Internet-Administered Smoking Cessation Treatment for Overweight and Obese Smokers: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Internet-Administered Smoking Cessation Treatment for Overweight and Obese Smokers (NCT01259466), a randomized na study. The primary outcome is Number of Participants With Verified Smoking Cessation (Abstinence).

2. Clinical Question

The trial asked whether adding cognitive behavioral therapy for weight concerns to internet-administered smoking cessation treatment was associated with different post-treatment smoking abstinence and weight-change results than adding general health education. Both groups also received nicotine replacement. The primary outcome was verified continuous abstinence during the last 14 days of treatment, assessed at post-treatment, while percent weight change was a secondary outcome.

This is a comparison of treatment packages that share smoking cessation treatment and nicotine replacement but differ in the additional internet-administered content. It does not isolate the effects of nicotine replacement, because both groups received it. Nor does the comparison isolate cognitive behavioral therapy from every other difference between the two programs. The primary endpoint is an abstinence count at a specified post-treatment assessment, not a measure of long-term cessation. The registry record does not report a longer-term primary outcome.

3. Trial Design

The registry describes a randomized, parallel-group trial with no masking. The record lists the study as completed and gives an enrollment of 54. It identifies Yale University as the sponsor. The listed phase is not applicable. The record gives a start date of 2010-07 and a primary completion date of 2013-11.

Participants were assigned to one of two internet-administered treatment programs. The cognitive behavioral treatment group received standard smoking cessation treatment with cognitive behavioral therapy for weight concerns. The health education group received standard smoking cessation treatment with general health education. Both groups received open-label treatment with a 21 mg transdermal nicotine patch. The record characterizes the treatment period as 12 weeks.

The primary outcome was assessed post-treatment at 12 weeks. It counted participants with continuous abstinence during the last 14 days of treatment, confirmed by biological verification. The secondary outcome was percent weight change, with its post-treatment timeframe listed as 12 weeks. The posted primary outcome contains 27 participants in each arm; the posted secondary outcome contains 26 in the cognitive behavioral treatment arm and 18 in the health education arm. The registry record does not explain why the secondary outcome has different arm counts or describe the analysis populations.

Random allocation can help balance measured and unmeasured characteristics on average, but the record does not provide details about sequence generation or concealment. With no masking, participants and treatment providers were not masked according to the registry description. The registry record does not report further operational details about allocation, adherence, follow-up, or the original statistical plan.

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

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 Number of Participants With Verified Smoking Cessation (Abstinence), measured over Post-treatment (12-weeks).

The primary endpoint counts participants who met the trial’s definition of verified smoking abstinence at post-treatment. Specifically, the registry describes continuous abstinence during the last 14 days of treatment, confirmed by a carbon monoxide level below 10ppm. The outcome is recorded as a number of participants, so it captures whether participants met the stated abstinence criterion rather than the degree or duration of smoking reduction.

Biological verification adds an objective measure to a reported abstinence status. This can make the outcome definition more specific than self-report alone, although the registry record does not report the verification procedures beyond the carbon monoxide threshold. The fixed assessment period also makes the two randomized groups comparable at the stated endpoint, provided outcome ascertainment and handling of missing outcomes were conducted appropriately; those details are not reported in the registry record.

Abstinence is used as the primary outcome because the intervention is intended to address smoking cessation. The posted result is limited to the treatment-end assessment. It does not establish whether abstinence continued after that assessment, and the registry record does not report a longer follow-up result for this primary endpoint. The count should therefore be read as an endpoint-specific comparison, not as a complete account of participants’ smoking trajectories.

7. Results Posted in the Registry

• Health Education + Nicotine Replacement: 18.5% (5/27) versus 25.9% (7/27) on control; risk difference -7.4 percentage points (95% CI -29.5 to 14.7), risk ratio 0.71 (0.26–1.97); unadjusted two-proportion z-test p = 0.513.

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.

Percent Weight Change

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Health Education + Nicotine Replacement: mean 1.79 versus 1.47 on control; difference 0.32 (95% CI -1.39 to 2.03), standardized effect d = 0.11; z-test p = 0.713.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Health Education + Nicotine Replacement and the control. The interval gives the range of effects that remain compatible with the data.

The registry posts one secondary outcome: percent weight change at post-treatment. Its unadjusted comparison does not provide strong evidence of a group difference, and its confidence interval includes zero. The result is uncertain rather than evidence that the groups had identical weight change. The outcome provides a related descriptive perspective on the trial’s focus on weight concerns, but it does not replace the primary smoking-abstinence endpoint.

The secondary result does not establish whether the weight-focused cognitive behavioral content changed weight outcomes, nor does it explain the primary abstinence comparison. The two outcomes address different questions and have different measurement scales. A secondary outcome may help characterize the pattern of results, but it cannot by itself confirm or overturn the primary finding. The registry record does not report a formal analysis linking weight change to abstinence or testing whether one outcome mediates or modifies the other.

Secondary results generally carry less evidential weight than a prespecified primary result because they may be exploratory and can be affected by the number of outcomes examined. The registry record does not report a multiplicity adjustment or a detailed hierarchy for outcome testing. Its secondary analysis is also listed without reported formal analyses, and the number of observations differs between the posted arms. The reason for that difference is not reported in the registry record. These features limit how confidently the secondary comparison can be interpreted, especially if it is considered apart from the primary result and the uncertainty around both estimates.

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

• Percent Weight Change

9. Statistical Interpretation

10. Statistical Methods Explained

The posted outcomes include a binary primary endpoint and a continuous secondary endpoint. The primary endpoint is a count of participants meeting the abstinence definition. Percent weight change is reported as a group mean with a standard deviation. The comparisons use different statistical summaries because the outcomes have different data types.

How should a binary outcome comparison be read?

For a binary outcome, each participant either meets the endpoint definition or does not. The event counts and the number of participants assessed in each group describe the observed data. A risk is the proportion meeting the endpoint in a group. The registry provides those group-level proportions as 0.259 for cognitive behavioral treatment and 0.185 for health education. These are descriptive estimates for the posted primary outcome, not guarantees of the underlying rates in a wider population.

The risk difference expresses the difference between the two group risks on an absolute scale. The reported comparison is health education relative to cognitive behavioral treatment, so its sign reflects the ordering of those groups. A value of zero would correspond to equal observed risks. The risk ratio compares the risks as a relative measure, while the odds ratio compares the odds of meeting the endpoint. Relative measures can look different in scale from an absolute difference and should not be interpreted as separate outcomes. For these data, the registry reports a risk difference of -0.074, a risk ratio of 0.714, and an odds ratio of 0.649.

What does the unadjusted p-value tell us?

A p-value describes how unusual results at least as discrepant as the observed result would be under a specified statistical model in which the comparison has no effect. It is not the probability that the null hypothesis is true, and it does not measure the probability that a result will be replicated. The primary comparison has an unadjusted p-value of 0.513. The registry record does not report enough detail to identify every modeling or testing choice behind the posted comparison. The p-value alone cannot indicate whether the treatment difference is important or whether the trial was capable of estimating it precisely.

Unadjusted means that the reported p-value has not been adjusted for multiplicity. The record does not report a multiplicity strategy. When several outcomes or comparisons are examined, repeated testing can increase the chance of at least one apparently notable result by chance. That general concern does not make any particular result invalid, but it is relevant when interpreting secondary results alongside the primary outcome.

How should a mean difference be read?

For the continuous weight-change outcome, a mean is the average value within a group. The standard deviation describes variation among observations around that group mean; it is not the uncertainty interval for the mean. The registry reports a standard deviation of 2.9 in the cognitive behavioral treatment group and 2.8 in the health education group. The reported mean difference is 0.32, calculated as the health education mean relative to the cognitive behavioral treatment mean. A value of zero would indicate equal group means. The unadjusted p-value is 0.713.

These group summaries do not describe every participant’s result. Means can conceal variation or unusual observations, and the registry record does not report distributions or additional summaries that would allow those features to be assessed. Nor does it report a formal analysis for the secondary outcome. The posted comparison is therefore best read as a summary of the observed group means and their estimated difference, rather than as a full account of the analysis plan.

What is the role of a confidence interval?

A confidence interval gives a range of estimates compatible with the observed data under the statistical procedure used. In general, wider intervals represent less precision, while narrower intervals represent greater precision. An interval that includes the no-difference value does not prove that there is no difference. It indicates that the data do not rule out that value at the confidence level used. The registry record does not state the confidence level for the posted intervals, so it should not be inferred from the display alone.

For the primary outcome, the interval for the absolute risk difference includes zero and covers effects in either direction. The relative-measure intervals also include their no-association values. For the secondary outcome, the mean-difference interval includes zero. These intervals reinforce that the estimates are uncertain; they do not establish equivalence or show that clinically meaningful effects have been excluded.

What can and cannot be inferred about the analysis?

The registry identifies randomization and a parallel design, but does not report the details of sequence generation, allocation concealment, an intention-to-treat definition, a per-protocol analysis, covariate adjustment, or the handling of missing outcomes. It also does not report the original analysis plan. Statistical concepts such as confidence intervals and p-values describe how results are commonly interpreted in general; they do not fill in methods that are absent from the registry record.

The posted primary group counts match the group sizes listed for that outcome. The secondary outcome lists different group counts, and the record does not explain the reason. It is therefore not possible from the registry record to determine whether those observations reflect missing measurements, a defined analysis population, or another circumstance. The distinction matters because analysis choices and missing outcomes can affect both the estimate and its uncertainty.

11. Confidence Intervals and Precision

The primary risk-difference estimate is -0.074, and its confidence interval runs from -0.295 to 0.147. The interval includes zero, the value corresponding to no absolute difference, and extends to values on both sides of zero. The observed estimate is therefore not precise enough to establish the direction of the group difference. The relative estimates are also uncertain: the risk-ratio interval runs from 0.259 to 1.973, and the odds-ratio interval runs from 0.177 to 2.377. Both ranges include their no-association value.

For the secondary weight-change comparison, the reported mean difference is 0.32, with a confidence interval from -1.388 to 2.028. That range includes zero and includes differences in either direction. The interval is compatible with the observed estimate but also with a range of other values, so the mean difference should not be read as a precise estimate of the underlying contrast.

In general, confidence intervals communicate uncertainty around an estimate, conditional on the statistical method and its assumptions. A wide interval signals that the data leave many plausible values; an interval containing zero does not demonstrate equivalence or absence of an effect. The confidence level for the posted intervals is not reported in the registry record, so no confidence percentage should be assigned to them. The unadjusted p-values likewise do not resolve the uncertainty: they are not measures of effect size or precision.

Precision depends on the amount of outcome information and on variability, among other factors. For a binary outcome, the number of events contributes to how much information is available; for a continuous outcome, both group size and variation matter. The posted outcome counts and intervals illustrate that the estimates remain uncertain, but they do not by themselves identify the cause of that uncertainty. The registry record does not report a precision target or the original sample-size rationale.

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 for both posted outcomes; they are not total sample sizes or total event counts. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The target effect is a stated fraction of the observed effect. These are planning illustrations based on the observed effect, not the trial’s original design assumptions; those original assumptions are not reported in the registry record.

The 80% power column gives the planned number of participants per arm for a design with an 80% chance of detecting the specified effect under the stated assumptions, if that effect and those assumptions were correct. The 90% power column uses a higher target chance of detection, and therefore generally calls for more participants per arm. The rows planning for a smaller fraction of the observed effect require more participants, because smaller differences are harder to distinguish from random variation.

These figures are not observed power. They do not describe the probability that the completed trial found an effect, and they should not be used to reinterpret its p-value. They are planning scenarios that show how required group size changes with the assumed effect and target power. Because they use an effect estimated from the posted data, the estimates used for planning are uncertain as well. The calculations should be read as illustrations rather than as a sample-size recommendation or a reconstruction of the trial’s intended design.

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 = 0.259; treatment proportion p₁ = 0.185; average p̄ = 0.222.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.5879 = 1.1524.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.5856 = 0.4929.
4. n = (1.1524 + 0.4929)² / (-0.0741)² = 493.3, rounded up to 494 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 <- 0.259259259259259                          # control proportion
p1 <- 0.185185185185185                          # 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(1259466)
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 = 494 (80% power), 660 (90% power)
 75% of observed effect: n per arm = 904 (80% power), 1,210 (90% power)
 50% of observed effect: n per arm = 2,091 (80% power), 2,799 (90% power)
power.prop.test: 493.3 
Simulated power at n = 494 per arm: 0.803 (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

Multiplicity concerns arise when a study evaluates more than one outcome, comparison, time point, or analysis. In general, the more statistical tests that are considered, the greater the opportunity for a chance finding to appear notable. This is why a prespecified primary outcome and a clearly described testing strategy help readers distinguish confirmatory analyses from exploratory ones.

The registry identifies a primary abstinence outcome and one posted secondary outcome, percent weight change. It reports unadjusted p-values for the posted comparisons. A multiplicity adjustment or other strategy for controlling the interpretation of multiple tests is not reported in the registry record. The record also does not report the original statistical analysis plan, so the intended hierarchy of outcomes, planned contrasts, and any rules for interpreting secondary results are not known.

The registry does not report a missing-data method, a definition of the analysis population, or whether the primary analysis followed an intention-to-treat approach. For the primary endpoint, the posted outcome counts list 27 participants in each arm. For the secondary outcome, the listed arm counts are 26 and 18. The reason for this difference is not reported in the registry record. It should not be attributed to a particular cause, such as withdrawal, missing measurement, or exclusion, without further information.

These omissions matter because the analysis population and handling of missing outcomes can affect estimates and their uncertainty. For an abstinence endpoint, the treatment of participants without an observed verification result can alter the endpoint count. For a continuous outcome, the way unavailable measurements are handled can change the group means and comparison. The registry record does not specify how either issue was addressed. The posted results remain interpretable as the reported summaries, but the missing methodological detail limits assessment of robustness and of how closely the analyses followed any prespecified plan.

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 0% reporting threshold.

The posted safety fields list zero participants affected by serious adverse events and zero affected by other adverse events in each treatment group. These figures should be read as the registry’s reported counts for the listed safety categories and groups. They are not a detailed description of event types, timing, severity beyond the serious-event classification, or possible relationships to treatment. The list of top serious-event terms is empty.

Death counts are not reported in the registry record; the blank death fields should not be interpreted as zero deaths. The record also does not provide additional information about safety monitoring, event collection procedures, or whether the posted fields capture all events during the treatment and follow-up periods. The absence of reported affected participants in these fields is a statement about the posted safety data, not proof that no adverse events occurred under every definition or at every time.

Because both groups received the nicotine patch and different internet-administered content, these group summaries do not isolate safety outcomes attributable to any single component. They are descriptive registry figures and do not support broader conclusions about safety outside the recorded groups and observation period.

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

The posted primary data show 7 participants meeting the verified abstinence endpoint in the cognitive behavioral treatment group and 5 in the health education group. The estimated absolute difference favors the cognitive behavioral group in direction, but the interval is broad and includes no difference as well as differences in the opposite direction. The unadjusted p-value does not provide strong evidence against a no-difference comparison. The statistical result therefore does not establish a clear difference between the programs, and it also does not establish that they are equivalent.

The same caution applies to percent weight change. Its estimated difference is uncertain, and the interval includes zero. The registry record does not report a formal analysis of how weight change relates to abstinence, so the secondary result cannot explain the primary result or identify a mechanism for any observed group pattern.

The design compared two treatment packages that shared standard smoking cessation treatment and open-label nicotine patch treatment, with different additional internet-administered content. It can describe the contrast between those packages in this randomized trial, but it does not estimate the effect of the patch against no patch or compare either package with no treatment. The record does not provide evidence about long-term abstinence beyond the post-treatment primary assessment.

These findings are specific to the enrolled trial population and the outcomes recorded. The registry does not report enough information about participant characteristics, missing-data handling, or analysis populations to assess all aspects of generalizability and robustness. Statistical uncertainty should not be translated into a claim that an intervention works or does not work. The results show what was observed in the posted outcomes and how uncertain the estimated comparisons remain.

17. Why This Trial Matters Statistically

This trial is statistically notable for comparing two active treatment packages in a population described as smokers who were overweight or obese. Both groups received standard smoking cessation treatment and nicotine replacement, while the internet-administered additional content differed. That structure focuses the comparison on the added content rather than on treatment versus no treatment, but it also means the findings cannot isolate every component independently.

The primary endpoint is a clinically interpretable binary outcome with biological verification, yet the posted event counts are limited and the estimate has substantial uncertainty. The confidence interval communicates more than the direction of the point estimate: it makes clear that the data do not tightly pin down the size or direction of the difference. This is a useful example of why a non-small p-value should not be translated into proof of no effect, and why a favorable point estimate alone should not be treated as decisive.

The secondary outcome adds a different type of information, but its listed group counts differ and the registry record does not explain why. That illustrates the importance of reporting analysis populations, missingness, and prespecified methods alongside outcome summaries. Without those details, readers can describe the posted comparisons but cannot fully assess their analytic basis.

The registry also offers planning illustrations based on observed effects. Such figures can show how statistical planning changes when smaller effects are targeted, but they are not the original trial rationale and cannot substitute for a documented design calculation. Taken together, the record underscores the distinction between observed results, uncertainty, and prospective planning assumptions.

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 questions unanswered. It does not report participant characteristics in enough detail to assess the composition of the enrolled population beyond the adult, overweight or obese smoker description. The information available also does not establish how closely participants’ treatment use, adherence, or follow-up matched the intended program.

The record does not describe random-sequence generation or allocation concealment, and it identifies the trial as unmasked. It does not explain whether outcome assessors were masked or provide further detail on biological verification beyond the carbon monoxide criterion. These are limitations on what can be assessed from the registry record, not evidence that any particular procedure was or was not used.

The secondary outcome has different listed group counts from the primary outcome, and the reason is not reported in the registry record. Missing-data handling, analysis populations, adjustment for baseline variables, and the original analysis plan are also not reported. The record does not state a multiplicity strategy or confidence level for the posted intervals. These omissions make it difficult to assess how sensitive the estimates might be to analytic choices.

The primary abstinence assessment is at post-treatment, with no longer-term primary result reported in the registry. The sample-size illustrations are based on the observed effects and do not establish the trial’s original planning rationale. Finally, the comparisons are between treatment packages that share core treatment and nicotine replacement, so they do not separately estimate the contribution of each shared or differing component.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Internet-Administered Smoking Cessation Treatment for Overweight and Obese Smokers — NCT01259466.
• Registry record last updated 2015-09-28; status last verified 2015-08.
• Results first posted 2015-09-28.
• 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.

22. Record Summary

NCT01259466 is a completed, randomized, parallel-group trial sponsored by Yale University, with no masking listed in the registry. It enrolled 54 participants and compared internet-administered smoking cessation treatment with cognitive behavioral therapy for weight concerns against treatment with general health education. Both groups received open-label 21 mg transdermal nicotine patch treatment.

The primary endpoint was verified continuous abstinence during the last 14 days of treatment, assessed post-treatment at 12 weeks. The posted counts were 7 participants in the cognitive behavioral group and 5 in the health education group. The comparison is uncertain, with an unadjusted p-value of 0.513 and an interval for the risk difference that includes zero. The single posted secondary outcome was percent weight change; its comparison also has an interval including zero. The registry record does not report the original analysis plan, missing-data methods, analysis populations, or multiplicity strategy.