Spanish-Language Smoking Cessation Trial: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Spanish-Language Smoking Cessation Trial (NCT02945787), a randomized na study. The primary outcome is Percentage of Participants With Tobacco Abstinence at 6 Months.

2. Clinical Question

3. Trial Design

This was a randomized, parallel-group trial with no masking recorded. The registry lists the study as completed and gives enrollment as 1417. The brief description states that participants (N = 1400) recruited nationally would be randomized to two arms. The record does not explain the difference between that figure and the enrollment field. The study start date is 2016-10-24, and primary completion is recorded as 2020-07.

The intervention was an extended Spanish-language self-help program, described as 11 Stop Smoking for Good booklets and 9 My Story pamphlets adapted for Spanish-speaking smokers. The comparator was an NCI-produced Spanish-language self-help booklet, designated usual care. Both arms therefore received self-help materials; the comparison is between two approaches rather than between materials and no materials.

The registry identifies smoking cessation as the condition and describes the purpose as testing a Spanish-language version of a validated extended self-help intervention against usual care. Random allocation can support a fair comparison by reducing systematic differences between groups at assignment, although the record does not report the sequence-generation or allocation-concealment procedures. Masking is listed as none; who knew assigned group and whether outcome assessment was masked are not further described.

The primary outcome is the percentage of participants with tobacco abstinence at six months. The description says follow-up assessment packets were planned at six-month intervals through 24 months and that investigators would calculate seven-day point-prevalence abstinence at each assessment. The primary result posted concerns the six-month assessment. Further details of recruitment, participant flow, adherence, and the analysis population 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 Percentage of Participants With Tobacco Abstinence at 6 Months, measured over 6 months.

The primary endpoint is the percentage of participants with tobacco abstinence at six months. The registry describes the measure as seven-day point-prevalence abstinence: whether a participant reports abstinence from tobacco during the seven days before an assessment. This is a time-specific measure, not a count of all abstinent days since enrollment and not, by itself, a measure of continuous abstinence over the full follow-up period.

Point-prevalence abstinence is useful for comparing the share of participants meeting the same defined status at a scheduled assessment. In this trial, that common assessment is six months, and the reported percentages are 21.7% in extended self-help and 11.3% in usual care. The registry description also refers to assessments at six-month intervals through 24 months, but the primary result is the six-month measure; it should not be read as a summary of the later assessments.

Like other self-reported status measures, the meaning of the endpoint depends on how abstinence was asked about, how responses were verified, and how missing assessments were handled. Those operational details are not reported in the registry record. The endpoint gives a direct proportion-based comparison at a specified time, but cannot alone explain the reasons for a participant's reported status or establish how durable abstinence was beyond the assessment window.

7. Results Posted in the Registry

• Extended Self-help: 21.7% (155/714) versus 11.2% (79/703) on control; risk difference 10.5 percentage points (95% CI 6.7 to 14.3), risk ratio 1.93 (1.50–2.48); unadjusted two-proportion z-test p = <0.001.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary result is a binary outcome expressed as a percentage: at the six-month assessment, each participant is classified according to whether the specified seven-day abstinence status was recorded. A percentage makes the group outcomes readily interpretable as proportions meeting that definition. The comparison uses the two assigned groups, extended self-help and usual care.

What does randomization contribute?

In general, randomization assigns participants to groups by chance. Its statistical purpose is to reduce systematic differences in baseline characteristics between groups, so that a group contrast can more credibly be attributed to the assigned approaches rather than to deliberate selection. Randomization does not guarantee that groups will be identical, especially for characteristics not reported or measured, and it does not resolve missing outcome data or errors in measurement. The registry identifies allocation as randomized but does not report the sequence-generation method, concealment procedures, or stratification factors.

The study is described as parallel-group: participants were assigned to one of the two approaches, and the primary group comparison is made at the six-month assessment. Masking is listed as none. In general, lack of masking can matter when knowledge of assignment could affect participant behavior, reporting, or study conduct. The record does not say whether the people collecting or assessing outcomes were masked, nor does it describe any procedures to reduce reporting or assessment bias.

What is a risk difference?

The posted risk difference is 0.105, with a 95% confidence interval from 0.067 to 0.143. In general, a risk difference subtracts one group's event proportion from the other's, retaining the absolute scale of the outcome. For this trial, the event is recorded tobacco abstinence at the six-month assessment, and a positive estimate indicates a higher proportion in extended self-help than in usual care. The registry separately reports group percentages of 21.7% and 11.3%. These displayed quantities have their own rounding, so the risk-difference estimate should be quoted as posted rather than reconstructed from rounded percentages.

How do ratios differ from differences?

The risk ratio of 1.932 compares the group proportions as a ratio, and its reported interval runs from 1.504 to 2.481. The odds ratio of 2.19 compares odds rather than proportions, with reported interval limits of 1.632 and 2.939. In general, a ratio expresses a multiplicative contrast, whereas a risk difference expresses an absolute contrast. Odds and risks are distinct quantities; an odds ratio is not the same as a risk ratio and can appear farther from 1, particularly when outcomes are not rare. The risk difference is therefore helpful for understanding the absolute separation, while the ratios provide relative-scale descriptions.

What does the p-value say?

The unadjusted p-value is p < 0.001. In general, a p-value quantifies how unusual data at least as discrepant as those observed would be under a specified null model and its assumptions. It does not give the probability that the null model is true, the probability that the result occurred by chance, or the probability that an intervention will produce a particular outcome in a future setting. A small p-value is not a measure of effect size. For interpretation, the estimate, interval, endpoint definition, and study conduct should be considered together.

The record labels the p-value unadjusted. It does not report a model specification, covariate adjustment, stratification, or other analytic details. The comparison is therefore presented as an unadjusted estimate rather than as an adjusted treatment-effect model. The registry does not provide details about the statistical test used, the confidence-interval construction, or any assumptions checked for the analysis.

What remains unknown about the analysis?

The registry reports no posted secondary analyses and lists the number of analyses as 0. It does not report participant flow by assessment, the number with available six-month outcomes, an intention-to-treat or per-protocol definition, imputation methods, or sensitivity analyses. Those omissions limit assessment of how incomplete follow-up or deviations from assigned intervention may have affected the reported percentages. Randomization supports the initial comparison, but interpretation of the endpoint still depends on outcome availability and analysis choices. These details are not reported in the registry record.

The result is a six-month comparison of a binary endpoint. In general, binary outcomes do not require modeling an unbounded count distribution, but their analysis still depends on a defined denominator, outcome ascertainment, and assumptions behind the estimate and its interval. Here, the arm records list 714 participants for extended self-help and 703 for usual care, while the posted outcome information does not explain how missing assessments, if any, were treated. The record also does not describe subgroup analyses or whether any were planned.

10. Confidence Intervals and Precision

The posted risk-difference estimate is 0.105, with a 95% confidence interval from 0.067 to 0.143. The interval gives a range of values reasonably compatible with the observed data under the method's assumptions. In repeated use of the same interval procedure under its assumptions, intervals constructed in this way would contain the fixed underlying quantity at the stated confidence rate. It is not a statement that there is a 95% probability that this particular interval contains the true effect.

Both limits of the reported interval are above zero. This means the interval, as calculated, does not include a zero risk difference. The posted unadjusted p-value is p < 0.001, which is consistent with the interval indicating evidence of a group difference under the corresponding statistical framework. These measures answer related questions, but neither establishes that all sources of bias or uncertainty have been removed. The interval reflects sampling uncertainty under the analysis assumptions; it does not automatically account for outcome misclassification, missing data, lack of masking, or limited generalizability.

The confidence interval applies to the risk difference, not directly to the percentages in either arm. The registry also reports intervals for relative measures: the risk ratio is 1.932 with limits 1.504 and 2.481, and the odds ratio is 2.19 with limits 1.632 and 2.939. Each interval is on its own measure's scale. A reader should not compare the numerical widths of intervals across risk difference, risk ratio, and odds ratio as though they measured precision in identical units.

The record does not provide interval methods or adjusted estimates, and the posted comparison is identified as unadjusted. The limits should therefore be read as precision estimates for the reported comparison, not as protection against all limitations in study design or reporting. The percentages themselves are reported to one decimal place, while the risk difference and its interval are posted with greater numerical detail; quoting the posted estimates avoids deriving a new contrast from rounded percentages.

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 participants per arm, not totals across both arms and not total events. They are planning illustrations computed from the observed effect, not the trial's own original design assumptions; those original assumptions are not reported in the registry record. The stated 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 as a stated fraction of the observed effect.

For planning for 100% of the observed effect, the listed requirement is 196 participants per arm for 80% power and 262 participants per arm for 90% power. For planning for 75% of the observed effect, the listed figures are 327 participants per arm for 80% power and 437 participants per arm for 90% power. For planning for 50% of the observed effect, the corresponding figures are 683 participants per arm for 80% power and 913 participants per arm for 90% power.

In general, power is the chance that a study will meet its specified statistical criterion if a particular effect is truly present and the planning assumptions hold. The 80% and 90% columns therefore describe alternative target chances for detecting the assumed effect under the stated calculation, not probabilities that the trial result is correct. A 90% target requires more participants than an 80% target for the same assumed effect. Smaller effects are harder to distinguish from random variation, so the planning figures increase as the assumed fraction of the observed effect becomes smaller.

These calculations use the observed effect as a planning reference and are not observed power. They do not establish the study's original sample-size rationale, which is not reported in the registry record, and they do not revise the posted trial outcome.

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 = 0.112; treatment proportion p₁ = 0.217; average p̄ = 0.165.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.5246 = 1.0282.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.5193 = 0.4371.
4. n = (1.0282 + 0.4371)² / (0.1047)² = 195.8, rounded up to 196 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 <- 0.112375533428165                          # control proportion
p1 <- 0.217086834733894                          # 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(2945787)
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 = 196 (80% power), 262 (90% power)
 75% of observed effect: n per arm = 327 (80% power), 437 (90% power)
 50% of observed effect: n per arm = 683 (80% power), 913 (90% power)
power.prop.test: 195.8 
Simulated power at n = 196 per arm: 0.808 (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 identifies one primary outcome: percentage of participants with tobacco abstinence at six months. It also describes planned follow-up assessments at six-month intervals through 24 months, with seven-day point-prevalence abstinence calculated at each assessment. The information available does not specify whether later assessments were treated as secondary outcomes, how many comparisons were planned, or how the investigators intended to address multiple testing. No multiplicity adjustment or prespecified testing hierarchy is reported in the registry record.

The record lists four outcome measures, but no secondary results are posted, and the number of analyses is recorded as 0. This means the posted information does not permit a complete review of all outcome comparisons or of any adjustment across them. The six-month primary comparison should be interpreted as the reported result, without assuming that it was the only analysis performed or that multiplicity was handled in a particular way.

Missing-data methods and analysis populations are also not reported in the registry record. The six-month result is presented with group sizes in the arm records, but the record does not explain whether every randomized participant contributed an outcome, how unavailable follow-up assessments were classified, or whether any imputation or sensitivity analysis was used. It does not identify an intention-to-treat, per-protocol, or other analysis population. These details matter because a proportion depends on which participants are included in its denominator and on how unknown outcome status is treated.

The record does not report participant flow, reasons for missing assessments, adherence, or deviations from the assigned interventions. Without those details, it is not possible to assess whether the reported groups and outcome denominators correspond to all randomized participants or to a subset with available follow-up. Randomization is a feature of assignment, but it cannot by itself resolve uncertainty caused by missing outcome data or selective reporting.

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

The posted result indicates that the percentage meeting the registry's seven-day abstinence definition at six months was higher in the extended self-help arm than in the usual-care arm: 21.7% compared with 11.3%. The unadjusted risk difference is 0.105, with a 95% confidence interval from 0.067 to 0.143, and p < 0.001. This is evidence of a difference in the recorded group outcomes at that assessment under the analysis represented in the registry.

The endpoint is a short-window status at follow-up. It does not establish continuous abstinence from assignment through six months, and it does not describe abstinence beyond the seven days covered by the measure. Although follow-up assessments were described through 24 months, the result discussed is the six-month primary outcome. No later results are reported in the information available for this comparison, so the six-month finding cannot be treated as a result for the full follow-up period.

The comparison does not address extended self-help versus no intervention. The comparator received an NCI-produced Spanish-language booklet, and the record describes it as a credible self-help intervention. The observed contrast is between that approach and the longer Spanish-language program. The trial's result also does not establish that the same outcome would occur for people with different characteristics, in other settings, or under different implementation conditions.

The posted association should not be interpreted as proof that the intervention caused each individual outcome. Randomization strengthens the group comparison, but interpretation still depends on the conduct of the trial, endpoint measurement, follow-up, and analysis. Masking is recorded as none, and missing-data handling, analysis population, and outcome verification are not reported in the registry record.

These statistics describe an outcome comparison; they are not medical advice. They do not determine what any particular person should do, and they do not establish the broader public-health impact, cost, reach, or durability of the program. Those questions require information beyond the six-month percentage and its statistical uncertainty.

15. Why This Trial Matters Statistically

This trial is statistically notable for testing a Spanish-language version of an extended self-help intervention against a Spanish-language booklet comparator. The clinical question is framed around a defined binary endpoint at a scheduled assessment, which permits a direct comparison of the proportion meeting the same abstinence definition in each randomized group.

Several measures describe the comparison from complementary angles. The arm percentages, 21.7% and 11.3%, show the recorded outcome levels. The risk difference of 0.105 expresses the absolute-scale contrast, while the risk ratio of 1.932 and odds ratio of 2.19 express relative contrasts on different scales. The confidence intervals communicate sampling precision, and the unadjusted p-value gives a test-based measure of compatibility with a null comparison. Reading these together is more informative than relying on a single statistic.

The comparator matters to interpretation: usual care in this trial included a Spanish-language self-help booklet. The statistical contrast therefore evaluates the extended program relative to another self-help resource, rather than relative to no materials. The randomized design is relevant to causal interpretation, but lack of masking and unreported details about missing data, outcome ascertainment, and analysis populations constrain how fully the posted result can be evaluated.

The registry's description of repeated follow-up assessments also highlights the distinction between an outcome at a particular time and a longer-term pattern. The primary posted finding is at six months; it cannot stand in for unreported later assessments. The statistical interpretation should remain tied to the stated endpoint, comparator, and time point.

16. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

The registry record leaves important details of trial conduct and analysis unreported. It identifies random allocation but does not describe sequence generation, allocation concealment, or whether any balancing factors were used. Masking is listed as none, and the record does not say whether outcome assessors were masked. These omissions limit assessment of potential selection and measurement influences.

The primary endpoint is seven-day point-prevalence abstinence at six months. The record does not describe the exact wording or mode of assessment, whether abstinence was biochemically verified, or how conflicting or uncertain responses were handled. It also does not state how missing six-month assessments were treated, which participants were included in the analysis, or whether the displayed group sizes are outcome denominators. The posted outcome percentages should therefore be interpreted with those unknowns in mind.

The registry describes follow-up through 24 months, but the available result information does not include the later outcome results. No secondary results are posted, and the record lists 0 analyses. The original analysis plan, multiplicity procedures, covariate adjustments, and sensitivity analyses are not reported in the registry record. As a result, the full set of analyses and the robustness of the six-month estimate cannot be assessed from this record alone.

The study was unmasked and compared two self-help approaches, so its result is specific to the contrast and setting described. The record does not provide detailed participant characteristics, intervention uptake, adherence, or implementation information. Generalizability to populations or delivery settings not described in the record is therefore uncertain. Finally, the registry reports zero serious adverse events, other adverse events, and deaths for both groups; the record does not provide further detail on how these outcomes were collected or reported, so these entries should not be interpreted as a complete assessment of all possible risks.

17. Related Tutorials

18. Related Statistical Calculators

19. Sources

• ClinicalTrials.gov: Spanish-Language Smoking Cessation Trial — NCT02945787.
• Registry record last updated 2022-11-04; status last verified 2022-11.
• Results first posted 2021-09-16.
• 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.

20. Record Summary

The registry record describes a completed, randomized, parallel-group trial with no masking recorded. It compares extended Spanish-language self-help, consisting of Stop Smoking for Good booklets and My Story pamphlets, with an NCI-produced Spanish-language self-help booklet designated usual care. The registry lists enrollment as 1417; the brief description refers to N = 1400.

The primary outcome is the percentage with seven-day point-prevalence tobacco abstinence at six months. The reported percentages are 21.7% for extended self-help and 11.3% for usual care. The unadjusted risk difference is 0.105 (95% confidence interval 0.067 to 0.143), with p < 0.001.

The registry describes follow-up assessments through 24 months, but later outcome results are not reported in the information available. Analysis methods, missing-data handling, analysis populations, and multiplicity procedures are not reported in the registry record. The study status is completed.