Multi-center, Pediatric, Open-label, Preference Study of Desloratadine 2.5 mg Reditab (SCH34117) and Zyrtec 5.0 mg Chewable Tablet Medications (Study P04574)(COMPLETED): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Multi-center, Pediatric, Open-label, Preference Study of Desloratadine 2.5 mg Reditab (SCH34117) and Zyrtec 5.0 mg Chewable Tablet Medications (Study P04574)(COMPLETED) (NCT00779116), a randomized phase 4 study. The primary outcome is Number of Subjects Who Preferred Desloratadine RediTab or Zyrtec Chewable Tablet..

2. Clinical Question

3. Trial Design

This was a completed, Phase 4, multicenter pediatric preference study with randomized allocation, no masking, and a two-way crossover model. The registry record lists allergies as the condition and Organon and Co as the sponsor. The study began in 2005-09, and primary completion was recorded in 2005-10. The registry reports enrollment of 217.

Each subject was assigned to one of two sequences. In one sequence, subjects took desloratadine RediTab and then Zyrtec chewable tablet. In the other, they took Zyrtec first and desloratadine RediTab second. The second dose followed 8-10 minutes after the first. The preference questionnaire was completed after the second product had been given, so each subject had tasted both study products before choosing.

The study was open-label: masking is listed as none. The preference question therefore followed an explicitly described tasting experience in which the products were not masked according to the registry record. This design addresses immediate product preference under the study's administration sequence; it is not described as a blinded assessment. The registry does not report further details about how the sequence was generated, whether any additional washout period was used, or whether the order was accounted for in the analysis.

The primary outcome is presented as three response categories: preference for RediTab, preference for Zyrtec, and no preference. All 217 subjects are listed as the denominator for each category. The sequence groups listed in the safety record contain 109 subjects in RediTab/Zyrtec and 108 in Zyrtec/RediTab. The registry record does not give additional details about the analysis population, exclusions, or missing questionnaire responses.

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.

First Intervention

Interval Between Doses (8-10 Minutes)

Second Intervention

Analysis population for the primary outcome, as defined in the registry: All randomized subjects received either Reditab or Zyrtec, followed 8-10 minutes later by the opposite study drug (Reditab followed by Zyrtec or Zyrtec followed by Reditab).

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 Number of Subjects Who Preferred Desloratadine RediTab or Zyrtec Chewable Tablet., measured over Following the second dose (8-10 minutes after the first dose).

The primary endpoint counts the number of subjects who preferred desloratadine RediTab, preferred Zyrtec chewable tablet, or reported no preference. The questionnaire was administered after the second study drug. The interviewer asked subjects to indicate which tablet they liked more after tasting both; a response of no preference could also be recorded. Thus, the endpoint is a direct report of relative liking after exposure to both products.

Preference is useful when the study question concerns acceptability of product attributes rather than only a clinical response. The registry summary describes taste and feeling in the mouth as attributes rated using a smile-face scale, and the primary outcome description specifies the final product-preference question. The reported primary outcome is the preference count, not a separate estimate of taste, mouthfeel, symptom relief, or adverse effects.

Because the same subject received both products, the response summarizes a within-subject experience, but the posted primary result is expressed as counts in preference categories. The sequence differed across randomized subjects, which makes order a relevant feature of the design when interpreting a brief, immediate preference assessment. The registry record does not report how the primary analysis incorporated sequence or whether the attribute ratings had separate results. No secondary outcome measures are posted.

7. Results Posted in the Registry

• RediTab: 69.1% (150/217) versus 12.9% (28/217) on control; risk difference 56.2 percentage points (95% CI 48.6 to 63.8), risk ratio 5.36 (3.75–7.66); unadjusted two-proportion z-test p = <0.001.
• Zyrtec: 18.0% (39/217) versus 12.9% (28/217) on control; risk difference 5.1 percentage points (95% CI -1.7 to 11.9), risk ratio 1.39 (0.89–2.18); unadjusted two-proportion z-test p = 0.144.

8. Statistical Interpretation

9. Statistical Methods Explained

What does the endpoint count?

The primary endpoint is a count outcome with three possible preference responses: RediTab, Zyrtec, or no preference. The registry reports 150, 39, and 28 subjects in those categories, respectively, with 217 listed in each category. These counts describe mutually exclusive responses to the post-dose preference question as it is written in the record. The record does not separately post the numerical results for taste or feeling-in-the-mouth ratings.

In general, a count outcome records how many participants fall into a stated category. It is not itself a continuous score, and its interpretation depends on the outcome definition and denominator. Here, the intended meaning is participants with a stated preference category. The results do not measure how strongly a participant preferred one product, since no strength-of-preference scale is reported.

What is a risk difference?

In general, a risk difference subtracts one event proportion from another. For a binary contrast, the event must be clearly specified, and the groups or categories being compared must be clear. In the RediTab recalculation, the comparison is RediTab preference versus no preference; in the Zyrtec recalculation, it is Zyrtec preference versus no preference. The risk differences are 0.562 and 0.051, respectively. They are not the direct RediTab-versus-Zyrtec contrast used by the sponsor.

These values are unadjusted recalculations from the posted summary statistics. They do not account for the crossover sequence or other individual-level information. The registry record does not report the details needed to determine whether the sponsor’s test adjusted for sequence or used additional information beyond the category counts.

How should the p-values be read?

In general, a p-value describes how unusual data at least as incompatible with a specified null hypothesis would be if that hypothesis and the test assumptions held. It is not the probability that the null hypothesis is true, and it does not quantify the size or practical importance of an effect. The sponsor reported p < 0.001 for the Mainland-Gart Test comparing the RediTab and Zyrtec preference groups. The unadjusted recalculations report p < 0.001 for RediTab versus no preference and p = 0.144 for Zyrtec versus no preference.

Those p-values cannot be treated as interchangeable because they correspond to different contrasts. Also, the sponsor’s test is the registry-reported analysis, whereas the other two values are recalculated comparisons based on posted summary statistics. The discrepancy flag means the sponsor’s own analysis takes precedence in describing the sponsor-reported finding.

What do confidence intervals add?

In general, a confidence interval gives a range of estimates compatible with the data and method used, while conveying uncertainty around a point estimate. It does not mean that there is a particular probability that the fixed underlying effect lies in the calculated interval. The recalculated RediTab-versus-no-preference risk difference has an interval from 0.486 to 0.638. The Zyrtec-versus-no-preference interval runs from -0.017 to 0.118. The registry gives a 95% confidence level for the sponsor-reported test, but does not report its interval bounds.

Intervals accompany unadjusted comparisons of preference categories. They do not automatically incorporate the paired nature of a crossover design or the effects of order. The posted record does not explain whether the sponsor’s analysis used a method that accounted for the randomized sequence, and it does not provide sufficient analysis details to reconstruct that method.

Why does over-dispersion matter in general?

In general, over-dispersion occurs when variation in data is greater than a statistical model expects. If a model assumes less variation than the data contain, its standard errors can be too small and its intervals too narrow. This is a general consideration for count and clustered data, not a finding reported for this trial. The endpoint is a set of preference counts, and the registry does not report a dispersion estimate or a model for over-dispersion.

The crossover structure also makes the unit and form of analysis important. Each subject tasted both products, while the posted preference result assigns a single response category after the second dose. A method that uses individual paired responses or sequence information could differ from a simple comparison of category counts. The record identifies a Mainland-Gart Test for the sponsor analysis but does not report enough detail to describe its implementation or reproduce it.

Finally, statistical significance and study design are separate issues. A test result addresses a defined contrast under a particular method; it does not resolve limitations in masking, timing, representativeness, or measurement. The registry outcome concerns an immediate stated preference in this study, and that scope should govern interpretation.

10. Confidence Intervals and Precision

The recalculated RediTab-versus-no-preference risk difference is 0.562, with an interval from 0.486 to 0.638. The corresponding Zyrtec-versus-no-preference risk difference is 0.051, with an interval from -0.017 to 0.118. These intervals reflect precision for the respective unadjusted contrasts; they do not describe the direct comparison between the two products’ preference counts.

In general, an interval shows a range of estimates that are reasonably compatible with the observed data under the method used. A narrower interval indicates greater statistical precision than a wider one, but precision alone does not establish that the endpoint is clinically important or that the analysis addresses all features of the design. The interval for the RediTab comparison is above zero. The interval for the Zyrtec comparison includes zero, so the posted recalculation does not rule out no difference between Zyrtec preference and no preference on that contrast.

The sponsor’s analysis is reported with a 95% confidence level, but the registry record does not report confidence interval bounds for that analysis. The recalculated interval bounds are available, but the registry does not explicitly state a confidence level for those recalculations. Because a discrepancy is flagged, the sponsor’s own analysis takes precedence for the sponsor-reported comparison.

Precision also depends on the relevance of the statistical method to the study structure. The two products were administered to the same subject, with order randomized, whereas the recalculations use posted category summaries. The record does not state whether those recalculations account for within-subject pairing or sequence. Thus, the intervals characterize the recalculated contrasts, not every source of uncertainty about immediate preference or the design.

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, not total events. They are illustrations based on the observed effect and are not the trial’s original sample-size justification. The planning assumptions are a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect to detect set to a stated fraction of the observed effect. The trial’s own original design assumptions are not reported in the registry record.

The 80% power column gives the illustrative number of participants per arm for 80% power under those assumptions; the 90% power column gives the corresponding number for 90% power. In plain terms, power is the chance that a specified analysis would detect an effect of the chosen size if that effect were present, under the assumptions used. Greater target power generally requires more participants for a given effect size.

For the RediTab-versus-no-preference recalculation, planning for 100% of the observed effect gives 11 participants per arm for 80% power and 14 for 90% power. Planning for 75% of the observed effect gives 19 and 25 participants per arm, while planning for 50% gives 38 and 51. For the Zyrtec-versus-no-preference recalculation, the corresponding figures are 797 and 1,066 for 100% of the observed effect; 1,369 and 1,832 for 75%; and 2,971 and 3,977 for 50%.

Smaller effects need more participants to detect under the same assumptions, which is why the planning figures rise when the target is a smaller fraction of the observed effect. These are planning illustrations, not observed power. They do not show the power achieved by this completed study, nor do they replace the sponsor’s own analysis or an original design justification.

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 = 0.129; treatment proportion p₁ = 0.691; average p̄ = 0.410.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6956 = 1.3633.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.5708 = 0.4804.
4. n = (1.3633 + 0.4804)² / (0.5622)² = 10.8, rounded up to 11 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 <- 0.129032258064516                          # control proportion
p1 <- 0.691244239631336                          # 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(779116)
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 = 11 (80% power), 14 (90% power)
 75% of observed effect: n per arm = 19 (80% power), 25 (90% power)
 50% of observed effect: n per arm = 38 (80% power), 51 (90% power)
power.prop.test: 10.8 
Simulated power at n = 11 per arm: 0.817 (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. Analyses Reported by the Sponsor

The registry reports that the sponsor used a Mainland-Gart Test to compare the RediTab and Zyrtec preference groups. The reported confidence level is 95%, and the reported p-value is < 0.001. No test statistic, effect estimate, or confidence interval bounds for that analysis are reported in the registry record.

The recalculations are different: each compares one product-preference category with the no-preference category. They are simple, unadjusted calculations from the posted summary statistics. The RediTab contrast has a risk difference of 0.562 and p < 0.001; the Zyrtec contrast has a risk difference of 0.051 and p = 0.144. These are not the sponsor’s direct comparison between the two product-preference groups.

A discrepancy is flagged between the reported analysis and the recalculated results. For that reason, the sponsor’s own analysis takes precedence when describing the registry-reported inference. The recalculations can be read as supplementary descriptions of distinct category-versus-no-preference contrasts, not as corrections to or replacements for the sponsor’s test. The registry record does not provide enough methodological detail to reproduce the sponsor’s analysis independently.

14. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome measure and no secondary outcomes. It also lists one analysis. This limits the amount of posted outcome-level information available for assessing how many statistical comparisons were planned or conducted. The record does not report a multiplicity adjustment, a hierarchy of outcomes, or a prespecified strategy for handling multiple tests. The existence or absence of other analyses beyond those posted is not reported in the registry record.

The primary endpoint has three response categories, while the sponsor’s reported test compares the RediTab and Zyrtec preference groups. The unadjusted recalculations additionally compare each of those categories with no preference. Since these are different contrasts, their p-values should not be treated as multiple versions of a single test. The registry does not state whether comparisons with no preference were prespecified or whether they were part of the sponsor’s analysis plan.

Missing-data reporting is limited. The record lists 217 subjects for each preference category, but it does not state whether any randomized subjects failed to complete the questionnaire, how incomplete responses were handled, or whether there were exclusions from the primary analysis. The reported study population description says all randomized subjects received one product followed by the opposite product, but it does not provide a participant flow account or explicit analysis-population definitions.

The registry record also does not report interim analyses, an original statistical analysis plan, or details of any sample-size justification. It does not describe the statistical handling of sequence, period, or within-subject dependence for the crossover design. Those are gaps in the available reporting; they should not be filled by assuming a particular protocol or analysis procedure.

Consequently, the posted counts support a plain description of the recorded preference categories, and the sponsor’s reported p-value supports only the test as identified in the record. Broader claims about prespecification, missing responses, analysis populations, or multiplicity control cannot be established from the registry record.

15. 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 serious and other adverse-event figures are reported by sequence group. In the RediTab/Zyrtec sequence, 109 subjects were at risk for each category and 0 were recorded as affected for serious adverse events and other adverse events. In the Zyrtec/RediTab sequence, 108 were at risk for each category and 0 were recorded as affected in either category.

These are the posted counts for the registry’s adverse-event fields. They should be read as zero recorded events in the listed categories and groups, not as proof that no event could occur or that every aspect of safety was assessed. The record does not give event follow-up details or a fuller account of how adverse events were collected. Deaths are not reported in the registry record.

The sequence-group counts should not be confused with the primary preference counts. The preference outcome is listed for 217 subjects overall, while the adverse-event figures are divided between the two administration sequences. The adverse-event entries do not establish comparative safety between products, especially because the record does not provide event-level details or a product-specific exposure analysis.

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

The posted results describe what subjects said they preferred after tasting both tablets in this open-label crossover study. RediTab was the most frequently selected category, while some subjects selected Zyrtec and some reported no preference. The sponsor’s reported comparison between RediTab and Zyrtec preference groups has p < 0.001 using a Mainland-Gart Test. That finding pertains to stated product preference in the study setting.

It does not establish that one product provides better allergy symptom control, is more effective, or is preferable for every child. The primary endpoint is not a symptom score, a clinical response, or a long-term outcome. The registry’s description concerns an immediate taste-related preference after two doses, with the second dose administered 8-10 minutes after the first.

The open-label design matters because participants knew which products they were taking, as masking is listed as none. The record does not report a blinded taste assessment. The order of product administration was randomized, but the registry does not report how order was included in the analysis. The immediate sequence and timing mean the result should be understood as a response to the study’s specific tasting procedure, not as a general ranking under every form of use.

The recalculated comparisons also require careful distinction. RediTab versus no preference and Zyrtec versus no preference are not the same question as RediTab versus Zyrtec. The flagged discrepancy means the sponsor’s own analysis takes precedence for the sponsor-reported comparison. The simple recalculations are supplementary and do not reconstruct the sponsor’s method.

Finally, the results do not settle whether the preference distribution generalizes beyond the pediatric subjects enrolled in this study. The registry does not report an age range or further participant characteristics, and there are no posted secondary outcome measures. The result therefore has a narrow interpretation: reported immediate preference among study subjects after they tasted both products in the randomized sequence.

17. Why This Trial Matters Statistically

This trial illustrates how an outcome can be meaningful while remaining distinct from clinical efficacy. Product preference is directly relevant to acceptability questions, but it measures a participant’s stated choice rather than a change in allergy symptoms. Keeping the endpoint’s meaning in view prevents a preference result from being read as a treatment-effect result.

The crossover arrangement is also statistically important. Each subject received both products, and the order was randomized. The resulting response is based on exposure to both products, while the posted primary outcome is a single preference category. A comparison that respects paired observations or sequence may answer a different statistical question from a simple analysis of category counts. The registry identifies the sponsor’s test but does not give enough detail to evaluate all aspects of its implementation.

The discrepancy between the sponsor-reported analysis and the recalculations demonstrates why the comparison itself must be stated explicitly. A direct comparison between two preference groups is not equivalent to separately comparing each group with no preference. Clear descriptions of the estimand, contrast, and analysis population are essential for interpreting p-values and intervals.

Finally, the record demonstrates the limits of registry reporting. The preference counts and sponsor p-value are available, but details about missing responses, original sample-size assumptions, multiplicity, and crossover-specific analysis are not. Statistical interpretation should separate the directly reported result from what is not documented, while avoiding unsupported assumptions about the protocol or analysis.

18. 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 outcome is an immediate stated preference after subjects tasted both products, not a measure of allergy symptoms or longer-term use. This limits the scope of the inference to the study’s preference question and procedure. The registry describes the study as open-label with no masking, so the reported preference was not recorded under masked product conditions.

Timing and order also shape interpretation. The second product followed the first by 8-10 minutes, and each subject received both products in one of two randomized sequences. The record does not report whether order or sequence effects were examined or incorporated in the sponsor’s analysis. It also does not report how the interval between products was handled beyond the stated timing.

The registry does not report an age range, detailed eligibility criteria, or further participant characteristics, limiting assessment of how broadly the findings may apply to pediatric populations. No secondary outcomes are posted, and separate numerical results for the taste and feeling-in-the-mouth ratings are not reported in the record.

The reporting of analysis methods is incomplete for independent reconstruction. The sponsor’s Mainland-Gart Test is named, but its test statistic, effect estimate, confidence interval bounds, analysis population, and detailed implementation are not reported. The discrepancy flag further cautions against treating simple recalculations as equivalent to the sponsor’s result. The registry record does not report the original sample-size justification, interim analyses, multiplicity strategy, or procedures for missing questionnaire data.

Safety reporting is limited to the listed counts by sequence group, with zero recorded serious and other adverse events and deaths not reported in the registry record. These entries do not provide event-level context, duration of follow-up, or a full comparative safety analysis. These limitations concern what can be established from the registry record; they do not imply unreported study procedures or findings.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Multi-center, Pediatric, Open-label, Preference Study of Desloratadine 2.5 mg Reditab (SCH34117) and Zyrtec 5.0 mg Chewable Tablet Medications (Study P04574)(COMPLETED) — NCT00779116.
• Registry record last updated 2022-02-09; status last verified 2022-02.
• Results first posted 2010-07-05.
• 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.

22. Record Summary

NCT00779116 is a completed Phase 4, randomized, open-label, two-way crossover pediatric preference study sponsored by Organon and Co. It enrolled 217 subjects and compared desloratadine RediTab 2.5 mg with Zyrtec 5.0 mg chewable tablet. Each subject received both products in a randomized order, with the second dose following 8-10 minutes after the first.

The primary outcome recorded whether subjects preferred RediTab, preferred Zyrtec, or had no preference after receiving both products. The posted counts are 150, 39, and 28, respectively. The sponsor reported a Mainland-Gart Test comparing the RediTab and Zyrtec preference groups, with p < 0.001. Unadjusted recalculations compare each product-preference category with no preference; a discrepancy is flagged, so the sponsor’s own analysis takes precedence for its reported comparison.

The registry record does not report secondary outcome measures, detailed missing-data handling, the original sample-size justification, or enough analysis details to independently reconstruct the sponsor’s test.