Alternative Options to Minimize Niacin-Induced Flushing: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Alternative Options to Minimize Niacin-Induced Flushing (NCT00895193), a randomized na study. The primary outcome is Incidence of Flushing.

2. Clinical Question

The trial record frames the question around whether isolated apple pectin, aspirin, or their combination is associated with a different incidence of flushing after niacin. The primary endpoint treats flushing as a binary outcome: a participant either experienced any flushing during the observation period or did not. It does not distinguish the number of episodes or the intensity of symptoms in the primary measure.

The registry summary describes the broader rationale as assessing whether apple pectin may affect the incidence and severity of niacin-related flushing. However, the posted primary outcome is incidence, and the registry record does not report a separate posted secondary outcome for severity. The outcome description specifies hourly assessment for 6 hours on the day of dosing.

3. Trial Design

The registry identifies this as a randomized, double-masked, parallel-group trial at a single site. The record lists enrollment of 100 and describes four treatment arms, with 25 randomized participants in each arm. It also reports that all participants completed the study. The trial status is completed, and the registry lists the study start as 2009-01 and primary completion as 2010-12.

The four groups received apple pectin 2000mg, regular non-enteric coated aspirin 325mg, apple pectin 2000mg plus aspirin 325mg, or placebo. In every group, the assigned treatment was administered 30 minutes before a one-time 1000mg dose of extended-release niacin. The primary endpoint was assessed hourly for 6 hours after niacin administration on the day of dosing.

Randomization is intended, in general, to distribute participant characteristics across treatment groups without relying on investigators to choose who receives each treatment. Masking is intended, in general, to limit the influence of knowledge about assigned treatment on participants' experiences or outcome assessment. The registry identifies randomization and double masking but does not report further details about the randomization procedure, who was masked, or how masking was maintained.

The posted comparisons evaluate each active-treatment group against the placebo group. The registry record does not report the trial's original statistical analysis plan, the method used to determine the planned enrollment, or whether any interim analyses were planned. The fact that the registry reports the trial's design and completed enrollment does not establish what assumptions were used in its original planning.

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: This was a single-site, randomized trial, 4-arm parallel design trial. Each arm consisted of 25 randomized participants. All participants completed the 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 Incidence of Flushing, measured over Hourly for 6 hours on day of dosing.

The primary endpoint is the number of participants who experienced any niacin-induced flushing during the 6-hour period after dosing. Assessment was hourly for 6 hours on the day of dosing. The outcome is recorded as a count of participants with an event in each group, rather than as a measure of symptom intensity or the number of flushing episodes.

A binary incidence outcome is useful when the question is whether an event occurred at all within a defined observation period. In general, it gives a direct group-level summary that can be compared between treatments, while reducing the outcome to event versus no event. That simplicity also limits what it can say: participants with different timing, duration, or severity of flushing can be counted alike if each experienced flushing at some point during the period.

The registry summary mentions both incidence and severity as interests, but the posted primary outcome specifically defines incidence. The record does not report a separate posted secondary outcome for severity. Consequently, the reported group counts address the occurrence of flushing during the specified observation window, not all aspects of the experience of flushing.

7. Results Posted in the Registry

• Apple-pectin 2000mg: 88.0% (22/25) versus 92.0% (23/25) on control; risk difference -4.0 percentage points (95% CI -20.6 to 12.6), risk ratio 0.96 (0.79–1.15); unadjusted two-proportion z-test p = 0.637.
• Regular Non-enteric Coated Aspirin 325mg: 72.0% (18/25) versus 92.0% (23/25) on control; risk difference -20.0 percentage points (95% CI -40.6 to 0.6), risk ratio 0.78 (0.60–1.03); unadjusted two-proportion z-test p = 0.066.
• Apple Pectin + Aspirin: 80.0% (20/25) versus 92.0% (23/25) on control; risk difference -12.0 percentage points (95% CI -30.9 to 6.9), risk ratio 0.87 (0.69–1.09); unadjusted two-proportion z-test p = 0.221.

8. Statistical Interpretation

9. Statistical Methods Explained

The posted primary outcome is binary: each participant is classified according to whether any flushing occurred during the 6-hour period after niacin dosing. The group summaries are counts of participants with that event. The record states that each arm had 25 randomized participants and that all participants completed the study. The event counts are therefore interpreted against the group sizes reported by the registry.

What does a risk difference express?

A risk difference subtracts the event proportion in the reference group from the event proportion in the treatment group. In these comparisons, the reference is placebo. A negative estimate indicates a lower observed event proportion in the active-treatment group, while a positive estimate would indicate a higher observed event proportion. The posted estimates are -0.04 for apple pectin, -0.2 for aspirin, and -0.12 for the combination. These are unadjusted contrasts; the registry record does not report covariate adjustment.

In general, the risk difference is an absolute measure: it describes the separation between the event proportions on the probability scale. It is distinct from a risk ratio, which compares the proportions by division, and an odds ratio, which compares event odds. The record includes risk-ratio and odds-ratio estimates as well as risk differences. These measures can present the same group comparison in different ways, and none should be interpreted without considering uncertainty.

How should confidence intervals be understood?

In general, a confidence interval expresses the statistical uncertainty around an estimate under the method's assumptions. A narrower interval indicates greater precision, while a wider interval indicates that a broader range of values remains compatible with the data and method. For a risk difference, zero represents no difference between the groups. Each of the posted risk-difference intervals extends across zero, so the results do not sharply distinguish a lower incidence from no difference or a higher incidence.

The intervals are based on limited group counts and are wide enough to leave substantial uncertainty about the magnitude of each contrast. An interval is not a range containing every possible value, nor does it describe the variation in individual participants' outcomes. It quantifies uncertainty in the estimated group contrast under the statistical method used. The registry record does not identify the interval-construction method.

What do the p-values add?

The unadjusted p-values for the comparisons are 0.637 for apple pectin, 0.066 for aspirin, and 0.221 for the combination. In general, a p-value measures how unusual data at least as discrepant as those observed would be under a specified null model and its assumptions. It does not measure the size or clinical importance of a difference, and it does not give the probability that the null hypothesis is true. The record does not report a trial-specific testing plan, so the p-values should not be treated as a complete account of the study's intended inference.

The comparisons are unadjusted, and the registry record does not report a method for controlling the chance of false-positive findings across the three active-treatment comparisons. If several comparisons are considered together, multiplicity can matter: in general, the more inferences made, the greater the chance that at least one appears noteworthy by chance alone. No adjustment should be assumed from the posted summaries.

Statistical methods also depend on the outcome definition, completeness of outcome data, analysis population, and assumptions used for inference. The record says that all participants completed the study, but it does not detail the analysis population or report a missing-data procedure. The statistical method used for the posted comparisons is not described in the registry record. Accordingly, the estimates can be interpreted as reported unadjusted summaries, without attributing an unreported model or analysis procedure to the trial.

10. Confidence Intervals and Precision

Precision concerns how narrowly the data estimate a group difference. The posted risk-difference estimates are -0.04 for apple pectin versus placebo, -0.2 for aspirin versus placebo, and -0.12 for the combination versus placebo. Each corresponding confidence interval extends from a negative value to a positive value and includes zero. Thus, each interval is compatible with no difference as well as with differences in either direction.

The intervals are broad in relation to the point estimates, particularly for these comparisons based on groups of 25 participants. That breadth means the observed estimates do not pin down the size of a possible difference. The aspirin comparison has the largest absolute point estimate among the three, but its interval still reaches across zero; the point estimate alone is not a precise or conclusive description of the treatment contrast.

The unadjusted p-values are 0.637 for apple pectin, 0.066 for aspirin, and 0.221 for the combination. These values accompany the uncertainty intervals but do not replace them. A p-value is not a measure of precision or effect size. In general, confidence intervals help readers assess both the range of plausible contrast values under the method and whether estimates are sufficiently precise for a particular question.

The registry record does not report the confidence-interval construction method or a prespecified threshold for a clinically important difference. It also does not report a separate precision target. Interpretation should therefore remain tied to the posted estimates and intervals: the observed differences are uncertain, and the registry data do not establish equivalence between any active-treatment group and placebo.

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 planning figures are participants per arm for the binary flushing outcome, not total events. They are planning illustrations based on the observed effect, rather than the trial's original design calculation. For each comparison, the rows consider planning for 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. The columns describe participants per arm for 80% power and participants per arm for 90% power.

In general, power is the chance that a planned study will detect an effect of a specified size under the assumptions used for planning. The 80% column gives the per-arm sample size associated with the 80% power target; the 90% column gives the per-arm size associated with the 90% target. A higher power target generally requires more participants for the same assumed effect. The planning assumptions listed are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is the stated fraction of the observed effect.

Smaller assumed effects require more participants per arm to achieve the same power target. For example, planning for 50% of an observed effect requires more participants per arm than planning for the full observed effect in the listed comparisons. These sample-size figures are not observed power: they are illustrations of future-study size under stated assumptions, not a measure of how powerful this completed trial was.

The planning method and assumptions for the trial's original enrollment are not reported in the registry record. The posted illustrations should not be read as evidence that the original trial was designed around these effect fractions or achieved the displayed power targets. They are conditional calculations based on the observed comparisons, and the observed effect estimates are themselves uncertain.

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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.920; treatment proportion p₁ = 0.880; average p̄ = 0.900.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.4243 = 0.8315.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.4233 = 0.3563.
4. n = (0.8315 + 0.3563)² / (-0.0400)² = 881.8, rounded up to 882 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
p0 <- 0.92                          # control proportion
p1 <- 0.88                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(895193)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 882 (80% power), 1,181 (90% power)
 75% of observed effect: n per arm = 1,499 (80% power), 2,006 (90% power)
 50% of observed effect: n per arm = 3,213 (80% power), 4,301 (90% power)
power.prop.test: 881.8 
Simulated power at n = 882 per arm: 0.802 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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 record reports three comparisons of active-treatment groups with placebo, but it does not report a multiplicity-adjustment procedure. In general, when several treatment contrasts are examined, considering them together can increase the chance of at least one apparently unusual result under a setting where none of the treatments differs from the comparator. The posted p-values are identified as unadjusted, and no family-wise or other adjustment should be inferred.

The record does not report a detailed statistical analysis plan, a prespecified hierarchy among the comparisons, or a trial-specific significance threshold. The sample-size illustrations list a two-sided significance level of 0.05, but those planning assumptions do not establish what threshold was used for the trial's own analysis. The registry record also does not report interim analyses.

All participants are reported to have completed the study. That information is relevant to follow-up, but it does not provide a full account of whether every outcome was available for every participant or how any unavailable outcome would have been handled. A missing-data procedure is not reported in the registry record. The analysis population is also not described beyond the primary-outcome description and the report of randomized participants and completion.

In general, the analysis population can affect interpretation: an analysis based on assignment at randomization answers a different operational question from one based only on participants who adhered to treatment. The registry does not specify which approach was used. It also does not report a per-protocol analysis or sensitivity analyses for missing outcomes. These omissions do not change the posted counts, but they limit the ability to assess how the analysis was conducted and how robust its interpretation may be.

The registry includes no posted secondary outcomes. The absence of a reported secondary outcome does not establish that no other outcomes were considered during the study; it means that additional outcomes are not reported in the registry record.

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 5% reporting threshold.

The registry reports zero serious adverse events in each of the four groups. For each group, 25 participants are listed as at risk, and zero serious events are listed as affecting participants. It also reports zero other adverse events in each group, with 25 participants at risk in each. No serious adverse-event terms are listed.

These are recorded event counts for the registry's safety reporting, not proof that no adverse event could occur. In general, observing zero events in a group does not establish that the underlying risk is zero, particularly when the group is limited in size or observation is limited. The safety results should be read alongside the reported treatment and follow-up context: a one-time niacin dose and assessment on the day of dosing are described for the primary outcome.

Deaths are not reported in the registry record. The adverse-event information does not provide additional detail about event definitions, collection methods, or duration of safety follow-up beyond the registry fields. These results describe what is posted, rather than establishing broader safety conclusions.

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

The results describe the observed incidence of any flushing during the 6-hour period after one-time extended-release niacin dosing in four randomized groups. The event counts were 22 with apple pectin, 18 with aspirin, 20 with the combination, and 23 with placebo; each group included 25 participants. The unadjusted risk-difference estimates versus placebo were -0.04, -0.2, and -0.12, respectively.

Those estimates indicate lower observed counts in each active-treatment group than in the placebo group, but each confidence interval includes zero and extends to values on both sides of no difference. The comparisons therefore leave uncertainty about whether the underlying incidence differs and about the size and direction of any difference. They should not be interpreted as proof that the groups are equivalent, nor as proof of a treatment effect.

The endpoint records whether any flushing occurred, not its severity, duration, or number of episodes. Although the registry summary refers to severity as an interest, the posted primary outcome is incidence, and a separate posted severity result is not reported in the registry record. The findings are also specific to the described single-site study, assigned regimens, one-time niacin dose, and 6-hour observation period.

In general, statistical evidence and clinical relevance are related but distinct. A group contrast may be estimated imprecisely even when the observed counts differ, and the importance of any difference depends on questions that the endpoint and registry results do not settle. The registry record does not report a prespecified clinically important difference or longer-term outcomes. Accordingly, these data do not resolve questions beyond the recorded incidence comparison.

16. Why This Trial Matters Statistically

This trial illustrates the difference between an observed group pattern and a precise estimate of a treatment contrast. The active-treatment groups have lower observed flushing counts than placebo, but each unadjusted risk-difference interval includes zero. Looking at the counts, effect estimates, and uncertainty together is more informative than drawing a conclusion from the ordering of the counts alone.

It also demonstrates why outcome definition matters. The primary measure is whether a participant experienced any flushing during a defined period. That binary endpoint is straightforward to compare, but it cannot convey differences in symptom intensity, timing, or duration. A result about incidence should not be treated as a result about every aspect of the symptom experience.

Comparisons among several active treatments raise a further statistical issue. The posted p-values are unadjusted, while the registry does not report a multiplicity plan. Readers therefore cannot assume that the three comparisons were controlled as a family or ranked according to a prespecified testing strategy. That context matters when interpreting several related estimates.

Finally, the sample-size illustrations show how planned group size depends on the effect a future study aims to detect. Smaller assumed effects require more participants per arm under the stated planning assumptions. Because the observed contrasts are uncertain, the planning figures are best understood as conditional illustrations, not as a definitive design recommendation or as evidence of the completed trial's power.

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 endpoint is limited to any flushing during the 6-hour period after dosing. It does not report severity, duration, or the number of episodes, and the registry record does not post a separate secondary severity result. The trial's one-time dose and observation period also constrain what can be inferred about outcomes beyond the recorded period.

The study is described as single-site, with 25 randomized participants per arm. The confidence intervals around the risk differences include zero and are broad, leaving substantial uncertainty about the treatment contrasts. The registry record does not report a clinically important difference against which to judge the estimates.

Although the record identifies randomization and double masking, it does not describe the randomization procedure, who was masked, or how masking was maintained. It does not report the trial's original sample-size assumptions, detailed statistical analysis plan, analysis population, missing-data procedure, or method for constructing confidence intervals. All participants are reported to have completed the study, but further details about outcome availability and analysis are not reported in the registry record.

The record lists three unadjusted active-treatment comparisons with placebo and does not report a multiplicity adjustment. The posted safety counts do not establish that the underlying event risk is zero, and deaths are not reported in the registry record. These limitations apply to interpretation of the posted outcomes and do not by themselves determine what the study observed.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Alternative Options to Minimize Niacin-Induced Flushing — NCT00895193.
• Registry record last updated 2014-06-05; status last verified 2014-05.
• Results first posted 2014-03-17.
• 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

The registry record for NCT00895193, titled Alternative Options to Minimize Niacin-Induced Flushing, describes a completed randomized, double-masked, parallel-group trial at a single site. It lists enrollment of 100, with 25 randomized participants in each of four arms, and reports that all participants completed the study.

Participants received apple pectin 2000mg, aspirin 325mg, their combination, or placebo 30 minutes before a one-time 1000mg dose of extended-release niacin. The primary outcome was the number of participants experiencing any flushing during the 6-hour period after dosing. Posted counts were 22, 18, 20, and 23, respectively.

Each unadjusted risk-difference interval for an active-treatment comparison with placebo includes zero. The registry record does not report a trial-specific statistical analysis plan, multiplicity procedure, or original sample-size assumptions. Serious and other adverse-event counts are recorded as zero in each group; deaths are not reported in the registry record.