Comparison of Two Daily Disposable Lenses: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Comparison of Two Daily Disposable Lenses (NCT04013789), a randomized na study. The primary outcome is Mean Distance Visual Acuity (VA) With Study Lenses.

2. Clinical Question

This is a comparison of measured visual acuity under the two lens conditions, not a comparison of separate parallel groups receiving only one product. The posted means are -0.2 for DACP FreshTech and -0.22 for DACP. The unadjusted contrast is reported as -0.02 for DACP relative to DACP FreshTech, with a confidence interval from -0.039 to -0.001. The registry’s separate model-based analysis reports a least-squares mean difference of 0.02, with a 95% confidence interval upper bound of 0.03 and no lower bound posted.

3. Trial Design

The registry record describes a randomized, double-masked, crossover study of two daily disposable contact lenses. Its listed enrollment is 79, and its status is completed. The study began on 2019-08-27 and had a primary completion date of 2019-11-22. The sponsor is Alcon Research. The phase is listed as not applicable.

Participants were randomized to one of two product orders: DACP FreshTech followed by DACP, or DACP followed by DACP FreshTech. Each product was worn in both eyes for approximately 8 hours per day for 1 week, with a new pair of lenses each day. The record does not describe a washout period, and details about how period or sequence effects were handled beyond the named analysis model are not reported in the registry record.

The primary outcome was mean distance visual acuity with study lenses at Week 1 for each product. The outcome population is defined as randomized subjects who were exposed to any study lenses, excluding optimized habitual and trial fit lenses. The reported product results each have a sample size of 66. In a crossover study, the same participant can contribute observations under both products; the two product counts therefore should not be interpreted as proof of two independent sets of 66 participants.

The registry lists one outcome measure and one analysis. The posted analysis is identified as a mixed effects repeated measures model and reports a least-squares mean difference for a non-inferiority analysis. Its full model specification, including which repeated measures and covariates were included, is not reported in the registry record. The allocation concealment process, details of masking, and original sample-size assumptions are also not reported in the registry record. No secondary outcomes are posted.

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: Of the 79 enrolled subjects, 11 were screen failures and 1 withdrew prior to randomization. This reporting group includes all randomized subjects (67).

First Wear Period (1 Week)

Second Wear Period (1 Week)

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set: All randomized subjects (as randomized) who were exposed to any study lenses, not including the optimized habitual and trial fit lenses.

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.

Population: This analysis population includes all randomized subjects.

6. Primary Endpoint

The registry lists the primary outcome as Mean Distance Visual Acuity (VA) With Study Lenses, measured over Week 1, each product.

Mean distance visual acuity measures how clearly participants could see at a distance while wearing the study lenses. The record says acuity was assessed at 4 meters using a letter chart and expressed in logMAR, or logarithm of the minimum angle of resolution. The scale has a meaningful direction: a lower logMAR value indicates better visual acuity. The record notes that a value of 0 corresponds to 20/20 Snellen visual acuity.

Using a continuous measurement retains information about the measured level of acuity rather than reducing each observation to a category. Reporting a mean gives a summary of the group’s measured values, while the standard deviation describes the spread of participant measurements around that mean. Those summaries help readers see both the average and the variability, although they do not show the full distribution of individual results.

The outcome was assessed at Week 1 for each product, after each product’s stated wear period. A within-participant comparison can be useful in a crossover design because each participant receives both products; the statistical analysis must account for the repeated observations rather than treating them as independent groups. The registry identifies the reported model as a mixed effects repeated measures model, but details of its specification are not reported in the registry record.

Visual acuity is the measured endpoint in this record. It should not be treated as a complete description of all aspects of lens experience or performance. No secondary outcome measures are posted, so other dimensions cannot be assessed from these results.

7. Results Posted in the Registry

• DACP: mean -0.22 versus -0.20 on control; difference -0.02 (95% CI -0.04 to -0.00), standardized effect d = -0.36; z-test p = 0.037.

8. Statistical Interpretation

9. Statistical Methods Explained

A mean is the arithmetic average of the observed values. For this continuous endpoint, each participant’s visual acuity measurement contributes to a group mean expressed in logMAR. The standard deviation describes how dispersed the observations are around the mean. A smaller standard deviation means measurements are more closely clustered around the average; it does not indicate how precisely the treatment contrast has been estimated.

Why account for repeated measurements?

In a crossover study, participants receive both products in different periods. Measurements from the same participant are usually related: factors affecting one measurement may also affect the other. A method that treats all product observations as independent can fail to account for that within-participant relationship. The registry identifies the sponsor’s method as a mixed effects repeated measures model. In general, mixed effects models can represent both systematic group or period patterns and the correlation among repeated observations. The exact model terms and covariance structure are not reported in the registry record, so the model cannot be reconstructed from the description alone.

The posted sponsor analysis is described as a least-squares mean difference. In general, a least-squares mean is a model-based estimate that may account for factors included in the model, unlike a simple arithmetic mean. The registry does not list all factors used in the analysis. The sponsor’s reported estimate therefore should not be assumed to be identical to the unadjusted difference calculated directly from the posted product means.

What does the unadjusted recalculation represent?

The unadjusted comparison uses the posted product means and standard deviations to form a simple contrast and its confidence interval. It is a descriptive recalculation, not a replacement for the sponsor’s repeated-measures analysis. The recalculated contrast is -0.02, with a 95% confidence interval from -0.039 to -0.001 and an unadjusted p-value of 0.037. It does not incorporate unreported model terms or the participant-level pairing that may be relevant in this crossover design. The standard deviations and group sample sizes alone do not reveal the within-participant correlation, which can affect precision in a paired comparison.

In general, a p-value measures how incompatible the observed data are with a specified null hypothesis, assuming the statistical model and its assumptions. It is not the probability that the null hypothesis is true, and it does not quantify the size or practical importance of an effect. A confidence interval provides a range of estimates compatible with the data and method at its stated confidence level. The interval and p-value in the unadjusted results apply to that recalculation, not automatically to the sponsor’s model-based non-inferiority analysis.

What is non-inferiority analysis?

In general, a non-inferiority analysis asks whether the results rule out an unacceptable loss relative to a comparator, using a prespecified margin. The margin defines how large a difference could be tolerated for the study’s stated purpose. Interpreting a non-inferiority result requires knowing the direction of the contrast, the margin, and the confidence interval in relation to that margin. The registry reports a non-inferiority analysis, a least-squares mean difference of 0.02, and an upper 95% confidence limit of 0.03. The margin and lower confidence limit are not reported in the registry record. Thus, the recorded result does not contain all the information needed to evaluate the criterion.

The sign of a contrast depends on the order in which products are subtracted. A positive estimate can describe the same underlying separation as a negative estimate if the contrast order is reversed. However, the registry does not state enough about the contrast coding to establish whether that explains the difference between the model-based estimate and the recalculation. The model-based estimate should not be silently reoriented or combined with the unadjusted interval.

Why can over-dispersion matter?

In general, over-dispersion means that observed variability is greater than a model assumes. For continuous outcomes, a mismatch between assumed and actual variability can make standard errors, confidence intervals, and tests unreliable. The posted endpoint includes standard deviations, but the registry does not provide diagnostics for distributional assumptions or evidence of over-dispersion. This is a general consideration, not a claim that over-dispersion occurred in this study.

Other design and analysis choices can also influence an estimate. In crossover trials, period effects, sequence effects, carryover, missing measurements, and within-person correlation may be relevant considerations. The registry’s brief description does not report enough detail to determine how each was assessed or handled. This does not establish that any such issue occurred; it identifies information needed for a fuller appraisal.

10. Confidence Intervals and Precision

The unadjusted mean difference is reported as -0.02 logMAR, with a 95% confidence interval from -0.039 to -0.001. This interval expresses uncertainty in the contrast calculated from the posted summary statistics under the unadjusted method. It does not include every source of uncertainty, such as possible effects of missing observations, model choice, or study conduct.

In general, a confidence interval gives a range of estimates that are reasonably compatible with the observed data and the method used, at the stated confidence level. It is not a guarantee that the true value lies within the particular interval, and it is not a range containing a specified proportion of individual participant measurements. The interval’s endpoints are estimates of the contrast, not limits on individual visual acuity.

The sponsor’s mixed effects repeated measures analysis reports a least-squares mean difference of 0.02 and an upper 95% confidence limit of 0.03. The lower confidence limit is not reported in the registry record. Without both bounds, the reported model-based interval cannot be fully described or compared with a non-inferiority margin. That margin is also not reported in the registry record.

The discrepancy flag is false, so the record does not designate a discrepancy between the reported and recalculated analyses. Nevertheless, the model-based and unadjusted estimates have opposite signs as posted. Their estimands, contrast coding, and model specifications are not documented in enough detail to explain that difference. Precision should therefore be discussed separately for each result rather than treating the estimates and intervals as interchangeable.

Precision is not the same as importance. The interval describes statistical uncertainty in an estimated contrast; it does not establish whether a difference is meaningful for participants. The registry does not provide a threshold for a clinically important difference in visual acuity.

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 original trial design. They are expressed as participants per arm, rather than total events. The assumptions are a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect to detect equal to the stated fraction of the observed effect. These are planning assumptions for the illustration; the trial’s own original design assumptions are not reported in the registry record.

The 80% power column gives the number of participants per arm that the illustration estimates would be needed for an 80% chance of detecting the chosen effect under those assumptions, if that effect were the true one. The 90% power column gives the corresponding planning count for a 90% chance. Power is a property of a proposed design under assumptions, not a measure of what happened in the completed study.

Rows describe planning for 100%, 75%, and 50% of the observed effect. Smaller effects require more participants to distinguish them from random variation with the same target power and significance level. The increase in planned sample size across those rows illustrates why planning directly from an observed effect can be sensitive to the effect chosen.

These values are not observed power. They are illustrations using the observed effect as an input, not an estimate of the study’s realized ability to detect an effect. They do not account for the crossover structure in the listed two-arm planning assumptions, or for unreported design features. The figures should therefore be read as generic planning calculations, not as a retrospective judgment that the trial was adequately or inadequately sized.

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 = -0.020; pooled standard deviation σ = 0.055.
2. n = 2 × (1.96 + 0.842)² × 0.055² / -0.020² = 119.7, rounded up to 120 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 <- -0.02                      # observed difference in means
sigma <- 0.0552268050859363                     # 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(4013789)
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 = 120 (80% power), 161 (90% power)
 75% of observed effect: n per arm = 213 (80% power), 285 (90% power)
 50% of observed effect: n per arm = 479 (80% power), 641 (90% power)
power.t.test: 120.7 
Simulated power at n = 120 per arm: 0.797 (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 registry reports the sponsor’s analysis as a mixed effects repeated measures model, with a least-squares mean difference of 0.02 and an upper 95% confidence limit of 0.03. The lower confidence limit and p-value are not reported in the registry record. The analysis is labelled non-inferiority, but the non-inferiority margin is not reported in the registry record.

The unadjusted recalculation from the posted means and standard deviations gives a mean difference of -0.02, with a 95% confidence interval from -0.039 to -0.001 and an unadjusted p-value of 0.037. This calculation is not the same analysis as the sponsor’s repeated-measures model. In general, model-based estimates can differ from simple summary-statistic contrasts because of the model and the way observations are represented.

The posted sponsor estimate and the recalculated estimate have opposite signs. The record does not provide enough detail to determine whether contrast order or another analysis feature accounts for this. The discrepancy flag is false, and the registry does not identify the results as discrepant. The two analyses should nonetheless be reported as recorded, without substituting one estimate or interval for the other. The sponsor’s non-inferiority conclusion cannot be independently evaluated from the registry values alone because the margin and complete confidence interval are unavailable.

14. Multiplicity, Missing Data and Analysis Populations

The registry lists one outcome measure and one analysis, and no secondary outcome measures are posted. That limited set of posted results makes the scope of any multiplicity issue difficult to assess. The record does not state whether additional outcomes, time points, subgroup analyses, or other statistical tests were planned or conducted but not posted. A multiplicity adjustment or strategy is not reported in the registry record.

In general, testing multiple hypotheses can increase the chance of observing at least one nominally unusual result by chance. Researchers may address that issue through prespecified testing hierarchies, adjustments, or interpretation focused on estimation rather than isolated significance tests. The registry does not report which, if any, approach was used. The unadjusted p-value of 0.037 should therefore be understood as the value for the posted unadjusted comparison, not as evidence that all possible testing concerns were resolved.

The outcome population is defined as randomized participants who were exposed to any study lenses, excluding optimized habitual and trial fit lenses. The record reports 66 observations for each product, while enrollment was 79. It does not provide a participant flow account, reasons for non-inclusion, or missing-data methods. The handling of incomplete observations, withdrawals, or deviations from randomized product order is not reported in the registry record.

In general, missing data can affect both the estimated treatment contrast and its uncertainty, particularly if the chance of a missing measurement is related to the measured outcome or treatment experience. This is a general concern, not evidence that missingness biased these results. The registry does not give enough information to assess the potential effect of missing data.

The record defines the outcome analysis population, but details about analysis-set exclusions and whether all randomized participants were analyzed as randomized are not reported beyond that definition. Further information about the statistical analysis plan, prespecified contrasts, missing-data procedures, and any multiplicity strategy is not reported in the registry record.

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 5% reporting threshold.

The serious adverse event figures are reported separately for ocular and systemic or nonocular categories, and separately for each product. For DACP FreshTech, the registry lists 134 at risk in the ocular category and 67 at risk in the systemic or nonocular category. For DACP, it lists 132 at risk in the ocular category and 66 at risk in the systemic or nonocular category. The record reports zero serious events in each category and zero deaths.

These are the registry’s posted serious-event counts; they do not establish that no other adverse events occurred. The listed figures distinguish serious events from other adverse events, and the record reports zero other affected participants in the listed product categories as well. The record does not provide detailed adverse-event terms, severity breakdowns, or an account of event collection procedures.

Because the study is a crossover, participants may contribute exposure to both products. The at-risk counts should be read as recorded for each product and category, rather than added to infer a number of unique participants. These counts are descriptive safety information from the registry record and are not a substitute for a complete safety assessment.

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

The posted data describe mean distance visual acuity after each product period. The mean was -0.2 logMAR with DACP FreshTech and -0.22 with DACP. Since lower values indicate better acuity, the observed means favor DACP on this measured scale. The unadjusted contrast is -0.02, with a 95% confidence interval from -0.039 to -0.001 and an unadjusted p-value of 0.037.

These statistics do not by themselves establish whether the difference is clinically important. The record does not report a threshold for a meaningful difference in logMAR. Nor does the result describe every aspect of lens performance or participant experience: no secondary outcome measures are posted.

The registry’s primary reported analysis is a mixed effects repeated measures model, identified as a non-inferiority analysis. It reports a least-squares mean difference of 0.02 and an upper 95% confidence limit of 0.03. The lower confidence limit and the non-inferiority margin are not reported in the registry record. Consequently, the information needed to assess the non-inferiority criterion is incomplete. The model-based result and unadjusted recalculation have opposite signs, and the record does not provide enough detail to resolve that difference.

The study’s randomized, double-masked crossover design means that participants experienced both products in a randomized order. That design can support a within-participant comparison, but interpretation depends on appropriate handling of repeated measurements, periods, and missing data. The registry identifies a repeated-measures model but does not give its full specification or a detailed missing-data account.

The results should therefore be read as a limited statistical description of the posted visual-acuity measurements and reported analysis. They do not establish a broader claim about all clinical or practical differences between products, and the incomplete non-inferiority reporting prevents a full assessment of that specific analysis.

17. Why This Trial Matters Statistically

This trial is statistically notable because its crossover structure makes the relationship between observations important. Each participant was assigned an order and wore both products. A method that accounts for repeated measurements is relevant to such data, and the registry identifies a mixed effects repeated measures model as the reported analysis. At the same time, the registry does not provide enough detail to reproduce or fully assess that model.

The record also illustrates why an estimate should be read alongside its uncertainty and its analysis definition. The unadjusted recalculation uses product means and standard deviations, while the sponsor reports a least-squares mean difference from a repeated-measures model. Those are not automatically equivalent quantities. The posted signs differ, and the available model details do not explain the contrast coding or resolve the difference.

Non-inferiority interpretation depends on a prespecified margin and a confidence interval that can be judged against that margin. The registry labels the model-based analysis as non-inferiority, but the margin and lower confidence limit are not reported. The label alone is not enough to determine whether the criterion was met.

Finally, the distinction between observed results and planning calculations matters. The sample-size illustrations use fractions of the observed effect and generic assumptions, whereas the original design assumptions are not reported. They describe hypothetical planning requirements, not the trial’s realized power. Taken together, these features show why statistical interpretation depends not only on a point estimate but also on design, model specification, uncertainty, and transparent reporting.

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 registry record leaves several trial-specific details unavailable. Although participants were randomized to one of two product orders, the method of sequence generation and allocation concealment is not reported in the registry record. Masking is listed as double, but who was masked and how masking was maintained are not reported. The record does not describe a washout period or provide information on period, sequence, or carryover assessments.

The sponsor’s analysis is named as a mixed effects repeated measures model, but the model specification is not reported in the registry record. The contrast coding, model terms, covariance structure, and handling of incomplete repeated observations are not described. The non-inferiority margin and a lower confidence limit for the model-based estimate are also not reported, limiting interpretation of that analysis.

Enrollment was 79, while the outcome results list 66 observations for each product. The record defines the outcome population but does not provide a detailed flow of participants, explain all exclusions, or describe missing-data handling. It is not possible to determine from the posted record how those details might affect the result.

Only one outcome measure and one analysis are listed, with no secondary outcomes posted. A multiplicity plan, original sample-size justification, and original design assumptions are not reported in the registry record. The planning illustrations are based on the observed effect and generic assumptions, not on the trial’s documented design plan. These reporting gaps limit assessment of design adequacy, analysis reproducibility, and the completeness of the posted results.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Comparison of Two Daily Disposable Lenses — NCT04013789.
• Registry record last updated 2020-11-24; status last verified 2020-11.
• Results first posted 2020-11-10.
• 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.

22. Record Summary

NCT04013789 is a completed, randomized, double-masked crossover study sponsored by Alcon Research. It compared DACP FreshTech and DACP daily disposable contact lenses, with participants randomized to product order and each product worn in both eyes for approximately 8 hours per day for 1 week.

The primary outcome was mean distance visual acuity in logMAR at Week 1 for each product. The posted means were -0.2 for DACP FreshTech and -0.22 for DACP. The registry reports a mixed effects repeated measures non-inferiority analysis, but its margin and lower confidence limit are not reported. The unadjusted recalculation is -0.02, with a 95% confidence interval from -0.039 to -0.001 and p = 0.037.

The record lists 79 enrolled participants and outcome counts of 66 for each product. It reports zero serious adverse events and zero deaths in the listed categories. No secondary outcomes are posted.