Project Impact 2: A Culturally Tailored Smoking Cessation Intervention for Latino Smokers: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Project Impact 2: A Culturally Tailored Smoking Cessation Intervention for Latino Smokers (NCT02596711), a randomized phase 1, phase 2 study. The primary outcome is Intervention Feasibility & Acceptability.

2. Clinical Question

3. Trial Design

This was a randomized, parallel-group pilot study listed as Phase 1 and Phase 2. The registry identifies three groups: Health Education (HE), Culturally-Tailored (CT), and Culturally-Tailored With Adherence Enhancement (CT+AE). The trial was open-label, meaning masking was not used. The method used to generate the random allocation sequence, and whether allocation was concealed before assignment, are not reported in the registry record.

Participants in the HE group received general health education and handouts. The CT group received culturally tailored reading materials about culture, health, smoking, and quitting. The CT+AE group received those culturally tailored materials and additional talks related to smoking cessation. Each group attended 3 counseling sessions. The counseling-session descriptions indicate that sessions were audio recorded. The registry also lists nicotine patches, questionnaires, carbon monoxide testing, and behavioral materials or counseling among the interventions, but does not give enough detail to establish how each item was used in every group.

The primary outcome was average session satisfaction across 3 study visits, from Week 0 to Week 12. The record lists group sizes of 9 for HE, 8 for CT, and 8 for CT+AE for this outcome. Overall enrollment is listed as 26. The relationship between the enrollment total and the outcome group sizes is not explained in the registry record.

The study started on 2015-11-02, reached primary completion on 2017-08-22, and is listed as completed. The registry record does not report a detailed statistical analysis plan or the trial’s sample-size justification.

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: During baseline visit (prior to randomization), an expired carbon monoxide sample was collected using Bedfont Micro+Smokerlyzer.Additionally, participants able to become pregnant were required to take a routine hCG urine sample pregnancy test to rule out potential pregnancy.An assessment battery was also administered at the baseline visit.

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 Intervention Feasibility & Acceptability, measured over Averaged across 3 study visits (Week 0 to Week 12).

The primary endpoint was intervention feasibility and acceptability, represented by participants’ satisfaction with counseling sessions. After completing each session, participants anonymously rated satisfaction using an investigator-created 5-point Likert scale. The scale ran from 1, Extremely Unsatisfied, to 5, Extremely Satisfied. Higher scores indicated greater satisfaction.

For each participant, the session satisfaction ratings were averaged. The registry then reports treatment-group means and standard deviations, with the outcome averaged across 3 study visits from Week 0 to Week 12. This makes the endpoint a continuous score: it summarizes the level of satisfaction rather than counting participants who reached a particular threshold.

Satisfaction was used as a proxy measure of overall intervention acceptability and feasibility. It captures participants’ reported experience of counseling, which can help describe whether an intervention was acceptable to those who took part. It is not itself a measure of smoking cessation. The registry does not report a primary endpoint based on quitting, smoking reduction, or carbon monoxide results.

The reported means were 4.87 for HE, 4.71 for CT, and 4.83 for CT+AE. The corresponding standard deviations were 0.35, 0.48, and 0.4. These descriptive results place all three group means toward the upper end of the 1-to-5 scale, but do not establish whether the groups differ beyond chance variation.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is continuous because it is a numerical satisfaction score. Each participant’s mean was formed from session ratings on a 5-point scale, and the registry reports a mean and standard deviation for each treatment group. These statistics describe different features of the observed scores: the mean locates the group’s average response, while the standard deviation describes how much individual responses varied around that average.

What does a mean tell us?

In general, a mean is the arithmetic average of observations. It provides a compact description of the group but can hide differences between participants. For this endpoint, a mean near the top of the scale indicates that the average rating was close to Extremely Satisfied. It does not mean that every participant gave a high rating, and it does not indicate how many participants chose any particular response.

What does the standard deviation tell us?

In general, a standard deviation measures spread among observations in the group. A smaller standard deviation indicates that scores were more clustered around the mean; a larger one indicates more variation. It is not a measure of uncertainty in the estimated mean. Uncertainty in a mean or in a difference between means is usually conveyed with a confidence interval or an inferential model. No confidence intervals for the primary endpoint are reported in the registry record.

Why are there no two-group calculations?

The study has three treatment groups, while the registry’s available comparison calculation is not estimable for a two-arm comparison of this continuous endpoint. The registry record does not provide inferential analyses for the group differences. Thus, the reported means and standard deviations should be read as descriptive summaries, not as results of a statistical test. No recalculated contrast is reported, and no sponsor analysis is available in the record to take precedence over a recalculation.

What would a confidence interval add?

In general, a confidence interval gives a range of values compatible with the data and the assumptions of a specified statistical method. For a difference in means, it would help show the uncertainty in the estimated contrast, rather than only its direction or point estimate. A confidence interval would not by itself establish that a difference is important in practice, and its interpretation depends on the analysis and design. Because the registry does not report such intervals or the relevant analysis, the precision of between-group differences cannot be judged from the posted outcome summaries.

Why does the design matter?

Random allocation is intended, in general, to make treatment groups comparable on average with respect to factors that could influence an outcome. With small groups, chance imbalances can remain, and the registry’s group summaries do not show participant-level characteristics. The record identifies the study as randomized but does not report how the sequence was generated or whether assignment was concealed. It is open-label, so participants and counselors were not masked to group assignment according to the registry entry. Satisfaction is self-reported, and knowing the counseling approach could be relevant to how participants rate it; the registry does not assess the possible impact of this issue.

The outcome was collected after sessions and then averaged for each participant across the study period. Averaging repeated ratings can give a single summary of satisfaction over time, but it may conceal changes from one visit to another. The registry reports the averaged endpoint and does not provide visit-specific results, the number of ratings contributing to each participant’s mean, or a method for handling unavailable ratings.

More generally, statistical methods should match the outcome, design, and analysis question. A comparison across three groups could be addressed with an appropriate model or a set of planned contrasts, with uncertainty estimates and a stated approach to multiple comparisons. However, the specific statistical model, contrast definitions, covariate adjustments, assumptions, and multiplicity procedure are not reported in the registry record. It would be inappropriate to infer that any particular method was used.

Over-dispersion is a general concern for count outcomes when observed variability exceeds what a simple count model expects. It is not the central feature of this primary endpoint, which is a continuous satisfaction score. For continuous scores, relevant considerations can include the score distribution, variation between participants, repeated observations, and the handling of incomplete data. The registry does not report diagnostic checks or details of a model addressing these considerations.

Finally, sample-size calculations are planning tools, not evidence about observed treatment effects. The registry’s comparison information does not support a two-arm calculation for this continuous endpoint. Any planning illustration based on an observed effect would not be the trial’s original design justification, and such a calculation would not represent observed power. The trial’s own sample-size rationale is not reported in the registry record.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("Health Education (HE)", "Culturally-Tailored (CT)", "Culturally-Tailored With Adherence Enhancement (CT")
n   <- c(9, 8, 8)
m   <- c(4.87, 4.71, 4.83)
sp  <- c(0.35, 0.48, 0.4)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Health Education (HE)  9  4.870  0.350  4.601  5.139
CARM  Culturally-Tailored (CT)  8  4.710  0.480  4.309  5.111
CARM  Culturally-Tailored With Adherence Enhancement (CT  8  4.830  0.400  4.496  5.164

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 3 outcome measures, but no secondary outcome results are posted. The primary endpoint is session satisfaction, and the record describes it as an average across 3 study visits. It does not report whether multiple group contrasts or repeated-visit analyses were planned, or how any multiplicity from testing several outcomes or contrasts would be handled. No correction or other multiplicity strategy is reported in the registry record.

There is no reported account of missing primary-outcome ratings, participant withdrawals, or reasons for missing data. Although the record gives outcome group sizes of 9, 8, and 8, it does not explain whether these represent all randomized participants, participants with complete satisfaction ratings, or another analysis population. The record lists enrollment as 26, but does not reconcile that total with the outcome group sizes.

The method used to calculate a participant’s average when some session ratings were unavailable is not reported in the registry record. Nor does the record describe imputation, complete-case analysis, sensitivity analyses, or other approaches to missing observations. These details matter because the results could depend on which participants contributed data and how incomplete ratings were handled.

Definitions of intention-to-treat, per-protocol, or safety populations are not reported in the registry record. The registry identifies randomized assignment, but does not state which population was used for the primary outcome summaries. Consequently, the posted descriptive values cannot be assigned to a more specific analysis population than the reported group sizes.

12. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

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 registry lists serious adverse events for each group as 0: among 9 participants at risk in HE, 8 in CT, and 8 in CT+AE, no serious adverse events were reported. Deaths were also listed as 0 in each group. The serious-event terms list is empty.

Other adverse events affected 3 participants in HE, 1 in CT, and 0 in CT+AE. These are counts of participants affected, as recorded in the registry. The record does not give the types of these other events, their severity, timing, or whether investigators considered them related to study interventions. Those details are not reported in the registry record.

Zero reported serious events is a descriptive observation from this study, not proof that serious events cannot occur. The trial’s enrollment was 26, and the group-specific numbers at risk were limited. The registry’s safety summary does not provide a statistical comparison among groups or enough detail to assess differences in event risk. These figures should be read as event reporting within the recorded study, not as a general safety estimate or a causal conclusion.

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

The primary result describes participants’ satisfaction with counseling, not whether participants quit smoking. Average satisfaction scores were 4.87 in HE, 4.71 in CT, and 4.83 in CT+AE on a scale from 1 to 5, where higher values mean greater satisfaction. The corresponding standard deviations were 0.35, 0.48, and 0.4. These descriptive results suggest that the group averages were toward the high end of the scale; they do not show how every participant responded.

The registry does not report statistical tests or confidence intervals for differences among groups. Therefore, it is not possible from the posted results to determine whether the observed mean differences are compatible with chance variation, or how precisely any between-group contrast was estimated. The numerical ranking of the averages does not establish that one counseling approach was superior on satisfaction.

The endpoint was used as a proxy for acceptability and feasibility. Participant satisfaction can inform whether counseling was well received by those who provided ratings, but it is not a direct measure of intervention delivery, adherence, or smoking cessation. The registry does not post outcome results demonstrating whether participants stopped smoking or changed their smoking behavior.

The study’s pilot designation and enrollment of 26 provide context for the limited amount of information available. The findings are descriptive and specific to the participants and interventions recorded in this trial. They should not be interpreted as a definitive comparison of the three approaches or as proof that the results would generalize to other groups or settings.

The safety summary likewise has a limited interpretation: no serious adverse events or deaths were reported in the listed groups, while other adverse events affected some participants in two groups. The registry does not provide event descriptions or attribution. Neither these counts nor the satisfaction averages establish a causal effect of any intervention.

14. Why This Trial Matters Statistically

This trial illustrates why the endpoint must guide interpretation. The primary measure was satisfaction with counseling, selected as a proxy for feasibility and acceptability. A high average on that measure describes participants’ reported experience; it does not answer a different question such as whether smoking cessation occurred. Keeping the outcome aligned with the research question prevents a favorable score on one measure from being treated as evidence about an unreported outcome.

It also shows the distinction between descriptive summaries and inferential comparisons. Means and standard deviations provide useful information about the observed scores in each group. Without confidence intervals, tests, or a stated model for group comparisons, however, they do not quantify uncertainty in contrasts or establish a difference between interventions. That distinction is especially important when the outcome group sizes are 9, 8, and 8.

The registry identifies randomization and an open-label design, but does not report the allocation method or detailed analysis procedures. This makes clear that a trial label alone does not convey all design and analysis details needed to assess how a result was generated. Reporting the planned contrasts, analysis population, missing-data approach, and uncertainty estimates would help readers interpret the findings more fully.

Finally, pilot studies can contribute descriptive information about participant experience, but their results should be read within the scope of what was measured and reported. In this record, the available primary results address session satisfaction, while secondary results and inferential analyses are absent. The statistical lesson is to distinguish what the observed summaries describe from conclusions that would require additional outcomes or analyses.

15. 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 outcome is an investigator-created satisfaction scale. The registry gives its 5-point response range and interpretation, but does not report evidence about its measurement properties, validation, or reliability. That limits assessment of how consistently or comprehensively the scale captures acceptability.

The outcome is based on anonymous ratings after counseling sessions and averaged across 3 study visits. The registry does not report individual ratings, visit-specific averages, or how many session ratings contributed to each participant’s summary. Averaging can conceal variation over time or differences between sessions. The handling of incomplete ratings is also not reported in the registry record.

The outcome group sizes are 9 for HE, 8 for CT, and 8 for CT+AE, while total enrollment is listed as 26. The record does not explain the difference between those counts. It also does not define the population used for the reported summaries or describe participant flow and missing outcome data.

Although the study is described as randomized, the randomization procedure and allocation concealment are not reported. The trial was open-label, and satisfaction was participant-reported. The record does not assess whether awareness of group assignment influenced ratings. It also does not report a statistical analysis plan, inferential comparisons, confidence intervals, or a sample-size justification.

Finally, the registry’s primary endpoint concerns satisfaction as a proxy for acceptability and feasibility. The record does not provide results for smoking cessation or other secondary outcomes, and it does not report enough detail to judge whether the recorded intervention components were delivered consistently across participants. These limitations constrain conclusions to the descriptive satisfaction and safety information that is posted.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Project Impact 2: A Culturally Tailored Smoking Cessation Intervention for Latino Smokers — NCT02596711.
• Registry record last updated 2020-03-10; status last verified 2020-03.
• Results first posted 2020-03-10.
• 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.

19. Record Summary

NCT02596711, Project Impact 2: A Culturally Tailored Smoking Cessation Intervention for Latino Smokers, is listed as a completed randomized, open-label, parallel-group Phase 1 and Phase 2 study. The sponsor is M.D. Anderson Cancer Center. The study started on 2015-11-02, and primary completion was recorded on 2017-08-22. Enrollment is listed as 26.

The three groups were Health Education, Culturally-Tailored, and Culturally-Tailored With Adherence Enhancement. The primary endpoint was average session satisfaction on an investigator-created 5-point scale, averaged across 3 study visits from Week 0 to Week 12. The reported group means were 4.87, 4.71, and 4.83, with standard deviations of 0.35, 0.48, and 0.4, respectively. No inferential analyses for the primary endpoint are reported.

The safety record lists 0 serious adverse events and 0 deaths in each group. Other adverse events affected 3 participants in HE, 1 in CT, and 0 in CT+AE. Details about those other events are not reported in the registry record.