Effects of Two Doses of a Common Cold Treatment on Alertness: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Effects of Two Doses of a Common Cold Treatment on Alertness (NCT01686646), a randomized phase 3 study. The primary outcome is Change From Baseline in Number of Accurate Responses to Rapid Visual Information Processing (RVIP) Cognitive Test.

2. Clinical Question

The study summary describes an investigation of alertness and performance using cognitive function and mood assessment in people with the common cold. The posted primary result focuses specifically on accurate responses in the RVIP task. Other planned or listed measures include response times and performance on sustained, divided, and other attention tasks. The registry record does not report a single overall measure combining these outcomes, so the primary question should be interpreted as a question about this defined task and measurement time.

3. Trial Design

The registry identifies this as a Phase 3, randomized, double-blind, parallel-group trial, with an enrollment of 240. GlaxoSmithKline is listed as the sponsor. The condition is common cold, and the status is completed. The registry gives a study start of 2011-11 and primary completion of 2012-11. These design labels describe the structure recorded for the trial; they do not, by themselves, establish that every possible source of bias was prevented.

Four arms appear in the primary endpoint results: Paracetamol + Caffeine Combination (1000/130), Paracetamol (1000), Paracetamol + Caffeine Combination (500/65), and Paracetamol (500). The results can therefore be read as two dose-matched comparisons. The registered arm descriptions also refer to highest-dose and low-dose versions of the treatments. The registry record does not report further details about how doses were selected or how treatment was administered.

The primary efficacy population is described as the Intent to Treat (ITT) population, defined in the registry as all randomized participants who received study treatment and had at least one post-baseline efficacy evaluation. This definition is narrower than simply all randomized participants, because it includes the treatment-received and post-baseline-evaluation conditions. The registry record does not report how participants without a post-baseline efficacy evaluation were handled in the endpoint analysis.

The registered primary endpoint is change from baseline in the number of accurate responses on the RVIP cognitive test, measured from baseline to 60 minutes post treatment administration. The arm summaries are reported as least-squares means with standard errors. Sponsor-reported analyses include ANCOVA comparisons. The registry record does not report the complete statistical analysis plan, the covariates used in ANCOVA, or the original design assumptions used to set enrollment.

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: Out of 244 participants screened, 4 did not meet the study criteria. Remaining 240 were randomized into the study.

Overall Study

Analysis population for the primary outcome, as defined in the registry: Intent to Treat (ITT) population: all randomized participants who received study treatment and had at least one post-baseline efficacy evaluation.

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 Number of Accurate Responses to Rapid Visual Information Processing (RVIP) Cognitive Test, measured over Baseline to 60 minutes post treatment administration.

The primary endpoint is change from baseline in the number of accurate responses on the Rapid Visual Information Processing (RVIP) cognitive test, from baseline to 60 minutes post treatment administration. The registry describes the RVIP as assessing visual attention mechanisms involved in remaining vigilant to periodically occurring events. Participants watched single numbers appearing in the centre of a screen and were asked to respond to consecutive sequences of three odd or three even numbers. The endpoint counts responses classified as accurate by the computerized task output.

Accuracy is one way to summarize performance on a sustained attention task. A higher count indicates more correct target responses within the task as recorded; it does not, by itself, capture response speed, errors, missed responses, or performance in everyday situations. The registry lists response time and inaccurate or missed responses among other cognitive outcomes, which are distinct from the primary measure.

Using change from baseline focuses the comparison on how the measured response count shifted from each participant’s starting assessment. A prespecified measurement time also makes the treatment contrast specific: this primary outcome concerns the assessment at 60 minutes, not a general effect across all post-treatment times. The registry describes the RVIP test as lasting approximately 9 minutes. The outcome is useful for a focused comparison of task performance, but it should not be treated as a complete measure of alertness, cognition, mood, or the overall experience of a common cold.

7. Results Posted in the Registry

• Paracetamol (1000): mean 4.80 versus 8.30 on control; difference -3.50 (95% CI -6.60 to -0.40), standardized effect d = -0.47; z-test p = 0.027.
• Paracetamol + Caffeine Combination (500/65): mean 4.50 versus 8.30 on control; difference -3.80 (95% CI -6.60 to -1.00), standardized effect d = -0.50; z-test p = 0.008.
• Paracetamol (500): mean 2.70 versus 8.30 on control; difference -5.60 (95% CI -8.39 to -2.81), standardized effect d = -0.74; z-test p = <0.001.

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 Number of Accurate Responses to RVIP Cognitive Test

• 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 errors.
• Result:
  • Paracetamol (1000): mean 4.40 versus 7.30 on control; difference -2.90 (95% CI -6.10 to 0.30), standardized effect d = -0.37; z-test p = 0.076.
  • Paracetamol + Caffeine Combination (500/65): mean 6.20 versus 7.30 on control; difference -1.10 (95% CI -3.99 to 1.79), standardized effect d = -0.14; z-test p = 0.456.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Paracetamol (1000) and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Paracetamol + Caffeine Combination (500/65) and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists secondary cognitive measures that cover response accuracy, response times, incorrect or missed responses, sustained attention, and divided attention. These outcomes broaden the assessment beyond the primary RVIP accuracy measure, but they represent different dimensions of task performance and should not be combined into a single conclusion without a prespecified synthesis method. The record lists nine secondary outcomes as posted; complete result details are not available for every listed measure in the information used for this analysis.

The available 120-minute RVIP results offer a later-time comparison for accurate responses. The sponsor’s adjusted contrasts favor the combination arms over their dose-matched paracetamol arms, but the registry’s reported uncertainty and p-value information are not uniform across those comparisons. The simple recalculations at that time point have intervals that include zero for both dose-matched contrasts. These secondary findings are broadly compatible with investigating whether the primary task-performance pattern persists at a later assessment, but they do not independently establish a consistent effect across all cognitive outcomes.

Secondary outcomes generally carry less evidential weight than a clearly specified primary endpoint, especially when several outcomes, times, and treatment comparisons are considered. A result can appear notable by chance when many hypotheses are examined. The registry record does not report a multiplicity adjustment or testing hierarchy. Consequently, secondary findings are best viewed as supportive or exploratory rather than as a set of independent confirmations. The absence of detailed results for some listed outcomes also prevents a complete assessment of whether effects were consistent across task accuracy, speed, and error measures.

Interpretation should preserve the distinction between what is listed as an outcome and what has a posted estimate. The registry record does not report enough detail to infer the direction or magnitude of results for every listed secondary measure. Those unreported results should not be filled in by extrapolating from the primary endpoint or from the available later RVIP assessment.

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

• Change From Baseline in Number of Accurate Responses to RVIP Cognitive Test
• Change From Baseline in Mean Time of Accurate Responses to RVIP Cognitive Task
• Change From Baseline in Number of Inaccurate and Missed Responses to RVIP Cognitive Task
• Change From Baseline in Number of Accurate Responses to Sustained Attention Tasks (SAT) Cognitive Test
• Change From Baseline in Mean Time of Accurate Responses to SAT Cognitive Task
• Change From Baseline in Number of Incorrect and Missed Responses to SAT Cognitive Test
• Change From Baseline in Number of Valid Responses to Divided Attention Task (DAT) Cognitive Test
• Change From Baseline in Mean Time of Accurate Responses to DAT Cognitive Test

9. Statistical Interpretation

10. Statistical Methods Explained

What does a least-squares mean describe?

A least-squares mean is a model-based estimate of a group mean. In an analysis of covariance, often abbreviated ANCOVA, the model estimates group differences while accounting for specified covariates. This adjustment can improve comparability or precision when the covariates are appropriate and correctly included. The registry reports ANCOVA for the sponsor’s comparisons, but the covariates and model details are not reported in the registry record. The least-squares means in the arm summaries and the sponsor’s adjusted contrasts should therefore be understood as different statistical summaries, not assumed to be identical quantities.

The registry gives the primary arm results as least-squares means with standard errors. A standard error describes the estimated sampling variability of a statistic, such as a mean. It is not the spread of individual participant responses. A standard deviation instead describes variability among observations. Confusing these measures can lead to an incorrect impression of how variable individual performance was or how precise a group estimate is.

What is a treatment contrast?

A contrast subtracts one group estimate from another according to a chosen ordering. Reversing the order changes the sign but not the underlying separation. The sponsor’s primary comparison is reported as a positive difference for the combination relative to paracetamol alone. The recalculation is expressed in the opposite direction, so its difference is negative. When reading a contrast, the group order and sign convention matter. The clinical interpretation should also consider the outcome scale: this contrast is measured in correct responses, not in standardized units or a percentage.

The recalculated estimates use a simple, unadjusted comparison of posted summary statistics. The pooled standard deviations are marked as approximate because the arm-level summaries report standard errors rather than standard deviations. This type of recalculation can act as a check on the broad scale and direction of a contrast, but it does not reproduce an ANCOVA model. It may differ from the sponsor result because of adjustment, model specification, or other features that cannot be resolved from the summary data. Since the registry marks a discrepancy, the sponsor’s own analysis takes precedence.

How should a confidence interval be read?

A confidence interval gives a range of estimates compatible with the data under the statistical model and its assumptions. It conveys uncertainty around the estimated contrast. A narrower interval indicates greater precision than a wider interval on the same scale. An interval crossing zero means that the data are compatible with contrasts on either side of no difference under that model; it does not prove that the groups are identical. An interval excluding zero indicates a contrast separated from zero at the corresponding confidence level, subject to the model and analysis choices.

The sponsor’s confidence intervals are reported at the 95% level. The recalculated intervals also summarize uncertainty, but they are based on the simple unadjusted calculation. Their interpretation is not interchangeable with the sponsor’s ANCOVA interval when the estimates and methods differ. Neither interval accounts for all possible sources of uncertainty, such as multiplicity or missing-data assumptions, unless those are explicitly incorporated in the analysis.

What does a p-value add?

A p-value describes how unusual the observed data, or data more extreme, would be under a specified null hypothesis and statistical model. It is not the probability that the null hypothesis is true, and it does not measure the magnitude or practical importance of a contrast. The sponsor reports p-values for some comparisons, while a p-value is not reported in the registry record for the combination-dose comparison. The recalculated p-values are unadjusted and should not be substituted for sponsor-reported ANCOVA results.

Multiplicity arises when several outcomes, dose comparisons, or time points are examined. Testing many hypotheses can increase the chance of observing an apparently persuasive result by chance. Methods such as a prespecified testing hierarchy or adjustment can address this issue, but the multiplicity procedure is not reported in the registry record. The number of listed outcomes and analyses makes this an important aspect of interpretation, not a basis for assuming that a particular correction was or was not used.

Why can over-dispersion matter?

Over-dispersion is a general concern when count data vary more than a statistical model expects. If a model underestimates that variability, standard errors may be too small and confidence intervals too narrow. The primary outcome is a count of accurate responses, but the registry describes the reported analysis using least-squares means and ANCOVA. The record does not report a count-model analysis or provide enough model detail to assess whether over-dispersion was considered. This is a general statistical issue, not evidence that the reported analysis is invalid.

For continuous outcomes, model choice also depends on the distribution of residuals, the relationship between covariates and outcome, and other assumptions. The registry record does not report diagnostic checks, the full model specification, or whether assumptions were assessed. These details would help readers evaluate model fit and the reliability of standard errors, but they are not available in the registry record.

11. Confidence Intervals and Precision

The sponsor’s primary ANCOVA estimate is a least-squares mean difference of 3.5 correct responses, with a 95% confidence interval from 0.4 to 6.5. The interval expresses uncertainty around the adjusted estimate on the original response-count scale. Its lower endpoint is above zero, so the sponsor’s reported interval is consistent with a positive difference for the combination relative to paracetamol alone under that analysis. The interval still allows a range of possible contrast sizes; it does not identify one exact effect.

The unadjusted recalculation gives the same comparison in the reverse direction, with an estimate of -3.5 and a 95% interval from -6.604 to -0.396. This interval reflects a simple calculation from the posted summary statistics, not the sponsor’s ANCOVA model. Because the registry marks a discrepancy, the sponsor’s own analysis takes precedence. The recalculated interval should be treated as a supplementary check rather than as the primary inferential result.

For the lower-dose combination versus paracetamol comparison, the sponsor’s 95% interval runs from -0.6 to 4.1. It includes zero, indicating that the reported analysis does not tightly distinguish a positive contrast from no difference or a contrast in the opposite direction. The registry also reports a 95% interval from 1.1 to 6.6 for the higher- versus lower-dose combination comparison, but does not report a p-value for it.

Confidence intervals do not account automatically for every design or analysis issue. Their coverage depends on the statistical model, the data, and the analysis being appropriate. The intervals also do not address multiplicity unless a suitable procedure was used, and the registry record does not report the multiplicity approach. Precision should therefore be judged alongside the analysis method, the number of comparisons, and the limits of the posted information.

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 sample-size illustrations express planned sample sizes as participants per arm for 80% power and participants per arm for 90% power. They are not total event counts: the record specifies that total events apply to time-to-event calculations, while these calculations use participants per arm. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each illustration uses a stated fraction of the observed effect as the effect to detect.

The 80% power column describes the number of participants per arm indicated by those assumptions for an 80% chance of detecting the selected effect if that effect is present and the assumptions hold. The 90% power column uses a higher target probability of detection and consequently calls for more participants per arm under the same general setup. These are planning quantities, not observed trial outcomes. They are not evidence that the completed trial had a particular probability of finding a result.

The rows that use 100%, 75%, or 50% of the observed effect show how the planning requirement changes when the target effect is made smaller. Smaller effects need more participants because they are harder to distinguish from random variation. The listed values are illustrations based on observed effects and the stated calculation assumptions, not the original sample-size justification. The original trial’s sample-size assumptions and justification are not reported in the registry record. This is not observed power.

The underlying effect estimate may itself be uncertain, particularly when estimated from a study with limited precision. Planning directly from an observed effect can therefore give an optimistic or unstable illustration. The values should be read as conditional scenarios, not as a recommendation for a future study or as proof that a particular design would achieve its target in practice.

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 = -3.500; pooled standard deviation σ = 7.513.
2. n = 2 × (1.96 + 0.842)² × 7.513² / -3.500² = 72.3, rounded up to 73 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 <- -3.5                      # observed difference in means
sigma <- 7.51318840439929                     # 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(1686646)
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 = 73 (80% power), 97 (90% power)
 75% of observed effect: n per arm = 129 (80% power), 173 (90% power)
 50% of observed effect: n per arm = 290 (80% power), 388 (90% power)
power.t.test: 73.3 
Simulated power at n = 73 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 reports ANCOVA least-squares mean differences for the primary comparisons. For the higher-dose combination versus paracetamol comparison, the sponsor reports a difference of 3.5, a 95% confidence interval from 0.4 to 6.5, and p = 0.025. The summary-statistic recalculation gives a difference of -3.5 because it reverses the contrast order, and it uses an unadjusted method. The record explicitly flags a discrepancy between the sponsor analysis and the recalculation. The sponsor’s own analysis takes precedence.

This precedence matters because the recalculation does not have access to participant-level data or the full ANCOVA model. It uses arm-level means, standard errors, and an approximate pooled standard deviation. It cannot recreate covariate adjustment or other details of the sponsor’s analysis. Differences in estimates or uncertainty are therefore not unexpected and should not be resolved by selecting whichever result appears more favorable.

The sponsor’s analyses are the registry’s reported trial analyses; the recalculated estimates are supplementary and should be read as simple checks. The same distinction applies to the other comparisons: adjusted sponsor contrasts and unadjusted summary-statistic contrasts answer related, but not necessarily identical, statistical questions. The registry record does not report the complete model specification, so a more detailed reconciliation is not possible from the posted information.

15. Multiplicity, Missing Data and Analysis Populations

The trial includes several treatment arms, multiple cognitive outcomes, and more than one assessment time. Each additional comparison creates another opportunity for a result to appear unusual by chance. A prespecified multiplicity strategy can control the overall false-positive risk or organize testing in a hierarchy. The registry record does not report whether such a strategy was specified or applied. The reported p-values should therefore be interpreted as results for their individual comparisons, not assumed to account for all testing across the trial.

Missing-data handling is another important part of an efficacy analysis. The primary population is defined as randomized participants who received study treatment and had at least one post-baseline efficacy evaluation. The registry record does not report how missing measurements were handled, what assumptions were used for any imputation, or whether sensitivity analyses were performed. It also does not report the number of participants with missing primary endpoint data. Without those details, it is not possible to assess how robust the estimate is to missing outcomes.

The population definition should not be casually equated with every possible use of the term intention to treat. The registry uses ITT as its label, but explicitly includes the conditions of having received treatment and having at least one post-baseline efficacy evaluation. Those conditions affect who contributes to the analysis. The record does not report whether additional analyses used all randomized participants or another population.

The registry lists 10 outcome measures and 6 analyses. Those counts signal that the primary result sits within a broader analysis context, but they do not reveal which hypotheses were confirmatory, how outcomes were prioritized, or how testing was controlled. The statistical plan and these details are not reported in the registry record. They should remain acknowledged uncertainties rather than grounds for assuming a particular analysis procedure.

16. 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 1% reporting threshold.

The registry reports serious adverse event counts as zero in each of the four treatment groups. The corresponding numbers at risk are 46 for the higher-dose combination, 45 for Paracetamol (1000), 74 for the lower-dose combination, and 75 for Paracetamol (500). These figures describe the posted serious adverse event summary for the groups and the participants included in its at-risk counts.

A zero reported count means that no serious adverse events are recorded as affecting participants in those group summaries. It does not establish that treatment carries no risk, and it does not rule out events that were not captured, not classified as serious, or too uncommon to appear in this trial. The deaths field is not reported in the registry record. The registry also does not list serious adverse event terms for these groups.

Safety counts should be interpreted with the recorded at-risk population and the scope of the reporting in mind. They are not a complete assessment of every potential adverse effect. The registry’s serious-event information does not provide a basis for comparing all tolerability outcomes or for drawing conclusions about safety beyond the events and groups recorded.

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

The posted primary results describe a difference in change from baseline in accurate responses on a computerized attention task at a specified time after treatment. The sponsor’s ANCOVA comparison for the higher-dose combination and paracetamol-only groups reports a positive difference with a 95% confidence interval that excludes zero. The corresponding lower-dose comparison has a wider interval that includes zero. The record also reports a separate contrast between combination dose groups. These are statistical findings about defined comparisons and a defined endpoint.

They do not establish that a treatment improves every aspect of alertness, cognition, mood, or functioning. Accurate response counts are only one task-based measure. Response speed, errors, missed responses, other cognitive tasks, and participants’ experience are distinct outcomes. The registry record does not report a single overall measure that combines them or show that a task result translates into a broader clinical benefit.

A statistically distinguishable contrast is not automatically a clinically important one. The registry record does not provide a threshold for a meaningful change in correct responses, and the endpoint is not itself described as a measure of daily functioning. The size of the estimate should be read on its response-count scale and in light of its confidence interval, not solely by its p-value.

The results also do not establish what would happen in people or settings outside the population and treatment comparisons recorded. The registry describes participants suffering from the common cold, but the information available does not provide enough detail to characterize all eligibility criteria or generalizability. Nor can the safety summary be taken as evidence that there are no risks. Overall, the record supports a narrow statistical interpretation of the posted cognitive endpoint, while leaving broader clinical meaning and several analysis details unresolved.

18. Why This Trial Matters Statistically

This trial is statistically interesting because it compares combination treatment with dose-matched paracetamol alone at two dose levels and reports a focused cognitive endpoint. The design creates a clear distinction between a treatment-combination question and a dose-level question. Keeping those contrasts separate is essential: a comparison between combination and paracetamol alone is not the same as a comparison between two combination doses.

It also illustrates why readers should distinguish adjusted sponsor analyses from recalculations based on summary statistics. The primary recalculation has a contrast in the reverse direction and is flagged as discrepant from the sponsor analysis. The summary calculation cannot recreate the trial’s ANCOVA model. Giving precedence to the sponsor’s reported analysis, while retaining the recalculation as a transparent supplementary check, avoids treating a simplified estimate as though it were the original analysis.

The outcome also highlights the difference between statistical evidence and broad clinical interpretation. A count of accurate responses on a cognitive task is precise in definition, but it does not represent every dimension of alertness or everyday function. The confidence interval helps convey uncertainty in the group contrast, while the absence of reported multiplicity and missing-data procedures limits how fully the evidence can be evaluated.

Finally, the sample-size illustrations demonstrate that planning depends on the effect one intends to detect. Smaller target effects require more participants under the stated assumptions. Because the illustrations are based on observed effects rather than the trial’s original design justification, they are useful for understanding planning mechanics, not for inferring that the completed study was adequately powered for every comparison.

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.

Several trial-specific limitations follow from the registry information. The posted primary outcome is one cognitive measure at one post-treatment time, so it cannot summarize all aspects of alertness, mood, or cognitive performance described in the study summary. Other registered outcomes include response-time and attention-task measures, but detailed estimates are not reported for every listed outcome in the information available for this analysis. This limits assessment of consistency across the broader outcome set.

The sponsor’s ANCOVA results are not accompanied by the full model specification. Covariates, diagnostic checks, and other modeling details are not reported in the registry record. The record also flags a discrepancy between the sponsor analysis and the simple recalculation from posted summaries. The sponsor’s analysis takes precedence, but the available information does not permit a complete explanation of the discrepancy.

The primary efficacy population excludes randomized participants who did not receive treatment or lacked a post-baseline efficacy evaluation, according to the registry definition. The number of missing endpoint values and their handling are not reported in the registry record. The multiplicity strategy is also not reported, despite multiple outcomes, treatment comparisons, and assessment times being listed. These omissions limit assessment of how the nominal uncertainty measures relate to the full set of analyses.

The registry does not report the original sample-size justification or the assumptions used to plan the trial. The planning illustrations are based on observed effects and stated generic assumptions, rather than the trial’s original design plan. Finally, the serious adverse event summary records zero affected participants in each group, but the deaths field is not reported and the summary does not describe all possible adverse outcomes. These limits should shape interpretation without implying that unreported methods or results had a particular form.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Effects of Two Doses of a Common Cold Treatment on Alertness — NCT01686646.
• Registry record last updated 2014-12-08; status last verified 2014-07.
• Results first posted 2014-07-14.
• 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 record describes a completed Phase 3 randomized, double-blind, parallel-group study of paracetamol with caffeine versus paracetamol alone in people with the common cold. Enrollment is recorded as 240, and GlaxoSmithKline is listed as sponsor. The primary endpoint is change from baseline in accurate RVIP responses at 60 minutes after treatment.

The sponsor reports an ANCOVA difference for the higher-dose combination versus paracetamol comparison, with a 95% confidence interval excluding zero; the lower-dose comparison’s reported interval includes zero. A discrepancy is flagged between sponsor results and simple summary-statistic recalculations, so the sponsor’s own analysis takes precedence. Secondary cognitive outcomes and serious adverse event summaries are also recorded, but multiplicity procedures, missing-data handling, and the original sample-size justification are not reported in the registry record.