersion means that observed variability is greater than a model expects; ignoring it can make uncertainty estimates too small. The registry record does not state that over-dispersion was present or describe any model adjustment for it.

The central methodological distinction is between what the registry specifies and what a result would require. The outcome definition, time points, analysis-population description, and planning assumptions are recorded. The outcome values, estimated group contrast, uncertainty interval, and detailed model are not reported in the registry record. Without those elements, statistical interpretation must remain limited to the design and measurement information rather than a claim about the comparative effect.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists four outcome measures and four analyses, including the ISI primary outcome and secondary patient-reported measures of sleep-related impairment, anxiety, and depression. It does not describe a multiplicity procedure, such as an adjustment to account for evaluating several outcomes or comparisons. The registry record does not report whether a hierarchy of outcomes was prespecified or how the primary and secondary analyses were distinguished statistically. Without those details, the implications of multiple testing cannot be assessed.

The primary outcome population is described as intent to treat, with values from participants who have data at the respective time point. This indicates that data availability is relevant to the recorded outcome summaries, but does not explain how missing measurements were handled. The method for handling missing data, the amount of missingness at each assessment, and any sensitivity analyses are not reported in the registry record.

Missing data can affect interpretation when the participants with observed measurements differ in relevant ways from those without measurements. General approaches include making explicit assumptions about why data are missing and examining whether conclusions change under plausible alternatives. These are general considerations, not methods attributed to this trial. Without the missing-data details and outcome results, the extent to which missingness could influence the group comparison is unclear.

The registry’s intent-to-treat description should therefore be read together with its available-data qualification. It does not establish that every randomized participant contributed an outcome at every scheduled time point, nor does it specify how the analysis preserved the randomized comparison when measurements were unavailable.

11. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: surgical complications (0.8%), lung cancer (0.8%).

The registry lists serious adverse event figures for the online-only group (ONLN) and the stepped-care group (STEP). For serious adverse events, the number at risk is 121 in ONLN and 124 in STEP, with 1 affected in each group. For other adverse events, the number at risk is 121 in ONLN and 124 in STEP, with 8 affected in ONLN and 9 in STEP. The record lists 1 death in each group.

The registry also lists surgical complications and lung cancer among the top serious terms, each reported as 0.8%. These figures describe what is recorded in the registry; they do not establish that an event was caused by an intervention. The record does not provide further detail about event timing, severity beyond the serious-event classification, adjudication, or causal attribution.

Counts and percentages should be interpreted in the context of the recorded at-risk groups and the registry’s definitions. They do not, by themselves, support a comparative safety conclusion. In particular, the record does not explain how events were collected or whether the groups differed in follow-up completeness. The safety figures are descriptive information, not proof of benefit, harm, or equivalence.

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

The registry record establishes that the RESTING Insomnia Study was a randomized, double-masked, parallel-group comparison of online-only and stepped-care delivery of cognitive behavioral therapy for insomnia. It identifies the ISI as the primary outcome and gives its measurement schedule and scale interpretation. It also records secondary patient-reported outcomes and adverse-event counts.

What the record does not establish is the comparative change in insomnia severity. It contains no ISI means, standard deviations, estimated group difference, confidence interval, or primary outcome test result. Therefore it cannot show whether one group had lower scores, whether any difference was small or large, or how precisely an effect was estimated. The absence of a reported comparison is not evidence that the groups were the same.

The intervention descriptions also matter for interpretation. Online-only is described as online cognitive behavioral therapy for insomnia. Stepped care may involve online therapy, therapist-led therapy, or both in sequence. The record does not describe how participants in the stepped-care group received those options, so it does not support conclusions about the effect of a particular delivery mode.

The secondary outcomes and adverse-event figures offer additional registry information, but without fuller results and methods they do not resolve the primary outcome question. Counts alone do not show causation, and outcome names alone do not establish a difference between groups. The record also does not report the missing-data procedures or the approach to multiple analyses.

Accordingly, the defensible interpretation is limited: the study was designed to compare two ways of delivering insomnia therapy, and the registry identifies the measures used to assess that comparison. Its posted information does not allow a judgment about the comparative primary outcome, the uncertainty around that outcome, or whether any observed effect would be clinically important.

13. Why This Trial Matters Statistically

This trial is statistically interesting because it compares delivery strategies rather than simply contrasting receipt of therapy with no therapy. The online-only group has a single described delivery mode, while the stepped-care group can involve online delivery, therapist-led delivery, or both sequentially. That design raises questions about how an overall group comparison should be interpreted when the intervention includes several possible pathways. The registry record does not report how those pathways were assigned or used.

The outcome schedule also makes the distinction between a single endpoint and a trajectory important. ISI is assessed at baseline and at months 2, 4, 6, 9, and 12. A comparison could focus on a particular assessment or on changes across time, but the analysis approach is not reported in the registry record. Repeated observations from the same participants are related, so the choice of analysis can affect both the estimate and its uncertainty.

Another statistical issue is the difference between a registered measurement plan and a reported result. The record specifies the scale, its score interpretation, and the analysis population description, but not the outcome estimates. This illustrates why trial design information alone cannot answer whether groups differed or how confidently a difference can be estimated.

Finally, the record lists multiple outcomes and analyses while leaving the multiplicity approach unreported. This does not invalidate the study, but it limits interpretation of any isolated finding if results are later considered without knowing which comparisons were primary and how multiple testing was handled. Clear estimates, uncertainty intervals, missing-data methods, and analysis details are needed to interpret a comparative trial fully.

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 of the registry information is that the primary outcome results are not reported. There are no ISI group summaries or comparative estimates from which to assess the direction, size, or precision of an outcome difference. Consequently, the registry record supports description of the design and endpoint but not a conclusion about comparative insomnia severity.

The analysis methods are also incompletely described. Although the record identifies means and standard deviations for the continuous outcome and gives planning assumptions, it does not report the model used for the repeated assessments, the specific primary contrast, or the uncertainty measure used for the outcome comparison. The sample-size justification and planning estimates are not reported in the registry record.

The outcome population description refers to an intent-to-treat sample with data available at each time point. The record does not explain how missing values were handled, how many observations were available at each assessment, or whether sensitivity analyses were conducted. It also does not describe the approach to multiplicity despite listing multiple outcomes and analyses.

The stepped-care intervention is described as potentially online, therapist-led, or sequentially both. The registry does not report how those options were used or how treatment pathways were selected. Thus, even if an overall comparison were available, the registry description alone would not identify the contribution of each delivery mode.

For safety, the record gives affected counts and selected serious-event terms, but does not provide detailed event definitions, timing, follow-up completeness, or causal assessment. These limitations restrict the conclusions that can be drawn from the registry information, without implying that the underlying trial lacked methods or results beyond what is recorded.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: The RESTING Insomnia Study: Randomized Controlled Study on Effectiveness of Stepped-Care Sleep Therapy — NCT03532282.
• Registry record last updated 2024-12-19; status last verified 2024-12.
• Results first posted 2024-12-19.
• 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.

18. Record Summary

The RESTING Insomnia Study is a completed randomized, double-masked, parallel-group trial sponsored by Stanford University. The registry lists enrollment as 388 and describes a comparison of online-only cognitive behavioral therapy for insomnia with stepped care, which may include online therapy, therapist-led therapy, or both sequentially.

The primary outcome is the Insomnia Severity Index, assessed at baseline and at months 2, 4, 6, 9, and 12. Secondary measures include PROMIS Sleep Related Impairment and PHQ-4. The registry lists serious and other adverse-event counts and deaths by group. It does not report the primary outcome estimates, the comparative analysis, detailed missing-data methods, or the statistical approach to multiple outcomes. The record therefore describes the trial question and measures but does not provide enough outcome information to assess the comparative ISI result.