Frequency of Denture Cleanser Use and Denture Cleanliness: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Frequency of Denture Cleanser Use and Denture Cleanliness (NCT02780661), a randomized na study. The primary outcome is Change From Baseline in Aerobic Bacteria Microbial Count on Day 7.

2. Clinical Question

3. Trial Design

This was a randomized, single-masked, crossover study of daily and weekly denture-cleanser use. The registry lists the phase as NA and the status as completed. Enrollment was 19. The study began on 2016-06-20, and primary completion was recorded as 2016-11-15. GlaxoSmithKline is listed as the sponsor.

The crossover format means the study compared treatment periods within a trial designed around participants receiving the study treatments in sequence. However, the registry record does not report the sequence assignments, the period order, any washout interval, or how period and sequence effects were handled in the analysis. Those details should not be inferred from the label “crossover.” The record identifies random allocation and single masking but does not describe who was masked.

The daily period involved evening soaking with a cleansing tablet throughout the stated treatment period. The weekly period involved soaking in water on the intervening days and use of a tablet on Day 7. Both descriptions include brushing and rinsing instructions, although the weekly-period description in the registry record is incomplete after the rinse instruction. The posted outcome summaries report 19 participants for each treatment label; these arm summaries do not establish how many participants contributed paired observations or how missing period assessments were treated.

The registry record does not report the original sample-size justification, the planned statistical analysis in full, or whether interim analyses were planned. It also does not provide enough information to reconstruct the crossover analysis from the design description alone. The reported primary analysis is identified as ANCOVA, but the covariates and its handling of the crossover structure 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: A total of 25 participants were screened, out of which 19 participants were randomized to the study, 6 participants were not randomized because of screening failure.

Period 1

Wash Out Period

Period 2

Analysis population for the primary outcome, as defined in the registry: Analysis for this outcome was performed on intent-to-treat (ITT) population which included all participants who were randomized, received at least one dose of the study treatment and provided at least one post-baseline assessment of microbial count from disc sampling.

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 Change From Baseline in Aerobic Bacteria Microbial Count on Day 7, measured over Baseline (Day 0 pre-treatment), Day 7 (post-treatment).

The primary endpoint was change from baseline in aerobic bacteria microbial count on Day 7. A microbial count is a continuous measure: it records the level of cultured aerobic bacteria collected from the denture rather than classifying a participant as simply positive or negative. The unit was log10(CFU[colony forming unit]/disc+1), which expresses colony-forming units in a transformed scale and includes the addition indicated in the unit. On a log scale, changes are interpreted on that transformed measurement scale, not as raw counts of colonies.

Sampling used paper discs pressed against selected areas on the fitting surface of the maxillary denture. The registry describes pre-treatment sampling from the left rough and left smooth surfaces and post-treatment sampling from the right rough and right smooth surfaces at Day 7. Samples were diluted, plated, and incubated aerobically. These procedures aimed to measure aerobic microbial counts at standardized denture sites, making the endpoint relevant to the study’s comparison of cleansing frequency.

The registry reports the group outcome as a mean change and gives standard deviations as measures of spread. This endpoint was used to compare the average change between the daily-use and weekly-use periods. A microbial count outcome is a measure of microbiological change; by itself, it does not establish a broader clinical benefit or describe outcomes that were not measured.

7. Results Posted in the Registry

• Denture Cleanser Tablet: Weekly Use: mean -1.20 versus -1.78 on control; difference 0.58 (95% CI -0.98 to 2.14), standardized effect d = 0.24; z-test p = 0.466.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Change From Baseline in Aerobic Bacteria Microbial Count on Day 3

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Denture Cleanser Tablet: Weekly Use: mean 0.36 versus -1.74 on control; difference 2.10 (95% CI 0.49 to 3.71), standardized effect d = 0.83; z-test p = 0.010.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Denture Cleanser Tablet: Weekly Use than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in Anaerobic Bacteria Microbial Count on Day 3

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Denture Cleanser Tablet: Weekly Use: mean 1.08 versus -1.74 on control; difference 2.82 (95% CI 1.25 to 4.39), standardized effect d = 1.14; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Denture Cleanser Tablet: Weekly Use than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The posted Day 3 aerobic and anaerobic microbial-count comparisons show the same broad pattern in the group summaries: daily use is associated with a negative mean change, while weekly use is associated with a positive mean change. The unadjusted comparisons also point in the direction of a larger reduction during daily use on these measures. These secondary patterns do not match the unadjusted Day 7 primary recalculation, which does not show a clear difference between the periods. The primary sponsor-reported ANCOVA, however, differs from that recalculation, so comparisons across outcomes should be made cautiously.

The registry lists a Day 3 candidal microbial-count outcome among the secondary outcomes, but numerical results for that outcome are not reported in the registry record. The record also does not report adjusted analyses for the posted Day 3 outcomes. The numerical Day 3 comparisons are therefore unadjusted results, not evidence that a prespecified, multiplicity-controlled set of secondary hypotheses was confirmed.

Secondary outcomes can help describe whether patterns are consistent across measurements and time points, but they carry less weight when many outcomes or time points are examined without a reported plan to control multiplicity. Repeated testing increases the chance of observing apparently notable results by chance. The registry record does not report a multiplicity adjustment or a hierarchy specifying which secondary results should be treated as confirmatory. The observed secondary pattern is best treated as exploratory context for the primary outcome, rather than as independent confirmation of it.

The outcomes also measure microbial counts, not a broader clinical endpoint. Similar patterns across microbial measures may be informative about the measured laboratory outcomes, but they do not establish effects on outcomes that were not assessed. The missing numerical report for the candidal measure and the absence of a reported multiplicity strategy limit how confidently the secondary findings can be generalized.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Change From Baseline in Aerobic Bacteria Microbial Count on Day 3
• Change From Baseline in Anaerobic Bacteria Microbial Count on Day 3
• Change From Baseline in Candidal Microbial Count on Day 3

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous, and the posted group descriptions use means and standard deviations. A mean describes the average change in microbial count for the participants represented in that group summary. A standard deviation describes how spread out individual measurements are around that mean. It is not a confidence interval and does not, by itself, describe how precisely the mean difference has been estimated.

What does the ANCOVA estimate represent?

The registry identifies the primary reported analysis as ANCOVA and labels its estimate a least-squares mean difference. In general, ANCOVA compares group outcomes while adjusting for specified covariates. A least-squares mean is an adjusted group mean derived from the fitted model, and the least-squares mean difference is the contrast between adjusted means. Adjustment can make the model-based estimate differ from a raw comparison of the posted group means. The covariates, model details, and contrast direction are not reported in the registry record, so the adjustment cannot be independently reconstructed from the record.

ANCOVA is a general method, not a guarantee that every possible source of bias or variation has been addressed. Its interpretation depends on the model specification, the measurements included, and the assumptions used. In this trial, the crossover design makes it particularly important to know how treatment period, sequence, and within-participant dependence were handled. The registry record does not report those details. It is therefore possible to describe the named method and reported estimate, but not to verify from the registry description whether the model fully reflected the crossover structure.

Why distinguish the recalculation from the reported analysis?

The recalculated comparison is an unadjusted calculation from the posted group summaries. It is a useful consistency check, but it does not reproduce a participant-level ANCOVA. Summary statistics omit individual observations and the relationships between measurements from the same participant. In a crossover study, those relationships can contribute to the model-based estimate and its uncertainty. The recalculation should therefore be identified as recalculated, not presented as the registry’s analysis.

Here, the recalculated mean difference is 0.58, while the registry’s ANCOVA estimate is -0.86. Their estimates have different signs under the stated weekly-relative-to-daily direction of the recalculation. The discrepancy flag means that the sponsor’s analysis takes precedence. The record does not give enough information to determine whether the disagreement arises from adjustment, coding, crossover handling, or another feature of the analysis. A statistical interpretation should report the disagreement rather than select a cause without evidence.

What do the p-value and confidence interval say?

A p-value describes how unusual the observed data, or more extreme data, would be under a specified null hypothesis and the assumptions of the analysis. It does not give the probability that the null hypothesis is true, and it does not measure the clinical importance of an estimate. The sponsor-reported p-value is 0.014. The recalculated unadjusted p-value is 0.466. Because the estimates come from different analyses and conflict, those values should not be treated as interchangeable evidence from one model.

A confidence interval gives a range of estimates compatible with the data and model under the method used. For the reported ANCOVA, the 95% interval extends from -1.530 to -0.196. For the unadjusted recalculation, the interval spans negative and positive values. These intervals answer questions about uncertainty for their respective analyses; they do not eliminate the concern that the analyses disagree. The registry’s adjusted analysis is the primary analysis reported by the sponsor, and the record does not describe an alternative planned analysis that would resolve the discrepancy.

Why can variability matter?

When measurements vary substantially among participants, the observed group average may be estimated less precisely. Standard deviations are one way to describe that variability for continuous outcomes. In general, over-dispersion means that observations vary more than a statistical model expects. This can make standard errors and confidence intervals too small if the model fails to accommodate the extra variation. The registry gives standard deviations for the primary group summaries, but it does not report an over-dispersion assessment or describe a model adjustment for it. No claim about over-dispersion is warranted from the posted summaries alone.

The count is expressed on a log10 scale, so the model works with changes on that transformed scale. Analyses on a transformed scale can be useful when the raw measure has a wide range, but interpretation should remain tied to the stated log-scale unit unless a further transformation is explicitly reported. The registry does not provide a back-transformed estimate for the primary comparison.

What do the planning calculations represent?

The planning illustrations use the observed effect as a reference and show participant requirements for detecting specified fractions of that effect under stated assumptions. They are not a reconstruction of the original trial design. Their assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They give participants per arm for these continuous outcomes. The original sample-size justification and design assumptions are not reported in the registry record.

11. Confidence Intervals and Precision

The sponsor-reported primary estimate is a least-squares mean difference of -0.86, with a 95% confidence interval from -1.530 to -0.196. The interval stays on the negative side of zero, and the reported p-value is 0.014. This describes uncertainty under the sponsor’s ANCOVA model. It does not account for uncertainty about whether that model was specified and interpreted in a way that can be verified from the registry record.

The unadjusted recalculation is less conclusive: its interval includes values on both sides of zero, and its p-value is 0.466. The disagreement between the adjusted analysis and the summary-statistic recalculation is itself important to precision and interpretation. The two intervals do not represent alternative estimates from an identical model; each is tied to a different analysis. The sponsor analysis takes precedence, but the record does not provide the model details needed to independently assess its adjustment or reproduce its interval.

A confidence interval is not a range containing a fixed proportion of individual participant measurements. It is an interval estimate for the model-defined contrast. Its width reflects sampling variability under the analysis assumptions, while its location indicates the estimated contrast. A narrow interval can still be affected by model misspecification or incomplete reporting; a wide interval signals greater uncertainty in the estimated contrast.

The group standard deviations, 2.248 for daily use and 2.636 for weekly use, show substantial spread in the posted change scores relative to the scale of the group means. The registry reports 19 participants for each treatment label, but the record does not explain how the crossover observations contributed to the sponsor’s uncertainty calculation. The interval should therefore be read as the reported model-based precision, not as an independently validated description of all sources of uncertainty.

12. 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 illustrations give participants per arm, not a total number of events. They use the observed effect as a reference and show plans based on detecting 100% of that observed effect, 75% of the observed effect, or 50% of the observed effect. Under the stated assumptions, the primary-outcome illustration gives 281 participants per arm for 80% power and 375 participants per arm for 90% power when planning for 100% of the observed effect. Planning for 75% gives 498 participants per arm for 80% power and 667 participants per arm for 90% power. Planning for 50% gives 1,121 participants per arm for 80% power and 1,500 participants per arm for 90% power.

The calculations assume a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The figures are planning illustrations based on the observed effect, not the trial’s original design assumptions; the original sample-size justification is not reported in the registry record. The calculations concern participants per arm for this continuous outcome, rather than a required total number of events.

In plain terms, 80% power is the probability of detecting an effect of the specified size if that effect is present, under the calculation’s assumptions. The 90% column uses a higher probability of detection under those assumptions and therefore requires more participants for the same effect. Smaller effects are harder to distinguish from random variation, so planning to detect a smaller fraction of the observed effect requires more participants. This is not observed power; it is a planning calculation based on an assumed effect size and statistical model.

13. 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 = 0.580; pooled standard deviation σ = 2.450.
2. n = 2 × (1.96 + 0.842)² × 2.450² / 0.580² = 280.0, rounded up to 281 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 <- 0.58                      # observed difference in means
sigma <- 2.44969385842395                     # 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(2780661)
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 = 281 (80% power), 375 (90% power)
 75% of observed effect: n per arm = 498 (80% power), 667 (90% power)
 50% of observed effect: n per arm = 1,121 (80% power), 1,500 (90% power)
power.t.test: 281 
Simulated power at n = 281 per arm: 0.796 (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.

14. Analyses Reported by the Sponsor

The sponsor-reported primary analysis is an ANCOVA with a least-squares mean difference of -0.86, a 95% confidence interval from -1.530 to -0.196, and a p-value of 0.014. A simple unadjusted recalculation from the posted summary statistics gives a mean difference of 0.58 for weekly use relative to daily use and p = 0.466. The estimates differ in both magnitude and sign under that recalculation’s stated direction.

This is a material discrepancy, not a rounding difference. The recalculation uses posted group summaries, while the sponsor reports an adjusted model-based contrast. The registry does not report the covariates, model specification, crossover handling, or contrast coding in enough detail to reproduce the ANCOVA. It is therefore not possible to determine from the registry record why the estimates diverge.

Because the discrepancy is flagged, the sponsor’s own analysis takes precedence over the simple recalculation when reporting the trial’s primary statistical result. That does not make the recalculation disappear: it remains a useful check showing that the posted summaries do not reproduce the reported estimate. A careful reading keeps the two analyses distinct and avoids treating the unadjusted calculation as a correction to the sponsor result or assuming an undocumented explanation for their disagreement.

15. Multiplicity, Missing Data and Analysis Populations

The registry identifies a primary Day 7 aerobic microbial-count outcome and lists secondary microbial-count outcomes, including Day 3 aerobic, anaerobic, and candidal measures. It also reports multiple outcome measures and analyses. The registry record does not report a multiplicity adjustment, a testing hierarchy, or a procedure for deciding how to interpret results across outcomes and time points. Without such information, nominal p-values for secondary comparisons should not be read as if they were protected from the increased chance of false-positive findings created by multiple testing.

The record does not describe a missing-data strategy for the primary or secondary outcomes. The primary population is defined as an intent-to-treat population including randomized participants who received at least one dose and had at least one post-baseline assessment. This definition identifies eligibility for that analysis population; it does not explain how missing measurements were handled, whether imputation was used, or how participants with incomplete crossover-period data contributed to the analysis. Those details are not reported in the registry record.

The intent-to-treat description is not the same as confirmation that every randomized participant contributed to every endpoint. The posted arm summaries list 19 participants for each treatment label, but the registry does not explain the completeness of paired measurements or the relationship between those summaries and the analysis set for the ANCOVA. It would be inappropriate to assume that all participants had complete observations for every period and outcome.

The protocol’s original sample-size assumptions and any interim-analysis plan are also not reported in the registry record. The planning illustrations based on the observed effect are separate calculations and do not document the original design. Overall, uncertainty about multiplicity, missing-data handling, and crossover analysis limits independent assessment of the statistical plan. These reporting gaps do not establish that the methods were inadequate; they mean that the registry record does not allow those aspects to be verified.

16. 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 1% reporting threshold.

Most frequent non-serious adverse event terms

The serious-adverse-event figures list 19 participants at risk during daily use and 19 at risk during weekly use, with zero serious adverse events in each treatment group. Deaths are recorded as zero in each group. These are the registry’s reported counts for the stated treatment labels.

Other adverse events are listed for 8 participants in each group, with 19 at risk in each. The record does not provide event terms or further detail in the safety information, so these counts do not describe the types, severity, timing, or relatedness of those events. The figures should not be interpreted as establishing that no unlisted or unreported events occurred.

Because the study used a crossover design, the treatment-group safety figures should not be added together or treated as separate, non-overlapping populations. The record does not clarify how participants with events across periods were counted. These reported figures describe what is recorded for each treatment group; they do not by themselves establish a comparative safety profile or support medical advice.

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

The primary endpoint concerns change in aerobic bacterial microbial count on the fitting surface of a maxillary denture over the stated treatment period. The registry’s sponsor-reported ANCOVA estimates a least-squares mean difference of -0.86, with a 95% confidence interval from -1.530 to -0.196 and a p-value of 0.014. Those statistics describe the sponsor’s adjusted comparison on the endpoint’s log10 scale.

The posted group summaries and an unadjusted recalculation do not agree with that adjusted result. The recalculated mean difference is 0.58 for weekly use relative to daily use, with p = 0.466, and the recalculated interval includes values on both sides of zero. The sponsor’s analysis takes precedence because the discrepancy is flagged, but limited reporting of the ANCOVA prevents an independent reconstruction. The evidence should therefore be described with both the sponsor result and the discrepancy in view.

Neither analysis alone establishes what the observed microbial-count change means for denture cleanliness in everyday use, for a person’s health, or for outcomes not measured in the study. The endpoint is a laboratory microbial-count measure collected at specified denture sites; it is not itself a direct measure of symptoms, quality of life, or longer-term clinical outcomes. The record does not establish a clinically important threshold for the measured change.

The results also apply to the study population and procedures described in the registry record. The trial’s enrollment was 19, and the record does not provide enough information to assess how representative participants were of other denture users. Its crossover design, incomplete reporting of analysis details, unreported missing-data methods, and absent multiplicity strategy are relevant when judging how much certainty to place in the findings. Statistical evidence about a measured outcome should not be converted into medical advice or a general claim about treatment effects beyond the posted data.

18. Why This Trial Matters Statistically

This study illustrates why the distinction between a raw summary comparison and an adjusted model result matters. The posted group means allow a simple unadjusted recalculation, but the sponsor’s ANCOVA reports a different estimate and inferential result. When analyses disagree materially, readers need to know which analysis was prespecified, how the model was constructed, and how the design was represented. Those details are not reported in the registry record, so transparent reporting of the discrepancy is important.

The crossover design raises a further statistical issue: observations from the same participant may be related, and the sequence and timing of treatment periods can matter. A method that ignores those features may not estimate uncertainty in the same way as a model that accounts for them. The registry names ANCOVA but does not describe its handling of periods or within-participant structure. This makes the result a useful example of why naming a method is not the same as providing enough detail to reproduce it.

The record also separates observed results from planning illustrations. Calculations based on the observed effect can show how sample requirements change when a smaller effect is targeted, but they do not reveal the trial’s original design rationale. In this study, the original sample-size justification is not reported. Keeping planning calculations distinct from observed power and from the trial’s actual design avoids overstating what the registry can establish.

Finally, the secondary outcomes show why multiplicity and reporting completeness matter. Several microbial outcomes are listed, while numerical results for the candidal outcome are not reported in the registry record and no multiplicity strategy is described. The trial therefore offers a compact case study in interpreting continuous outcomes, model-based estimates, confidence intervals, crossover structure, and incomplete statistical reporting without treating a p-value as a complete summary of evidence.

19. 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 does not report enough detail to independently reproduce the primary ANCOVA. Its covariates, contrast coding, assumptions, and treatment of the crossover structure are not described. The sponsor result differs materially from the unadjusted recalculation, and the record does not explain the source of that discrepancy.

The crossover description does not specify treatment sequence, period order, washout, or how period and sequence effects were assessed. The record also does not report missing-data methods or clarify whether the posted group summaries reflect complete paired observations. Those omissions make it difficult to assess the analysis population and the uncertainty calculation fully.

The candidal Day 3 outcome is listed, but numerical results are not reported in the registry record. No multiplicity adjustment or hierarchy for the secondary outcomes is described. This limits the strength of conclusions that can be drawn from secondary comparisons, especially when several outcomes and time points are considered.

The study enrollment was 19, and the registry record does not report the original sample-size justification. The sample-size illustrations based on the observed effect do not fill that gap. The record also gives limited detail about the other adverse events, including their terms and severity. Finally, the primary outcome is a site-sampled microbial measure; the registry does not report a clinical threshold for interpreting its size or broader outcomes that would establish how the measured changes translate beyond the assay.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Frequency of Denture Cleanser Use and Denture Cleanliness — NCT02780661.
• Registry record last updated 2018-12-24; status last verified 2018-12.
• Results first posted 2018-08-10.
• 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.

23. Record Summary

The registry describes a completed randomized, single-masked crossover study of daily and weekly denture-cleanser use, sponsored by GlaxoSmithKline. Enrollment was 19, and the primary outcome was change from baseline in aerobic bacteria microbial count on Day 7, measured in log10(CFU[colony forming unit]/disc+1).

The sponsor-reported primary ANCOVA estimate was -0.86, with a 95% confidence interval from -1.530 to -0.196 and p = 0.014. A simple unadjusted recalculation from the posted group summaries differs; because the discrepancy is flagged, the sponsor’s analysis takes precedence. The registry record does not provide enough model detail to explain or reproduce the difference.

Day 3 aerobic and anaerobic outcomes are posted, while numerical results for the listed candidal outcome are not reported in the registry record. The original sample-size justification, multiplicity strategy, missing-data methods, and detailed crossover analysis are also not reported.