Chamomile for Chronic Primary Insomnia: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Chamomile for Chronic Primary Insomnia (NCT01286324), a randomized phase 2 study. The primary outcome is Change From Baseline of Chamomile Extract on Measures of Sleep at Day 28..

2. Clinical Question

3. Trial Design

The registry describes NCT01286324 as a randomized, parallel-group phase 2 study sponsored by the University of Michigan. The title identifies it as a pilot grant examining the feasibility, efficacy, and tolerability of a standardized chamomile extract in chronic primary insomnia. Enrollment was 34, with 17 participants listed in each arm for the primary outcome. The record gives the study status as completed, a start date of 2008-07, and a primary completion date of 2010-12.

One group received Chamomile High Grade Extract and the other received a placebo tablet containing lactose. The registry records quadruple masking, but does not explain which study roles were masked or how masking was implemented. The parallel model means the record describes separate intervention and control groups rather than a crossover comparison. Allocation is recorded as randomized; the sequence-generation and allocation-concealment procedures are not reported in the registry record.

The primary outcome timeframe was baseline and day 28. The endpoint description emphasizes change from baseline in sleep-diary measures and identifies sleep efficiency as the primary aim. The study also lists daytime-functioning measures, including BDI, STAI, and the Fatigue Severity Scale, as well as safety and tolerability outcomes. The registry does not report detailed eligibility criteria, participant characteristics, treatment adherence, or participant flow after enrollment. It also does not report the original sample-size justification or the assumptions used to plan the trial.

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

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline of Chamomile Extract on Measures of Sleep at Day 28., measured over baseline and day 28.

The primary endpoint concerns sleep efficiency, expressed as a percentage of time asleep. The registry defines it as total sleep time divided by time in bed, multiplied by 100. In practical terms, this measure describes what fraction of the recorded time in bed was spent asleep. A sleep diary was the stated means of assessing the measure, and the primary timeframe was baseline and day 28.

The endpoint is useful for describing sleep continuity in a way that accounts for time spent in bed: it is not simply a measure of total sleep duration. As a general statistical interpretation, a percentage endpoint retains a direct, familiar scale, while the change-from-baseline framing is intended to describe how the measure differs from a participant’s starting value over the study period. The registry’s title for the outcome and description both refer to change from baseline, but the posted arm results give values of 83.3 for placebo and 77.5 for chamomile without listing separate baseline values or a detailed change score. Those figures should therefore be read as the posted arm values, not used to reconstruct unreported baseline or individual-level changes.

The primary endpoint is one aspect of sleep. It does not encompass every sleep experience or the listed daytime-functioning measures. Nor does a group average describe the range of individual responses. The record does not report details such as the number of diary days contributing to each participant’s endpoint or how incomplete diary entries were handled.

7. Results Posted in the Registry

• Chamomile High Grade Extract: mean 77.50 versus 83.30 on control; difference -5.80 (95% CI -12.94 to 1.34), standardized effect d = -0.55; z-test p = 0.111.

8. Statistical Interpretation

9. Statistical Methods Explained

The trial’s registry entry identifies randomized allocation, quadruple masking, and a parallel-group model. Randomization is generally used to reduce systematic differences between groups at the point of allocation, while masking is generally intended to limit the influence of expectations on participants’ reports or study procedures. These are general purposes of the methods; the registry record does not describe how the random sequence was generated, how allocation was concealed, or which people were masked. The record therefore supports naming the design features but not assessing how they were carried out.

What does the group comparison estimate?

The endpoint is a continuous measure, reported as a percentage. The arm summaries give a mean of 83.3 for placebo and 77.5 for chamomile. A mean difference compares those group summaries on the original outcome scale. The recalculated comparison is -5.8, using chamomile minus placebo, so the estimate is expressed in percentage points. This is an unadjusted comparison: it does not incorporate covariate adjustment or any other analysis feature that is not reported in the registry record.

The recalculation also uses the reported group sizes and standard deviations to estimate a pooled standard deviation of 10.62. A pooled standard deviation represents a combined estimate of within-group spread under the assumptions used for this summary-statistic calculation. The record marks the pooled spread as approximate. The standardized difference, d = -0.546, expresses the estimated mean difference relative to that pooled spread. It can help describe the size of a difference on a scale independent of the original units, but it does not remove uncertainty or make the comparison more precise.

What does a t-test and p-value describe?

The registry reports a two-sided t-test and p = 0.21. In general, a two-sided test evaluates departures in either direction from a null comparison of no group difference. A p-value describes how compatible the observed test result is with that null model, under the assumptions of the test. It is not the probability that the null hypothesis is true, and it does not give the probability that a result will repeat in another study.

The recalculated unadjusted p-value is 0.111. It comes from the posted summary statistics and is not the same as the registry’s reported test result. Group summaries can support an approximate reanalysis, but they do not reveal all choices made in an original analysis, such as any adjustment, analysis population, or handling of missing outcome values. Those details are not reported in the registry record. The reported t-test and the recalculation should therefore be distinguished rather than treated as interchangeable outputs.

How should the confidence interval be understood?

The recalculated interval for the mean difference extends from -12.94 to 1.341. As a general explanation, a confidence interval describes a range of estimates compatible with the observed data and the method used to construct the interval. Its width communicates precision: a wider interval indicates less precision about the possible size of the difference. Here, the interval includes zero, so it is compatible with no difference as well as with differences in either direction. The confidence level for the registry’s own analysis is not reported, and the recalculated interval should not be assigned a confidence level that is absent from the record.

The interval is calculated from summary statistics rather than participant-level observations. Its construction relies on the approximate pooled standard deviation and the assumptions of the unadjusted comparison. The registry does not report the distribution of individual outcomes, diagnostic checks, or any model-based adjustments. This limits how fully the calculation can be evaluated. The number of decimal places in the interval does not imply that the estimate is known with that degree of practical certainty.

What do the design and analysis record leave unresolved?

Although the entry lists 34 participants enrolled and 17 per arm for the primary outcome, it does not give a participant-flow account or state whether every enrolled participant contributed to the posted endpoint. The analysis population is not reported in the registry record. The handling of missing diaries, withdrawals, protocol deviations, or adherence is also not reported. No original sample-size justification, interim-analysis plan, or detailed statistical analysis plan is reported. These omissions matter because they prevent readers from determining whether the posted summary includes all randomized participants and how the analysis decisions were selected.

Several daytime-functioning outcomes and safety and tolerability outcomes are listed, alongside the primary sleep outcome. General statistical practice recognizes that testing multiple outcomes can raise the chance of finding an apparently notable result by chance if no multiplicity strategy is used. The registry record does not report a multiplicity adjustment or a prespecified hierarchy across outcomes. It is therefore not possible to determine from this entry whether or how the reported analyses accounted for multiple comparisons.

These methodological points do not invalidate the posted values; they define the limits of interpretation. The numerical comparison describes the reported group summaries, while the strength of conclusions about the broader study depends on details that are not reported in the registry record.

10. Confidence Intervals and Precision

The recalculated mean difference is -5.8 percentage points, with a confidence interval from -12.94 to 1.341. This interval is wide enough to include zero and estimates on either side of zero. It therefore does not pin down the direction of the group difference with high precision. The interval also indicates that the point estimate alone should not be read as a definitive description of the range of plausible differences.

In general, a confidence interval combines an estimate with information about its uncertainty. A narrower interval indicates greater precision under the assumptions of the calculation; a wider interval indicates less precision. The interval reported for this recalculation is based on the posted arm summaries, with 17 participants per arm and an approximate pooled standard deviation of 10.62. No confidence interval for the sponsor’s reported analysis is included in the registry record, and the confidence level for the recalculated interval is not stated in the record.

Precision is distinct from statistical significance and from clinical importance. A p-value does not replace the interval’s information about possible effect sizes, and an interval’s inclusion of zero does not show that all meaningful effects are absent. The registry does not specify a threshold for a meaningful change in sleep efficiency, so the practical importance of the values cannot be evaluated against a stated clinical benchmark. The relatively small group summaries also mean that the observed estimate should be interpreted with caution; the available information does not support treating it as a precise estimate for a wider population.

11. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are participants per arm, not total events. They are illustrations based on the observed effect, not the trial’s original design calculations. The listed assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to detect is specified as a fraction of the observed effect. The trial’s own sample-size assumptions and justification are not reported in the registry record.

For 80% power, the planning calculation gives the number of participants per arm that would yield an 80% chance of detecting the selected effect under the stated assumptions, if that effect and those assumptions were correct. The 90% power column uses a higher target chance of detecting that effect and consequently calls for more participants per arm. These are prospective planning quantities: they do not describe the chance that this completed trial detected an effect, and they are not observed power.

The illustrations show the expected relationship between effect size and sample size. Planning for 100% of the observed effect gives 53 participants per arm for 80% power and 71 for 90% power. Planning for 75% of the observed effect gives 94 and 126 participants per arm, respectively. Planning for 50% of the observed effect gives 211 and 282 participants per arm. Smaller effects require more participants because they are harder to distinguish from the variability in the outcome, all else being equal.

These figures should not be interpreted as a recommendation or as evidence that the original trial was designed around these assumptions. They are illustrations tied to the observed estimate, which is uncertain. If the true effect differed from the observed effect, or if the assumptions differed, the planning results would differ as well.

12. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -5.800; pooled standard deviation σ = 10.623.
2. n = 2 × (1.96 + 0.842)² × 10.623² / -5.800² = 52.7, rounded up to 53 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -5.8                      # observed difference in means
sigma <- 10.6230880632705                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(1286324)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 53 (80% power), 71 (90% power)
 75% of observed effect: n per arm = 94 (80% power), 126 (90% power)
 50% of observed effect: n per arm = 211 (80% power), 282 (90% power)
power.t.test: 53.6 
Simulated power at n = 53 per arm: 0.793 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

13. Analyses Reported by the Sponsor

The registry reports the trial’s own primary comparison as a two-sided t-test with p = 0.21. It does not provide the corresponding sponsor-analysis estimate, confidence interval, analysis population, or detailed calculation procedure in the information available for this comparison. The registry result should be kept distinct from the unadjusted recalculation based on the posted group summaries.

The recalculation gives a mean difference of -5.8 percentage points, a confidence interval from -12.94 to 1.341, and an unadjusted p-value of 0.111. It uses the arm means, standard deviations, and group sizes, with an approximate pooled standard deviation. Such a calculation is useful for describing the summaries in a common comparison, but it may not reproduce the trial analysis if that analysis used details not included in the registry record.

The sponsor’s p-value and the recalculated p-value are different numerical outputs and should not be substituted for one another. The sponsor’s result is the analysis reported by the registry; the recalculation is a separate, summary-statistic analysis. Neither output by itself resolves the uncertainty about the effect size, and the registry does not report enough detail to explain the difference between the two results.

14. Multiplicity, Missing Data and Analysis Populations

The registry lists five secondary outcome entries. These include daytime-functioning measures identified by BDI, STAI, and the Fatigue Severity Scale, a daytime-functioning entry with a baseline and day-28 timeframe, and changes in safety and tolerability. The record also reports six outcome measures overall and five analyses. The detailed results for those secondary measures are not included in the information available for this analysis.

Multiplicity is the issue that arises when several outcomes or comparisons are assessed. As a general statistical point, the more tests that are considered, the greater the opportunity for at least one result to appear notable by chance if no strategy is used to account for the collection of tests. The registry record does not report a multiplicity adjustment, a hierarchy of outcomes, or a plan specifying how the primary and secondary results should be interpreted together. It is therefore not possible to tell whether multiplicity was addressed in the trial analysis.

Missing-data procedures and analysis populations are also not reported in the registry record. The entry lists 34 participants enrolled and 17 participants per arm for the primary outcome, but does not provide a participant-flow account or state whether these are all randomized participants with available endpoint data. The record does not describe withdrawals, missing sleep diaries, imputation, exclusions, adherence requirements, or whether the analysis followed an intention-to-treat principle. These omissions leave uncertainty about how incomplete or unavailable outcomes were handled.

The registry does not report the original sample-size justification, an interim-analysis plan, or a detailed statistical analysis plan. Without those details, readers cannot assess whether the final analysis followed a prespecified strategy or how the study’s several outcomes were prioritized. These are limitations in the available record, not evidence that a particular procedure was or was not used.

15. 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 5% reporting threshold.

Most frequent non-serious adverse event terms

The serious adverse event figures list 0 affected participants among 17 at risk in the placebo arm and 0 among 17 at risk in the chamomile arm. No serious adverse event terms are listed. These figures describe the serious events recorded in the registry for the stated groups; they do not establish that the risk of a rare event is zero.

The deaths field is not populated for either group, so deaths are not reported in the registry record. The record separately lists other adverse events affecting 10 of 17 participants in the placebo arm and 6 of 17 in the chamomile arm. Those are not the serious adverse event counts and should not be confused with them. The registry information does not provide event-level descriptions or further detail about severity, timing, attribution, or how adverse events were collected.

Because the groups were small, these counts offer limited information about uncommon events. A count of zero in a group of this size does not rule out events that were not observed, and the available figures alone do not establish a comparative safety profile. The interpretation is limited to what was recorded in the registry.

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

The primary result is a comparison of the posted day-28 sleep-efficiency values in a randomized, parallel-group study of chamomile extract and placebo. The group summaries are 77.5 for chamomile and 83.3 for placebo, and the recalculated mean difference is -5.8 percentage points. The recalculated interval extends from -12.94 to 1.341, while the registry reports a two-sided test with p = 0.21. Together, these results convey uncertainty rather than a sharply determined group difference.

The findings do not establish that the estimate applies to people beyond the participants represented in this study. The registry record does not report detailed participant characteristics, eligibility criteria, or the disposition of all enrolled participants. It also does not provide enough information to assess whether the observed group summaries represent the full randomized groups or only those with available outcome data.

The endpoint is a diary-based sleep-efficiency measure, not a comprehensive assessment of insomnia. Daytime functioning was also included among the registered outcomes, but results for those measures are not reported in the registry record for this analysis. The primary comparison therefore cannot be used to infer results for fatigue, mood, anxiety, or overall functioning. Nor does the record establish effects beyond the stated baseline-to-day-28 timeframe.

Statistical uncertainty and practical importance are separate questions. The registry does not state a threshold for a meaningful sleep-efficiency change, and the recalculated interval includes values in both directions. The record also does not report the original sample-size justification or a detailed analysis plan. The most defensible reading is limited to the posted group-level data and the reported trial test, with the uncertainty and missing methodological details kept in view.

17. Why This Trial Matters Statistically

This trial is statistically instructive because its small group summaries make the distinction between an estimated difference and the precision of that estimate especially visible. The recalculated mean difference is -5.8 percentage points, but its interval stretches from -12.94 to 1.341. A point estimate gives one summary of the data; the interval shows that the estimate is uncertain and compatible with a range that includes zero.

The registry also illustrates why a posted trial analysis and a summary-statistic recalculation should be clearly separated. The reported two-sided t-test has p = 0.21, while the unadjusted recalculation gives p = 0.111. The recalculation is based on published group summaries and an approximate pooled standard deviation, not on individual-level data or a fully described analysis plan. Recognizing this distinction prevents an approximate calculation from being mistaken for the trial’s own analysis.

The registry’s outcome set also raises a general issue of interpreting several measures. The primary endpoint concerns sleep efficiency, while the listed secondary measures include daytime functioning and safety and tolerability. Without a reported multiplicity strategy or detailed analysis plan, the relationships among those outcomes cannot be assessed from the registry record.

Finally, planning figures based on the observed effect are useful for illustrating how sample size depends on the effect a future study seeks to detect. They are not a substitute for the original design rationale, which is not reported. Taken together, the record provides a concrete setting for discussing estimates, uncertainty, analysis transparency, and the limits of small-study summaries without extending the conclusions beyond the data.

18. 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-outcome comparison is based on group-level summaries, not individual participant data. The posted values include 17 participants per arm, but the registry does not report whether all enrolled or randomized participants contributed to the endpoint. Participant flow, missing diary data, exclusions, and the analysis population are not described. These gaps prevent a full assessment of how the endpoint summaries were formed.

The trial is identified as phase 2 and its official title describes a pilot grant. Enrollment was 34. Such a study can produce an uncertain estimate, as reflected by the recalculated interval, and the registry’s original sample-size justification is not reported. The registry does not report participant demographic characteristics, detailed eligibility criteria, treatment adherence, or a fuller account of the intervention procedures. The arm description refers to capsules, while the primary-outcome description refers to three tablets; the record does not clarify this wording.

The primary endpoint is sleep efficiency measured by sleep diary at baseline and day 28. The registry does not provide baseline outcome values, individual-level changes, diary completion details, or follow-up results beyond the stated timeframe. Results for the listed secondary outcomes are also not included in the information available for this analysis. The clinical meaning of a change cannot be judged against a threshold because no such threshold is reported.

Finally, the registry reports a two-sided t-test but does not provide the sponsor’s effect estimate or confidence interval, a detailed statistical analysis plan, or a multiplicity procedure. The recalculated estimate and interval are approximate, unadjusted calculations from summary statistics. These limitations constrain interpretation of the posted evidence and do not establish that any unreported procedure was absent from the conduct of the trial.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Chamomile for Chronic Primary Insomnia — NCT01286324.
• Registry record last updated 2017-11-07; status last verified 2017-10.
• Results first posted 2013-07-30.
• 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.

22. Record Summary

NCT01286324 is a completed, randomized, quadruple-masked, parallel-group phase 2 study sponsored by the University of Michigan. The registry lists enrollment of 34 and compares Chamomile High Grade Extract with a lactose-containing placebo tablet. The primary outcome concerns change from baseline in sleep measures at day 28, with sleep efficiency identified as the primary aim.

The posted primary-outcome summaries list 17 participants per arm, with values of 77.5 for chamomile and 83.3 for placebo. The registry reports a two-sided t-test with p = 0.21. A separate unadjusted recalculation gives a mean difference of -5.8 percentage points and an interval from -12.94 to 1.341. Secondary outcomes include daytime-functioning measures and safety and tolerability. Detailed participant characteristics, missing-data procedures, the original sample-size justification, and a full statistical analysis plan are not reported in the registry record.