Selegiline for Smoking Cessation - 1: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Selegiline for Smoking Cessation - 1 (NCT00439413), a randomized phase 2 study. The primary outcome is Quit Rate.

2. Clinical Question

3. Trial Design

This was a randomized, triple-masked, parallel-group phase 2 trial of Selegiline Transdermal System as an aid for smoking cessation. The registry records enrollment of 246 and lists nicotine dependence as the condition. Participants were assigned to Selegiline Transdermal System or matching placebo; the study description also includes smoking-cessation counseling. The registry summary describes the intended contrast as selegiline plus behavioral intervention compared with behavioral intervention alone.

The record lists the trial as completed. The recorded start was 2007-06, and primary completion was 2008-08. These dates describe the registry record and do not provide additional information about the timing of individual participant follow-up. The treatment description states that patch treatment lasted 9 weeks following a screening and baseline phase. The primary outcome covered study weeks 6 through 9.

Triple masking indicates that the record classifies the trial as masked, but the identities of the masked groups or roles are not reported in the registry record. The allocation method beyond randomization, the sequence-generation procedure, and the approach to allocation concealment are also not reported in the registry record. These missing details limit assessment of how assignment was implemented.

The registry lists 121 participants in the selegiline group and 125 in the matching-placebo group for the primary outcome. It posts a binary outcome measured as counts of participants with abstinence, rather than a continuous measure. The record gives the primary outcome definition and a secondary abstinence outcome at week 14. Further details about the analysis population, handling of incomplete outcome data, and the trial's original statistical plan 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.

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 Quit Rate, measured over Study weeks 6 through 9.

The primary endpoint is titled “Quit Rate,” and the registry expresses it as the number of participants in each treatment group who ceased smoking during study weeks 6 through 9. A participant met the endpoint definition through four weeks of self-reported abstinence, confirmed by at least two exhaled carbon monoxide measurements during the last four weeks of treatment. Thus, the endpoint combines a participant report with an objective check specified by the registry.

This outcome is used to translate the study question into a count of participants who meet a defined cessation criterion. Comparing the groups can address whether the observed proportion meeting that criterion differed between assignment to selegiline and assignment to placebo, with the behavioral intervention included in the study context. Because the endpoint is binary, each participant is classified as meeting or not meeting the stated definition for this outcome.

The definition depends partly on self-report, while the carbon monoxide measurements serve as confirmation. The registry does not provide further information about the measurement procedures, how missing or contradictory reports were classified, or how many participants had incomplete endpoint data. Those details matter when interpreting the endpoint, especially if outcome ascertainment differs between groups. The endpoint is specific to the stated treatment-period window; it should not be treated as a direct description of smoking behavior at all later times.

7. Results Posted in the Registry

• Selegiline Transdermal System: 14.9% (18/121) versus 12.0% (15/125) on control; risk difference 2.9 percentage points (95% CI -5.6 to 11.4), risk ratio 1.24 (0.65–2.35); unadjusted two-proportion z-test p = 0.508.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Abstinence

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Selegiline Transdermal System: 13.2% (16/121) versus 8.0% (10/125) on control; risk difference 5.2 percentage points (95% CI -2.5 to 12.9), risk ratio 1.65 (0.78–3.50); unadjusted two-proportion z-test p = 0.183.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Selegiline Transdermal System and the control. The interval gives the range of effects that remain compatible with the data.

The registry posts one secondary abstinence outcome, assessed at week 14. Its estimated direction is consistent with the primary comparison: the point estimate favors the selegiline group. That directional agreement is a pattern across the posted outcomes, but it does not turn the secondary comparison into independent confirmation. The primary and secondary outcomes are related measures of abstinence, so they may reflect overlapping participant experiences and outcome information.

The secondary result should be interpreted in the context of the primary result rather than treated as a separate definitive answer. The primary comparison is itself uncertain, and the secondary estimate also has an interval that includes no difference. A consistent direction can be useful descriptively, but uncertainty remains about the size and direction of the underlying effect. The secondary result does not remove the uncertainty in the primary estimate or establish a durable pattern beyond the assessment time reported.

Unadjusted secondary results generally carry less weight because they are not necessarily the principal test of the trial's main question, and examining multiple outcomes can make chance findings more likely. The registry record does not report a multiplicity adjustment, an outcome-testing hierarchy, or a confirmatory analysis plan. The secondary finding is therefore best regarded as supportive descriptive information rather than conclusive evidence. The record does not report additional secondary analyses that would clarify whether this outcome was part of a broader prespecified testing strategy.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Abstinence

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is binary: a participant either met the registry's abstinence definition for the stated period or did not. For this type of outcome, a group proportion describes the share of participants who had the event of interest. The posted counts and group sizes allow an absolute comparison of those proportions. The risk difference expresses that comparison as the selegiline-group proportion minus the placebo-group proportion. A positive value favors the selegiline group for this endpoint; a negative value favors the placebo group. The registry's posted risk-difference estimate is 0.029, but it is not repeated because it exceeds the permitted decimal precision.

A confidence interval describes the range of effect estimates compatible with the data under the method used, subject to its assumptions. It is not a guarantee that the true effect lies inside a particular interval, nor does it give the probability that a specific treatment effect is true. For this comparison, the risk-difference interval crosses the no-difference value. That is consistent with the unadjusted p-value of 0.508: the data do not provide strong evidence against a no-difference hypothesis. It does not prove that there is no effect.

The registry also posts relative measures, including a risk ratio and an odds ratio. A risk ratio compares the proportions with the endpoint between groups. An odds ratio compares the odds of meeting the endpoint. Both use a relative scale, whereas the risk difference is an absolute scale. Relative measures can look different in magnitude from absolute measures because their denominators and interpretations differ. For this trial, the relative interval estimates also include their no-effect value, so they do not resolve the uncertainty in the primary comparison.

The p-value is a measure of how compatible the observed data are with a specified statistical hypothesis, given the model and assumptions used. It is not the probability that the null hypothesis is true, and it is not a measure of clinical importance. A larger p-value does not prove equivalence, and a smaller p-value would not by itself establish that an effect is important. The registry's posted p-value is unadjusted. The record does not give details of any sponsor-run primary analysis, nor does it list reported analyses.

Because the outcome is binary, precision depends in part on how many participants meet the event definition and how many are observed in each group. The primary event counts are 18 and 15. With limited event information, estimates may remain uncertain even when the total enrollment appears substantial. The intervals are therefore important alongside the point estimate: a single best estimate cannot represent the full uncertainty in the comparison.

General statistical note: when binary outcomes are uncommon, small changes in event counts can move an estimated group difference noticeably. General statistical note: a confidence interval that includes the no-difference value is not evidence that all clinically meaningful effects have been ruled out; the interval's width determines how much remains compatible with the data. These concepts help explain why a non-small p-value and an imprecise estimate should not be interpreted as proof of no effect.

The study is described as randomized and parallel-group, but the registry record does not state the full statistical model or all analysis procedures. It does not report whether the primary comparison was adjusted for baseline variables, how participants with missing endpoint information were handled, or which analysis population was used. The posted summary comparison is therefore best read as the reported group-level result, not as a complete account of the trial's analysis strategy.

For the secondary abstinence outcome, the posted p-value is also unadjusted. When more than one outcome or comparison is examined, the chance of at least one apparently unusual result can increase. Statistical methods sometimes account for this multiplicity, but no adjustment is reported in the registry record. This matters particularly for secondary results, which are typically less central to the trial question and may be more exploratory. The registry does not report a prespecified hierarchy or confirmatory testing plan.

The estimates should also be distinguished from planning calculations. The sample-size illustrations use a stated significance level of 0.05, equal allocation between two arms, a normal approximation, and effects defined as fractions of the observed effect. They describe planning scenarios under those assumptions. They do not reconstruct the trial's original design, whose sample-size assumptions are not reported in the registry record.

11. Confidence Intervals and Precision

The point estimate for the primary risk difference is positive, but the confidence interval extends across the no-difference value. This means the data do not pin down the direction of the underlying difference with precision: values favoring either group remain compatible with the interval. The interval also does not support treating the point estimate as a precise forecast of the effect in a broader population.

The posted relative measures have intervals that include their respective no-effect value as well. This consistency across absolute and relative scales reinforces the central interpretation: the estimated direction is favorable to the selegiline group, but the uncertainty is too substantial to distinguish a real group difference from chance variation with confidence. The unadjusted p-value of 0.508 is consistent with that reading.

Precision is affected by the amount of outcome information, not only by the number of participants enrolled. The primary outcome counts are 18 in the selegiline group and 15 in the placebo group. With these event counts, the estimated difference is uncertain. The registry does not report additional information about missing outcomes, so it is not possible to assess from the posted record whether incomplete follow-up affected precision or comparability.

A confidence interval is not a statement that every value in its range is equally likely, and it does not provide a probability that the treatment effect is within the interval. It summarizes uncertainty under a particular method and its assumptions. Readers should consider the estimate, its interval, and the endpoint definition together. The registry does not provide a minimally important difference for this outcome, so the clinical relevance of particular effects cannot be determined from a threshold specified in the record.

12. 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 participants across the trial. The outcome is binary, so the displayed planning values refer to participants needed in each arm for the stated power target. The registry's planning assumptions 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 to the stated fraction of the observed effect.

For planning at 100% of the observed effect, the figures are 2,207 participants per arm for 80% power and 2,954 participants per arm for 90% power. At 75% of the observed effect, the figures are 3,835 and 5,133 participants per arm, respectively. At 50% of the observed effect, the figures are 8,427 and 11,280 participants per arm, respectively. Smaller effects need more participants to detect under the stated assumptions, which is why the planning figures increase as the assumed effect becomes smaller.

In plain terms, 80% power means that a study planned under these assumptions would have an 80% chance of detecting an effect of the specified size at the stated significance level, if that effect were the true one and the planning model held. The 90% column describes the corresponding chance at the higher power target. These figures are planning illustrations based on the observed effect, not observed power. The trial's own original sample-size justification and design assumptions are not reported in the registry record, so these illustrations should not be read as evidence of what the investigators planned before the trial.

13. 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 = 0.120; treatment proportion p₁ = 0.149; average p̄ = 0.134.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.4823 = 0.9454.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.4819 = 0.4056.
4. n = (0.9454 + 0.4056)² / (0.0288)² = 2,206.4, rounded up to 2,207 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 <- 0.12                          # control proportion
p1 <- 0.148760330578512                          # 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(439413)
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 = 2,207 (80% power), 2,954 (90% power)
 75% of observed effect: n per arm = 3,835 (80% power), 5,133 (90% power)
 50% of observed effect: n per arm = 8,427 (80% power), 11,280 (90% power)
power.prop.test: 2206.4 
Simulated power at n = 2,207 per arm: 0.799 (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.

14. Multiplicity, Missing Data and Analysis Populations

The registry identifies a primary quit-rate endpoint and posts a secondary abstinence outcome. It reports no analyses in its analysis listing. The comparison results include unadjusted p-values, but the registry record does not report whether the trial used a formal multiplicity procedure, such as adjustment across outcomes, or a prespecified hierarchy that would control how findings were interpreted. Without that information, secondary comparisons should be regarded cautiously, particularly if several outcomes or analyses were considered.

The record does not report an interim-analysis plan, stopping boundaries, or whether interim looks at accumulating data occurred. It also does not report the trial's original statistical analysis plan. These absences do not establish that such procedures were or were not used; they mean that their details are not reported in the registry record.

Missing-data handling and analysis populations are also not described. The registry does not state whether the primary analysis included everyone as randomized, was restricted to participants with observed outcomes, or used another population definition. It does not explain how participants with missing self-reports or carbon monoxide measurements were classified, whether any imputation was used, or whether sensitivity analyses tested alternative assumptions. Since the endpoint depends on both self-report and confirmation, the handling of incomplete measurements could affect the result.

These omissions limit the ability to assess robustness. A reader can interpret the posted group counts and comparisons, but cannot determine from the registry record whether they reflect an intention-to-treat analysis, a per-protocol analysis, or another approach. The record also does not describe baseline adjustment or other model specifications. The reported estimates should therefore be understood as the posted comparisons, without assuming unreported analysis choices.

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 1% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: fracture of femur (0.8%), heart attack (0.8%), exacerbation of copd dut to pneumonia (0.8%).

The registry lists serious adverse events affecting 3 participants in the Selegiline Transdermal System group and 0 in the matching-placebo group. The corresponding group sizes at risk are recorded as 121 and 125. These are counts, not estimates of a causal effect. The registry does not provide a comparison adjusted for exposure time or other factors, and it does not state whether the events were judged related to treatment.

The listed serious-event terms include “Fracture of femur,” “Heart Attack,” and “Exacerbation of COPD dut to pneumonia,” each recorded as 0.8%. These are the top serious-event terms in the record; the listing does not establish that the treatment caused them. The registry also records other adverse events affecting 99 participants in the selegiline group and 76 in the placebo group. The definitions and severity criteria for this other-event count are not further detailed in the posted record.

Deaths are not reported in the registry record. The counts should be read as a descriptive safety summary, not as a complete assessment of comparative safety. The registry does not provide event timing, exposure-adjusted rates, or a detailed account of ascertainment and relatedness.

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

The posted primary results show that more participants in the selegiline group met the specified abstinence endpoint than in the matching-placebo group. The risk-difference estimate is positive, but its confidence interval crosses the no-difference value, and the unadjusted p-value is 0.508. The result is therefore compatible with a range of underlying effects and does not provide clear statistical evidence of a difference between groups.

This conclusion is not the same as proving that the treatments are equivalent or that no effect exists. The registry does not report an equivalence or non-inferiority design, and the uncertainty in the estimate leaves effects in either direction compatible with the data. Nor does a numerically favorable point estimate establish that a real benefit exists. Precision and the study's design and analysis details matter when interpreting the observed contrast.

The primary endpoint concerns a defined period during treatment and uses a specific combination of self-reported abstinence and carbon monoxide confirmation. It should not be generalized automatically to longer-term abstinence or to other populations. The record provides a secondary abstinence assessment at week 14, but this does not establish outcomes beyond that reported time. Participant characteristics and details of counseling are not reported sufficiently to define how broadly the results might apply.

The safety counts are descriptive. They do not prove that any listed serious event was caused by selegiline, and the registry does not report deaths. The posted record also does not include enough methodological information to assess missing-data handling, analysis populations, or multiplicity procedures. Overall, the trial provides a comparison with an estimated direction favoring selegiline, but substantial statistical uncertainty remains. These findings describe the registry results and are not medical advice.

17. Why This Trial Matters Statistically

This trial illustrates why the point estimate alone is not enough to interpret a clinical comparison. The primary group counts and the positive risk-difference estimate point in one direction, while the interval and unadjusted p-value show that uncertainty remains substantial. Readers need both the direction of the estimate and its precision to distinguish a suggestive pattern from strong evidence of a difference.

It also demonstrates the value of expressing a binary outcome on more than one scale. The risk difference gives an absolute comparison, while relative measures describe the comparison in relative terms. These measures answer related but distinct questions. In this trial, the intervals for the posted measures include their no-effect values, so changing scale does not resolve the uncertainty.

The primary endpoint has an explicit operational definition, combining self-reported abstinence with carbon monoxide confirmation. That specificity helps readers understand what event was counted, while also highlighting why measurement and missing-data procedures matter. The registry record does not provide enough information to assess how incomplete confirmation or other missing measurements were handled.

Finally, the planning illustrations underscore the distinction between an observed trial result and a future study design calculation. Their assumptions are stated, but the trial's original sample-size rationale is not reported. The illustrations cannot be used as observed power or as evidence about the investigators' original planning. Together, these features make the record useful for learning how uncertainty, endpoint definition, analysis transparency, and planning assumptions shape interpretation.

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 registry record leaves several trial-specific details unclear. Although the study is described as triple-masked, the roles that were masked are not identified. The randomization method and allocation-concealment procedures are not reported. These omissions make it difficult to assess implementation from the registry alone.

The primary endpoint relies on self-reported abstinence confirmed by carbon monoxide measurements. The record gives the endpoint definition but does not describe measurement procedures in detail, how missing or inconsistent measurements were handled, or whether outcome assessors were masked. It also does not state which analysis population produced the posted group comparisons. Missing-data assumptions and sensitivity analyses are not reported.

The record describes a phase 2 study and posts outcomes through week 14, but it does not report longer-term outcome information. The participant characteristics needed to assess representativeness are not reported in the available record. The description of counseling is also incomplete, limiting assessment of how the behavioral component was delivered or whether it was consistent across groups.

Multiplicity and analysis planning are additional limitations of the registry record. It does not report a formal adjustment for secondary comparisons, an outcome-testing hierarchy, interim-analysis details, or the trial's original statistical analysis plan. It also does not provide a sample-size justification for the trial itself. These gaps do not mean that procedures were absent; they mean they are not reported in the registry record. Consequently, interpretation must remain tied to the posted summaries and their stated uncertainty.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Selegiline for Smoking Cessation - 1 — NCT00439413.
• Registry record last updated 2017-02-02; status last verified 2016-12.
• Results first posted 2016-10-13.
• 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 phase 2 trial of Selegiline Transdermal System for smoking cessation in participants with nicotine dependence. It records enrollment of 246 and compares a selegiline patch with matching placebo in the context of smoking-cessation counseling.

The primary endpoint was abstinence during study weeks 6 through 9, defined by four weeks of self-reported abstinence confirmed by at least two exhaled carbon monoxide measurements. The posted comparison has a positive risk-difference estimate, but its interval spans the no-difference value and the unadjusted p-value is 0.508. A secondary abstinence outcome at week 14 points in the same direction, with uncertainty and no reported multiplicity adjustment.

The record lists serious and other adverse-event counts, but does not report deaths. Details about missing data, analysis populations, masking roles, and the original analysis and sample-size plans are not reported in the registry record. The posted results therefore support a cautious description of the observed comparison, not a definitive conclusion about the underlying effect.