Evaluating Online Messages About Colon Cancer Screening: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Evaluating Online Messages About Colon Cancer Screening (NCT06134089), a registered phase not stated study. The primary outcome is Number of Participants in Determining Messages.

2. Clinical Question

The research question is therefore broader than a simple comparison of two treatment groups. It concerns responses to messages and prompts, while also considering whether those responses and other participant characteristics relate to future screening intentions. The registry record does not report results for either the message-evaluation aim or the secondary intention outcome. It also does not describe a prespecified statistical contrast that would turn the prompt-order groups into a causal comparison.

3. Trial Design

The registry identifies this as a completed study sponsored by the University of Utah. Its title is “Evaluating Online Messages About Colon Cancer Screening,” and the condition listed is Colonic Cancer. The study start date is 2023-12-05, and the primary completion date is 2024-02-08. Registry enrollment is 2210. That figure is the recorded enrollment, not a reported number of participants included in an outcome analysis.

The brief summary describes a choice-based approach using messages taken from various online sites. One goal was to determine which messages people considered more or less persuasive and shareable. Another goal was to examine how self-reported health-information seeking and encountering, demographic variables, individual-difference variables, and message exposure were associated with intentions to follow recommended colorectal cancer screening guidelines. The stated interest included differences among Black and White Americans of recommended screening age, described as 45-74.

Two behavioral interventions are registered: Perceived Effectiveness Prompt and Perceived Shareability Prompt. The arm descriptions identify a perceived shareability prompt first and a perceived effectiveness prompt first, but do not give further details. The registry also lists an undetermined-first-message-prompt group. Allocation is not stated. The registry record does not describe randomization, masking, recruitment procedures, study setting, or the assignment process, so those design features cannot be characterized further.

The primary outcome timeframe is 15 minutes. The registry lists one secondary outcome, intentions to follow screening recommendations in the future. It records two outcome measures overall and zero analyses. There is no posted statistical analysis plan or reported outcome estimate in the registry record. As a result, the design can be described from the registered aims and groups, but not as a fully specified comparative analysis.

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

Analysis population for the primary outcome, as defined in the registry: Participants in the "Undetermined First Message Prompt" group were excluded from outcome measure reporting because data were not available. Data for this group were not collected during the study, as evidenced by blank fields or entries containing erroneous or unusable information. These participants could not be included in the reported dataset

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: Participants in the "Undetermined First Message Prompt" group were excluded from baseline characteristics reporting because baseline characteristics data were not available. Data for this group were not collected during the study, as evidenced by blank fields or entries containing erroneous or unusable information. These participants could not be included in the reported dataset.

6. Primary Endpoint

The registry lists the primary outcome as Number of Participants in Determining Messages, measured over 15 minutes.

The primary registered endpoint is the number of participants in determining messages. Its unit is participants, and its description says the measure reports how many participants took part in determining online messages about colon cancer screening. The stated purpose is to help determine the content of screening messages for future research. The timeframe is 15 minutes.

A participant count can describe participation in an activity, but by itself it does not quantify how persuasive a message was, how shareable it was, or whether one prompt changed a response. Those questions require defined response measures and outcome results. The registry record does not report the primary endpoint’s observed count, group-specific counts, or a comparison between groups.

The endpoint is also described with the parameter label for a count of participants, while the registry classifies its kind as binary and describes that kind as participants with an event, in counts. The record does not clarify how the endpoint was operationalized for analysis. It states that participants in the undetermined-first-message-prompt group were excluded from outcome reporting because data were unavailable; the record describes fields as blank or erroneous or unusable, and says data for that group were not collected. No further accounting of the endpoint population is reported.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does the registered endpoint represent?

The primary measure is described as a number of participants. In general, a count records how many individuals meet a stated condition or take part in an activity. For interpretation, the condition being counted needs to be explicit, and the population contributing to the count needs to be known. Here, the registry describes participants taking part in determining online messages, but does not provide an observed count or a fuller operational definition. A count alone also does not say how strongly participants favored one message or whether their judgments differed by prompt order.

The registry classifies the outcome kind as binary, while the measure title and parameter describe a participant count. In general, a binary outcome assigns each observation to one of two categories; counts can then be formed by counting observations in a category. The registry record does not explain the relationship between those descriptions or specify the unit of analysis beyond its stated unit of participants. Without reported analysis details, it is not possible to know which statistical model or summary was used.

What do group comparisons require?

In general, a comparative analysis needs a clearly defined outcome, group assignment process, and target contrast. If groups are formed through random allocation, that process can support a causal interpretation under appropriate assumptions. If allocation is not stated, observed group differences may reflect other differences between participants or study conditions. The registry record does not state allocation and indicates that the prompt-order arms are not a like-for-like control comparison. It therefore does not support treating a contrast between those groups as an isolated causal effect.

A confidence interval, in general, describes statistical uncertainty around an estimate under the analysis assumptions. Its width is affected by such factors as the amount of usable information and variability in the outcome. A p-value addresses compatibility between the data and a specified null hypothesis under a statistical model; it does not describe the size or practical importance of an effect. The registry record reports no estimates, confidence intervals, or p-values, so these concepts cannot be applied to numerical findings for this study.

What can the planning illustration tell readers?

The sample-size illustration is described as a planning exercise based on an observed effect, rather than the study’s own design. It uses a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; the effect to detect is described as a stated fraction of the observed effect. In general, such an illustration estimates how many participants per arm might be needed under its assumptions to detect a chosen effect with a target power. These calculations are planning illustrations, not observed power and not evidence that a study did or did not detect an effect.

The registry record does not report the observed effect that would anchor those illustrations, nor does it report the study’s own sample-size justification. It does not report a target power or explain how the enrollment figure related to a planned analysis. A planning calculation cannot replace the observed results, and its assumptions may not match the actual allocation or analysis population. The record does not state that allocation was equal, even though equal allocation is an assumption in the illustration.

What analysis details are absent?

For outcomes involving counts or binary responses, statistical methods can differ depending on the outcome definition, the distribution of responses, and whether observations are independent. In general, over-dispersion matters when observed count variability exceeds what a chosen count model assumes; ignoring it can make uncertainty estimates too small. The registry does not report a model, a dispersion assessment, adjustment variables, or any other analysis method. There is therefore no basis for saying whether over-dispersion or another model assumption was relevant to the posted results.

The study summary mentions associations with information behaviors, demographic variables, individual differences, and message exposure. In general, an adjusted model can estimate associations while accounting for measured covariates, but it cannot automatically remove bias from unmeasured factors. The registry does not report which variables were measured in the final analysis, how they were coded, or whether any adjustment was performed. The intended association questions should not be mistaken for reported model results.

The record lists two outcome measures and zero analyses. It does not describe an analysis plan, handling of multiple outcomes or comparisons, interim analyses, or a strategy for missing data beyond the note about the undetermined-first-message-prompt group. These omissions limit assessment of model choice, precision, multiplicity, and the population represented by any analysis. No numerical result should be inferred from the registered aims or from the planning assumptions.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Perceived Shareablility Prompt First", "Perceived Effectiveness Prompt First")
n      <- c(1051, 1135)
events <- c(1051, 1135)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Perceived Shareablility Prompt First  1051  1051  100.0  99.6  100.0  99.6  100.0  99.6  100.0
ARM  Perceived Effectiveness Prompt First  1135  1135  100.0  99.7  100.0  99.7  100.0  99.7  100.0

11. Multiplicity, Missing Data and Analysis Populations

The registry lists two outcome measures: the primary participant-count endpoint and a secondary outcome concerning intentions to follow screening recommendations in the future. The study summary also describes several kinds of information behaviors and participant characteristics as topics of interest. Considering multiple outcomes or associations can raise multiplicity concerns because examining many questions increases the chance that some results appear noteworthy by chance. In general, an analysis plan can define which outcome or contrast is primary and how secondary tests will be interpreted. The registry record does not report multiplicity procedures, a hierarchy among secondary analyses, or a prespecified analysis plan.

The registry records zero analyses, so there are no posted estimates or tests from which to assess how multiplicity was handled in practice. It also does not report whether interim analyses were conducted. The absence of those details is not evidence that any particular procedure was or was not used.

Missingness is directly relevant to the primary endpoint. The registry says participants in the undetermined-first-message-prompt group were excluded from outcome reporting because data were unavailable; it describes blank fields or entries containing erroneous or unusable information and says data for that group were not collected. It does not report the number of participants in that group, usable outcome counts in the other groups, or how missingness within other groups was handled.

The analysis population is not defined beyond that exclusion. The registry does not say whether all enrolled participants were eligible for each outcome analysis, or give a participant flow from enrollment to analysis. The enrollment figure of 2210 therefore cannot be treated as the denominator for the primary endpoint or the secondary outcome. These gaps prevent evaluation of the extent and possible impact of missing data.

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

The study addresses a relevant statistical distinction: asking which messages people find persuasive or shareable is not the same as measuring whether they intend to follow screening recommendations. The registry names both message evaluation and future intentions as aims, but does not report results for either. The primary endpoint is a participant count, and its reported description does not itself provide a measure of message preference or intention.

The posted record also does not establish whether any observed group difference would be attributable to prompt order. Allocation is not stated, and the registry says the arms are not a like-for-like control comparison. A descriptive difference, if reported, would need to be interpreted in light of how the groups were formed and what participants experienced. No such estimates are available in the registry record.

These reporting gaps do not show that the study failed to collect useful information, nor do they demonstrate that messages had no effect. They mean that the registry record alone does not allow readers to determine what participants judged, how precise those judgments were, or how the judgments related to future screening intentions. Enrollment of 2210 is not a substitute for those results and does not establish the number analyzed.

The record’s zero entries for adverse events should also be read narrowly. The listed groups have zero participants at risk in the adverse-event fields, alongside zero event counts and zero deaths. With no reported at-risk denominator, these fields cannot be interpreted as evidence that no adverse events occurred among a defined study population. The record does not provide additional safety results.

Accordingly, the registry supports conclusions about the stated research aims and the limitations of the posted reporting, but not conclusions about the effectiveness of any message or prompt, participants’ future behavior, or differences between population groups.

13. Why This Trial Matters Statistically

Statistically, this study illustrates why a clear link between the research question and the measured endpoint matters. The summary focuses on message persuasiveness and shareability, while the primary registered measure is the number of participants taking part in determining messages. Participation counts can describe activity, but they do not by themselves quantify participants’ judgments. Interpreting a study requires the outcome definition and the research aim to align closely enough that the reported estimate answers the intended question.

The registry also distinguishes prompt-order groups without reporting allocation. That matters because the meaning of a comparison depends on how groups were created. When allocation is not stated and the arms are not a like-for-like control comparison, a group contrast cannot automatically be read as a causal effect of prompt order. Clear reporting of assignment, outcome definitions, and analysis populations would help readers judge what conclusions are warranted.

Finally, the record shows how enrollment and outcome reporting answer different questions. Enrollment of 2210 describes the registered study size, but it does not identify the denominator for an endpoint or establish how much information was available for analysis. The note that one group’s data were unavailable makes transparent reporting of participant flow and missingness especially important.

These statistical distinctions are useful beyond this study: a registered aim is not a result, a count is not necessarily a measure of preference, and a planning calculation is not evidence about the observed data. The registry’s limited results record makes those distinctions central to a careful reading.

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 main limitation for interpretation is that the registry record reports no outcome analyses. It gives no observed primary endpoint count, no group-specific results, and no estimates for future screening intentions. Without results, neither the magnitude nor the precision of any association or difference can be evaluated.

The outcome description leaves important operational details unresolved. The primary measure is a participant count, while its kind is classified as binary. The record does not explain that classification, define the counted event in greater detail, or state how the count was analyzed. Its 15-minute timeframe is reported, but further details about measurement and scoring are not.

The group structure also limits comparative interpretation. The record names two prompt-order groups and an undetermined-first-message-prompt group, but does not state allocation. It says the undetermined group was excluded from outcome reporting because data were unavailable, and the arm descriptions provide no additional detail about what participants saw. The number excluded and the usable sample in each remaining group are not reported.

Other design and analysis information is not reported in the registry record, including full eligibility criteria, recruitment and setting details, a statistical analysis plan, the study’s own sample-size justification, adjustment methods, and handling of multiplicity. The summary identifies intended subgroup and association questions, but the record does not show how those questions were analyzed. These limitations mean the posted information is insufficient to assess representativeness, potential confounding, or robustness of results.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Evaluating Online Messages About Colon Cancer Screening — NCT06134089.
• Registry record last updated 2025-10-20; status last verified 2025-09.
• Results first posted 2025-10-20.
• 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

NCT06134089 is a completed University of Utah study titled “Evaluating Online Messages About Colon Cancer Screening.” The registry lists Colonic Cancer as the condition, enrollment of 2210, a start date of 2023-12-05, and a primary completion date of 2024-02-08.

The study used a choice-based approach to examine online screening messages and registered two behavioral prompt conditions, perceived effectiveness first and perceived shareability first. Its primary outcome is the number of participants in determining messages, with a 15-minute timeframe. The secondary outcome concerns intentions to follow screening recommendations in the future.

Allocation is not stated, and the registry does not describe the groups as a like-for-like control comparison. Participants in the undetermined-first-message-prompt group were excluded from outcome reporting because data were unavailable. The registry lists zero analyses and reports no outcome estimates. As a result, the posted record describes the study aims and design elements but does not establish what participants reported or whether outcomes differed among groups.