Study of Azilect® (Rasagiline) in Levodopa-treated Parkinson's Disease Patients With Motor Fluctuations in Korea: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of Azilect® (Rasagiline) in Levodopa-treated Parkinson's Disease Patients With Motor Fluctuations in Korea (NCT01268891), a randomized phase 3 study. The primary outcome is Change From Baseline in Mean Total Daily OFF Time Using Parkinson's Disease Patient Diary.

2. Clinical Question

The endpoint focuses on time spent in the OFF state, when Parkinson’s motor symptoms fluctuate rather than being in an ON state. Participants recorded their daily motor state in a self-administered diary divided into 30-minute intervals. The study’s primary outcome summarized the diary-based total daily OFF time at baseline and follow-up visits.

The registry record describes a comparison of a fixed dose of Azilect® with placebo among people already receiving levodopa and experiencing motor fluctuations. The primary outcome combined measurements from Weeks 6, 10, 14, and 18 and compared their average with baseline. The analysis therefore concerns change in a daily time measure over the stated treatment period, not a single diary entry or a direct measure of all aspects of Parkinson’s disease.

The registry record also lists clinical status during ON time and two UPDRS outcomes as secondary measures. Those outcomes address other dimensions of status or function, but they do not replace the primary question about total daily OFF time. The statistical results describe the posted group summaries and comparisons; they do not by themselves establish what an individual patient should expect.

3. Trial Design

This was a Phase 3, randomized, triple-masked, parallel-group, placebo-controlled, fixed-dose study. The registry record lists 132 enrolled participants and identifies the condition as Parkinson’s disease. The trial compared Azilect® with placebo in levodopa-treated patients with motor fluctuations in Korea. The study is recorded as completed, with a start date of 2011-01 and primary completion in 2012-06.

The intervention was Azilect® (rasagiline) at 1 mg/day; the comparator was placebo. The registry describes the study as randomized and triple-masked but does not report the details of sequence generation, allocation concealment, or which specific roles were masked. Those details are not reported in the registry record. The record identifies a parallel-group structure, meaning the treatment groups were compared alongside one another rather than through a crossover arrangement.

The primary outcome was change from baseline in mean total daily OFF time, assessed with the Parkinson’s Disease Patient Diary. Its stated timeframe includes baseline and Weeks 6, 10, 14, and 18. The primary analysis population is described as the full-analysis set using observed cases. The posted arm summaries list 59 participants in the placebo group and 63 in the Azilect® group for this outcome. The record does not explain the relationship between these outcome-specific counts and the overall enrollment figure.

The registry lists three secondary outcomes: clinical status using the CGI-I score during ON time, change from baseline in UPDRS-ADL score during OFF time, and change from baseline in UPDRS Motor score during ON time. The record reports ANCOVA analyses for the primary and these secondary outcomes. Further details of the statistical analysis plan, including model covariates and any prespecified hierarchy among outcomes, 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.

Before assignment: The study consisted of a 2-week Screening Period during which the levodopa dose was optimised (if required), a 2-week Screening Period during which the levodopa dose was stabilised, an 18-week double-blind treatment period with rasagiline or placebo once daily (patients were randomised in a 1:1 ratio), and a 4-week Safety Follow-up Period.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full-analysis set (FAS); observed cases (OC)

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: Age and Gender: all-patients-treated set (APTS) - all patients in the APRS who took at least one dose of investigational medicinal product (IMP). Study-specific Characteristics: full-analysis set (FAS) - all patients in the APTS who had at least one valid post-baseline assessment of total daily OFF time (at least one valid post-baseline diary).

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in Mean Total Daily OFF Time Using Parkinson's Disease Patient Diary, measured over Baseline and Weeks 6, 10, 14, and 18.

The primary endpoint is the change from baseline in mean total daily OFF time, measured in hours using the Parkinson’s Disease Patient Diary. The diary is self-administered and divided into 30-minute intervals. For each interval, the participant selects one of four states: asleep; off; on with no dyskinesia or without troublesome dyskinesia; or on with troublesome dyskinesia. Daily OFF time is derived from the intervals classified as OFF.

The registry defines the change measure by comparing baseline total daily OFF time with the average total daily OFF time at Weeks 6, 10, 14, and 18. This combines repeated follow-up measurements rather than using only the final visit. A negative change indicates a lower mean daily OFF time than at baseline; the magnitude and uncertainty of the group comparison are needed to understand how precisely the groups differ.

This outcome is used because motor fluctuations include periods when a person is in an OFF state, and a diary can capture those states across the day. The measure is specific to reported daily OFF time. It is not, on its own, a complete measure of overall disease status or of every potential treatment effect. The registry does not report additional validation details for the diary in this trial or a threshold for interpreting a change as clinically important.

7. Results Posted in the Registry

• Azilect®: mean -1.59 versus -1.24 on control; difference -0.35 (95% CI -1.06 to 0.36), standardized effect d = -0.18; z-test p = 0.332.

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.

Clinical Status Using CGI-I Score During ON Time

• 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:
  • Azilect®: mean 3.05 versus 3.35 on control; difference -0.30 (95% CI -0.66 to 0.06), standardized effect d = -0.30; z-test p = 0.103.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Azilect® and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in UPDRS-ADL Score During OFF Time

• 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:
  • Azilect®: mean -0.57 versus 0.13 on control; difference -0.70 (95% CI -1.85 to 0.45), standardized effect d = -0.22; z-test p = 0.233.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Azilect® and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in UPDRS Motor Score During ON Time

• 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:
  • Azilect®: mean -2.87 versus -1.52 on control; difference -1.35 (95% CI -3.30 to 0.60), standardized effect d = -0.25; z-test p = 0.176.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Azilect® and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes cover clinical status during ON time and two UPDRS measures relating to activities of daily living during OFF time and motor status during ON time. Across these outcomes, the recalculated point estimates are negative for Azilect® relative to placebo, and each reported recalculated interval includes zero. The sponsor-reported ANCOVA intervals for the secondary outcomes also include zero. Taken together, the posted secondary results do not provide a clearly precise contrast across these different measures.

The secondary outcomes address related but nonidentical aspects of status and function. They should be considered alongside, rather than in place of, the primary endpoint, which focuses on mean daily OFF time. Their overall pattern does not remove the uncertainty in the primary comparison. Nor should agreement in the direction of point estimates be treated as independent confirmation: the outcomes come from the same trial population and may be related to one another.

The registry reports three secondary outcomes, but multiplicity adjustment or a prespecified testing hierarchy is not reported in the registry record. When multiple outcomes are examined, the chance of finding an apparently notable result by chance can increase if each is interpreted separately without accounting for the full set. Unadjusted secondary p-values therefore carry less evidential weight than a single prespecified primary analysis, especially when no multiplicity strategy is documented.

These secondary results are best treated as supporting context and as estimates with their own uncertainty, not as proof of a consistent effect across all clinical domains. The record does not report clinically important thresholds for these measures, so the scale of the estimates cannot be classified against such thresholds. The secondary outcomes also do not establish that one group was better or worse in a broad clinical sense; they report specific group comparisons for defined measures and timeframes.

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

• Clinical Status Using CGI-I Score During ON Time
• Change From Baseline in UPDRS-ADL Score During OFF Time
• Change From Baseline in UPDRS Motor Score During ON Time

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is a continuous measure: a mean change in hours of daily OFF time. For a continuous outcome, a group mean summarizes the average observed value, while the standard error describes uncertainty in that estimated mean. The posted standard errors are 0.26 for placebo and 0.25 for Azilect®. Standard errors are not the same as the spread of individual participants’ outcomes; they describe precision of the estimated group mean.

What does a mean difference represent?

The primary comparison is expressed as the mean difference for Azilect® relative to placebo. Its estimate is -0.35 hours in the recalculated comparison. The negative sign reflects the direction of subtraction and the direction of the observed contrast: the Azilect® group’s mean change was more negative. A mean difference is an average contrast between groups, not a statement that every participant had that change or that the groups had identical individual responses.

The recalculated comparison is an unadjusted calculation from posted summary statistics. It uses the group means and their reported standard errors rather than the trial’s participant-level data. It does not account for any covariates or other adjustments that may have been used in the sponsor’s model. The reported ANCOVA result is the registry’s own analysis, which uses an adjusted analysis approach, although the covariates and model specifications are not reported in the registry record.

How should the interval be read?

A confidence interval expresses uncertainty around an estimate under the assumptions of the analysis. It gives a range of values reasonably compatible with the observed data and statistical model. A narrower interval represents greater precision, while a wider interval leaves more uncertainty about the size and direction of the underlying difference. The recalculated primary interval runs from -1.057 to 0.357. Because it includes zero, it is compatible with no mean difference as well as with differences in either direction. The registry’s ANCOVA interval is reported at the 90% confidence level, from -0.93 to 0.23, and also includes zero.

The confidence interval does not assign a probability that the true effect lies within its particular limits. Nor does it show the range of individual participant responses. Its interpretation depends on the model and assumptions used to construct it. In this record, the interval from the recalculation and the sponsor-reported interval differ in width, even though their point estimates agree when rounded as displayed. They arise from different analyses, so they should not be treated as interchangeable.

What does the p-value add?

A p-value describes how unusual the observed data, or data more extreme, would be under a specified null hypothesis and analysis model. It is not the probability that the null hypothesis is true, nor does it measure the clinical importance of the estimate. The recalculated primary p-value is 0.332; the sponsor-reported ANCOVA p-value is 0.326. Both accompany estimates whose reported intervals include zero. These statistics do not establish that the groups are equivalent; demonstrating equivalence would require an appropriate design and a prespecified equivalence margin, which are not reported in the registry record.

Statistical significance and clinical importance are different questions. A result can be statistically uncertain while still allowing effects that could matter, and a precisely estimated difference need not necessarily be important to patients. The registry does not report a threshold for clinically important change in daily OFF time, so the posted estimate cannot be classified against such a threshold.

Why can adjusted and unadjusted results differ?

ANCOVA is a regression-based method that can compare outcome values while adjusting for other variables in the model. Adjustment may alter the estimated uncertainty and can also affect the estimate, depending on the data and model. The sponsor-reported primary analysis is ANCOVA and reports a mean difference in final values. The recalculation uses only the summary statistics and is unadjusted. The registry does not report the ANCOVA covariates, how baseline values entered the model, or other model diagnostics. Consequently, the adjusted result cannot be reconstructed from the posted group summaries alone.

The displayed arm summaries report mean changes with standard errors; the sponsor analysis describes a mean difference in final values. These descriptions are not identical formulations. The sponsor’s analysis is the trial’s reported analysis, whereas the recalculated contrast is a secondary, simple check using the posted summary statistics. Neither should be used to infer unavailable participant-level results.

Why do repeated measurements matter?

The primary endpoint averages daily OFF-time assessments from Weeks 6, 10, 14, and 18 and compares this average with baseline. Repeated measurements can represent experience across the treatment period more broadly than a single follow-up assessment. They also create analysis choices about incomplete visit data, correlation among repeated observations, and the construction of the average. The registry defines the averaging approach but does not report further details on how missing measurements were handled or how the ANCOVA model accounted for repeated observations.

General statistical context: when outcome variability is greater than expected under a simple model, over-dispersion can make standard errors too small if it is ignored. The registry does not report an over-dispersion assessment for this continuous endpoint, and the posted summary statistics do not permit one to be inferred. The primary comparison should therefore be read using the methods and uncertainty actually reported, without assuming additional model checks or adjustments.

11. Confidence Intervals and Precision

The primary estimate is -0.35 hours for Azilect® relative to placebo. The recalculated interval extends from -1.057 to 0.357, spanning negative and positive values and including zero. This range indicates that the point estimate is not precise enough to determine the direction of the underlying group difference. It also permits effects that differ meaningfully in size from the central estimate; the registry does not report a clinical-importance threshold with which to judge those possibilities.

The sponsor-reported ANCOVA estimate is -0.35, with a 90% confidence interval from -0.93 to 0.23. This also includes zero. Its reported p-value is 0.326. The recalculated p-value is 0.332, and its interval is from -1.057 to 0.357. These results are broadly similar in their central estimate and general interpretation, while the intervals are not identical because they come from different analyses. The registry record does not provide enough model detail to reproduce the ANCOVA interval.

Precision is about the range of uncertainty, not just whether an interval includes zero. An interval that includes zero does not prove the absence of an effect; it indicates that the data do not distinguish the estimated contrast from no difference under the stated analysis. Conversely, the negative point estimate does not establish a reliably negative difference when the interval also permits a positive one. The primary result therefore leaves uncertainty about both direction and magnitude.

The observed standard errors for the group means are 0.26 for placebo and 0.25 for Azilect®. These values describe precision of each mean, not the spread of participants’ individual daily OFF times. A group mean and its standard error alone cannot show how individual outcomes were distributed. The posted evidence is most appropriately read as an uncertain average contrast within the stated analysis population and outcome definition.

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 planning figures are participants per arm, not total events. They are planning illustrations calculated from the observed effect, not the trial’s original design assumptions. The planning assumptions listed are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each planning scenario uses the stated fraction of the observed effect as the effect to detect. The trial’s own original sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the estimated participants per arm for a design with an 80% chance of detecting the specified effect under those planning assumptions, if that effect is the true one and the assumptions hold. The 90% power column expresses the corresponding planning target for a 90% chance. These are design calculations, not a description of what happened in this completed trial. They are not observed power.

The effect scenarios are labeled as planning for 100%, 75%, and 50% of the observed effect. Smaller target effects require more participants per arm to distinguish them from no difference with the same planned power and significance level. The calculation is tied to the observed effect estimate, which itself is uncertain; it should therefore be treated as an illustration rather than a definitive prescription for a future study. Any actual design would also need assumptions about outcome variability, analysis, missing data, and other design features, many of which are not reported in the registry record.

The figures should be read as conditional planning quantities. They do not indicate that the completed trial had a particular probability of success, and they do not change the interpretation of the observed confidence interval. The displayed planning scenarios use the reported primary comparison’s effect and the stated assumptions, rather than reconstructing the sponsor’s original design process.

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 = -0.350; pooled standard deviation σ = 1.991.
2. n = 2 × (1.96 + 0.842)² × 1.991² / -0.350² = 507.7, rounded up to 508 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 <- -0.35                      # observed difference in means
sigma <- 1.9905028677866                     # 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(1268891)
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 = 508 (80% power), 680 (90% power)
 75% of observed effect: n per arm = 903 (80% power), 1,209 (90% power)
 50% of observed effect: n per arm = 2,031 (80% power), 2,719 (90% power)
power.t.test: 508.7 
Simulated power at n = 508 per arm: 0.804 (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 registry reports the sponsor’s primary analysis as ANCOVA, with a mean difference in final values of -0.35, a 90% confidence interval from -0.93 to 0.23, and p = 0.326. The unadjusted recalculation from posted summary statistics gives a mean difference of -0.35, an interval from -1.057 to 0.357, and p = 0.332. The central estimates agree at the displayed precision, while the intervals and p-values differ modestly because the calculations use different methods and information.

The recalculation is not a replacement for the trial’s analysis. It uses group-level means and standard errors and cannot reproduce an adjusted participant-level ANCOVA model. The registry does not report the covariates or full specification of that model, so the precise source of the interval-width difference cannot be identified from the record. The reported sponsor analysis remains the primary trial analysis; the recalculation offers an unadjusted comparison as a supplementary perspective.

No discrepancy is flagged between the recalculation and the sponsor-reported result. Both estimates are negative, and both reported intervals include zero. The results therefore have a similar broad interpretation while retaining uncertainty about the size and direction of the underlying difference.

15. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome and three secondary outcomes, with four outcome analyses reported. Testing several outcomes raises a multiplicity question: interpreting each result as though it were the only test can overstate the strength of evidence across the whole set. A prespecified hierarchy or adjustment can define how such results should be interpreted. Whether such a plan was used is not reported in the registry record. The secondary p-values are therefore described as unadjusted in this analysis, and should not be treated as though a multiplicity correction had been applied.

The primary population is described as the full-analysis set, using observed cases. This identifies the stated analysis population and indicates that observed cases contributed to the reported outcome summary. It does not, by itself, explain how participants entered the full-analysis set, whether all randomized participants were included, or how missing visits and diary entries were handled. Those details are not reported in the registry record.

Missing outcome data can affect estimates if the availability of measurements is related to participant characteristics or outcomes. Statistical approaches may make different assumptions about unobserved values, and those assumptions can influence the result. The registry does not report a missing-data method, sensitivity analyses, imputation strategy, or reasons for missing primary outcome observations. It is therefore not possible to assess from the record whether the posted result is robust to alternative missing-data assumptions.

The posted primary outcome counts are 59 for placebo and 63 for Azilect®, while overall enrollment is listed as 132. The record does not explain the relationship between those figures, so no reason for the difference should be inferred. It also does not report the number of participants with missing primary measurements or a participant flow account in the registry record for this analysis.

The registry reports ANCOVA for the primary and secondary outcomes but does not provide model covariates, diagnostics, or a full statistical analysis plan. Interim analyses and any associated statistical procedures are not reported in the registry record. These gaps limit independent assessment of analysis choices, multiplicity handling, and the sensitivity of results to missing data.

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: borderline ovarian tumour (3.0%), gastritis (1.5%), pyelonephritis acute (1.5%), joint injury (1.5%), subdural haemorrhage (1.5%).

The registry reports serious adverse events for groups with 66 participants at risk in each arm. Serious adverse events were reported for 4 participants in the placebo group and 5 in the Azilect® group. Other adverse events were reported for 12 participants in the placebo group and 19 in the Azilect® group. These are descriptive counts from the registry record; they do not establish that treatment caused an event or provide a complete comparison of safety.

The listed serious adverse event terms include Borderline ovarian tumour (3.0%), Gastritis (1.5%), Pyelonephritis acute (1.5%), Joint injury (1.5%), Subdural haemorrhage (1.5%), and Wrist fracture (1.5%). The record does not provide a full breakdown of these terms by treatment group in the registry record for this analysis. The percentages should therefore not be used to infer a group-specific risk for any listed term.

Deaths are not reported in the registry record. The adverse-event figures are not a substitute for a detailed safety analysis: information about event timing, severity beyond the serious classification, relatedness to study treatment, exposure duration, and statistical comparisons is not reported in the registry record. Counts from a trial describe what was recorded during the study, but they cannot by themselves establish causation or quantify every potential safety concern.

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

The posted primary results show mean changes of -1.24 hours for placebo and -1.59 hours for Azilect® in daily OFF time. The recalculated contrast is -0.35 hours, and the sponsor-reported ANCOVA estimate is also -0.35. Both analyses leave uncertainty around the group difference: the recalculated interval extends from -1.057 to 0.357, while the sponsor’s 90% interval extends from -0.93 to 0.23. Each interval includes zero.

This means the posted analyses do not precisely determine whether the underlying average difference is negative, positive, or close to no difference. It does not mean the groups have been shown to be equivalent. Equivalence requires a suitable design and a prespecified margin, neither of which is reported in the registry record. Nor does a negative point estimate alone establish a reliably larger reduction in OFF time for the Azilect® group.

The result applies to the measured outcome, the stated treatment period, and the analysis population described in the registry. It concerns diary-based mean daily OFF time averaged over specified follow-up visits. It does not directly answer every question about Parkinson’s disease, daily functioning, individual response, long-term outcomes, or other populations. The registry record does not provide a clinical-importance threshold for the primary outcome, so the estimate cannot be classified as clinically important or unimportant on that basis.

The secondary outcomes add context but do not resolve the primary uncertainty. Their analyses are unadjusted for multiplicity in the posted summaries, and multiplicity handling is not reported. The adverse-event counts are descriptive and cannot establish whether events were caused by treatment. The study’s results should therefore be understood as statistical estimates with defined limits, rather than as a general conclusion about treatment for all patients or as medical advice.

18. Why This Trial Matters Statistically

This trial illustrates a central distinction in clinical statistics: an estimated difference and the precision of that estimate answer separate questions. The primary point estimate is -0.35 hours, but the confidence intervals span values on either side of zero. A reader who focuses only on the sign of the estimate would miss the uncertainty; a reader who focuses only on whether zero is included would miss the range of effects still compatible with the data.

The registry also makes it possible to compare a sponsor-reported ANCOVA result with an unadjusted recalculation from posted summaries. Their central estimates agree at the displayed precision, while their intervals differ. This is a useful reminder that adjusted and unadjusted analyses need not produce identical uncertainty, and that summary statistics cannot reproduce a model fit to participant-level data. The sponsor’s analysis and its stated method should be distinguished from the supplementary calculation.

The diary-based primary outcome is also a specific measure with repeated follow-up observations. Understanding how it was constructed—the average at Weeks 6, 10, 14, and 18 compared with baseline—helps keep the interpretation tied to the actual estimand. The registry leaves important analysis details, including missing-data handling and multiplicity procedures, unreported. Those omissions matter because they constrain how fully the result can be independently evaluated.

Finally, planning quantities based on an observed effect are not evidence of the completed study’s power or a substitute for a prospective design justification. They illustrate how required participant numbers depend on the target effect and planned assumptions. Together, these features make the trial useful for learning to separate the observed estimate, its uncertainty, the analytic method, and what the record does not document.

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 record does not provide the detailed statistical analysis plan, ANCOVA covariates, model diagnostics, or the method used to handle missing observations. The primary analysis population is described as full-analysis set using observed cases, but the criteria for that set and the completeness of outcome measurement are not reported. These omissions limit assessment of potential bias from missing data and prevent independent reproduction of the sponsor’s adjusted estimate.

The record does not report whether multiplicity was addressed across the secondary outcomes, nor does it provide a testing hierarchy. No interim analysis details or original sample-size justification are reported. The planning illustrations use the observed effect and specified assumptions; they should not be confused with the trial’s original design process.

The outcome-specific group counts and the overall enrollment figure are both reported, but the registry does not explain their relationship. It does not state why the outcome counts differ from the enrollment number, and no explanation should be inferred. The record also gives no clinical-importance threshold for change in daily OFF time or the secondary scales.

Some design details are also unavailable in the registry record, including randomization implementation and allocation concealment. Although triple masking is reported, the identities of the masked roles are not stated. Adverse-event reporting is limited in the registry record for this analysis: deaths are not reported, serious event terms are not fully broken down by group, and event relatedness, timing, exposure-adjusted comparisons, and detailed safety methods are not provided. These limitations restrict what can be concluded from the posted summaries without negating the descriptive results that are reported.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Study of Azilect® (Rasagiline) in Levodopa-treated Parkinson's Disease Patients With Motor Fluctuations in Korea — NCT01268891.
• Registry record last updated 2013-12-03; status last verified 2013-10.
• Results first posted 2013-12-03.
• 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

NCT01268891 is a completed Phase 3 randomized, triple-masked, parallel-group, placebo-controlled study of fixed-dose Azilect® (rasagiline) in levodopa-treated patients with Parkinson’s disease and motor fluctuations in Korea. The registry lists 132 enrolled participants and a study period beginning in 2011-01, with primary completion in 2012-06.

The primary outcome was change from baseline in mean total daily OFF time, measured with the Parkinson’s Disease Patient Diary and averaged across Weeks 6, 10, 14, and 18. The posted group means were -1.24 hours for placebo and -1.59 hours for Azilect®. The sponsor-reported ANCOVA estimate was -0.35, with a 90% confidence interval from -0.93 to 0.23 and p = 0.326. The interval includes zero, leaving uncertainty about the direction and size of the between-group difference.

Three secondary outcomes and descriptive adverse-event counts are also reported. Multiplicity procedures, missing-data methods, the original sample-size justification, and several analysis details are not reported in the registry record.