Parallel-Group Study to Assess the Effect of Rasagiline on Cognition in Patients With Parkinson's Disease: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Parallel-Group Study to Assess the Effect of Rasagiline on Cognition in Patients With Parkinson's Disease (NCT01723228), a randomized phase 4 study. The primary outcome is Mean Change From Baseline to Week 24 in the Scales for Outcomes in Parkinson's Disease-Cognition (SCOPA-COG) Summary Score.

2. Clinical Question

The central statistical question concerns the difference between group mean changes, not whether every participant’s score changed in the same way. SCOPA-COG assesses memory, attention, executive functioning, and visuospatial functioning. Its scores range from 0 to 43, with higher scores reflecting better performance. The registry reports a mean change of 1.6 units for rasagiline and 0.8 units for placebo in the primary analysis population. The reported between-group difference is 0.8 units, with a 95% confidence interval from -0.48 to 2.05.

The interval includes zero, so the posted primary analysis is compatible with no average difference as well as with differences in either direction. The point estimate is positive, but its precision does not isolate a positive difference from no difference. The analysis therefore describes the estimated group contrast and its uncertainty; it does not establish that the intervention caused a cognitive change or determine the importance of any possible difference to participants.

3. Trial Design

This completed phase 4 study was randomized, double-blind, placebo-controlled, and parallel-group. It evaluated rasagiline as add-on treatment over 24 weeks in adults with mild cognitive impairment in Parkinson’s disease. The registry lists enrollment of 170 participants. Rasagiline was given as a 1 mg oral tablet once daily, and placebo was given as an oral tablet once daily; both were used for 24 weeks.

The primary outcome was mean change in the SCOPA-COG summary score from baseline to Week 24 or early discontinuation. The primary outcome analysis population was modified intent-to-treat: participants had to be randomized, receive at least one dose of study drug, and have at least one postbaseline SCOPA-COG assessment. The analysis counts reported for the two groups were 82 and 80. Those counts describe the primary outcome population, not necessarily everyone enrolled or every analysis population used for other outcomes.

The registry also lists five secondary outcomes with posted results, including cognitive, daily-activity, and Parkinson’s disease rating measures. These outcomes were assessed over the same stated baseline-to-Week-24-or-early-discontinuation timeframe. The record reports 6 outcome measures and 13 analyses overall, but does not report the full analysis plan or explain how the analyses were selected or prioritized.

The study began in 2012-11, had primary completion in 2015-01, and is marked completed. The registry record does not report the original sample-size justification, the planned allocation ratio, the sequence-generation procedure, concealment details, or whether any interim analyses were planned. Randomization and double masking are recorded, but further operational details are not reported in the registry record.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Modified intent-to-treat population: all participants who were randomized, received at least 1 dose of study drug and had at least 1 postbaseline SCOPA-COG assessment.

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 Mean Change From Baseline to Week 24 in the Scales for Outcomes in Parkinson's Disease-Cognition (SCOPA-COG) Summary Score, measured over Baseline to Week 24 (or early discontinuation).

The primary endpoint is mean change from baseline to Week 24, or early discontinuation, in the SCOPA-COG summary score. SCOPA-COG evaluates four cognitive domains: memory, attention, executive functioning, and visuospatial functioning. Scores range from 0 to 43, and higher scores reflect better performance. The registry reports the endpoint as a least-squares mean with a standard error.

A continuous score retains information about the amount of change rather than reducing results to a binary category. Comparing mean change between groups can describe an average contrast across participants, while the interval around that contrast communicates uncertainty. A positive between-group difference in this score is oriented toward greater average change in the rasagiline group; the scale description indicates that higher scores reflect better performance. That orientation alone does not establish the clinical importance of a difference.

The endpoint is used to evaluate cognitive performance over the study period. It combines several domains into a summary score, so it gives an overall measure rather than separate estimates for memory, attention, executive functioning, and visuospatial functioning. Domain-specific primary results are not reported in the registry record. Nor does the record provide a threshold for a clinically important change, so the statistical estimate cannot by itself identify whether a particular score difference would matter to participants.

7. Results Posted in the Registry

• Rasagiline 1.0 mg/Day: mean 1.60 versus 0.80 on control; difference 0.80 (95% CI -0.48 to 2.08), standardized effect d = 0.19; z-test p = 0.219.

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 to Week 24 in the Montreal Cognitive Assessment (MoCA) Score

• 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:
  • Rasagiline 1.0 mg/Day: mean 0.90 versus 1.00 on control; difference -0.10 (95% CI -1.02 to 0.82), standardized effect d = -0.03; z-test p = 0.830.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Rasagiline 1.0 mg/Day and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline to Week 24 in the Penn Daily Activities Questionnaire (PDAQ) Score

• 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:
  • Rasagiline 1.0 mg/Day: mean -0.90 versus -0.10 on control; difference -0.80 (95% CI -2.84 to 1.24), standardized effect d = -0.12; z-test p = 0.442.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Rasagiline 1.0 mg/Day and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline to Week 24 in the Unified Parkinson's Disease Rating Scale (UPDRS), Motor Subscale (Part 3), Version 3, Score

• 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:
  • Rasagiline 1.0 mg/Day: mean -3.70 versus -1.20 on control; difference -2.50 (95% CI -4.48 to -0.52), standardized effect d = -0.39; z-test p = 0.013.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Rasagiline 1.0 mg/Day than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes cover several dimensions beyond the primary cognitive summary score, including cognitive assessment, daily activities, and motor function. Across the posted secondary results, estimates do not form a consistent pattern of group differences: some are close to zero, while another has a confidence interval that excludes zero. This variability is a reason to consider the secondary findings as a set rather than selecting an isolated result.

The secondary results can help describe whether the primary finding sits alongside similar or different patterns in other measures. They do not establish the primary endpoint, and differences among outcomes may reflect that the instruments assess distinct aspects of cognition and function. The primary SCOPA-COG result remains the central result for the registered primary question; secondary measures provide context rather than an independent confirmation of it.

Several outcomes and analyses increase the chance that at least one result may appear more notable by chance. The registry record does not report whether the sponsor adjusted secondary analyses for multiplicity, used a hierarchy, or designated particular outcomes as confirmatory. Without that information, unadjusted secondary p-values should carry less weight than a prespecified primary analysis. They are best treated as descriptive or hypothesis-generating evidence, not as stand-alone proof of an effect.

The registry lists 6 outcome measures and 13 analyses, while posted results are available for five secondary outcomes. The full analysis plan and the reason for any outcome or analysis not represented in the posted results are not reported in the registry record. Those omissions limit assessment of selective reporting and of how the secondary analyses fit into the original testing strategy.

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

• Change From Baseline to Week 24 in the Montreal Cognitive Assessment (MoCA) Score
• Change From Baseline to Week 24 in the Penn Daily Activities Questionnaire (PDAQ) Score
• Alzheimer's Disease Cooperative Study's Clinical Global Impression of Change Modified for Mild Cognitive Impairment (ADCS MCI-CGIC) Score at Week 24
• Change From Baseline to Week 24 in the Unified Parkinson's Disease Rating Scale (UPDRS), Motor Subscale (Part 3), Version 3, Score
• Change From Baseline to Week 24 in UPDRS, Activities of Daily Living (ADL) Subscale (Part 2), Version 3, Score

9. Statistical Interpretation

10. Statistical Methods Explained

What does the mean change describe?

The endpoint is continuous, meaning it is measured on a numerical scale rather than as a yes-or-no event. The reported group values are least-squares mean changes, estimates from a statistical model rather than necessarily simple arithmetic averages. The comparison of interest is the estimated mean change in the rasagiline group minus the estimated mean change in the placebo group. The posted difference is 0.8 units.

The primary endpoint reports standard errors of 0.45 and 0.47 for the two group estimates. A standard error describes the sampling uncertainty of an estimated mean: it reflects how much an estimate would vary across repeated samples under a model. It is not the spread of individual participant scores. The registry does not report standard deviations for the primary endpoint values.

What does the repeated measures model do?

The sponsor’s reported primary analysis used a repeated measures model. In general, repeated-measures methods analyze observations taken at more than one time point while accounting for the fact that observations from the same participant are related. Such models can estimate group contrasts over time and use information from repeated assessments according to the model specification. The registry record does not report the model’s full specification, including the covariance structure, included covariates, handling of incomplete observations, or all time points used in the model. Those details should not be inferred from the method label alone.

The primary estimate is a least-squares mean difference. In general, a least-squares mean is a model-based mean adjusted for terms included in the model. The registry names this parameter but does not list the covariates or other model terms. The estimate should therefore be read as the sponsor-reported model contrast, not as an independently reconstructed adjusted estimate.

How should the confidence interval and p-value be read?

A confidence interval expresses uncertainty around an estimated effect. The reported primary interval is -0.48 to 2.05 units at the 95% level. Because it includes zero, the range includes no difference between group means. It also spans values on both sides of zero, so the estimate is not precise enough to settle the direction of the contrast. The interval is not a range containing 95% of individual participant outcomes, and it does not assign a probability to a particular treatment effect.

The reported p-value is 0.220. It is a measure of compatibility between the observed data and a null hypothesis under the analysis model; it is not a measure of effect size or clinical importance. It should be considered alongside the effect estimate and interval, not used alone to characterize the result. The registry record does not report a multiplicity adjustment for the primary analysis.

What does the recalculation add?

The simple recalculation uses the posted group estimates and standard errors to form an unadjusted comparison. For the primary outcome it gives a mean difference of 0.8 and a p-value of 0.219. Its pooled standard deviation is approximate because the posted group dispersion values are standard errors rather than standard deviations. This calculation is a rough comparison based on summary statistics; it is not a reconstruction of the sponsor’s repeated-measures model, and it does not account for model covariates or repeated observations.

For this study, the sponsor’s posted primary result and the straightforward calculation are close, and the registry discrepancy indicator is false. The sponsor’s model remains the relevant reported analysis. More generally, over-dispersion matters when observed variability exceeds what a simple model assumes: an analysis that understates variability can produce intervals that are too narrow and tests that appear more decisive than warranted. That is a general statistical concern, not a finding established for this trial.

What is the role of analysis populations?

The primary population includes randomized participants who received at least one dose and had at least one postbaseline SCOPA-COG assessment. This is the registry’s definition of modified intent-to-treat for this outcome. It differs from an analysis of everyone randomized because participants without a dose or without a postbaseline assessment do not meet the stated inclusion definition. The primary outcome counts are 82 for rasagiline and 80 for placebo. The record does not report how many randomized participants were excluded from this outcome analysis or why.

Several secondary outcomes have their own reported participant counts, which can differ from the primary counts. A different count does not by itself establish why observations are missing or whether the difference affects the result. The registry record does not report a detailed missing-data procedure or sensitivity analyses for the primary endpoint.

11. Confidence Intervals and Precision

The primary estimated difference is 0.8 units, with a reported 95% confidence interval from -0.48 to 2.05. The interval is fairly broad in relation to the point estimate and crosses zero. It is compatible with no average difference, with a small difference in the opposite direction, and with a larger positive difference. Thus, the point estimate alone gives an incomplete account of what the study data support.

Precision concerns how narrowly the data locate an effect estimate, not whether an effect is important. A confidence interval is a range generated by an inferential procedure that, under its assumptions, would cover the true value in a stated proportion of repeated studies. It does not mean that there is a 95% probability that the true effect lies between the particular endpoints after the data have been observed. Nor does it describe the range of changes among individual participants.

The group standard errors for the primary mean changes are 0.45 and 0.47. These indicate uncertainty in the estimated means, not the variability of participant-level outcomes. The registry does not post primary standard deviations or a separate precision estimate for each cognitive domain. The primary contrast’s interval is the more direct summary of uncertainty in the between-group result.

Precision is also limited by the number of observations contributing to the analysis and by model and missing-data assumptions. The registry gives the primary analysis counts, but does not report the full information needed to judge the effect of missing outcomes or alternative modeling choices. The interval should therefore be interpreted as conditional on the sponsor’s reported analysis, rather than as resolving every source of uncertainty.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are participants per arm, not total participants or total events. This is a continuous-outcome illustration using the observed effect as its reference. The stated assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation; each planning scenario targets the stated fraction of the observed effect. The original trial’s own sample-size assumptions and justification are not reported in the registry record.

For the primary outcome, planning for 100% of the observed effect gives 421 participants per arm for 80% power and 563 participants per arm for 90% power. Planning for 75% of the observed effect gives 748 participants per arm for 80% power and 1,001 participants per arm for 90% power. Planning for 50% of the observed effect gives 1,681 participants per arm for 80% power and 2,251 participants per arm for 90% power.

In plain terms, the 80% power column gives the estimated participants per arm for a design with an 80% chance of detecting the specified effect under the stated assumptions; the 90% column gives the corresponding estimate for a higher chance. These are design probabilities for hypothetical future studies under the assumptions, not probabilities that the result in this trial is true. Smaller target effects require more participants because they are harder to distinguish from random variation. The figures are planning illustrations, not observed power, and they do not establish the sample size used or justified for the completed trial.

The planning curve should be understood in the same way: it illustrates how planned sample size changes as the target effect changes under the stated assumptions. It does not add evidence about the observed treatment contrast or replace the confidence interval for the primary result.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = 0.800; pooled standard deviation σ = 4.139.
2. n = 2 × (1.96 + 0.842)² × 4.139² / 0.800² = 420.2, rounded up to 421 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 <- 0.8                      # observed difference in means
sigma <- 4.13906163882588                     # 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(1723228)
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 = 421 (80% power), 563 (90% power)
 75% of observed effect: n per arm = 748 (80% power), 1,001 (90% power)
 50% of observed effect: n per arm = 1,681 (80% power), 2,251 (90% power)
power.t.test: 421.2 
Simulated power at n = 421 per arm: 0.802 (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’s primary analysis is reported as a repeated measures model. It estimates a least-squares mean difference of 0.8 units, with a 95% confidence interval from -0.48 to 2.05 and a p-value of 0.220. The simple unadjusted recalculation from the posted summary statistics also estimates a difference of 0.8, with a p-value of 0.219. The registry marks no discrepancy between the sponsor analysis and the recalculation.

The similarity of the estimates is reassuring as a basic numerical check, but the methods are not interchangeable. The recalculation is based only on group summary values and standard errors, uses an approximate pooled standard deviation for standardized calculations, and does not reproduce the repeated-measures model. It cannot verify the sponsor’s covariate adjustment, use of repeated observations, or treatment of incomplete data.

The sponsor’s analysis is the principal result because it is the posted model-based analysis. The unadjusted recalculation is supplementary context and should not supersede the reported model. Both results indicate that the primary estimate is imprecise enough that a zero difference remains compatible with the data.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when multiple outcomes, time points, subgroups, or statistical tests are examined. Each additional test creates another opportunity for a result to appear notable by chance. This is a general statistical concern. The registry lists 6 outcome measures and 13 analyses overall, and five secondary outcomes have posted results. It does not report a multiplicity adjustment, a testing hierarchy, or a complete prespecified analysis plan. The registry record therefore does not establish how the family of analyses was controlled or prioritized.

The primary outcome is identified, which provides a principal result to interpret. However, the record does not state whether the primary test was protected from other planned tests by a formal strategy, or whether secondary results were intended as confirmatory. The secondary results should consequently be interpreted with caution, particularly when individual findings are considered apart from the overall pattern.

For the primary analysis, the stated modified intent-to-treat population includes participants who were randomized, received at least one dose, and had at least one postbaseline SCOPA-COG assessment. This definition makes clear that the analysis is not simply everyone randomized. The registry reports 82 participants in the rasagiline group and 80 in the placebo group for the primary endpoint, but the number and reasons for exclusions from the randomized population are not reported in the registry record.

The outcome timeframe includes Week 24 or early discontinuation. That description does not specify how measurements after discontinuation were collected, how incomplete repeated assessments were handled, or what assumptions the repeated measures model made about missing data. The registry record does not report imputation methods, sensitivity analyses, or reasons for missing observations. Therefore, the effect of missing data on the primary estimate cannot be assessed from the posted details alone.

Other outcomes have their own analysis counts, and those counts are not identical across all measures. The record does not provide enough detail to distinguish missing measurements from other analysis-population requirements. These are reporting limitations; they do not by themselves show that the analyses are biased or that missingness changed the result.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: angina pectoris (1.2%), atrial fibrillation (1.2%), transient ischaemic attack (1.2%).

For serious adverse events, the registry reports one affected participant among 86 at risk in the rasagiline group and one among 84 at risk in the placebo group. The record lists angina pectoris, atrial fibrillation, and transient ischaemic attack among the top serious adverse event terms, each at 1.2%. These counts and listings describe events recorded in the study; they do not establish whether an event was caused by study treatment.

The registry also reports other, non-serious adverse events for 24 of 86 participants at risk in the rasagiline group and 14 of 84 at risk in the placebo group. These are overall counts rather than a description of the event types or their severity. The death values are not reported in the registry record.

Safety counts require context: the number of participants at risk, the event definitions, the observation period, and the completeness of reporting all matter. The record gives the at-risk counts and study duration, but does not provide enough detail to assess event timing, recurrence, exposure-adjusted rates, or causal attribution. Small differences in counts should not be read as evidence of a treatment effect.

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

The posted primary result estimates a 0.8-unit larger mean change in SCOPA-COG for rasagiline than placebo. The reported 95% confidence interval ranges from -0.48 to 2.05 and includes zero. The data therefore do not precisely determine whether the average difference is positive, absent, or slightly negative. The result is an estimate with uncertainty, not a definitive statement about what happened to every participant.

The outcome scale assesses cognitive performance across memory, attention, executive functioning, and visuospatial functioning, with higher scores reflecting better performance. The registry does not report a threshold for a clinically important change. Statistical uncertainty and clinical importance are different questions: an interval describes uncertainty about an average contrast, while clinical importance requires an interpretable threshold or other evidence about what differences matter to participants. Such a threshold is not reported in the registry record.

The study was conducted over 24 weeks and enrolled adults with mild cognitive impairment in Parkinson’s disease. Its result should not automatically be generalized to people outside that population, to other durations, or to treatment contexts not described in the record. The study’s add-on design also means the comparison concerns rasagiline versus placebo as add-on treatment, rather than treatment in isolation.

The posted data do not establish that rasagiline improves cognition, nor do they establish that it has no effect. They show a positive point estimate with an interval that remains compatible with no average difference. Secondary outcomes and adverse-event counts add context but do not resolve the uncertainty in the primary result. Individual treatment decisions require clinical judgment and are outside the scope of these statistical findings.

18. Why This Trial Matters Statistically

This trial illustrates why an effect estimate should be read together with its uncertainty. The primary point estimate is positive, but the confidence interval extends across zero. A reader who focuses only on the direction of the point estimate could overstate what the study resolves; a reader who focuses only on a p-value could miss the range of effects still compatible with the data.

It also shows the distinction between model-based sponsor results and simple recalculation from summary statistics. The unadjusted calculation provides a useful numerical check, while the repeated measures model is the reported primary analysis. Similar estimates do not make the methods identical: one uses posted summary values, while the other is based on a model whose complete specification is not available in the registry record.

The multiple secondary outcomes underscore the importance of a prespecified testing strategy. Findings across different measures can help characterize a result, but unadjusted testing across multiple analyses makes isolated findings less conclusive. Clear reporting of the analysis hierarchy, missing-data methods, and multiplicity approach would make it easier to judge the evidential weight of each result.

Finally, the planning illustrations show how sample-size needs depend on the effect a future study aims to detect. Smaller target effects require larger planned groups under the stated assumptions. Those calculations are not evidence about whether the completed study was adequately designed, because its original sample-size justification is not reported in the registry record. Together, these points make the study useful for understanding how design, model choice, precision, and reporting shape interpretation.

19. Limitations

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

The registry provides the primary estimate and the sponsor’s analysis method, but not a complete statistical analysis plan. The repeated measures model is named without a full description of its covariates, covariance structure, time-point specification, or handling of incomplete measurements. The registry record does not report the original sample-size justification, interim analyses, or detailed randomization and allocation procedures.

The primary modified intent-to-treat definition excludes randomized participants who did not receive a dose or did not have a postbaseline SCOPA-COG assessment. The record reports the analysis counts but does not describe exclusions, attrition, or reasons for missing outcome data. It also does not report sensitivity analyses for missingness. These gaps limit evaluation of how robust the primary result is to alternative assumptions.

The primary interval includes zero and spans effects in both directions. The registry does not report a clinically important difference threshold for SCOPA-COG, so the clinical relevance of the estimated range cannot be determined from the posted result alone. The endpoint is a summary across four domains; separate primary estimates for those domains are not reported.

There are multiple secondary outcomes and analyses, but the multiplicity strategy is not reported in the registry record. The results therefore cannot be fully placed within a known confirmatory testing hierarchy. The study’s completed status and enrollment are recorded, but details about adherence, treatment exposure, protocol deviations, and generalizability beyond the described population are not reported in the registry record.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Parallel-Group Study to Assess the Effect of Rasagiline on Cognition in Patients With Parkinson's Disease — NCT01723228.
• Registry record last updated 2021-11-09; status last verified 2021-11.
• Results first posted 2016-03-21.
• 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

This completed phase 4 study compared rasagiline 1 mg once daily with placebo as 24-week add-on treatment in adults with mild cognitive impairment in Parkinson’s disease. It was randomized, double-blind, placebo-controlled, and parallel-group, with registry enrollment of 170.

The primary outcome was mean change in SCOPA-COG from baseline to Week 24 or early discontinuation. In the modified intent-to-treat analysis, the reported group changes were 1.6 units and 0.8 units, with a least-squares mean difference of 0.8. The 95% confidence interval was -0.48 to 2.05, so the posted result remains compatible with no average difference.

Secondary measures cover cognitive, daily-activity, and Parkinson’s disease rating outcomes. The registry record does not report the full analysis plan, multiplicity approach, original sample-size justification, or detailed missing-data methods. The primary estimate should be interpreted with its uncertainty and these reporting limits in mind.