Auriculotherapy for Smoking Cessation: Pilot: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Auriculotherapy for Smoking Cessation: Pilot (NCT01189110), a randomized na study. The primary outcome is Percentage of Self-reported Abstinence at 6 Weeks..

2. Clinical Question

3. Trial Design

The registry record describes a completed, randomized, triple-masked, parallel-group pilot trial of auriculotherapy for smoking cessation. Enrollment was 125. The brief summary says veterans were evaluated for enrollment and randomized to true or sham auriculotherapy in a 6 week trial. The registry lists a functioning-device intervention group with 64 participants and a disabled-device comparison group with 61 participants.

Both groups received stimulation at points on both ears once a week for 5 weeks. The active group used a functioning Stim Flex 400A TENS unit; the sham group used the same named unit in its disabled state. The record labels the allocation randomized and masking triple, but it does not identify which roles were masked or explain how masking was maintained.

The stated population was veterans who smoked at least 10 cigarettes per day and were not receiving another smoking-cessation intervention. The brief summary also describes male and female veterans age 19 or older. The primary-outcome population description calls the group middle-aged. These descriptions define the setting and eligibility context recorded for the trial; further eligibility criteria are not reported in the registry record.

The listed study start was 2010-08, primary completion was 2011-03, and the study status is completed. The sponsor is the US Department of Veterans Affairs. The phase is listed as NA. The record does not report the trial's original sample-size justification or other design assumptions, so the planning illustrations associated with the posted results should not be treated as a reconstruction of the original trial design.

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: Seventeen were excluded due to eligibility criteria. The remaining 196 were scheduled to attend a 1-hour smoking cessation class. Twenty-nine did not attend. Eleven did not keep the consent appointment. Another 31 did not enroll for other reasons. Thus, 125 participants were randomized: 64 to the intervention group and 61 to the placebo group.

Overall Study

Analysis population for the primary outcome, as defined in the registry: A middle-aged, US military veteran population not free of smoking (at least 10 cigarettes per day) and not currently in reciept of any other form of smoking cessation intervention.

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.

Population: Demographic data, smoking history, fagerstrom nicotine dependence, stage of change, PHQ-9, Percieved stress scale, Minnesota withdrawal scale

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Self-reported Abstinence at 6 Weeks., measured over 6 weeks.

The primary endpoint was the percentage of participants who reported being free from smoking at 6 weeks. The registry defines the response as self-reported abstinence, recorded as yes or no. In this kind of binary outcome, each participant contributes a response that falls into one of two categories; the reported percentage describes the proportion in the group with the specified response.

Abstinence is relevant to the trial's stated question because the study was intended to assess auriculotherapy as an approach to smoking cessation. Measuring the outcome at a specified follow-up point gives the groups a common time at which to compare reported smoking status. The endpoint is explicitly self-reported, so it represents participants' reports rather than a separately described biochemical verification measure. Such a distinction matters when interpreting what the result directly measures: it is evidence about reported abstinence at the stated follow-up, not a broader measure of all changes in smoking behavior.

The registry reports 12.3% for the functioning-device group, with a 95% confidence interval from 4.0% to 20.7%, and 12.9% for the disabled-device group, with a 95% confidence interval from 4.0% to 21.7%. The outcome description does not specify other abstinence definitions or report later follow-up outcomes. Those details are not reported in the registry record.

7. Results Posted in the Registry

• Arm 1- Intervention: 12.5% (8/64) versus 13.1% (8/61) on control; risk difference -0.6 percentage points (95% CI -12.3 to 11.1), risk ratio 0.95 (0.38–2.38); unadjusted two-proportion z-test p = 0.918.

8. Statistical Interpretation

9. Statistical Methods Explained

The registry reports a binary primary endpoint: self-reported abstinence at 6 weeks. A binary outcome places each participant into a category such as abstinent or not abstinent. The group percentage summarizes how common the specified response was among the participants represented in that group. The registry lists 12.3% in the intervention group and 12.9% in the placebo group, as well as the group sizes and confidence intervals.

What does a risk difference describe?

A risk difference compares the outcome proportions by subtracting one group's proportion from the other's, with the direction determined by which group is defined as the intervention. It is an absolute contrast, expressed on the proportion scale. The recalculated unadjusted risk difference for the intervention group is -0.006. Its 95% confidence interval runs from -0.123 to 0.111. Because this interval includes zero and extends in both directions, the posted summary does not give a precise direction or magnitude for the contrast. The interval is not a probability statement that the true value lies within it; under the usual repeated-sampling interpretation, the method produces intervals that contain the fixed underlying value at the stated rate when its assumptions hold.

How do relative measures differ?

A risk ratio compares the outcome proportions as a ratio; an odds ratio compares the odds of the outcome. These measures are relative rather than absolute, and their values depend on the scale used. The recalculated risk ratio is 0.953, with a 95% confidence interval from 0.382 to 2.38. The recalculated odds ratio is 0.946, with a 95% confidence interval from 0.331 to 2.703. The registry's own analysis reports an odds ratio of 0.81, with a 95% confidence interval from 0.23 to 2.83. The registry says this analysis used a chi-squared method. The record does not give further details of the sponsor's calculation.

Why do the intervals matter?

A confidence interval communicates uncertainty around an estimate. A narrow interval indicates greater precision on the scale used; a broad interval leaves more possible values compatible with the data and method. Here, the intervals for the risk difference, risk ratio, and odds ratios are broad. For relative measures, an interval spanning values below and above the null value indicates that the data do not precisely distinguish effects in either direction. The numerical width also depends on the measure's scale, so interval widths should not be compared across measures as if they were expressed in the same units.

What does the p-value add?

The recalculation gives an unadjusted p-value of 0.918 for the risk-difference comparison. The registry reports p = 0.74 for its chi-squared analysis. A p-value measures compatibility between the observed data and a specified null model under the assumptions of the test; it is not the probability that a treatment has no effect. A large p-value does not demonstrate that the groups are equivalent, and a small p-value would not by itself tell readers whether an effect is important. Interpretation should consider the estimated effect, its interval, the endpoint, and the study context together.

Why might a small event count limit precision?

When an outcome is uncommon in the observed groups, relatively few responses contribute information about the group contrast. That generally leaves less precision than would be available with more outcome information, all else equal. The registry reports 8 abstinent responses in each group. This count helps explain why the confidence intervals leave substantial uncertainty, but it does not prove that a particular design or analysis choice caused that uncertainty.

All recalculated contrasts are simple unadjusted comparisons based on posted summary statistics. They do not account for participant-level covariates or any analysis features that are not represented in those summaries. Whether the sponsor's analysis used additional details beyond the stated chi-squared method is not reported in the registry record. The registry does not report adjusted analyses or a fuller statistical analysis plan.

10. Confidence Intervals and Precision

Precision concerns how tightly the data and analysis locate an effect estimate. The group-specific 95% confidence interval is 4.0% to 20.7% for the intervention group's reported abstinence percentage of 12.3%. For the comparison group's 12.9% estimate, the interval is 4.0% to 21.7%. Each interval covers a range of possible underlying group percentages that remain compatible with the observed data and the interval method.

The recalculated risk difference is -0.006, with a 95% confidence interval from -0.123 to 0.111. The lower and upper limits lie on opposite sides of zero, so the interval allows both a negative and a positive difference. The recalculated relative measures also have broad intervals: 0.382 to 2.38 for the risk ratio and 0.331 to 2.703 for the odds ratio. The sponsor-reported odds ratio has a 95% confidence interval from 0.23 to 2.83.

These intervals do not show that all values inside them are equally plausible, nor do they assign a probability to the effect after observing the data. They show the uncertainty left by the data and method. The point estimates alone would conceal that uncertainty. In this trial, the intervals are important because the observed percentages are close but the available information does not sharply constrain the possible contrast. The registry record does not report a prespecified threshold for a clinically meaningful difference, so the interval cannot be judged against such a threshold from the posted information.

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 give participants per arm for 80% power and participants per arm for 90% power. They are not totals across groups and are not total event counts. The registry's assumptions for these illustrations are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set as the stated fraction of the observed effect. The registry's original design assumptions and sample-size justification are not reported in the registry record.

The 80% power column represents the planned number of participants per arm under the stated assumptions for a design with an 80% chance of detecting the specified effect if that effect were the true one. The 90% column uses a higher target chance of detection under those same assumptions. These are planning concepts: power depends on the effect specified, outcome frequency, variability, analysis, and design assumptions. The displayed values are not observed power.

The rows represent planning for 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. As the effect to detect becomes smaller, more participants are needed to distinguish it from random variation at the stated power target. The posted figures increase across those rows. They are illustrations based on the observed effect, not evidence that the trial was designed with those targets or that the assumptions match the original protocol. The planning curve should be interpreted in that same way: it visualizes how the planned participant requirement changes with the effect size under the stated calculation assumptions.

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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.131; treatment proportion p₁ = 0.125; average p̄ = 0.128.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.4726 = 0.9263.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.4726 = 0.3977.
4. n = (0.9263 + 0.3977)² / (-0.0061)² = 46,383.5, rounded up to 46,384 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
p0 <- 0.131147540983607                          # control proportion
p1 <- 0.125                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(1189110)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 46,384 (80% power), 62,094 (90% power)
 75% of observed effect: n per arm = 82,883 (80% power), 110,956 (90% power)
 50% of observed effect: n per arm = 187,434 (80% power), 250,920 (90% power)
power.prop.test: 46383.5 
Simulated power at n = 46,384 per arm: 0.798 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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's own result is an odds ratio of 0.81, with a 95% confidence interval from 0.23 to 2.83 and p = 0.74, reported using a chi-squared method. The recalculated summary gives an odds ratio of 0.946, with a 95% confidence interval from 0.331 to 2.703, and an unadjusted risk-difference p-value of 0.918. The recalculation is a simple unadjusted re-analysis of posted summary statistics; it is not a replacement for the sponsor's reported analysis.

The sponsor result uses the odds-ratio scale, while the highlighted recalculated test is for the risk difference. Even where the same general contrast is of interest, estimates and p-values may not match when methods, scales, or underlying data differ. The registry does not provide enough detail to identify the precise reason for the numerical differences. The discrepancy flag is false, so the registry record does not flag a discrepancy between the analyses. The sponsor's own analysis should be read as the trial's reported analysis, with the recalculation treated as a transparent, unadjusted comparison based on the posted summaries.

14. Multiplicity, Missing Data and Analysis Populations

The registry lists 1 outcome measure and 1 analysis. It reports no posted secondary outcomes. With only the posted primary endpoint and analysis identified, there is no listed set of multiple outcome tests for which a multiplicity adjustment can be assessed. This does not establish that no other outcomes were collected or considered; any such information is not reported in the registry record.

Multiplicity arises when several statistical questions are tested and the chance of at least one apparently unusual result can increase across those tests. Researchers may address this through a prespecified hierarchy, adjustment, or other strategy, depending on the aims and analysis plan. The registry record does not report a multiplicity strategy or explain whether the listed analysis was prespecified.

How missing outcome data were handled is not reported in the registry record. The posted results do not describe whether all randomized participants were included in the outcome analysis, how participants without a 6-week response were treated, or whether any imputation or sensitivity analysis was used. The analysis population is also not reported in detail. Although arm sizes are listed, the record does not state whether the primary analysis followed an intention-to-treat approach, a per-protocol approach, or another rule for including participants.

These omissions matter because missing responses and analysis-population choices can affect the estimate and its uncertainty, especially when the endpoint is a self-reported response at follow-up. The available description is not enough to determine whether missingness could have differed between groups or how any such difference was addressed. No conclusion about the direction or size of a missing-data effect can be drawn from the registry record.

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 3% reporting threshold.

Most frequent serious adverse event terms

Serious events with the highest arm-level rate: hospitalization (1.6%).

The registry lists serious adverse events for 2 participants in the intervention group and 0 in the placebo group. The numbers at risk are 64 and 61, respectively. The registry identifies hospitalization as the top serious-event term and reports 1.6%. No other adverse events are listed for either group in the posted figures.

These are counts recorded in this trial, not estimates of a stable event rate for other populations or settings. A zero count in one group does not show that the underlying risk is zero; it means that no serious adverse event was reported for that group in the registry's listed results. The record does not provide descriptions of the hospitalization events, event timing, attribution to the intervention, or a detailed method for collecting adverse-event information.

Deaths are not reported in the registry record. The posted adverse-event counts should therefore be interpreted narrowly: they describe the serious adverse events recorded for the trial groups and the listed hospitalization term. The information is not sufficient to characterize every possible safety outcome or to compare safety precisely.

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

The result is a comparison of self-reported smoking abstinence at 6 weeks after a course of active auriculotherapy or sham auriculotherapy. The reported percentages are 12.3% in the active group and 12.9% in the sham group. The recalculated risk-difference interval includes values on both sides of zero, and the sponsor-reported odds-ratio interval is broad. The estimates therefore leave substantial uncertainty about the size and direction of the difference in this trial.

This result does not establish that the procedures are equivalent. A failure to distinguish a difference with the posted analysis is not the same as demonstrating that any difference is sufficiently small. Equivalence or noninferiority requires a stated margin and an appropriate design and analysis; such a margin is not reported in the registry record. The wide intervals also mean that the results do not precisely exclude meaningful differences in either direction.

The endpoint is self-reported abstinence at a single stated follow-up point. The record does not describe biochemical confirmation, later abstinence outcomes, or broader measures of changes in smoking. The findings therefore apply to the endpoint as recorded, not to every possible definition of smoking cessation or to longer-term outcomes.

The registry describes a pilot trial of veterans who smoked at least 10 cigarettes per day and were not receiving another smoking-cessation intervention. Generalization beyond that population and setting is uncertain. The posted results cannot establish the effect in other groups or when auriculotherapy is combined with other approaches. They also do not establish that either procedure works or does not work. They report an uncertain contrast in this trial, with the limitations of the available outcome and analysis details.

17. Why This Trial Matters Statistically

This trial is statistically informative as an example of the distinction between a point estimate and the uncertainty around it. The two posted abstinence percentages are close, but the confidence intervals are broad. Reporting the point estimates alone could make the comparison appear more settled than the data support. The intervals show that the observed summaries do not precisely determine the underlying contrast.

It also illustrates why a nonsignificant result should not be read as proof of no difference. The recalculated p-value is 0.918, while the sponsor's reported p-value is 0.74. Neither p-value establishes equivalence, and neither replaces consideration of the effect estimate and confidence interval. A specific equivalence question would require a margin and a suitable plan, neither of which is reported in the registry record.

The posted outcome is binary and based on self-report at 6 weeks. Its definition, measurement method, and timing are all important to the question being answered. A result for this endpoint is not automatically a result for later abstinence, independently verified abstinence, or other cessation outcomes. The distinction between what was measured and what readers may wish to know is central to interpreting clinical trial results.

Finally, the planning illustrations emphasize the relationship between the effect a study aims to detect and the number of participants needed under specified assumptions. Smaller target effects require larger planned participant numbers. Those illustrations should not be confused with the trial's original design plan or with observed power. The original planning rationale is not reported, which limits what can be inferred about the pilot's intended precision.

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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

The posted primary endpoint is self-reported abstinence at 6 weeks. The registry does not describe independent verification, the exact question used to elicit the response, or how incomplete responses were handled. Those details could affect interpretation of the outcome, but their impact cannot be determined from the record.

The trial is described as a pilot and enrolled 125 participants. The observed abstinent response count is 8 in each group, and the effect intervals are broad. This limits precision for the comparison. The registry does not report the original sample-size rationale, so it is not possible to determine the intended target effect or precision from the record.

The record labels the design randomized and triple-masked but does not explain the randomization procedure, allocation concealment, or which participants or study personnel were masked. It also does not explain how masking was assessed or maintained when the comparison used a disabled device. These design details are not reported in the registry record.

The analysis population, handling of missing data, prespecified analysis plan, and any adjusted analyses are not reported. The registry lists one primary outcome measure and one analysis, with no secondary outcomes posted. The study's stated population and setting may also limit how directly the results apply beyond veterans who met the recorded smoking and intervention criteria. These limitations do not determine the direction of bias; they identify aspects of the record that remain uncertain.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Auriculotherapy for Smoking Cessation: Pilot — NCT01189110.
• Registry record last updated 2015-04-28; status last verified 2013-08.
• Results first posted 2014-04-15.
• 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.

22. Record Summary

The registry describes a completed randomized, triple-masked, parallel-group pilot trial of auriculotherapy for smoking cessation. It enrolled 125 veterans and compared a functioning Stim Flex 400A TENS unit with a disabled unit. Stimulation was delivered to points on both ears once a week for 5 weeks.

The primary outcome was self-reported abstinence at 6 weeks. The registry reports 12.3% in the intervention group and 12.9% in the placebo group. Its own analysis reports an odds ratio of 0.81, with a 95% confidence interval from 0.23 to 2.83 and p = 0.74. A simple unadjusted recalculation gives a risk difference of -0.006, with a 95% confidence interval from -0.123 to 0.111.

The estimates are imprecise, and the record does not report key details about missing data, analysis populations, or the original sample-size rationale. The posted results describe this trial's outcome and do not establish equivalence or resolve the effect of auriculotherapy.