Online Trial Examining Validity and Reliability of the Shared Decision Making Process Survey: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Online Trial Examining Validity and Reliability of the Shared Decision Making Process Survey (NCT04317690), a registered phase not stated study. The primary outcome is Shared Decision Making Process Measure.

2. Clinical Question

3. Trial Design

The registry describes an online survey study of adults who had recently made a decision about treatment for high cholesterol or high blood pressure, or about screening for colorectal, breast, or prostate cancer. Its stated main goal was to gather evidence about the validity and reliability of the Shared Decision Making Process Measure. A secondary goal was to gather evidence about decision quality in these medical situations.

The condition-specific groups had different eligibility descriptions. The high cholesterol and high blood pressure groups included people aged 30-75, without a previous heart attack or stroke, who had a diagnosis and either recent medication use or a recent discussion about management. The colorectal screening group covered people aged 50-75 without a previous colon cancer diagnosis who had recently screened or discussed screening. The breast screening group covered females aged 40-50 without a previous breast cancer diagnosis who had recently had or discussed a mammogram. The prostate screening group covered men aged 45-69 without a previous prostate cancer diagnosis who had recently screened or discussed screening.

Enrollment is listed as 539. The registry gives a start date of 2020-03-17, a primary completion date of 2020-06-29, and a completed status. It does not describe random assignment, a treatment allocation procedure, or a common comparator. The decision-specific groups therefore represent different contexts rather than a documented controlled comparison. How participants were recruited, how many completed the survey, and how many contributed to each 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.

Before assignment: Eligible respondents were adults in the US who had talked with a healthcare provider about screening for cancer (breast, colon, or prostate) or taking medication for a common chronic condition (depression, high cholesterol, or high blood pressure) in the past two years. Respondents were re-contacted approximately one-week post survey for a re-test survey.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: participants who provided complete information to calculate a shared decision making process score (primary outcome of interest)

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 who had discussed with their healthcare provider about cancer screening (breast, colon, prostate) or medication for a chronic condition (high cholesterol, high blood pressure) within the last 2 years. Participants needed to have provided enough information to calculate the shared decision making process score (primary outcome of interest)

6. Primary Endpoint

The registry lists the primary outcome as Shared Decision Making Process Measure, measured over Baseline survey.

The primary outcome is the Shared Decision Making Process Measure score at the baseline survey. It is a short patient-reported survey intended to measure the amount of shared decision making that occurs in an interaction. The registered scale ranges from 0-4, with higher values indicating a better shared decision making process occurred.

The registry specifies a mean score and standard deviation as the outcome summary, among participants who provided complete information to calculate the score. A mean describes the central score across the analyzed participants, while a standard deviation describes how spread out individual scores are around that mean. Those summaries would characterize reported shared decision making in the surveyed decision contexts; by themselves, they would not establish that the measure is valid or reliable.

Validity concerns whether a measure captures the concept it is intended to measure. Reliability concerns the consistency of measurement. Assessing those properties generally requires evidence beyond a mean and standard deviation, such as relationships with other measures or consistency across repeated assessments. The registry lists a retest measure among secondary outcomes, but does not report its results or a planned reliability analysis. The primary score value and its dispersion are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous: it is a score on a scale, summarized in the registry as a mean and standard deviation. In general, a mean represents the arithmetic center of observed scores, while a standard deviation describes their dispersion. These summaries can convey the overall score level and heterogeneity, but they do not by themselves demonstrate measurement validity, reliability, or a causal relationship.

What does a confidence interval add?

In general, a confidence interval expresses uncertainty around an estimate under the assumptions of the statistical method used. A narrower interval indicates greater precision for that estimate; a wider interval indicates less precision. For a mean score, an interval could help distinguish a relatively precise estimate from one that remains uncertain. The registry record does not report a confidence interval for the primary outcome, so its precision cannot be assessed from the posted results.

What would reliability analysis address?

Reliability concerns the consistency of a measurement. For a patient-reported scale, consistency can be examined in different ways, depending on the design and intended use. A retest assessment can address whether scores are reproducible when the construct is expected to remain stable. Internal consistency approaches address whether items intended to measure a common construct behave coherently. These are general methods, not analyses documented for this record. A retest measure is listed as a secondary outcome, but the retest timing, analysis method, estimates, and uncertainty are not reported in the registry record.

What would validity evidence address?

Validity is not established by a score’s mean or by a single statistical test. It is supported by evidence that the measure behaves as expected for its intended interpretation and use. General evidence might examine relationships with relevant measures, whether scores distinguish contexts expected to differ, or whether respondents understand the items as intended. The listed secondary outcomes include decisional conflict, decision regret, treatment choice, preferences, and knowledge. The registry record does not report whether or how these measures were used to evaluate validity, nor does it report the relevant estimates.

Why does the population definition matter?

The primary outcome is defined for participants with complete information needed to calculate the score. This is an analysis population defined by outcome completeness, not necessarily everyone enrolled. In general, restricting an analysis to complete records can affect interpretation if missingness is related to participant characteristics or responses. The number with complete primary outcome data, the amount and pattern of missingness, and any approach to incomplete responses are not reported in the registry record. Without these details, the relationship between enrollment and the analyzed outcome population is unclear.

How should the sample-size illustration be read?

The registry’s stated planning illustration uses a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation, with the target effect defined as a stated fraction of the observed effect. For time-to-event settings, its description refers to a total event count; for other settings, it refers to participants per arm. These are general planning assumptions, not evidence that the study was designed using those assumptions. The registry record does not report a trial-specific sample-size justification, and no sample-size result or observed-effect estimate is available for interpretation. Planning illustrations are not observed power and do not replace an analysis of the collected data.

Because the registry does not describe a randomized treatment comparison, standard treatment-effect interpretations do not apply to its decision-specific groups. A difference between groups would be an association across distinct contexts unless a suitable design and analysis supported a stronger interpretation. The record does not report an analysis plan, adjustment strategy, model specification, or inferential results. Any such methods should not be presumed from the outcome labels or study aims.

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("High Cholesterol", "High Blood Pressure", "Colorectal Cancer Screening", "Breast Cancer Screening", "Prostate Cancer Screening")
n   <- c(100, 96, 140, 98, 99)
m   <- c(2.12, 2.65, 1.61, 1.4, 1.87)
sp  <- c(1.03, 1.04, 1.12, 1.1, 0.97)
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  High Cholesterol  100  2.120  1.030  1.916  2.324
CARM  High Blood Pressure  96  2.650  1.040  2.439  2.861
CARM  Colorectal Cancer Screening  140  1.610  1.120  1.423  1.797
CARM  Breast Cancer Screening  98  1.400  1.100  1.179  1.621
CARM  Prostate Cancer Screening  99  1.870  0.970  1.677  2.063

11. Multiplicity, Missing Data and Analysis Populations

The registry lists several secondary outcomes: the Decisional Conflict Tool (SURE), the Decision Regret Scale, a single-item measure of decision regret, treatment choice, an adapted controlled preference scale, a retest measure of the Shared Decision Making Process Measure, and knowledge. It does not report results for these outcomes or describe a prespecified strategy for handling multiple statistical tests. The number of outcome measures is listed as 9, while the number of analyses is listed as 0. These entries do not establish that no analyses were conducted; they indicate that analyses are not reported in the registry record.

In general, testing many outcomes can increase the chance of finding an apparently noteworthy result by chance. Researchers may address this through a prespecified hierarchy, adjustment procedures, or a clear distinction between confirmatory and exploratory analyses. The registry record does not report whether any such approach was planned or used. Without the analysis plan and outcome estimates, it is not possible to determine how multiplicity should affect interpretation.

The primary outcome is limited to participants with complete information to calculate a score. The number of complete records, the extent and reasons for missing responses, and any imputation or other missing-data method are not reported in the registry record. The record also does not give the number analyzed for each secondary outcome. These omissions prevent assessment of whether the analyzed populations differ across outcomes or from the enrollment entry. No assumptions about missing-data handling or analysis populations can be made from the available registry description.

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.

The registry lists serious adverse event figures separately for the five decision-specific groups. Each entry reports the number at risk for serious adverse events and the number affected, with zero affected in every listed group. Deaths are also listed as zero in each group. The listed serious-event at-risk counts are 100 for High Cholesterol, 100 for High Blood Pressure, 140 for Colorectal Cancer Screening, 100 for Breast Cancer Screening, and 99 for Prostate Cancer Screening. These are registry entries and should be read in the context of the groups as named.

These figures do not establish that every enrolled participant was included in safety monitoring, because the record does not explain the relationship between enrollment, group membership, and safety follow-up. It also does not describe a treatment exposure or comparison. The absence of reported events in these entries is not evidence from a randomized safety comparison, and it should not be interpreted as a general claim about risk in other populations or settings. The registry’s serious adverse event terms list is empty; details of safety collection and reporting are not reported in the registry record.

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

The record identifies a study designed to gather evidence about a patient-reported measure of shared decision making in several common decision settings. It states the intended primary outcome, the score’s range and direction, and the population used to define the primary analysis. It also identifies secondary measures related to decision conflict, regret, choice, preference, retest measurement, and knowledge. These details clarify what the study set out to examine.

What the record does not establish is how participants scored, how variable their scores were, whether the measure showed reliability or validity, or what the secondary outcomes indicated. Primary outcome results, uncertainty estimates, and analysis details are not reported in the registry record. The completed status and enrollment entry cannot answer those questions. Nor can the study aim itself be treated as evidence that the measure performed well.

The design description concerns surveyed experiences across different clinical decision contexts. It does not document randomized assignment or a like-for-like control comparison. Accordingly, the record does not support a conclusion that one treatment, decision process, or clinical strategy caused an outcome. The groups are defined around different conditions and screening decisions, with different eligibility descriptions.

More broadly, validity and reliability are properties supported by evidence, not conclusions that follow from using a named instrument or reporting an average score. A mean score would describe responses in the analyzed population; additional analyses and transparent reporting would be needed to assess the measure’s performance. The registry record does not report enough outcome evidence to determine those properties.

14. Why This Trial Matters Statistically

This study is statistically relevant because it focuses on measurement: before researchers can interpret patient-reported shared decision making scores, they need evidence that those scores are meaningful and consistent for their intended use. A short measure may be practical to administer, but brevity alone does not establish that it captures the intended construct or performs consistently.

The study’s settings span treatment decisions and cancer screening decisions. Those contexts may involve different choices and participant eligibility, making it important to evaluate whether a measure has an interpretable role across them rather than assuming that a score has the same meaning everywhere. The registry’s aim recognizes this broad measurement question, but the posted record does not report the analyses needed to answer it.

The record also illustrates why study aims, enrollment, and completion status should be distinguished from results. Enrollment describes the registry’s study entry, while the primary outcome is defined for participants with complete score information. Without the analyzed sample size, score distribution, or uncertainty estimates, the precision and generalizability of any primary result cannot be judged.

For clinical researchers, the key statistical issue is not merely whether a scale produces a number, but whether evidence supports the interpretation attached to that number. The listed retest and related decision measures could be relevant to such an evaluation, but their results and analytical role are not reported in the registry record. The study question is important; the registry entry does not provide the empirical findings needed to resolve it.

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 registry record contains no reported primary outcome estimate, standard deviation, confidence interval, or hypothesis test. As a result, the observed score level and its precision cannot be assessed. Although the stated primary outcome population consists of participants with complete information to calculate a score, the number with complete data is not reported. The record also does not describe missing responses, reasons for missingness, or how incomplete questionnaires were handled.

The study includes several decision contexts with differing eligibility criteria. The registry does not report outcome results by context or explain whether the measure was evaluated separately across groups. This prevents assessment of whether score interpretation was consistent across the treatment and screening settings. The record does not report demographic characteristics beyond the eligibility descriptions, recruitment methods, or information needed to assess how well participants represent the broader populations of interest.

No analysis plan, model specification, validity framework, reliability method, or multiplicity approach is reported. Although retesting and several related decision measures are listed, their timing, completeness, analytic use, and results are not reported in the registry record. There is also no documented randomized comparator, so the study should not be read as a controlled test of a treatment or decision intervention.

Finally, the safety entries give group-specific at-risk and affected counts but do not explain the monitoring procedures or how safety populations were defined. These reporting gaps limit interpretation of both the measurement aims and the safety record. They do not establish that analyses were not performed; they mean that the relevant analyses and details are not reported in the registry record.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Online Trial Examining Validity and Reliability of the Shared Decision Making Process Survey — NCT04317690.
• Registry record last updated 2022-05-20; status last verified 2022-05.
• Results first posted 2022-05-20.
• 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.

19. Record Summary

This completed online survey study enrolled 539 and addressed decisions about high cholesterol treatment, high blood pressure treatment, and colorectal, breast, or prostate cancer screening. Its primary aim was to gather evidence about the validity and reliability of the Shared Decision Making Process Measure; decision quality was a secondary aim.

The primary outcome is a baseline mean score on a 0-4 scale, with higher values indicating a better shared decision making process. It is defined for participants with complete information to calculate the score. The registry lists several secondary decision measures, but does not report outcome estimates, analysis methods, or the number contributing to each analysis. The primary score result and evidence needed to assess validity and reliability are not reported in the registry record.