Evaluation of Three Daily Disposable Contact Lenses: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Evaluation of Three Daily Disposable Contact Lenses (NCT02568254), a randomized na study. The primary outcome is Overall Comfort.

2. Clinical Question

This is a question about patient-reported experience on a continuous scale, not a question about a clinical event or a binary success outcome. Higher CLUE scores indicate a more favorable response. The registry record reports the group means, standard deviations, confidence intervals for the comparisons, and unadjusted p-values. It does not report a detailed analysis method explaining whether the comparison calculations accounted for the crossover pairing. That matters because each participant's ratings across the lenses may be related.

3. Trial Design

The registry describes a completed, randomized, double-masked, single-site crossover study of three marketed contact lens products. Enrollment was 78. The study began on 2015-09-03, and primary completion was recorded as 2016-01-18. Participants were assigned to one of six lens sequences, with each sequence specifying a different order for wearing etafilcon A, nelfilcon A, and nesofilcon A.

The brief summary describes an 8-visit study. Each lens was intended to be worn for approximately 2 weeks, specified as 12 +/- 2 days. A minimum washout period of 3 days was planned before entering the study, and a minimum 7 day washout period was planned between dispensing each lens type. These features are relevant to the crossover structure: participants experienced all three lenses, and each person's ratings could potentially be compared across lens periods.

The primary outcome population was defined as subjects who completed all study visits without a major protocol deviation. The posted summaries give 72 for each lens. The record does not explain how the outcome population relates to all enrolled participants, how missing observations were handled, or whether every participant contributed data for every lens. It also does not report the methods used to account for treatment sequence, period, or possible carryover effects. These omissions limit what can be inferred about how the design was incorporated into the posted comparisons.

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 78 subjects were enrolled in this study. Of the enrolled subjects 74 subjects were dispensed at least 1 study lens and 4 subjects did not meet the eligbility criteria. Of the dispensed subjects 72 completed the study and 2 subjects were discontinued.

Period 1

Period 2

Reasons for not completing this period:

Period 3

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Subjects that completed all study visits without a major protocol deviation.

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: All subjects that were dispensed at least 1 study lens.

6. Primary Endpoint

The registry lists the primary outcome as Overall Comfort, measured over 2- Week Follow-up.

The primary endpoint is overall comfort measured with the Contact Lens User Experience™ (CLUE) questionnaire at the 2-Week Follow-up. CLUE is described in the registry as a validated patient-reported outcomes questionnaire for soft contact lens experience, covering comfort, vision, handling, and packaging. The endpoint reported for this trial is the comfort score, rather than a combined score across all those attributes.

The registry describes CLUE scores as derived using Item Response Theory and as following a normal distribution, with a population average score of 60 (SD 20) and a range of 0-120. Higher scores indicate a more favorable or positive response. The posted results summarize this continuous outcome with a mean and standard deviation for each lens.

Patient-reported comfort is relevant to a comparison of contact lenses because the outcome captures the wearer's experience directly. A mean difference describes the difference in average reported scores between lens types; it does not describe how every individual participant responded. The registry record does not report a threshold for a difference that participants or clinicians would consider important, so the practical importance of a score difference cannot be determined from statistical significance alone.

7. Results Posted in the Registry

• Nelfilcon A: mean 48.14 versus 58.74 on control; difference -10.60 (95% CI -18.85 to -2.35), standardized effect d = -0.42; z-test p = 0.012.
• Nesofilcon A: mean 57.32 versus 58.74 on control; difference -1.42 (95% CI -9.78 to 6.94), standardized effect d = -0.06; z-test p = 0.739.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is continuous: each participant's comfort response is represented by a CLUE score. The posted lens summaries use means and standard deviations. The mean describes the average score in the reported outcome population; the standard deviation describes the spread of individual scores around that mean. A standard deviation is not the uncertainty in the mean, and it does not describe the range of scores observed.

What does a mean difference express?

A mean difference compares average scores between two lens types. In the posted comparisons, etafilcon A is the reference. A negative difference for another lens means its posted mean is lower than the etafilcon A mean; a positive difference would mean it is higher. The mean difference is expressed in CLUE scale units. It does not mean that every participant's score changed by that amount, and it does not capture variation in individual responses.

How should the confidence intervals be read?

In general, a confidence interval describes the range of effect estimates compatible with the observed data under the calculation's statistical assumptions. A narrower interval conveys greater precision than a wider interval. If an interval for a mean difference includes zero, the data are compatible with no mean difference as well as with differences on either side, within the interval. If it excludes zero, the comparison is statistically distinguishable from zero at the corresponding unadjusted level. This interpretation does not determine whether the size of the difference matters to participants.

What does an unadjusted p-value tell the reader?

In general, a p-value measures how surprising the observed result, or a more extreme result, would be if the null hypothesis of no difference were true and the calculation's assumptions held. It is not the probability that the null hypothesis is true, and it is not a measure of effect size. The reported p-values are unadjusted. The registry record does not state whether a multiplicity procedure was planned or used, so the p-values should not be read as multiplicity-adjusted evidence across the comparisons.

Why does the crossover structure matter?

In a crossover design, the same participants receive more than one treatment, so measurements from a participant may be related. In general, a paired analysis can use this within-participant relationship, while an analysis treating observations as independent may not. The registry record reports arm-level means, standard deviations, mean differences, and unadjusted p-values, but does not report whether the within-participant correlation was incorporated. It also does not report whether the analysis included period or sequence effects, or how possible carryover was assessed. The presence of washout periods in the design description does not establish how these features were handled statistically.

What can be inferred from the posted summaries?

The means show the average reported comfort scores for each lens in the defined outcome population. The comparison estimates and confidence intervals describe uncertainty around the stated differences, subject to the methods used. The record does not provide an analysis plan or a detailed account of the calculation, and it lists no posted analysis entries. Therefore, interpretation should remain anchored to the reported summaries and their stated unadjusted status rather than assuming additional modeling or adjustment.

10. Confidence Intervals and Precision

The confidence interval for nelfilcon A versus etafilcon A runs from -18.85 to -2.349 around a mean difference of -10.6. Its endpoints are both below zero, so the posted interval is consistent with a lower mean score for nelfilcon A under the calculation used. The interval also shows that the estimate is not exact: values across a range of magnitudes remain compatible with the data and assumptions. The record does not give a threshold for a meaningful comfort-score difference, so the interval cannot be classified as wholly clinically important or unimportant from this information alone.

For nesofilcon A versus etafilcon A, the confidence interval runs from -9.781 to 6.941 around a mean difference of -1.42. It includes zero and includes differences in either direction. Thus, the estimate is compatible with a lower mean for nesofilcon A, little or no mean difference, or a higher mean, within the interval. The unadjusted p-value of 0.739 is consistent with this uncertainty; it is not evidence that the means are exactly equal.

Both comparisons have substantial uncertainty relative to the precision needed to pin down a single difference. The registry record does not report confidence intervals for the individual lens means, nor does it explain whether the comparison intervals account for paired observations in the crossover design. Their interpretation therefore depends on the calculation's assumptions, which are not fully described. Precision and statistical significance should be considered separately from practical importance and from any conclusion about individual participants.

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 own design assumptions. For these continuous-outcome comparisons, the entries 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 assumed effect to detect is a stated fraction of the observed effect. The registry record does not report the original trial's sample-size justification or planning assumptions.

The 80% power column gives the illustrative number of participants per arm that would yield an 80% chance of detecting the assumed effect under those planning assumptions, if the effect and other assumptions were correct. The 90% power column uses a higher target chance of detecting that effect and therefore generally requires more participants per arm. These figures are planning quantities, not observed power.

Rows for 100% of the observed effect use the full estimated difference as the planning target; rows for 75% and 50% use smaller effects. Smaller effects require more participants to distinguish them from random variation at the stated significance level and power target. For the comparison with nesofilcon A, the observed difference is close to zero relative to its uncertainty, so planning calculations based on fractions of that observed effect produce very large participant requirements. Such projections are especially sensitive to an imprecise observed effect and should not be treated as a forecast of the sample size needed for a future crossover study. The planning setup assumes equal allocation between two arms and does not establish that it matches this trial's design or analysis.

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 = -10.600; pooled standard deviation σ = 25.258.
2. n = 2 × (1.96 + 0.842)² × 25.258² / -10.600² = 89.1, rounded up to 90 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 <- -10.6                      # observed difference in means
sigma <- 25.2581675503192                     # 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(2568254)
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 = 90 (80% power), 120 (90% power)
 75% of observed effect: n per arm = 159 (80% power), 213 (90% power)
 50% of observed effect: n per arm = 357 (80% power), 478 (90% power)
power.t.test: 90.1 
Simulated power at n = 90 per arm: 0.799 (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. Multiplicity, Missing Data and Analysis Populations

The registry reports two unadjusted comparisons against etafilcon A: one for nelfilcon A and one for nesofilcon A. When several comparisons are examined, the chance of obtaining at least one apparently notable result can increase. In general, multiplicity methods control that risk by adjusting the testing approach or interpretation. The registry record does not report whether an adjustment was planned, which procedure might have been used, or whether another hierarchy of testing applied. The posted p-values should therefore be treated as unadjusted rather than as results from a documented multiplicity-controlled analysis.

The record lists no posted analysis entries. It does not report a statistical analysis plan, model specification, handling of within-participant correlation, treatment-period or sequence terms, or an approach to possible carryover. The crossover design and washout periods are described, but the registry does not explain how those design features were addressed in the endpoint analysis. The record also does not report interim analyses or stopping rules.

The outcome population is defined as subjects who completed all study visits without a major protocol deviation. The summaries report 72 for each lens, while enrollment was 78. The registry record does not give a participant flow explaining this difference, the number of missing measurements, reasons for missingness, or an imputation method. It does not state whether analyses were conducted in an intention-to-treat population or another population beyond the stated completion and protocol-deviation definition. Accordingly, the results apply to the reported outcome summaries; the record does not establish how missing data or exclusions might affect the estimates.

14. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

The serious adverse event figures report 0 affected among 74 at risk for etafilcon A, 0 among 74 at risk for nelfilcon A, and 0 among 74 at risk for nesofilcon A. No serious adverse event terms are listed. The other adverse event figures likewise report 0 affected among 74 at risk for each lens. These are the registry's posted counts for the groups and should be read as counts, not as proof that an event could not occur.

The record gives no death count; deaths are not reported in the registry record. It also does not provide additional detail about event definitions, collection procedures, exposure time, or how the crossover periods were accounted for in the safety summaries. The group risk denominators are not the same as the primary outcome summary counts, and the record does not explain that distinction. These results describe the posted adverse event counts only; they do not establish comparative safety in broader populations or under different use conditions.

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

The results describe average comfort ratings for three lenses among participants meeting the registry's stated outcome-population definition. The mean score for etafilcon A was 58.74, compared with 48.14 for nelfilcon A and 57.32 for nesofilcon A. The posted unadjusted comparison for nelfilcon A versus etafilcon A estimates a lower mean for nelfilcon A, with a confidence interval that excludes zero. The comparison for nesofilcon A versus etafilcon A is near zero in the posted estimate, but its interval includes differences in both directions.

These results do not establish that all participants preferred the same lens, because group means conceal individual response patterns. The standard deviations show substantial spread in scores, but the record does not provide individual-level distributions or paired response summaries. Nor does the record state what score difference would matter to participants. Statistical evidence about a mean difference and evidence about practical importance are separate questions.

The findings are limited to the endpoint, population, products, and follow-up described in the registry. They should not be extended to other contact lenses, other populations, or outcomes not reported. The record does not report secondary outcome results or a detailed analysis method, and it does not explain whether the crossover pairing was incorporated into the comparisons. For these reasons, the posted statistics support a description of the reported scores and comparisons, but not a broader claim about treatment effect or a definitive ranking of lenses for every wearer.

16. Why This Trial Matters Statistically

This study illustrates why trial design and statistical analysis need to be read together. In a crossover study, participants try each lens, so comparisons can potentially benefit from within-person information. At the same time, the analysis needs to account for the relationship among repeated measurements and may need to consider period, sequence, and carryover. The registry describes randomized sequences and washout periods, but does not report how these design features entered the endpoint calculations.

The endpoint also highlights the distinction between a statistically detectable mean difference and a difference that is important to users. The nelfilcon A comparison has an unadjusted interval that excludes zero, while the registry gives no threshold for interpreting the score difference's practical importance. The nesofilcon A estimate is close to zero, yet its interval remains compatible with a range of values in either direction. Looking only at whether a p-value crosses a conventional threshold would miss this difference in precision.

Finally, the record demonstrates the value of reporting analysis populations, missing-data handling, and multiplicity procedures. The study reports a defined completion population and unadjusted comparisons, but leaves key analysis details unreported. That limits independent assessment of how the crossover design and multiple comparisons affect interpretation. Clear methods alongside estimates and confidence intervals are essential for readers to judge both the statistical evidence and its limits.

17. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

Several trial-specific limitations affect interpretation. First, the registry record does not report whether the mean comparisons account for the crossover structure, including the paired measurements from participants who wore all three lenses. Nor does it describe adjustment for treatment sequence or period, or assessment of carryover. Washout periods are included in the design description, but their presence alone does not clarify the analysis.

Second, the primary outcome population excludes subjects who did not complete all study visits or had a major protocol deviation, by definition. The registry does not provide participant flow, reasons for exclusion, missing outcome counts, or details of missing-data handling. Enrollment was 78 and the outcome summaries report 72 per lens; the record does not explain the relationship between these figures.

Third, the posted p-values are unadjusted, and there are two comparisons against the etafilcon A reference. The record does not report a multiplicity plan or the original sample-size justification. It also does not report a threshold for a meaningful CLUE score difference, secondary outcome results, or the detailed model used to calculate the estimates and intervals. These gaps make it difficult to assess the sensitivity of the conclusions to analysis choices or the practical importance of the estimated differences.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Evaluation of Three Daily Disposable Contact Lenses — NCT02568254.
• Registry record last updated 2017-07-17; status last verified 2017-07.
• Results first posted 2017-07-17.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

21. Record Summary

NCT02568254 is a completed randomized, double-masked crossover study evaluating etafilcon A, nelfilcon A, and nesofilcon A. Enrollment was 78. The primary outcome was overall comfort measured by the CLUE questionnaire at the 2-Week Follow-up, among subjects completing all study visits without a major protocol deviation.

The posted mean scores were 58.74 for etafilcon A, 48.14 for nelfilcon A, and 57.32 for nesofilcon A. The unadjusted comparison against etafilcon A estimated a mean difference of -10.6 for nelfilcon A and -1.42 for nesofilcon A. The registry reports no serious or other adverse events affecting participants in the posted lens groups. Analysis details, missing-data methods, multiplicity procedures, and the original sample-size justification are not reported in the registry record.