Pivotal Study in Advanced Parkinsons Disease Patients: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Pivotal Study in Advanced Parkinsons Disease Patients (NCT00466167), a registered phase 3 study. The primary outcome is Change From Baseline in Unified Parkinson's Disease Rating Scale (UPDRS) Parts II+III Score at Week 18.

2. Clinical Question

3. Trial Design

The registry identifies this as a Phase 3 study with a parallel-group structure and an enrollment of 517. The title describes a double-blind, double-dummy, placebo-controlled study with three groups: pramipexole extended release, pramipexole immediate release, and placebo. The study summary describes oral treatment during a 26-week maintenance phase. The listed primary outcome, however, is measured at week 18; the relationship between that assessment and the full maintenance period is not explained further in the registry record.

The title calls the study randomized, but the registry record’s comparison note says that allocation was not stated and cautions that the arms are not a like-for-like control comparison. The allocation procedure and the basis for that caution are not reported in the registry record. Consequently, the design labels should not be treated as a complete account of how participants entered each group or how comparable the groups were.

The study summary identifies efficacy, safety, and tolerability as aims. It describes the main efficacy measure as change in the combined UPDRS Parts II and III score and also mentions a numerical comparison of extended-release with immediate-release treatment. Immediate release versus placebo is described as an assessment of assay sensitivity. These aims do not establish which comparisons were formally confirmatory, how they were ordered, or what statistical procedures were used; those details are not reported in the registry record.

The registry lists 17 outcome measures and 4 analyses. It also lists additional outcomes involving off-time, on-time, global improvement, and UPDRS components. The timing and definitions are not equally detailed across the listed outcomes. The start is recorded as 2007-04, primary completion as 2008-11, and status as completed. The registry does not give further detail about recruitment, treatment adherence, or the conduct of visits.

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: Full analysis set (FAS 1) population = 507 patients FAS 1 defined as all patients who were dispensed study medication, were documented to have at least one dose of study medication, were treated for 18 weeks (or had prematurely discontinued treatment prior to week 18) and provided baseline and any on-drug post-baseline efficacy 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 Change From Baseline in Unified Parkinson's Disease Rating Scale (UPDRS) Parts II+III Score at Week 18, measured over baseline and week 18.

The primary endpoint is described as change from baseline in the combined Unified Parkinson’s Disease Rating Scale Parts II and III score at week 18. The registry says the combined score ranges from 0 (normal) to 160 (severe). Part II measures activities of daily living, and Part III measures motor symptoms. Combining these components gives an outcome that reflects two aspects of Parkinson’s disease burden rather than either component alone.

The record labels the endpoint unit as percentage of change from baseline, while its description defines the reported calculation as the week 18 score minus the baseline score. The formula used to express that change as a percentage is not reported in the registry record. This distinction matters when interpreting units: a difference in score units and a percentage change are not interchangeable without knowing the calculation.

The endpoint is summarized as a least-squares mean with a standard error. General: a mean change describes the average outcome change in a group, while a least-squares mean typically comes from a statistical model and may account for specified factors. The model and any covariates are not reported in the registry record. A standard error describes uncertainty in an estimated mean, not the spread of individual participants’ scores. No primary endpoint estimates or standard errors are reported, so the observed changes and their uncertainty cannot be assessed.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes a continuous primary outcome summarized with a least-squares mean and standard error. General: a continuous outcome can take values across a scale, and a group mean describes its average. A least-squares mean is generally an estimate from a model rather than necessarily the raw arithmetic mean. Its interpretation depends on the model, the covariates, and the population included. The registry record does not identify the model specification, covariates, or the method used to compare groups.

What does a standard error describe?

General: a standard error describes how much an estimate would tend to vary across repeated samples under a statistical model. It reflects precision of an estimated mean, not the distribution of individual observations. A confidence interval commonly combines an estimate with its standard error to show a range of values compatible with the data and assumptions. The primary outcome’s standard errors and confidence intervals are not reported in the registry record, so readers cannot assess precision from the posted primary results.

What is the role of the analysis population?

The primary outcome description names a Full Analysis Set of 507 patients. The record’s definition refers to dispensing and receiving at least one dose of study medication, treatment through 18 weeks or earlier discontinuation, and baseline plus further outcome information. Because the definition ends incompletely, its full eligibility conditions cannot be established. The number enrolled is 517, but the registry does not provide a complete flow of participants from enrollment into each analysis group. General: an analysis population definition determines which participants contribute to a particular estimate, so it is relevant to understanding what that estimate represents.

How should LOCF be understood?

The endpoint description specifies LOCF, meaning last observation carried forward. General: this approach fills a later missing measurement with a participant’s last available measurement. It is a missing-data assumption, not an observed week 18 measurement. Its appropriateness depends on why measurements are missing and how outcomes may change after the last observation. The registry record does not report the amount or pattern of missing data, the timing of carried-forward observations, or sensitivity analyses using other assumptions. Therefore, the effect of LOCF on the primary results cannot be assessed.

Why do comparison methods matter?

General: a treatment contrast estimates the difference between groups on an outcome, while a confidence interval conveys uncertainty around that contrast. A p-value addresses compatibility with a specified statistical null model; it does not measure the size or clinical importance of an effect. None of the primary contrasts, intervals, or p-values is reported. The registry’s caution that allocation was not stated and that the arms are not a like-for-like control comparison also limits interpretation of group contrasts. The procedures used to address baseline differences, if any, are not reported in the registry record.

What can be said about sample-size planning?

General: a sample-size calculation is a planning exercise that depends on assumptions about the effect to detect, variability, significance level, allocation, and analysis. The record describes a planning illustration based on the observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and planning at stated fractions of the observed effect. These are described as planning assumptions, not as the trial’s own design. The actual illustration values are not reported in the registry information available for interpretation. Such planning quantities are not observed power and do not replace estimates and confidence intervals from the trial.

General: over-dispersion is relevant when observed variability exceeds what a chosen model assumes. It can make standard errors too small if not accounted for. The registry does not identify an over-dispersion assessment or a model for the primary outcome, so there is no basis to say whether it arose or how it was handled in this study.

How do multiple outcomes affect interpretation?

The registry lists 17 outcome measures and 4 analyses, including several secondary outcomes related to time in different movement states, global ratings, and UPDRS components. General: testing multiple outcomes or contrasts can increase the chance of at least one nominally unusual result under a set of null hypotheses. Prespecified testing sequences or multiplicity adjustments can address this concern, but the procedures used are not reported in the registry record. Because the numerical outcome results are also absent, neither the pattern of findings nor the influence of multiplicity can be evaluated.

These methodological descriptions explain what the listed statistical terms usually mean; they do not establish which detailed methods were actually used beyond the features explicitly stated in the registry record. The model, contrast specification, confidence-interval method, and sensitivity analyses are not reported in the registry record.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("Pramipexole ER", "Pramipexole IR", "Placebo")
n   <- c(161, 172, 174)
m   <- c(-11, -12.8, -6.1)
sp  <- c(1, 0.9, 0.9)
sd  <- sp * sqrt(n)      # standard errors converted to SDs
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Pramipexole ER  161  -11.000  12.689  -12.975  -9.025
CARM  Pramipexole IR  172  -12.800  11.803  -14.577  -11.023
CARM  Placebo  174  -6.100  11.872  -7.876  -4.324

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 17 outcome measures and 4 analyses. The primary outcome is change from baseline in the combined UPDRS Parts II and III score at week 18. Other listed measures include percentage off-time, several categories of on-time, global improvement or patient global impression, and UPDRS components. The record does not explain which outcomes or comparisons were designated confirmatory, whether there was a testing hierarchy, or whether any multiplicity adjustment was used. These details are not reported in the registry record.

General: when several outcomes or contrasts are examined, interpreting each result as if it were the only test can overstate how surprising a nominal finding is. Prespecified hierarchies, adjusted thresholds, or other procedures can help manage that issue. No such approach can be attributed to this trial from the registry information. The absence of reported primary estimates and p-values also means the overall pattern of results cannot be assessed.

The primary outcome description states that LOCF was used. This approach carries the last observed value forward for a later missing assessment. The registry does not give the number of missing week 18 measurements, reasons for missingness, or sensitivity analyses. The named Full Analysis Set includes 507 patients, but its definition is incomplete in the record, and arm-specific analysis counts are not reported. The full statistical analysis plan, missing-data assumptions beyond LOCF, and any handling of protocol deviations are not reported in the registry record.

12. 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: hallucination, visual (1.2%), insomnia (1.1%), fall (1.1%), bronchitis (0.6%), delusion (0.6%).

The registry reports serious adverse events affecting 15 of 178 participants in the placebo group, 8 of 164 in the pramipexole ER group, and 11 of 175 in the pramipexole IR group. It also reports other adverse events affecting 74 of 178, 73 of 164, and 90 of 175 participants in those groups, respectively. These are participant counts as recorded in the registry; they should not be read as estimates of comparative risk or as proof that an event was caused by treatment.

The record lists serious adverse event terms with percentages: hallucination, visual at 1.2%, insomnia at 1.1%, fall at 1.1%, bronchitis at 0.6%, delusion at 0.6%, and depressed level of consciousness at 0.6%. The denominators, event-count details, and whether participants could contribute to more than one term are not reported in the registry record. The listed term percentages therefore should not be directly equated with the group-level counts without more information.

Death counts are not available in the record. Nor are event timing, exposure duration by group, severity beyond the serious classification, or uncertainty estimates reported in the safety information. General: adverse-event summaries describe events recorded during a study; comparisons require attention to participant exposure, definitions, follow-up, and the possibility of chance variation. The posted figures are descriptive and do not alone establish a treatment-related difference.

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

The registry record establishes that the study examined pramipexole extended release, pramipexole immediate release, and placebo in a Phase 3 parallel-group study with 517 enrolled participants. It identifies a primary outcome based on the combined UPDRS Parts II and III score at week 18 and lists a Full Analysis Set of 507 patients. It also supplies some group-level adverse-event counts. These are useful details about the question and the reported record.

They do not establish the primary efficacy result. There are no reported group means, treatment contrasts, confidence intervals, or p-values for the primary endpoint. Thus, the available information cannot show the direction or size of any contrast, how precisely it was estimated, or whether a statistical criterion was met. The registry summary of study aims should not be read as evidence that a treatment did or did not produce a particular outcome.

The registry’s wording also leaves important interpretive questions unresolved. It labels the outcome as percentage change but describes a week 18 minus baseline calculation, without reporting the percentage formula. It names LOCF and a Full Analysis Set, but provides no missing-data counts, complete population definition, or sensitivity analyses. Allocation is described as not stated, and the record cautions that the arms are not a like-for-like control comparison. These points constrain what can be inferred from the group labels and analysis description.

Safety counts and listed serious-event terms describe events recorded in the registry, but they do not by themselves establish causal relationships or comparative safety. Details needed to interpret the listed percentages are not reported in the registry record. The appropriate reading is therefore limited: the record documents the trial’s stated design and outcomes, but the posted information does not permit a quantitative judgment about the primary treatment comparisons.

14. Why This Trial Matters Statistically

This study illustrates why a registry entry should be read as a record of both design and reporting, rather than as a complete statistical results report. It contains a defined clinical outcome, a named analysis population, and a missing-data method. Yet without the numerical endpoint estimates and their uncertainty, readers cannot assess the central efficacy comparison. The distinction between an analysis being described and its results being reported is fundamental to clinical biostatistics.

The record also highlights the importance of precise endpoint definitions. “Percentage of change from baseline” and “week 18 minus baseline” may describe different scales unless the percentage calculation is specified. Clear units and formulas are necessary for interpreting effect estimates and comparing them with other measurements. Here, the calculation beyond the stated difference is not reported in the registry record.

Another statistical issue is the relationship between population definitions and missing data. The record names a Full Analysis Set and LOCF, but does not provide a complete definition, participant counts by arm, missingness patterns, or sensitivity analyses. Those details help readers judge which patients the estimates represent and how dependent conclusions may be on assumptions about unobserved outcomes.

Finally, the registry lists multiple outcomes and analyses and describes several intended comparisons, but does not report a multiplicity strategy or the corresponding results. Without this context, one cannot determine how planned comparisons were prioritized or how a collection of findings should be interpreted. These reporting gaps do not establish that an analysis was inappropriate; they mean the registry record does not contain enough information to evaluate it.

15. 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 principal limitation for interpreting this trial from the registry record is that numerical primary outcome results are absent. No group estimates, contrasts, confidence intervals, standard errors, or p-values are listed for the primary endpoint. The study’s stated aims therefore cannot be translated into an account of observed efficacy or precision.

Some design information is internally difficult to reconcile: the title describes a randomized study, while a registry note says allocation was not stated and warns that the arms are not a like-for-like control comparison. The allocation procedure and rationale for that warning are not reported in the registry record. This uncertainty limits interpretation of comparisons between the listed groups.

The endpoint description identifies a score difference and also labels the unit as percentage change. The formula for the percentage is not given. The Full Analysis Set definition is incomplete, and the record does not report arm-specific analysis counts, participant flow, missingness by outcome, or sensitivity analyses for LOCF. The statistical model and adjustment factors are not reported in the registry record.

The registry lists multiple outcomes and analyses, but does not describe a testing hierarchy or multiplicity adjustment. The primary completion date and completed status do not resolve these statistical reporting gaps. Safety information is also limited: death counts are unavailable, and the listed serious-event percentages lack denominator and event-count context. These limitations concern what can be assessed from the registry record; they do not establish what analyses may have been conducted elsewhere.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Pivotal Study in Advanced Parkinsons Disease Patients — NCT00466167.
• Registry record last updated 2014-07-08; status last verified 2014-05.
• Results first posted 2010-02-08.
• 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.

19. Record Summary

The registry record describes NCT00466167, a completed Phase 3 parallel-group study of pramipexole extended release, pramipexole immediate release, and placebo in advanced Parkinson’s disease. Enrollment was 517. The primary outcome was change from baseline in combined UPDRS Parts II and III score at week 18, summarized as a least-squares mean with a standard error. The record names a Full Analysis Set of 507 patients and specifies LOCF.

The record lists 17 outcome measures and 4 analyses. It reports serious and other adverse-event participant counts by group and several serious-event term percentages. It does not report numerical primary outcome estimates, treatment contrasts, confidence intervals, or p-values. Allocation is noted as not stated, and the comparison note cautions that the arms are not a like-for-like control comparison. The endpoint’s percentage calculation, full analysis-population definition, multiplicity procedures, and further missing-data assessments are not reported in the registry record.