A Clinical Bite Force Study of Two Marketed Adhesives Against no Adhesive: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Clinical Bite Force Study of Two Marketed Adhesives Against no Adhesive (NCT03037307), a randomized na study. The primary outcome is Area Over Baseline Over 12 Hours (AOB0-12) for the Incisal Bite Force (Positive Control Adhesive Versus [vs.] Negative Control).

2. Clinical Question

3. Trial Design

This was a randomized, single-masked crossover study with an enrollment of 44 participants. The registry lists three conditions: a test adhesive, a positive-control adhesive, and a negative control with no assigned treatment. For the adhesive conditions, participants applied product to the clean, wet fitting surface of the upper denture following the product label and application instructions. The record does not identify who was masked, how the crossover sequences were arranged, or how long participants spent in each treatment period.

The study objective was to compare bite-force measurements over a 12-hour period. Its primary endpoint was area over baseline over 12 hours for incisal bite force. The primary analysis population included randomized participants with at least one post-baseline efficacy assessment. The registry labels the study completed and gives the start date as 2017-02-13 and primary completion date as 2017-05-04.

Although the study includes three treatment conditions, the posted primary outcome and analysis concern the positive-control adhesive versus the negative control. The reported analysis is an ANCOVA of the least-squares mean difference. The registry does not report the crossover sequence, the timing or conduct of assessments beyond the endpoint’s up-to-12-hour timeframe, the washout approach, or the model covariates. Those details matter when assessing how the repeated treatment periods and measurements were handled, so they cannot be inferred from the crossover label alone.

The record lists 44 participants enrolled, while the displayed group summaries each show 44. The analysis population is defined by having at least one post-baseline efficacy assessment, but the number meeting that criterion is not separately reported. The registry does not report the original sample-size justification or other design assumptions.

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 53 participants were screened. Out of which 44 participants were randomized in the study. 9 participants were not randomized because they did not meet the study criteria.

Period 1

Reasons for not completing this period:

Wash Out Period 1

Period 2

Wash Out Period 2

Analysis population for the primary outcome, as defined in the registry: Analysis for this outcome was performed on intention-to-treat (ITT) population which included all randomized participants with at least one post baseline assessment of efficacy.

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 Area Over Baseline Over 12 Hours (AOB0-12) for the Incisal Bite Force (Positive Control Adhesive Versus [vs.] Negative Control), measured over Up to 12 hours.

The primary endpoint, area over baseline over 12 hours for incisal bite force (AOB0-12), summarizes bite force across the assessment period relative to baseline. The registry says the calculation used the area under the curve over 12 hours, divided by 12 hours, and then subtracted baseline bite force. The area under the curve was calculated using the trapezoidal method. The transformation returns the measure to the scale of the original bite-force observations, with units of lbs.

This endpoint is used to represent how bite force changes over the full observation window rather than relying on a single measurement. In general, an area-over-time measure can capture both the magnitude and duration of deviations from baseline; averaging the area over the observation period gives the result the same scale as the original measurements. The registry describes higher AOB0-12 values as demonstrating stronger bite force over time than lower values.

The endpoint is continuous, and the posted group summaries are least-squares means with standard errors. The registry reports the timeframe as up to 12 hours. It does not report the specific assessment schedule, the baseline measurement distribution, or the detailed model specification. As a result, the endpoint’s definition is available, but some operational details about how measurements were collected and modeled are not reported in the registry record.

7. Results Posted in the Registry

• Negative Control: mean 2.03 versus 4.78 on control; difference -2.75 (95% CI -4.57 to -0.93), standardized effect d = -0.63; z-test p = 0.003.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous: each participant’s AOB0-12 is a numerical measurement in lbs. The registry reports group means as least-squares means and gives a standard error for each group. A least-squares mean is a model-based group estimate, while a standard error describes the estimated uncertainty of that mean under the fitted model. The record names ANCOVA as the method for the sponsor’s comparison, but does not identify the covariates or other model details.

What does ANCOVA contribute?

In general, analysis of covariance compares group outcomes while accounting for selected covariates in a statistical model. Such adjustment can change the estimated contrast compared with a direct comparison of the observed group means. The registry reports an adjusted least-squares mean difference of 2.76 for the positive-control adhesive versus the negative control. It does not report which covariates were included, how they were selected, or how the crossover design was represented in the model. Those omissions limit independent assessment of the adjusted estimate.

What does the unadjusted re-calculation represent?

The re-calculation is a simple, unadjusted comparison derived from the posted summary statistics. It reports negative control minus positive control as -2.75, with p = 0.003. The sponsor reports the contrast in the reverse direction, positive control minus negative control, as 2.76. Reversing the comparison order reverses the sign; it does not imply a different substantive contrast. The small difference in the displayed magnitudes is consistent with the distinction between a direct summary-statistic calculation and the sponsor’s adjusted model estimate.

The re-calculation uses a pooled standard deviation of 4.358, marked as approximate, and the standard errors of 0.657 for each displayed group. It also reports a standardized effect estimate of -0.631 for its comparison order. These calculations are not substitutes for the sponsor’s ANCOVA. In particular, the registry’s crossover designation means that observations may be related within participants, but the available summary-statistic calculation does not use a reported within-participant covariance structure. The registry does not provide that structure or enough detail to independently reconstruct the sponsor’s model.

How should the p-values be understood?

In general, a p-value measures how incompatible the observed data are with a specified null model, assuming that model and its analysis assumptions hold. It is not the probability that the null hypothesis is true, nor does it quantify the clinical importance of an estimate. The re-calculated p-value is 0.003, whereas the sponsor reports p < 0.001 from ANCOVA. Different adjustment and modeling approaches can yield different p-values. Because the analyses are not identical, their p-values should not be treated as competing estimates from the same procedure.

What is the role of the confidence interval?

In general, a confidence interval describes uncertainty around an estimated effect under the method used to calculate it. The sponsor’s 95% interval for the adjusted contrast ranges from 1.89 to 3.63 lbs. Its placement on the positive side of zero corresponds to the positive-control-minus-negative-control ordering. The interval communicates both direction and a range of values compatible with the model and data at the stated confidence level; it does not guarantee that the true effect lies within those particular limits.

In general, standard errors and confidence intervals depend on the analysis model and the information available in the data. They can be affected by the relationship between repeated observations, variation between participants, and missing outcome measurements. The posted record identifies an intention-to-treat analysis population but does not describe imputation, exclusions after randomization, or a missing-data sensitivity analysis. It also does not report whether any interim analyses were conducted. These are limits on what can be evaluated from the record, not evidence that a particular method was or was not used.

The endpoint is constructed from measurements across up to 12 hours using a trapezoidal area-under-the-curve calculation. In general, this approach uses the measured values and the intervals between them to approximate area over time. The assessment schedule and handling of irregular or missing measurements are not reported in the registry record. Consequently, the formula and method are stated, but the detail needed to reproduce the endpoint from participant-level measurements is unavailable.

10. Confidence Intervals and Precision

The sponsor’s adjusted estimate is a least-squares mean difference of 2.76 lbs for positive control minus negative control. Its 95% confidence interval runs from 1.89 to 3.63 lbs. In general, a confidence interval expresses the uncertainty associated with an estimate under a specified statistical method. The reported interval gives a range of effect sizes compatible with the ANCOVA analysis and its assumptions; it is not a guarantee about the value in the wider population.

The interval does not include zero, and both limits are positive in the sponsor’s comparison order. That conveys the direction of the adjusted contrast as reported. The interval’s width also shows that the result is not a single exact value. Precision depends on the amount of information in the analysis and the variability represented by the model. The registry reports standard errors of 0.657 for each displayed group summary, but does not provide a participant-level dataset or full model specification with which to independently reproduce the adjusted interval.

The unadjusted re-calculation is a separate analysis and reports an estimate of -2.75 for negative control minus positive control, with p = 0.003. Its sign is opposite because the comparison order is reversed. No confidence interval for that re-calculation is needed to interpret the sponsor’s posted interval, and the sponsor’s ANCOVA interval should not be treated as the interval for the unadjusted calculation.

In general, confidence intervals address statistical precision, not the practical or clinical importance of an effect. The registry does not report a threshold for interpreting a meaningful difference in AOB0-12. It also does not report the extent to which the result might vary across participants, treatment periods, or settings. The reported interval is therefore best understood as precision for the sponsor’s modeled contrast, rather than as a complete description of every source of uncertainty.

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 based on the observed effect, not the trial’s original design justification. They are participants per arm, not total events. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set as the stated fraction of the observed effect.

For planning at 100% of the observed effect, the illustration gives 40 participants per arm for 80% power and 53 participants per arm for 90% power. For planning at 75% of the observed effect, it gives 71 participants per arm for 80% power and 94 participants per arm for 90% power. For planning at 50% of the observed effect, it gives 158 participants per arm for 80% power and 212 participants per arm for 90% power.

In general, power is the probability that a planned study will detect an effect of a specified size under the assumed statistical model and design. The 80% and 90% columns describe different target probabilities of detecting the specified effect if the assumptions hold; they are not probabilities that the trial’s result is correct. The illustrations use the observed effect as their reference, then consider smaller fractions of that effect. Smaller effects need more participants to achieve the same target power under these assumptions.

These figures are not observed power. They do not show what power the completed study achieved, and they should not be read as the trial’s actual enrollment requirements. The registry does not report the original sample-size assumptions or justification. The illustrations also state equal allocation between two arms, whereas the trial itself is labeled crossover; they are planning calculations for the stated two-arm comparison, not a reconstruction of the trial’s design process.

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 = -2.750; pooled standard deviation σ = 4.358.
2. n = 2 × (1.96 + 0.842)² × 4.358² / -2.750² = 39.4, rounded up to 40 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 <- -2.75                      # observed difference in means
sigma <- 4.358044974527                     # 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(3037307)
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 = 40 (80% power), 53 (90% power)
 75% of observed effect: n per arm = 71 (80% power), 94 (90% power)
 50% of observed effect: n per arm = 158 (80% power), 212 (90% power)
power.t.test: 40.4 
Simulated power at n = 40 per arm: 0.795 (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. Analyses Reported by the Sponsor

The sponsor’s posted analysis is an ANCOVA comparing the positive-control adhesive with the negative control. It reports a least-squares mean difference of 2.76, a 95% confidence interval from 1.89 to 3.63, and p < 0.001. The estimate is expressed as positive control minus negative control.

The simple unadjusted re-calculation uses the displayed group summaries and expresses the contrast in the reverse order: negative control minus positive control. It reports -2.75 and p = 0.003. The reversed sign reflects the order of subtraction. The small difference in the displayed estimates reflects that the sponsor’s result is an adjusted model estimate, while the re-calculation is unadjusted and based on summary statistics. The registry indicates no discrepancy, so the sponsor’s own analysis takes precedence as the reported primary analysis.

The re-calculation is useful as a basic check on the direction and broad scale of the contrast, but it does not reproduce the ANCOVA or account for any unreported model details. The registry does not provide covariates, detailed crossover modeling, or enough information to independently reproduce the sponsor’s estimate and interval.

14. Multiplicity, Missing Data and Analysis Populations

The registry lists 2 outcome measures and 2 analyses, while the posted results identify this primary endpoint comparison. It reports no secondary posted outcomes. A plan for handling multiplicity across outcomes, treatment contrasts, or repeated analyses is not reported in the registry record. Consequently, it is not possible to determine whether the reported p-value was adjusted for multiple testing or whether a prespecified hierarchy of analyses was used.

The primary analysis population is described as intention-to-treat and includes randomized participants with at least one post-baseline efficacy assessment. This definition does not establish how participants without a post-baseline assessment were handled, or how missing measurements within a participant’s assessment period were treated. Imputation methods, missing-data assumptions, and sensitivity analyses are not reported in the registry record.

The trial is labeled crossover, but the registry does not report the treatment sequence, period structure, washout procedures, or the details of how within-participant correlation was modeled. The ANCOVA method is named, but the covariates and full model specification are not reported. These details are relevant to assessing the analysis of repeated treatment periods and measurements.

The registry also does not report whether interim analyses, stopping rules, or protocol deviations affected the analysis. Their absence from the registry record does not establish that none occurred. The available record supports a description of the stated population, endpoint, and posted comparison, but does not allow a full audit of analysis decisions or the effect of missingness and multiplicity on the result.

15. 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 0% reporting threshold.

Most frequent non-serious adverse event terms

The adverse-event summary reports no serious adverse events in the listed groups and no deaths. For other adverse events, the test-adhesive group had 2 affected participants among 42 at risk, and the positive-control group had 2 among 43 at risk. The negative-control group had 0 among 44 at risk. The overall group reports 4 affected participants among 44 at risk.

These are participant counts in the registry’s adverse-event summary. The record does not provide event terms for the reported non-serious events, so their nature cannot be described from these figures. The group counts should be read as the posted safety summaries, not as a detailed comparison of event rates or as evidence about a particular event type. The registry record also does not provide further context about exposure time or how adverse events were collected.

The figures are descriptive and do not replace the bite-force analysis. They also do not establish that an event was caused by an adhesive. No serious-event terms are listed in the record, and the displayed serious-event counts are zero for the treatment groups and overall participants.

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

The posted primary analysis describes a difference in AOB0-12 between the positive-control adhesive and the no-adhesive control. The sponsor’s adjusted estimate is 2.76 lbs for positive control minus negative control, with a 95% confidence interval from 1.89 to 3.63 and p < 0.001. The displayed group means are 4.78 lbs and 2.03 lbs, respectively. These statistics describe the endpoint and comparison reported in the registry.

They do not provide a result for the test adhesive against either comparator. The test product appears in the study design, but the posted primary analysis is the positive-control-versus-negative-control contrast. No conclusion about the test product’s comparative result follows from that contrast alone.

The statistical result also does not establish the practical importance of the observed difference. The registry does not report a threshold for a meaningful change in AOB0-12, nor does it describe how the bite-force measure relates to outcomes beyond the measured endpoint. A small p-value is not a measure of the magnitude or importance of an effect; the estimate and interval are needed to understand the reported scale and precision.

The record’s crossover label and ANCOVA result do not provide enough information to assess all design and modeling choices. Treatment sequence, period handling, washout, covariates, and missing-data methods are not reported in the registry record. The finding should therefore be interpreted as the sponsor’s posted adjusted comparison within this study, with those details and broader applicability remaining uncertain.

The adverse-event summary reports no serious adverse events and no deaths, with other adverse events recorded for some participants in the adhesive groups. Those figures are descriptive and do not establish causation or provide the event-level detail needed to characterize the non-serious events.

17. Why This Trial Matters Statistically

This study illustrates why an analysis needs to be read in the context of its design and the exact contrast being reported. The trial includes a test adhesive, a positive control, and a no-treatment control, but the posted primary result concerns only the positive control versus the negative control. Without keeping that distinction clear, a reader could incorrectly attribute the primary result to the test product.

It also shows how comparison order affects the sign of an estimate. The sponsor reports positive control minus negative control, while the simple re-calculation reports negative control minus positive control. The estimates therefore have opposite signs while representing the same pair of groups in reverse order. Stating the comparison alongside the estimate is essential for interpreting direction.

The adjusted ANCOVA result and unadjusted summary-statistic re-calculation answer related but not identical statistical questions. The sponsor’s model-based estimate is the primary reported analysis; a basic re-calculation can serve as a check on the posted means, but it cannot recreate unreported model details. This distinction is especially relevant for a study labeled crossover, where within-participant structure can matter.

Finally, the record separates statistical evidence from precision and design planning. The confidence interval gives information about uncertainty in the adjusted contrast, while the sample-size illustrations are hypothetical planning calculations based on fractions of the observed effect. Neither should be mistaken for a measure of clinical importance or for the trial’s original sample-size rationale, which is not reported in the registry record.

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.

Several design and reporting details needed to assess this particular study are not reported in the registry record. Although the trial is labeled crossover, the treatment sequence, number and duration of periods, washout approach, and period-specific assessment schedule are not described. The registry also does not say who was masked. These omissions make it difficult to assess potential period, sequence, or carryover considerations from the posted record alone.

The primary result compares the positive-control adhesive with no treatment. A corresponding posted primary result for the test adhesive is not included, limiting interpretation of the test product’s role in the study objective. Product names and further product-specific details are not reported in the posted results.

The ANCOVA model is named, but its covariates and treatment of the crossover structure are not reported. The intention-to-treat population is defined as randomized participants with at least one post-baseline efficacy assessment, yet the number meeting this definition and the handling of missing outcome measurements are not reported. The assessment schedule and details needed to reproduce the trapezoidal AOB0-12 calculation are also not included.

Finally, the record does not report the original sample-size justification, a multiplicity strategy, or whether interim analyses were conducted. The posted safety summary does not name the non-serious events. These gaps do not invalidate the reported statistics, but they constrain independent assessment of the analysis, completeness of reporting, and the scope of conclusions that can be drawn.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: A Clinical Bite Force Study of Two Marketed Adhesives Against no Adhesive — NCT03037307.
• Registry record last updated 2018-08-31; status last verified 2018-04.
• Results first posted 2018-08-31.
• 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

The registry record describes a completed randomized, single-masked crossover study with 44 participants, comparing two denture adhesives and a no-treatment control. The primary endpoint was AOB0-12 for incisal bite force over up to 12 hours, measured in lbs.

The posted primary result compares the positive-control adhesive with the negative control. The sponsor’s ANCOVA reports a least-squares mean difference of 2.76, with a 95% confidence interval from 1.89 to 3.63 and p < 0.001. A simple unadjusted re-calculation reports -2.75 for the reverse comparison order, with p = 0.003.

The registry does not report a primary result for the test adhesive, full crossover-model details, missing-data methods, or the original sample-size justification. The adverse-event summary lists no serious adverse events or deaths.