The Impact of Cigarillo Warnings on Purchasing: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for The Impact of Cigarillo Warnings on Purchasing (NCT05434013), a randomized na study. The primary outcome is Average Total Number of Cigarillos Purchased.

2. Clinical Question

3. Trial Design

This was a randomized, parallel-group behavioral experiment with single masking. The registry identifies three cigarillo warning conditions: pictorial, FDA-proposed text-only, and Surgeon General text-only. It does not identify who was masked, nor does it report further details of the randomization procedure or allocation concealment.

Participants were cigarillo users ages 21-35 and completed the study in an online Experimental Tobacco Marketplace. Each arm description specifies six mock shopping trips and a weekly tobacco budget. Participants were asked to spend that budget, with single cigarillos available for mock purchase and the warning format assigned to the arm displayed on cigarillos. This setup permits comparison of choices made in a controlled, hypothetical marketplace task; it is not a report of purchases in a retail setting.

The registry records enrollment of 1578, a study start date of 2022-06-24, primary completion on 2022-07-21, and status as completed. The phase is listed as NA. Although the record describes the intended randomized comparison and outcome measures, it does not include posted primary outcome estimates or analysis results. The participant flow, exclusions after randomization, and numbers included in each outcome analysis 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 Average Total Number of Cigarillos Purchased, measured over Within the 20-minute survey.

The primary endpoint is the average total number of cigarillos purchased, measured in cigarillos. Participants were asked to make mock purchases of single cigarillos during six marketplace shopping trips, using a specified budget. The registry places the outcome within the 20-minute survey and describes the measure as the average number purchased during each shopping trip.

A purchase count provides a direct behavioral measure of demand in the experimental marketplace: it records how many cigarillos participants chose to add to their mock purchases under the assigned warning condition. Unlike a rating of perceived warning effectiveness, it concerns a choice in the shopping task itself. It remains a simulated choice, however, and the registry does not establish that it predicts purchasing outside the experiment.

The record identifies the outcome as a mean with standard deviation as its dispersion measure. It does not report the observed means, standard deviations, a comparison estimate, or a confidence interval. It also does not clarify the exact participant-level aggregation used to combine behavior across the repeated shopping trips. Those omissions prevent interpretation of the size and precision of any observed difference.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes a randomized, parallel-group comparison. Randomization is a method for assigning participants to study conditions by chance. General statistical rationale: random assignment can reduce systematic differences between groups at the start of a study, on average, while it does not guarantee that every participant characteristic is balanced in a particular sample. The record does not describe the random sequence generation, allocation concealment, or any checks of baseline balance.

What does the primary measure represent?

The primary measure is a mean of a continuous count outcome: the average number of cigarillos purchased in the marketplace task. The record identifies standard deviation as the measure of dispersion. General explanation: a mean gives a central summary of observed values, and a standard deviation describes how spread out individual values are around that mean. Reporting both can help readers understand not only the average but also the variability of participant choices. Neither measure is posted for the primary outcome in this registry record.

The task includes repeated mock shopping trips for each participant. Repeated observations from one person are generally related to one another, rather than behaving like independent observations from different people. General statistical rationale: an analysis of repeated measures should account for that within-person dependence or define a participant-level summary before comparing arms. The registry gives the average outcome description but does not report the precise aggregation, model, or variance estimation method used. The record also does not say whether the six trip-level counts were analyzed jointly or reduced to a single summary for each participant.

How would a comparison be interpreted?

A comparison among the warning formats could be reported as differences in mean purchase counts, with uncertainty around each contrast. General explanation: a confidence interval communicates the precision of an estimate and the values reasonably compatible with the data under the stated model. Its interpretation depends on the design and analysis assumptions. Since the registry does not post estimates or confidence intervals, precision and the direction of the primary comparisons cannot be evaluated.

There are three warning conditions, so analyses could involve more than one pairwise comparison or a broader test of group differences. General statistical rationale: testing multiple contrasts can increase the chance of finding at least one apparently unusual result by chance unless the analysis plan accounts for multiplicity. The registry does not report the planned contrasts, whether comparisons were adjusted for multiplicity, or whether a single overall test preceded pairwise tests. No particular comparison strategy should therefore be assumed.

What does over-dispersion mean for a count?

General explanation: count outcomes can vary more than a simple model assumes, especially when many observations are concentrated at one value while others are widely spread. This is called over-dispersion relative to that model. If present and ignored, uncertainty estimates may be inaccurate. A model appropriate for the count distribution, or a robust method for estimating uncertainty, may be considered depending on the data and design. The registry does not report the distribution of purchase counts, diagnostics for over-dispersion, or the model used for analysis. It is therefore not possible to determine whether over-dispersion was present or how it was handled.

What is the role of the planning assumptions?

The registry describes planning illustrations based on a fraction of the observed effect, a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It specifies that non-time-to-event illustrations are expressed as participants per arm. General explanation: such calculations estimate the sample size that would be needed under stated assumptions to detect a target effect with a chosen power. They are planning aids, not findings from the completed experiment and not observed power. The registry does not report an observed effect or numerical planning estimates, so those assumptions cannot be used to assess whether the actual study was adequately powered.

Finally, the registry identifies 14 outcome measures and records 0 analyses. It does not post the statistical analysis plan, model specification, tests, confidence intervals, p-values, or handling of missing data. These omissions limit reproducibility and prevent a statistical assessment of the trial's findings beyond the design and definitions recorded.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 14 outcome measures, including the primary purchase-count outcome and secondary measures concerning combusted and non-combusted tobacco, cigarillo intensity, cost-related indices, and rate of change in demand. Examining multiple outcomes or contrasts can make isolated findings harder to interpret unless the analysis plan specifies which tests are primary and how multiplicity will be addressed. The registry does not report a multiplicity procedure, a hierarchy of outcomes, or a prespecified set of pairwise comparisons. It records 0 analyses, so there are no posted results with which to assess this issue.

Missing-data handling is not reported in the registry record. The record does not state how incomplete shopping trips, survey noncompletion, or unavailable outcome measures were handled. It also does not report the number of participants with complete primary outcome data or whether any imputation or sensitivity analysis was used. These details matter because analyses based only on observed outcomes can be affected when missingness is related to participant behavior or study condition.

The analysis population is not reported in the registry record. There is no description of whether participants were analyzed according to randomized assignment, whether any participants were excluded after randomization, or how exclusions were determined. Although the record lists enrollment of 1578, that figure alone does not identify the analysis population for the primary or secondary outcomes. Without these details and the analysis results, readers cannot assess the extent to which the reported analysis, if any, followed the randomized design.

11. 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 0% reporting threshold.

The registry safety entries list 526 participants at risk in each warning group. For each group, the entries record 0 serious adverse events, 0 other adverse events, and 0 deaths. These are the posted registry figures; they do not describe the type of safety monitoring, the period covered by the entries, or how events were collected.

The study is described as an online experimental marketplace task involving mock cigarillo purchases and warning formats. The adverse-event entries should be read as registry-reported counts, not as a detailed safety analysis. The registry does not report definitions for serious or other adverse events, whether events were actively solicited, or whether all randomized participants were included in safety follow-up. It also does not report event narratives or an explanation of the group denominators.

Zero recorded events in these entries should not be interpreted as proof that no adverse experiences occurred, nor does it establish a broader safety conclusion. It means only that the registry lists zero events in the categories recorded for these groups. The study's primary focus was mock purchasing behavior, and the posted safety information is limited to these counts.

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

The registry record establishes the question the experiment was designed to address: whether the warning format displayed in an online experimental tobacco marketplace was associated with differences in mock cigarillo purchasing among young adult cigarillo users. It describes random assignment to pictorial or text-only warning conditions and defines average cigarillos purchased as the primary outcome. These design details make the intended comparison clear.

The record does not establish what the experiment found. It contains no arm-specific primary outcome values, effect estimates, confidence intervals, or p-values, and it records 0 analyses. It is therefore not possible to determine whether mock purchasing differed by warning format, how large any difference might have been, or how precisely it was estimated. No statement that one warning format increased, reduced, or had no effect on purchasing is justified from the posted results.

Even if numerical results were available, the outcome would represent choices in a mock marketplace during a 20-minute survey, not observed retail purchases or longer-term behavior. General interpretation: an experimental measure can be useful for comparing responses under controlled conditions, while its relationship to behavior outside the study depends on how well the task represents real-world decisions. The registry does not report evidence about that relationship.

The intended population was cigarillo users ages 21-35. The record does not report detailed participant characteristics or findings for subgroups, so applicability beyond that population cannot be assessed. Nor does it report the analysis methods needed to judge uncertainty, missing data, or the handling of multiple outcomes. The study's completed status indicates that the trial record marks the study complete; it does not substitute for posted outcome results.

13. Why This Trial Matters Statistically

This trial is statistically interesting because it frames warning design as a randomized behavioral comparison rather than only a comparison of opinions about warnings. The experimental tobacco marketplace gives participants a specified budget and asks them to make mock purchases, while the primary outcome counts purchased cigarillos. This creates a measurable endpoint linked to a choice in the task.

The design also illustrates why outcome definition and analysis detail matter. Each participant was to complete six shopping trips, so the observations may have a repeated-measures structure. A clear account of how trip-level behavior is summarized or modeled would help readers understand the estimate and its uncertainty. The registry defines the main measure but does not report that analytic detail.

There are three warning formats, and the record lists multiple outcome measures. That raises questions about which contrasts were prioritized, how repeated observations were handled, and how multiplicity was addressed. Those are general design and interpretation issues; the registry does not report the analysis plan or results needed to answer them for this study.

The posted record is therefore most informative about the intended experiment and its endpoint, rather than its findings. Enrollment and completion information describe the trial's conduct at a high level, but without results they cannot show the size or precision of any difference. The distinction between a well-defined research question and an interpretable estimate is important: the former is documented, while the latter is not reported in the registry record.

14. 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 principal limitation for interpreting the trial is that the registry record does not post primary or secondary outcome results. There are no arm-level means, standard deviations, effect estimates, confidence intervals, or p-values. It records 0 analyses, leaving the direction, magnitude, and precision of the intended comparisons unknown.

The endpoint is based on mock shopping behavior in an online marketplace. It measures choices in that task, not actual retail purchasing. The registry does not report whether or how this experimental behavior was validated against purchasing outside the marketplace, so that relationship is not reported in the registry record.

Several analytic details are also absent. The record does not report how the repeated shopping-trip observations were combined or modeled, what comparisons were prespecified, whether multiplicity was addressed, or how missing data and exclusions were handled. The identities of those masked and the randomization procedure are not reported in the registry record. Without these details, the intended design cannot be fully connected to an analysis population or reproducible statistical analysis.

The registry records enrollment of 1578, but participant flow and arm-specific analyzed populations are not reported. It lists safety denominators and zero event counts, but does not explain the follow-up period or event ascertainment. Finally, participant characteristics beyond the intended ages and cigarillo-use status, as well as subgroup results, are not reported in the registry record. These gaps limit assessment of representativeness and the scope of any conclusions.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: The Impact of Cigarillo Warnings on Purchasing — NCT05434013.
• Registry record last updated 2023-08-02; status last verified 2023-08.
• Results first posted 2023-08-02.
• 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.

18. Record Summary

The registry describes a completed, randomized, parallel-group, single-masked behavioral study sponsored by Boston University. Participants were cigarillo users ages 21-35 assigned to pictorial, FDA-proposed text-only, or Surgeon General text-only cigarillo warning formats in an online Experimental Tobacco Marketplace. The record lists enrollment of 1578, study start on 2022-06-24, and primary completion on 2022-07-21.

The primary outcome was the average number of cigarillos purchased during the six mock shopping trips within the 20-minute survey. Secondary outcomes concerned tobacco amounts, cigarillo intensity, cost-related indices, and demand. The registry lists 14 outcome measures and 0 analyses. It does not report outcome estimates, statistical comparisons, missing-data methods, or an analysis population. Safety entries list 0 serious adverse events, 0 other adverse events, and 0 deaths for each warning group. Thus, the record documents the study question and design but does not provide results for evaluating differences in purchasing.