Innovative Interventions for Smoking Cessation: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Innovative Interventions for Smoking Cessation (NCT01050569), a randomized phase 2 study. The primary outcome is End of Treatment Abstinence Rate.

2. Clinical Question

3. Trial Design

The registry describes NCT01050569, “Innovative Interventions for Smoking Cessation,” as a phase 2 randomized study sponsored by the University of Minnesota. Its recorded design model is factorial, and masking is recorded as none. The study status is completed. The record lists a start date of 2008-10 and primary completion of 2011-12.

Three intervention groups are listed: VLNC cigarettes, nicotine patch, and VLNC cigarettes plus nicotine patch. Each arm description specifies daily use for 6 weeks. The combination arm includes a 21 mg patch and VLNC cigarettes with a stated nicotine yield of 0.05 mg to 0.09 mg. Although the record labels the model factorial, the factors, allocation details within that model, and any interaction analysis are not reported in the registry record. The listed intervention groups should therefore be read as recorded, without assuming an unreported factorial contrast.

Enrollment is recorded as 235. The primary outcome entries give an arm-level denominator of 79.0 for VLNC cigarettes, 76.0 for the combination, and 80.0 for nicotine patch. The primary endpoint is end-of-treatment abstinence at 12 week, recorded as a number of participants with cotinine- and carbon-monoxide-verified point-prevalence abstinence. These arm-level denominators and outcome counts are reported separately; the record does not explain how they relate to the enrollment figure or specify the analysis population.

The registry lists exposure to tobacco toxicants and time to lapse or relapse to tobacco use as secondary outcomes. Numerical secondary results are not reported in the registry record. The study’s original sample-size assumptions, allocation procedures beyond randomization, and any planned interim analyses are also 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: After signing consent and before randomization to groups, 44 were lost to follow-up, 17 were ineligible, 10 were no longer interested, 10 were family members of enrollees.

Overall Study

Reasons for not completing this period:

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 End of Treatment Abstinence Rate, measured over 12 week.

The primary endpoint is the number of participants with cotinine- and carbon-monoxide-verified point-prevalence abstinence at the 12 week timeframe. Cotinine and carbon monoxide are the verification measures named in the registry description. The endpoint is recorded as a count of participants, rather than as a continuous measure or a time-to-event outcome.

In general, point-prevalence abstinence describes abstinence status at a defined assessment, rather than documenting uninterrupted abstinence over the entire period since treatment began. The registry does not report the precise assessment window used to define point prevalence, the rules for handling incomplete or conflicting verification, or the analysis population for this endpoint. Those details should not be inferred from the endpoint label alone.

End-of-treatment abstinence offers a direct way to compare the groups’ recorded abstinence counts at the specified assessment. It does not by itself describe how long abstinence lasted, whether participants later lapsed, or changes in toxicant exposure. The registry lists time to lapse or relapse and exposure to tobacco toxicants as secondary outcomes, but numerical results for those outcomes are not reported in the registry record.

7. Results Posted in the Registry

• VLNC Cigarette Plus Nicotine Patch: 23.7% (18/76) versus 24.1% (19/79) on control; risk difference -0.4 percentage points (95% CI -13.8 to 13.1), risk ratio 0.98 (0.56–1.73); unadjusted two-proportion z-test p = 0.957.
• Nicotine Patch: 23.8% (19/80) versus 24.1% (19/79) on control; risk difference -0.3 percentage points (95% CI -13.6 to 13.0), risk ratio 0.99 (0.57–1.72); unadjusted two-proportion z-test p = 0.965.

8. Statistical Interpretation

9. Statistical Methods Explained

What does a risk difference express?

In general, a risk difference subtracts the event proportion in one group from the event proportion in another. It is measured on the proportion scale, so a value near zero represents little separation in the observed proportions, while positive and negative values indicate opposite directions according to the comparison’s stated ordering. The posted comparisons use VLNC cigarettes as the control and report the combination and nicotine patch contrasts against that group.

The combination comparison has a posted risk difference of -0.004. The nicotine patch comparison has a posted risk difference of -0.003. Both point estimates are close to zero and negative. The corresponding posted intervals extend to positive as well as negative values, so the data are compatible with differences in either direction. These are unadjusted comparisons as identified in the registry results; no adjusted contrast is reported.

How should the intervals be understood?

In general, a confidence interval represents uncertainty around an estimated effect under the method used to construct it. It is not a range containing a known, fixed proportion of future outcomes, and it does not assign a probability to a particular treatment effect. A broad interval signals that the estimate is imprecise. The registry reports intervals from -0.138 to 0.131 for the combination contrast and from -0.136 to 0.130 for the nicotine patch contrast. The confidence level and interval-construction method are not reported in the registry record, so they cannot be specified further.

The interval endpoints matter alongside the point estimates. Although each estimate is close to zero, neither interval is confined to values close to zero. The endpoints encompass both negative and positive differences. This means the posted estimates alone do not sharply identify the direction or magnitude of a group difference. A failure to obtain a small p value is not the same as demonstrating that any difference is absent.

What do the p values add?

In general, a p value measures how incompatible the observed data are with a specified null model, under the assumptions of the test. It is not the probability that the null hypothesis is true, nor is it a measure of the clinical importance of an effect. The unadjusted p values reported for the two contrasts are 0.957 and 0.965. These values do not indicate strong evidence against a null model of no difference, but they cannot establish equivalence. The registry does not report the test specification, any multiplicity adjustment, or a full statistical analysis plan.

The posted counts are the primary outcome data used to frame the comparisons: 19 participants with abstinence in the VLNC cigarette group, 18 in the combination group, and 19 in the nicotine patch group. The respective arm denominators are 79.0, 76.0, and 80.0. The registry presents the resulting risk differences and intervals. No separate adjusted model output is posted, and the analysis population and missing-data handling are not reported in the registry record.

Why can over-dispersion matter?

In general, over-dispersion means that variability in observed data is greater than a statistical model expects. When a model underestimates variability, standard errors can be too small and intervals can be too narrow. Over-dispersion is especially relevant when the outcome or data structure calls for a model that explicitly represents variation beyond its simplest assumptions. It is not a reported feature of this binary abstinence outcome, and the registry record does not describe a model in which over-dispersion was assessed or handled. It should therefore be treated as a general statistical consideration, not as a claim about this study’s analysis.

What can be said about the design and analysis?

The registry describes the study as randomized, unmasked, and factorial, but does not give enough detail to reconstruct the randomization scheme or a factorial model. In particular, the record does not report factor definitions, interaction estimates, covariate adjustments, or any analysis population. The posted group comparisons can be read as pairwise contrasts with VLNC cigarettes as the control; they do not substitute for unreported factorial effects.

The registry records 0 analyses, while it also posts the primary outcome counts and comparison statistics. These entries do not supply a detailed account of the statistical methods. The sponsor’s own analysis is not identified as discrepant from the simple posted summary comparisons; the registry discrepancy indicator is false. The posted estimates are therefore described as recorded, without reconstructing an unreported model or inventing analysis details.

10. Confidence Intervals and Precision

Precision concerns how tightly the available data locate an effect estimate. The posted risk-difference estimates are near zero, but the intervals are wide enough to include differences in either direction. For the combination compared with VLNC cigarettes, the estimate is -0.004 and the interval is -0.138 to 0.131. For nicotine patch compared with VLNC cigarettes, the estimate is -0.003 and the interval is -0.136 to 0.130. The intervals therefore communicate more uncertainty than the point estimates alone.

The observed abstinence counts are close across groups: 19 participants in the VLNC cigarette group, 18 in the combination group, and 19 in the nicotine patch group. Similar counts do not, by themselves, imply a precise estimate of the difference. Precision also depends on the amount of information available and the variability expected under the analysis. The posted intervals are the more direct guide to uncertainty about the contrasts.

The registry does not report the confidence level or the method used to construct the intervals. No confidence level should be assigned by assumption. The record also does not describe whether the intervals account for any design features associated with the factorial label, or whether they are adjusted for other variables. The unadjusted p values are 0.957 for the combination contrast and 0.965 for the nicotine patch contrast; these do not replace the intervals as a description of the range of effect estimates compatible with the analysis.

Because both intervals include zero and extend to negative and positive differences, the posted results do not establish that there is no difference. Nor do they show that any difference is small enough to meet an equivalence criterion. Such a conclusion would require a prespecified margin and an analysis plan, neither of which is reported in the registry record. The main precision finding is that the point estimates are close to zero while uncertainty about the direction and size of the contrasts remains substantial.

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 expressed as participants per arm, not as total events. They are illustrations based on the observed effect, not the trial’s own original design assumptions. The stated 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 the stated fraction of the observed effect. The trial’s original sample-size justification and design assumptions are not reported in the registry record.

The 80% power column means the planning illustration’s number of participants per arm under which the specified design would have 80% power to detect the assumed effect, if the planning assumptions held. The 90% power column expresses the corresponding per-arm requirement for 90% power. Power is a design property under an assumed effect and analysis model; it is not the probability that the observed result is correct.

The displayed planning scenarios use 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. The participant requirements increase as the assumed effect becomes smaller. For the combination comparison, the per-arm figures for 80% power are 212,446, 378,179, and 852,021 across those scenarios; for 90% power they are 284,404, 506,274, and 1,140,613. For the nicotine patch comparison, the corresponding 80% power figures are 315,900, 562,207, and 1,266,325, and the 90% power figures are 422,900, 752,634, and 1,695,250.

These unusually large planning illustrations reflect the very small observed risk-difference estimates used as their starting point. They are hypothetical planning calculations, not observed power, and they should not be interpreted as the actual enrollment target or as a retrospective judgment of the trial’s design. The registry’s original sample-size rationale is not reported.

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 = 0.241; treatment proportion p₁ = 0.237; average p̄ = 0.239.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6028 = 1.1815.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6028 = 0.5074.
4. n = (1.1815 + 0.5074)² / (-0.0037)² = 212,445.4, rounded up to 212,446 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 <- 0.240506329113924                          # control proportion
p1 <- 0.236842105263158                          # 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(1050569)
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 = 212,446 (80% power), 284,404 (90% power)
 75% of observed effect: n per arm = 378,179 (80% power), 506,274 (90% power)
 50% of observed effect: n per arm = 852,021 (80% power), 1,140,613 (90% power)
power.prop.test: 212445.4 
Simulated power at n = 212,446 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.

13. Multiplicity, Missing Data and Analysis Populations

The registry record does not report a multiplicity plan. It lists a primary abstinence outcome, as well as secondary outcomes for exposure to tobacco toxicants and time to lapse or relapse. It does not describe whether the investigators prespecified a hierarchy among outcomes, adjusted for multiple comparisons, or treated any analyses as exploratory. The posted p values are identified as unadjusted, so they should not be read as multiplicity-adjusted results.

The registry lists no posted numerical results for the secondary outcomes. As a result, the abstinence contrasts cannot be considered alongside results for toxicant exposure or time to lapse or relapse. The record also does not report how many comparisons were planned, whether any additional subgroup or sensitivity analyses were conducted, or whether any results were omitted from the registry entry.

Missing-data methods are not reported in the registry record. The primary outcome entries give arm denominators and abstinence counts, but do not explain whether missing endpoint assessments were excluded, counted as smoking, imputed, or handled by another method. The analysis population is not specified. Consequently, the reported denominators should not be assumed to represent a particular analysis set, and the posted counts do not reveal how participants without endpoint data were treated.

The registry does not report a protocol-level statistical analysis plan, prespecified covariate adjustment, sensitivity analyses, or interim analyses. The study is described as factorial, but no factor-specific analysis or interaction result is posted. These omissions do not show that such methods were or were not used; they mean the relevant details are not reported in the registry record. The available comparisons can be interpreted as posted, unadjusted pairwise risk differences, while broader claims about the full analysis strategy remain unsupported.

14. 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 entries report 0 affected participants in the VLNC cigarette group, with 79 at risk; 0 in the combination group, with 76 at risk; and 0 in the nicotine patch group, with 80 at risk. No serious adverse event terms are listed. These are registry-reported counts, not a demonstration that serious events were impossible or that the interventions have no serious risks.

The record also lists other adverse event counts: 60 affected among 79 at risk for VLNC cigarettes, 56 among 76 at risk for the combination, and 54 among 80 at risk for nicotine patch. No percentages are calculated. The registry record does not define the “other” category in the posted entry, describe event severity or duration, or provide event-specific details in this summary.

Deaths are not reported in the registry record. The adverse event entries also do not specify the observation period, methods for collecting events, or whether events were judged related to study interventions. These counts should therefore be read as the safety information recorded in the registry, not as a complete assessment of comparative safety.

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

The posted primary results show closely grouped abstinence counts at the 12 week endpoint: 19 participants in the VLNC cigarette group, 18 in the VLNC cigarette plus nicotine patch group, and 19 in the nicotine patch group. The associated risk-difference estimates are small in magnitude and negative for both comparisons with VLNC cigarettes. Their intervals extend across zero and include values in both directions, so the observed data do not precisely identify which group had a higher abstinence proportion.

This does not mean the groups have been shown to be equivalent. An equivalence conclusion requires a defined margin and an analysis designed to assess that margin. Neither is reported in the registry record. Likewise, the results do not demonstrate that any possible difference is clinically unimportant. The posted p values are unadjusted, and the registry does not provide a full analysis plan or explain how missing outcome data were handled.

The endpoint is a cotinine- and carbon-monoxide-verified point-prevalence abstinence count at the specified timeframe. It does not establish continuous abstinence throughout treatment or beyond the assessment, and it does not answer the separate questions about toxicant exposure or time to lapse or relapse. Numerical results for those listed secondary outcomes are not reported in the registry record.

The record documents a randomized, unmasked phase 2 trial and its reported outcome counts. It does not, by itself, establish a clinical recommendation, show that a particular intervention works or does not work, or determine which group would have the most favorable outcomes in another population or setting. The findings are best understood as imprecise registry-reported comparisons for this endpoint, with important analysis and population details not reported.

16. Why This Trial Matters Statistically

This trial illustrates why a point estimate and its uncertainty need to be read together. The abstinence counts are similar across the three listed groups, and the risk-difference point estimates are close to zero. However, the intervals extend substantially to both sides of zero. Looking only at the counts or point estimates could make the contrasts appear more settled than the interval estimates support.

The results also demonstrate the distinction between an inconclusive comparison and evidence of equivalence. The unadjusted p values are 0.957 and 0.965, and the intervals include zero, but neither feature establishes that the interventions have the same effect. Equivalence requires a prespecified boundary for an acceptable difference and an appropriate analysis; that information is not reported in the registry record.

The planning illustrations further show how a small observed effect can lead to large hypothetical per-arm sample-size requirements, particularly when planning for effects smaller than the observed estimate. Those figures are not a retrospective assessment of the study’s design. The original sample-size assumptions are not reported, and the planning calculations use stated assumptions that may not match the trial’s actual design or analysis.

Finally, the registry labels the study factorial while reporting pairwise results for three intervention groups. Without the factor definitions, interaction analysis, and analysis plan, readers should avoid inferring effects beyond the posted contrasts. The example is statistically useful because it separates what is directly reported from broader conclusions that require information absent from the registry record.

17. 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.

Several trial-specific limitations constrain interpretation. The study is recorded as unmasked, so participants and study personnel were not masked according to the registry entry. The registry does not report allocation concealment, adherence, participant characteristics, or baseline comparability. It also does not specify the primary outcome analysis population or how missing endpoint assessments were handled.

The primary outcome counts are close across groups, but the risk-difference intervals are broad and span values on both sides of zero. The registry does not report the confidence level or interval method. The reported p values are unadjusted, and no multiplicity plan, prespecified adjustment strategy, or equivalence margin is available in the registry record. This limits both the precision of interpretation and the ability to assess the analysis against a prespecified decision framework.

Although the design model is labeled factorial, the record does not define its factors or provide interaction estimates. The listed pairwise comparisons therefore should not be treated as a complete account of potential factorial effects. Secondary outcomes are listed, but their numerical results are not reported in the registry record. The observation periods and analysis methods for safety outcomes are also not specified; deaths are not reported in the registry record.

The record identifies tobacco use disorder and enrollment of 235 but provides limited information about the characteristics of the participants represented in the primary analysis. This restricts assessment of how broadly the results may apply. The study’s original sample-size rationale and any interim analyses are not reported, so neither can be inferred from the posted planning illustrations or outcome estimates.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Innovative Interventions for Smoking Cessation — NCT01050569.
• Registry record last updated 2019-11-18; status last verified 2019-10.
• Results first posted 2014-02-28.
• 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.

21. Record Summary

NCT01050569 is a completed, randomized, unmasked phase 2 study sponsored by the University of Minnesota. The registry records a factorial model, enrollment of 235, a start date of 2008-10, and primary completion in 2011-12. The listed groups received daily VLNC cigarettes, a daily 21 mg nicotine patch, or both; each arm description specifies 6 weeks of use.

The primary endpoint is the number of participants with cotinine- and carbon-monoxide-verified point-prevalence abstinence at 12 week. The registry reports counts of 19 among 79.0 for VLNC cigarettes, 18 among 76.0 for the combination, and 19 among 80.0 for nicotine patch. The pairwise risk differences versus VLNC cigarettes are -0.004 and -0.003, with broad intervals spanning zero and unadjusted p values of 0.957 and 0.965.

The registry also lists toxicant exposure and time to lapse or relapse as secondary outcomes, without numerical results. Details on missing-data handling, analysis populations, multiplicity, and the original sample-size rationale are not reported in the registry record.