Improving Adherence to Web-Based Cessation Programs: A Social Network Approach: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Improving Adherence to Web-Based Cessation Programs: A Social Network Approach (NCT01544153), a randomized na study. The primary outcome is Self-reported 30-day Point Prevalence Abstinence.

2. Clinical Question

3. Trial Design

The registry record describes a completed, randomized, single-masked, factorial study of web-based smoking cessation support. Its title is Improving Adherence to Web-Based Cessation Programs: A Social Network Approach, and the sponsor is Truth Initiative. The record lists phase as NA. The study started in 2012-02 and reached primary completion in 2015-12.

The four posted arms were WEB only, WEB+SN, WEB+NRT, and WEB+SN+NRT. WEB was the common program. The Social Network component was a behavioral intervention; NRT was also classified as behavioral in the registry record. The description states that the social network protocol was intended to integrate participants into an online community, and that the NRT component involved access to a 4-week supply of free product.

The listed group sizes for the primary outcome were 1337.0 for WEB only, 1323.0 for WEB+SN, 1313.0 for WEB+NRT, and 1317.0 for WEB+SN+NRT. The registry record describes the primary endpoint population as intent to treat. It does not report details about how participants were masked, how allocation was generated or concealed, adherence to the assigned components, or how outcome data were collected beyond self-report.

Although the design is labeled factorial, the posted primary comparisons are each combination versus WEB only. The record does not report factorial main-effect estimates or an interaction analysis. The listed comparisons therefore address the added-component combinations relative to the common WEB-only comparator, rather than establishing separate component effects or whether components interact.

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:

Analysis population for the primary outcome, as defined in the registry: Intent to treat

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: Includes baseline characteristics of participants who completed participation in the full study.

6. Primary Endpoint

The registry lists the primary outcome as Self-reported 30-day Point Prevalence Abstinence, measured over 9 months post-randomization.

The primary endpoint is self-reported 30-day point prevalence abstinence at 9 months post-randomization. It counts participants who answered “No” to the question asking whether they had smoked any cigarettes at all, even a puff, in the past 30 days. It is a count of participants, not a continuous measure of smoking frequency or duration of abstinence.

A point prevalence measure captures status during a defined recent period. It offers a direct, interpretable way to compare reported abstinence between randomized groups at a specified follow-up. It does not establish continuous abstinence throughout the time since randomization, and a self-reported response is not equivalent to biochemical verification. Whether biochemical verification was collected is not reported in the registry record.

The outcome is listed for an intent-to-treat population, which indicates that the registry record frames the primary outcome around randomized group assignment rather than only participants who adhered to an intervention. The registry record does not explain how missing responses were handled or whether every randomized participant was included in the posted outcome counts. Those details matter when interpreting a count of reported abstinence, since the outcome depends on participants providing a response and on the analysis approach to unavailable data.

7. Results Posted in the Registry

• WEB+SN: 11.0% (146/1323) versus 12.4% (166/1337) on control; risk difference -1.4 percentage points (95% CI -3.8 to 1.1), risk ratio 0.89 (0.72–1.10); unadjusted two-proportion z-test p = 0.269.
• WEB+NRT: 13.9% (182/1313) versus 12.4% (166/1337) on control; risk difference 1.4 percentage points (95% CI -1.1 to 4.0), risk ratio 1.12 (0.92–1.36); unadjusted two-proportion z-test p = 0.271.
• WEB+SN+NRT: 14.0% (184/1317) versus 12.4% (166/1337) on control; risk difference 1.6 percentage points (95% CI -1.0 to 4.1), risk ratio 1.13 (0.93–1.37); unadjusted two-proportion z-test p = 0.236.

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.

Self-reported 30-day Point Prevalence 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:
  • WEB+SN: 9.8% (129/1323) versus 12.3% (164/1337) on control; risk difference -2.5 percentage points (95% CI -4.9 to -0.1), risk ratio 0.79 (0.64–0.99); unadjusted two-proportion z-test p = 0.038.
  • WEB+NRT: 14.5% (190/1313) versus 12.3% (164/1337) on control; risk difference 2.2 percentage points (95% CI -0.4 to 4.8), risk ratio 1.18 (0.97–1.43); unadjusted two-proportion z-test p = 0.095.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically lower for WEB+SN than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between WEB+NRT and the control. The interval gives the range of effects that remain compatible with the data.

The registry record lists self-reported 30-day point prevalence abstinence at 3 months as a secondary outcome. Across the posted arm counts, the direction of the contrasts is not uniform: the social network-only combination has fewer reported abstinent participants than WEB only, while the two combinations containing NRT have more. The 3-month comparisons show a different pattern of statistical uncertainty from the primary 9-month results, including an unadjusted result for WEB+SN whose interval excludes zero. No comparison for the combined WEB+SN+NRT arm is listed for this secondary endpoint.

The secondary endpoint is related to the primary endpoint because it uses the same self-reported 30-day abstinence question, but it measures status at an earlier follow-up. It therefore provides a separate time-specific view, not an independent confirmation of the 9-month finding. A difference at one assessment does not establish a sustained pattern across follow-up, and the registry record does not report an analysis of change over time or a repeated-measures model.

Unadjusted secondary results carry less weight as confirmatory evidence when several outcomes or contrasts are considered. In general, examining multiple comparisons creates more opportunities for a nominally unusual result to occur by chance. Without a reported multiplicity plan, a single unadjusted p-value should be treated as exploratory rather than as definitive evidence. The registry record does not report a correction, outcome hierarchy, or prespecified rule for interpreting the secondary findings. The 3-month pattern can inform questions for further study, but it does not override the primary outcome or resolve the uncertainty in its comparisons.

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

• Self-reported 30-day Point Prevalence Abstinence

9. Statistical Interpretation

10. Statistical Methods Explained

Comparisons in the registry record are expressed as risk differences. In general, a risk difference is the difference between the observed proportions with an outcome in two groups. It is an absolute-scale measure: it describes how far apart the groups are in outcome frequency, rather than expressing one group’s outcome relative to the other as a ratio. A positive estimate in the posted contrasts indicates a higher observed abstinence proportion in the named combination arm than in WEB only; a negative estimate indicates a lower observed proportion. The posted comparison also includes a confidence interval and an unadjusted p-value.

What does the confidence interval convey?

In general, a confidence interval represents uncertainty about an estimated effect under the statistical procedure used to construct it. A narrower interval indicates greater precision; a wider interval indicates less precision. When an interval for a risk difference includes zero, the data are compatible with no difference under that interval procedure, as well as with values on either side of zero. It does not establish that the groups are identical. The registry record does not report the method used to calculate the primary confidence intervals.

How should the p-values be read?

The posted p-values are marked unadjusted. In general, a p-value describes how unusual data at least as incompatible with a specified null hypothesis would be if that null hypothesis and the test assumptions were true. It is not the probability that the null hypothesis is true, nor a measure of clinical importance. A p-value alone does not show the range of effects compatible with the data; the estimate and interval provide complementary information. Because the values are unadjusted, they do not account for the fact that the record lists multiple comparisons and outcomes.

What does randomized assignment contribute?

Randomization is intended to make assigned groups comparable on average at the start of a study, including with respect to factors that were not measured. This supports interpretation of between-group contrasts, subject to the conduct of the trial and the analysis. The registry record identifies the study as randomized but does not report the sequence-generation or allocation-concealment procedures. It also does not report baseline characteristics or an adjusted analysis. The posted comparisons should therefore be described as reported group contrasts, not as evidence that every possible source of bias has been eliminated.

What is distinctive about the factorial label?

A factorial design can investigate more than one intervention component and, when appropriately analyzed, can estimate component effects and whether components work differently in combination. In this record, the four arms correspond to WEB alone, WEB with a social network intervention, WEB with NRT, and WEB with both additions. However, the listed comparisons are each added-component arm against WEB only. The registry record does not report estimates for the social network component averaged across NRT assignments, for NRT averaged across social network assignments, or for an interaction between the components. A factorial label by itself does not establish that those effects were analyzed or that the reported contrasts answer those questions.

What is meant by intent to treat?

In general, an intent-to-treat analysis seeks to retain participants in the groups to which they were randomized, regardless of adherence or intervention uptake. This preserves the comparison based on assignment and can reflect the effects of offering an intervention under the study conditions. The primary outcome is labeled intent to treat in the registry record, but the record does not specify the exact analysis population, how missing outcome data were treated, or whether any participants were excluded from the posted counts. The label should not be taken as a substitute for those implementation details.

Which analysis details remain unavailable?

The registry record lists no reported analyses for the primary outcome, and its listed analyses count is 0. It nevertheless posts outcome counts and comparison statistics. The specific statistical model, any covariate adjustment, handling of missing data, multiplicity procedure, and prespecified analysis plan are not reported in the registry record. The reported p-values are unadjusted, so the findings should be read as individual contrasts rather than as results protected by a stated family-wide error control procedure. No claim about interim analyses, sample-size justification, or stopping rules can be made from the record.

11. Confidence Intervals and Precision

The primary risk-difference intervals are broad enough to include zero for all three comparisons with WEB only. This means the posted estimates do not pinpoint a single direction or size of difference. For WEB+SN, the estimated direction is negative; for WEB+NRT and WEB+SN+NRT, it is positive. In each case, the uncertainty interval also allows values consistent with no difference. The intervals therefore do not support a confident ranking of the three combinations on the primary endpoint.

Confidence intervals are useful because they show a range of effects compatible with the data under a statistical procedure, rather than reducing the comparison to a single estimate or a thresholded p-value. Their interpretation depends on the method and assumptions used to construct them. The specific interval method is not reported in the registry record. The posted risk-difference estimates and intervals are unadjusted comparisons; no adjusted intervals are listed.

Precision is also tied to what the outcome measures. These intervals concern self-reported 30-day abstinence at 9 months post-randomization, not continuous abstinence or an objectively verified smoking measure. They do not describe uncertainty for outcomes or follow-up times that are not included in these comparisons. The listed counts and group sizes give context for the estimates, but the registry record does not report missing-data handling, which limits assessment of how unavailable responses may affect precision or interpretation.

For the secondary outcome at 3 months, the posted WEB+SN interval excludes zero, while the intervals for WEB+NRT include zero. Those are unadjusted secondary comparisons and should be interpreted cautiously in light of multiple outcomes and contrasts. The record does not report a multiplicity adjustment or a hierarchy that would make a secondary finding confirmatory.

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 sample-size planning figures are illustrations based on the observed effects, not the trial’s 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. Each scenario considers an effect equal to the stated fraction of the observed effect. The trial’s own original sample-size justification and assumptions are not reported in the registry record.

For these binary outcomes, the planning figures are participants per arm, not total participants across both arms and not total events. The 80% power column means that, under the stated assumptions and for the effect used in that scenario, a study with the listed participants per arm would have an 80% chance of rejecting the null hypothesis if that effect were the true effect. The 90% power column expresses the corresponding planning target for a 90% chance. These are design concepts, conditional on the assumed effect and statistical model; they are not guarantees about the result of a future study.

The scenarios using 75% or 50% of the observed effect assume smaller effects than the scenario using 100% of the observed effect. Smaller effects are harder to distinguish from random variation, so they require more participants per arm to reach the same planned power under the stated assumptions. The figures also depend on the observed effect used as their starting point, which is uncertain and may not represent the effect in another study.

These calculations are not observed power. Observed power is not a useful substitute for reading the estimate and its confidence interval after a study has been completed. Here the planning figures answer a prospective question: what per-arm enrollment would be needed under a set of stated assumptions to target a chosen power for a specified fraction of the observed effect? They do not change the uncertainty in the trial’s posted results.

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 = 0.124; treatment proportion p₁ = 0.110; average p̄ = 0.117.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.4550 = 0.8918.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.4549 = 0.3828.
4. n = (0.8918 + 0.3828)² / (-0.0138)² = 8,526.8, rounded up to 8,527 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 <- 0.12415856394914                          # control proportion
p1 <- 0.110355253212396                          # 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(1544153)
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 = 8,527 (80% power), 11,415 (90% power)
 75% of observed effect: n per arm = 15,353 (80% power), 20,553 (90% power)
 50% of observed effect: n per arm = 34,978 (80% power), 46,825 (90% power)
power.prop.test: 8526.8 
Simulated power at n = 8,527 per arm: 0.800 (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 record lists a primary outcome, a secondary outcome at a different follow-up, and multiple arm comparisons. The p-values attached to the comparisons are unadjusted. The registry record does not report whether a multiplicity strategy was prespecified, such as a hierarchy among hypotheses or an adjustment for the family of comparisons. Without such information, individual p-values should not be interpreted as controlling the chance of false-positive findings across all tested outcomes and contrasts.

Missing-data handling is not reported in the registry record. The primary outcome is described as intent to treat, but this label does not reveal how participants without a response at follow-up were treated in the analysis. The record does not state whether missing responses were classified as smoking, excluded, imputed, or handled through another method. It also does not report the amount or pattern of missing outcome data. These omissions limit assessment of whether the posted counts represent all randomized participants or how nonresponse could affect the comparisons.

The registry record does not report a detailed analysis population beyond the intent-to-treat label for the primary endpoint, nor does it provide a per-protocol analysis or a sensitivity analysis for missing data. It lists no reported analyses for the primary or secondary outcome. The exact analysis plan, covariate adjustments, interim analyses, and the trial’s original sample-size justification are not reported in the registry record. Consequently, the posted statistics can be described, but their relationship to a prespecified analysis plan cannot be assessed from this record alone.

These reporting gaps do not establish that a particular method was or was not used in the conduct of the study. They mean only that the registry record does not document it. The unadjusted contrasts and their uncertainty remain interpretable as posted, while claims about multiplicity control, missing-data robustness, or consistency with a prespecified plan would require information not reported in 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 0% reporting threshold.

Most frequent non-serious adverse event terms

The registry record lists serious adverse events as affecting 0 participants in each of the four groups. The serious-event populations at risk are listed as 1337 for WEB only, 1324 for WEB+SN, 1314 for WEB+NRT, and 1317 for WEB+SN+NRT. The registry record does not list serious adverse event terms.

For other adverse events, the record lists 0 affected participants in WEB only, 0 in WEB+SN, 4 in WEB+NRT, and 0 in WEB+SN+NRT. The populations at risk for these figures are listed as 1337, 1324, 1314, and 1317, respectively. Death counts are not reported in the registry record.

These are registry-reported counts and should not be read as proof that no other events occurred or that the interventions have equivalent safety. The record does not describe event definitions, ascertainment methods, severity categories for other events, or the observation period for safety reporting. It also does not provide comparative statistical analyses of adverse events. The figures therefore describe what is entered in the registry record, with important limits on interpretation.

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

The posted primary results describe how many participants in each randomized group reported no smoking during the 30 days before the 9-month assessment. They show different observed counts across the four groups, but the three comparisons with WEB only have confidence intervals that include zero and unadjusted p-values of 0.269, 0.271, and 0.236. The estimates therefore remain uncertain, and the record does not establish a clear difference on this endpoint between any of the added-component combinations and WEB alone.

This does not mean the groups have been shown to be equivalent. Establishing equivalence would require a defined margin and an analysis designed to evaluate whether the interval falls within that margin; such a framework is not reported. Nor do the results establish that a difference is impossible. The intervals express uncertainty, and the exact clinical importance of differences cannot be judged from statistical significance alone.

The endpoint is self-reported point prevalence abstinence, not continuous abstinence. It records status during the past 30 days at a single follow-up, rather than whether participants remained abstinent throughout the study. The registry record does not report biochemical verification. The results also do not isolate the separate effects of the social network protocol and NRT, or their interaction, because the posted primary contrasts are each combination against WEB only.

The findings apply to the reported study groups and outcomes. They do not establish the effect of the website or its components in other populations, settings, or intervention formats. The record does not provide enough information to assess missing-data handling, multiplicity control, or the full prespecified analysis plan. Those gaps counsel against extending the interpretation beyond the specific, self-reported outcome comparisons recorded at the stated follow-up.

17. Why This Trial Matters Statistically

This trial is statistically informative because it places several combinations of web-based cessation support within one randomized, factorial design. The common WEB-only comparator helps frame the specific contrasts of interest: adding social network support, adding NRT, or adding both. The design label also raises a distinct statistical question about whether components have separate or interacting effects, but the registry record posts only combination-versus-control comparisons.

The primary comparisons illustrate why an effect estimate, its interval, and a p-value should be considered together. The observed directions differ across arms, while the intervals include zero and the unadjusted p-values do not indicate clear evidence of a difference for these comparisons. The data therefore invite careful attention to uncertainty rather than a simple ranking based on the counts alone. A non-significant result is not evidence of equivalence, and a directionally favorable estimate is not by itself proof of a difference.

The record also shows how interpretation can be affected by reporting details. The outcome is self-reported, missing-data methods are not reported, and the analysis record does not specify multiplicity handling. The secondary endpoint has a different pattern from the primary results, but its unadjusted status and timing make it an exploratory complement rather than a definitive resolution. Keeping these distinctions explicit helps prevent a single isolated finding from carrying more weight than its design and uncertainty support.

Finally, planning illustrations based on observed effects demonstrate the dependence of future sample-size requirements on the effect one aims to detect. Smaller target effects call for more participants per arm under the stated assumptions. Those illustrations do not substitute for the trial’s unreported original design rationale, nor do they measure the probability that the completed trial found a true effect.

18. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The primary endpoint is based on self-report. The registry record does not report biochemical confirmation, so the posted counts cannot be interpreted as objectively verified abstinence. The measure is point prevalence over the past 30 days at 9 months, not continuous abstinence or a full account of smoking behavior between assessments.

Important analysis details are not reported in the registry record. These include the amount and handling of missing outcome data, the statistical model and interval method, any covariate adjustment, the prespecified analysis plan, and any multiplicity strategy. The record labels the primary population intent to treat but does not explain how that population was implemented in the posted counts. No reported primary analyses are listed despite the presence of outcome counts and comparison statistics.

The factorial design is not fully represented by the posted contrasts. The primary results compare each added-component combination with WEB only, but do not report component main effects or an interaction analysis. The 3-month secondary outcome does not list a comparison for the combined social network and NRT arm. Thus the record does not permit a complete assessment of the component-specific questions suggested by the factorial arrangement.

The secondary finding for WEB+SN is unadjusted and arises among multiple outcomes and contrasts; the record does not document a plan to control multiplicity. The posted adverse event information is also limited: definitions, ascertainment procedures, safety observation period, and death counts are not reported. Finally, the trial’s original sample-size justification and assumptions are not reported, so the planning illustrations based on observed effects should not be mistaken for the rationale used to design the completed study.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Improving Adherence to Web-Based Cessation Programs: A Social Network Approach — NCT01544153.
• Registry record last updated 2026-10-21; status last verified 2026-09.
• Results first posted 2017-02-10.
• 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 record describes a completed randomized, single-masked, factorial study sponsored by Truth Initiative, with enrollment of 5292. It compared WEB alone with WEB plus a social network intervention, WEB plus NRT, and WEB plus both additions. The primary outcome was intent-to-treat self-reported 30-day point prevalence abstinence at 9 months post-randomization.

All three posted primary risk-difference intervals include zero, and the unadjusted p-values are 0.269, 0.271, and 0.236. The record also lists the same abstinence measure at 3 months as a secondary outcome, with unadjusted comparisons. Missing-data methods, multiplicity handling, factorial component analyses, and the original sample-size justification are not reported in the registry record. Serious adverse event counts are listed as 0 in each group; other adverse events are listed for 4 participants in WEB+NRT and 0 in the other groups.