Using Stories to Address Disparities in Hypertension: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Using Stories to Address Disparities in Hypertension (NCT01276197), a randomized na study. The primary outcome is Systolic BP at Follow-up.

2. Clinical Question

3. Trial Design

The registry record describes a randomized, single-masked, parallel-group trial. Participants were assigned to the Story-Telling DVD arm or the Non-Storytelling DVD arm. The first arm received a DVD with informational and story-telling components; the comparison arm received an informational DVD. This active comparison helps define the question: the trial contrasts two kinds of information DVD, not a DVD with no intervention.

The condition listed is hypertension, and the registry summary describes the intended population as patients with high blood pressure. Enrollment is listed as 618. The trial status is completed; its recorded start is 2013-01 and primary completion is 2015-05. The phase is listed as NA. The sponsor is the VA Office of Research and Development.

The primary outcome was systolic blood pressure at follow-up, measured in mmHg at 6 months after intervention. The record says that the analysis modeled intervention assignment while adjusting for baseline systolic blood pressure. Baseline systolic blood pressure was collected as a covariate, rather than treated as the outcome. The analysis population consisted of participants who completed the follow-up visit, and the registry notes that it differs from participant flow because those lost to follow-up could not be included.

The posted outcome summaries give results for both arms, but the adjusted model estimate is not reported in the registry record. The registry record also does not report the trial's original sample-size assumptions or a detailed statistical analysis plan. Those omissions limit what can be concluded about how the trial was planned and how its primary model was implemented.

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: Our analyses was completed with those who completed follow-up visit and varies from participant flow as we are not able to include those lost to follow-up.

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 Systolic BP at Follow-up, measured over 6 months after intervention.

The primary endpoint is systolic blood pressure at the follow-up visit, measured in mmHg at 6 months after intervention. Systolic blood pressure is the upper pressure recorded during a heartbeat. The registry describes it as a continuous measure summarized by a mean and standard deviation. These summaries describe the distribution of observed follow-up values within each arm; they do not, on their own, account for baseline differences or other features of the planned model.

The registry states that intervention assignment was modeled while adjusting for baseline systolic blood pressure. Baseline pressure was collected for use as a covariate, not as the outcome. In general, adjustment for a baseline measurement can account for the starting value when estimating the relationship between assigned intervention and follow-up outcome. The registry record does not report the adjusted estimate or details of the model, so the posted group means should not be mistaken for that adjusted result.

Blood pressure is an outcome aligned with the study's stated purpose of examining blood pressure control after viewing a DVD. A single follow-up measure also gives a direct comparison of the groups at the specified time point. It does not, by itself, describe changes at other times or establish how values changed for each individual. The posted results focus on systolic pressure; no secondary outcome results are posted in the registry record.

7. Results Posted in the Registry

• Arm 2: Non-Storytelling DVD: mean 141.20 versus 137.90 on control; difference 3.30 (95% CI 0.23 to 6.37), standardized effect d = 0.18; z-test p = 0.035.

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies a randomized, single-masked, parallel-group design and describes the primary endpoint as a continuous measurement. The posted results include arm means and standard deviations, together with a mean-difference comparison and an unadjusted p-value. The registry's description of the intended primary analysis says that intervention assignment was modeled with baseline systolic blood pressure as a covariate. The adjusted model result and the statistical plan are not reported in the registry record.

What does a mean describe?

In general, a mean is a measure of the center of a set of numerical observations. For this endpoint, each arm's mean summarizes systolic blood pressure at the follow-up visit. A mean does not show the full distribution: different groups can have the same mean while differing in spread or in the shape of their values. The registry also reports standard deviations, which describe how dispersed individual measurements are around the arm mean.

The story-telling arm's posted mean is 137.9 mmHg, with a standard deviation of 18.4. The non-storytelling arm's posted mean is 141.2 mmHg, with a standard deviation of 17.8. These summaries are not the baseline-adjusted model estimate. The description of the primary analysis distinguishes baseline systolic pressure, used as a covariate, from follow-up systolic pressure, used as the outcome.

What is the mean difference?

A mean difference expresses the separation between group means in the measurement's original units. The comparison is 3.3 mmHg for the non-storytelling arm relative to the story-telling arm, so a positive value corresponds to a higher posted mean in the non-storytelling arm. This makes the direction interpretable in mmHg, unlike a standardized effect measure. The comparison is marked as unadjusted; it should not be conflated with the baseline-adjusted primary model described in the registry.

In general, an unadjusted comparison uses the observed group summaries without accounting for a covariate in the model. A baseline-adjusted analysis instead estimates the association between assignment and follow-up outcome conditional on baseline pressure, according to the model specification. Adjustment can improve precision when baseline values predict follow-up values, but the amount and direction of any change in the estimate depend on the data and model. The adjusted result is not reported in the registry record, so it cannot be inferred from the group means alone.

What does a p-value convey?

The unadjusted p-value is 0.035. In general, a p-value assesses how incompatible the observed data are with a specified null model, under the assumptions used for the calculation. It is not the probability that the null hypothesis is correct, and it does not quantify the size or importance of the difference. Because this value is unadjusted, it should be understood as referring to the summary comparison, not as a reported result from the baseline-adjusted primary model.

The statistical plan and the exact model specifications are not reported in the registry record. That means the record does not establish which modeling details, covariate terms, or diagnostics were used in the sponsor's primary analysis. The registry lists no analysis results, although it posts outcome summaries and the unadjusted comparison. These pieces of information answer different questions: a group mean describes observed outcomes, while a model estimate addresses a contrast under the analysis assumptions.

Why does over-dispersion matter in general?

Over-dispersion is a general concern for count outcomes when observed variability exceeds what a simple model assumes. The primary endpoint is continuous systolic blood pressure, not a count outcome. For a continuous measure, the posted standard deviations convey the observed spread, and the mean comparison and confidence interval communicate the group contrast and its uncertainty. A specific modeling distribution or residual-diagnostic approach is not reported in the registry record, so no claim can be made about whether such checks were performed.

What role does baseline adjustment have?

In general, adjustment for a prognostic baseline measurement can improve precision by accounting for how starting values relate to follow-up values. It also defines the estimand differently from a comparison of raw follow-up means. The registry says baseline systolic pressure was collected and used as a covariate, while the outcome was systolic pressure at follow-up. Since the adjusted estimate is not posted, the available mean difference is best treated as an unadjusted descriptive comparison, not a substitute for the stated primary analysis.

The interpretation of any model also depends on who contributed data. The registry says the analysis was completed with participants who attended follow-up and that people lost to follow-up could not be included. In general, restricting analysis to people with observed follow-up outcomes can affect a comparison if outcome availability is related to group assignment or outcome values. The record does not report a missing-data method or information sufficient to assess that possibility.

10. Confidence Intervals and Precision

The posted mean difference is 3.3 mmHg, with a 95% confidence interval extending from a lower endpoint just above zero to 6.372 mmHg. The interval gives a range of values compatible with the summary comparison under the method used to calculate it. In general, a confidence interval expresses sampling uncertainty; it is not a range containing a guaranteed proportion of individual participants' blood pressure values.

The interval lies on the positive side of zero, but its lower endpoint is close to zero relative to the scale of the measurement. Its width also indicates that the data do not pinpoint a single exact difference. The unadjusted p-value is 0.035, but the p-value and confidence interval answer related, not identical, questions: the interval conveys uncertainty about the size and direction of the contrast, while the p-value summarizes evidence against a null value under the calculation's assumptions.

These precision measures apply to the posted unadjusted summary-statistic comparison. The registry describes a primary analysis adjusted for baseline systolic blood pressure, but does not report that model's estimate or interval. Consequently, the precision of the intended adjusted result cannot be assessed from the registry record. The endpoint summaries also concern participants who completed follow-up, and the record notes that those lost to follow-up could not be included. Uncertainty from missing outcome data is not represented by the confidence interval for the observed summary comparison.

In general, precision is affected by both the amount of information and the variability of measurements. The posted standard deviations show that blood pressure values varied within each arm. The confidence interval summarizes statistical uncertainty in the mean contrast, while leaving questions about model choice, missing follow-up data, and relevance beyond the observed analysis population unresolved.

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 sample-size figures are planning illustrations expressed as participants per arm, not total event counts. They are based on the observed effect and assume a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each row considers detecting the stated fraction of the observed effect. These figures do not describe the trial's original design assumptions, which are not reported in the registry record. This is not observed power.

For planning for 100% of the observed effect, the illustration gives 473 participants per arm for 80% power and 633 participants per arm for 90% power. For planning for 75% of the observed effect, it gives 840 participants per arm for 80% power and 1,124 participants per arm for 90% power. For planning for 50% of the observed effect, it gives 1,889 participants per arm for 80% power and 2,529 participants per arm for 90% power.

In general, power is the chance that a study using specified assumptions will detect an effect of a stated size if that effect is present. The 80% and 90% columns represent different target probabilities under the planning assumptions; the higher target is associated with a larger planned sample in these illustrations. Smaller effects need more participants to distinguish them from random variation with the same design assumptions. The curve should be read as a visual representation of this planning relationship, not as an additional observed trial result. The registry record does not report the assumptions used to set the original enrollment target.

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, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = 3.300; pooled standard deviation σ = 18.099.
2. n = 2 × (1.96 + 0.842)² × 18.099² / 3.300² = 472.2, rounded up to 473 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
delta <- 3.29999999999998                      # observed difference in means
sigma <- 18.0991027069574                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^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 (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(1276197)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 473 (80% power), 633 (90% power)
 75% of observed effect: n per arm = 840 (80% power), 1,124 (90% power)
 50% of observed effect: n per arm = 1,889 (80% power), 2,529 (90% power)
power.t.test: 473.2 
Simulated power at n = 473 per arm: 0.802 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-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 lists a primary outcome of systolic blood pressure at follow-up. It also reports two outcome measures overall, but no secondary outcome results are posted. The registry record does not report a multiplicity adjustment or a hierarchy for testing outcomes. In general, testing multiple outcomes or comparisons can increase the chance of at least one apparently notable result by chance; prespecified strategies can address that issue. Without a reported strategy or the secondary results, the implications of multiplicity cannot be assessed from the registry record.

The registry describes a primary analysis adjusted for baseline systolic pressure, but the adjusted model estimate and the detailed statistical analysis plan are not reported. The posted comparison includes an unadjusted p-value. The record does not establish whether that summary comparison was prespecified as an analysis, how it relates to the adjusted primary model, or whether other analyses were conducted outside the posted results. No trial analysis results are listed in the registry, despite the posted arm summaries and comparison.

Missing follow-up data are relevant to interpretation. The registry says the analysis included people who completed the follow-up visit and differed from participant flow because those lost to follow-up could not be included. It does not report a missing-data method, reasons for loss to follow-up, or a sensitivity analysis. In general, analysis restricted to participants with observed outcomes can be affected if follow-up availability is related to assignment or to the outcome. The record does not provide enough information to evaluate that possibility.

The registry record does not report whether the primary analysis followed an intention-to-treat approach, how protocol deviations were handled, or which participants were included in any analysis beyond the stated follow-up completers. The outcome group sizes are 264 for the story-telling arm and 270 for the non-storytelling arm, but these group-specific analysis counts do not resolve the missing-data questions. The enrollment figure and the follow-up analysis population describe different stages of the trial and should not be treated as interchangeable.

14. Safety Results

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

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

Most frequent serious adverse event terms

Serious events with the highest arm-level rate: hospitalization (3.2%), death (0.6%).

The serious adverse event summary lists 308 participants at risk in the Story-Telling DVD arm, with 12 affected, and 310 at risk in the Non-Storytelling DVD arm, with 10 affected. The registry lists no other adverse events in either arm. These figures describe the posted serious-event summary; they do not provide a complete account of event timing, duration, severity, or relationship to the DVD intervention.

The registry also lists hospitalization at 3.2% and death at 0.6% among the top serious-event terms. It does not assign these percentages to a particular arm in the posted terms, so they should not be interpreted as arm-specific rates. Death counts by arm are not reported in the registry record. The record does not provide further detail about whether serious events were judged related to the intervention.

In general, adverse-event summaries are descriptive and depend on how events were defined, collected, and coded. The posted counts alone do not establish comparative risk or causation. The registry record does not report the details needed to assess those aspects, so the figures are best read as a summary of the recorded serious events and affected participants.

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

The registry's posted summaries show mean systolic blood pressure of 137.9 mmHg in the story-telling DVD arm and 141.2 mmHg in the non-storytelling DVD arm at follow-up. The unadjusted mean difference is 3.3 mmHg, with a 95% confidence interval whose lower endpoint is just above zero and whose upper endpoint is 6.372 mmHg. These figures describe the follow-up values among participants included in the outcome analysis.

The result does not supply the adjusted effect from the primary model described in the registry. That model was intended to account for baseline systolic blood pressure, but its estimate is not reported in the registry record. The posted means and unadjusted comparison should therefore not be presented as the reported adjusted primary result. The unadjusted p-value of 0.035 is evidence about the summary comparison under its assumptions; it does not by itself establish the size, importance, or practical meaning of a difference.

The comparison is between an informational DVD with story-telling components and an informational DVD without story-telling. It does not compare either DVD with no intervention. The study's results also do not describe outcomes beyond the follow-up time point of 6 months after intervention. No secondary outcome results are posted.

In general, a randomized comparison can help estimate differences between assigned groups, but the interpretation depends on the analysis and follow-up completeness. The registry states that the primary analysis included follow-up completers and that participants lost to follow-up could not be included. The posted results do not resolve whether missing follow-up outcomes affected the comparison. The findings should consequently be understood as summaries of the reported analysis population and outcome, rather than as a complete account of every enrolled participant's result or a guarantee of individual outcomes.

16. Why This Trial Matters Statistically

This trial raises a clear statistical distinction between a planned adjusted analysis and the summary comparison that is posted. The registry identifies follow-up systolic blood pressure as the primary outcome and says baseline systolic pressure was included as a covariate. Yet the reported arm means and mean difference are unadjusted, and the adjusted estimate is not reported in the registry record. Readers therefore need to distinguish descriptive group summaries from the primary analysis as described in the record.

The endpoint is continuous, so the means and standard deviations offer an interpretable description of level and spread in mmHg. The mean difference preserves the measurement scale, while the confidence interval conveys uncertainty about the unadjusted contrast. These statistics are more informative together than a p-value alone, but they still do not establish whether the difference is meaningful for patients or how it relates to baseline pressure.

Follow-up completion is another important statistical feature. The record explicitly notes that the analysis population differs from participant flow because those lost to follow-up could not be included. This makes the connection between enrollment and outcome analysis consequential: the reported comparison describes the observed follow-up data, not a documented analysis of every enrolled participant. Missing-data methods and sensitivity analyses are not reported.

Finally, the comparison uses an active information control. Any measured difference pertains to the story-telling components relative to an informational DVD, not to receiving information versus receiving none. The record's missing adjusted model, detailed analysis plan, and secondary results limit the scope of statistical conclusions. These distinctions matter when evaluating what the observed summaries can support and what remains uncertain.

17. 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 limitation in interpreting the reported endpoint is that the registry describes a baseline-adjusted analysis but does not report its estimate. The available means, standard deviations, mean difference, confidence interval, and unadjusted p-value do not reproduce that model. Model specifications, diagnostics, and the detailed statistical analysis plan are not reported in the registry record.

The analysis population consisted of participants who completed the follow-up visit. The registry states that those lost to follow-up could not be included and that the analysis population differs from participant flow. The record does not report reasons for missing follow-up, a missing-data method, or sensitivity analyses. These gaps limit assessment of whether the observed comparison could be affected by incomplete outcome data.

The posted primary outcome is systolic blood pressure at 6 months after intervention. Results at other time points are not reported in the registry record, and no secondary outcome results are posted. The registry does not report multiplicity procedures. The comparison is between two informational DVDs, so its scope is limited to those approaches rather than to information versus no information.

The serious-event summary lists affected participants and top serious-event terms but does not report detailed event descriptions, timing, intervention relationship, or arm-specific attribution for the listed percentages. Death counts by arm are not reported. These omissions restrict interpretation of the safety summaries. The registry also does not report the trial's original sample-size assumptions; the available planning illustration is based on the observed effect and is not a description of the original design.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Using Stories to Address Disparities in Hypertension — NCT01276197.
• Registry record last updated 2016-12-02; status last verified 2016-10.
• Results first posted 2016-09-30.
• 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.

21. Record Summary

NCT01276197, titled “Using Stories to Address Disparities in Hypertension,” is recorded as a completed randomized, single-masked, parallel-group trial sponsored by the VA Office of Research and Development. Enrollment is listed as 618. The recorded start is 2013-01 and primary completion is 2015-05. The phase is listed as NA.

The comparison was between a story-telling DVD with informational content and a non-storytelling informational DVD. The primary outcome was systolic blood pressure at follow-up, measured in mmHg at 6 months after intervention. The registry describes a baseline-adjusted primary analysis but does not report its model estimate. The posted arm summaries and unadjusted comparison concern participants who completed follow-up, and the record notes that people lost to follow-up could not be included.

The registry posts no secondary outcome results. Its serious-event summary reports affected participants by arm and lists hospitalization and death among the top serious-event terms, without arm-specific percentages. Original design assumptions and detailed analysis methods are not reported in the registry record.