A Phase 3 Study of TVP-1012 (1 mg) in Early Parkinson's Disease Patients: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Phase 3 Study of TVP-1012 (1 mg) in Early Parkinson's Disease Patients (NCT02337725), a randomized phase 3 study. The primary outcome is Change From Baseline in Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) Part II + Part III Total Score.

2. Clinical Question

The primary outcome combines measures of motor experiences of daily living and motor examination. The scale description states that higher scores reflect greater severity. The registry-reported adjusted mean difference was -6.39 units, with a 95% confidence interval from -8.530 to -4.250 and p < 0.001. The posted group means changed in opposite directions: the placebo group’s mean change was 1.87, and the TVP-1012 group’s mean change was -4.52.

These results describe the endpoint and analysis recorded in the registry. They do not, by themselves, establish how a participant would fare outside this study or answer questions about outcomes that were not measured. The registry record does not report a minimum clinically important difference for the scale, so the clinical importance of a particular score difference cannot be determined from that information alone.

3. Trial Design

This was a randomized, quadruple-masked, parallel-group Phase 3 study with placebo as the comparator. The record lists an enrollment of 244 and describes the study as completed. The sponsor was Takeda. The study began on 2015-02-07, and primary completion was recorded as 2016-09-15.

The study evaluated TVP-1012 1 mg in Japanese patients with early Parkinson’s disease. The official title specifies patients not treated with levodopa. Participants assigned to TVP-1012 and placebo followed the same described schedule during the run-in period: placebo orally once daily before or after breakfast for 2 weeks. During the 26-week treatment period, the TVP-1012 group took one 1 mg tablet once daily, while the comparator group continued placebo once daily. The registry record does not report additional details about how randomization was generated or implemented.

For the primary outcome, the registry defines the Full Analysis Set as randomized participants who received at least 1 dose of study drug during the treatment period. It further notes that the number analyzed for this outcome comprises participants evaluable for the measure. The posted primary analysis includes 125 participants in the placebo group and 115 in the TVP-1012 group. These outcome-specific counts are not the same as the overall enrollment figure; the registry record does not describe all reasons why participants were not evaluable for this outcome.

The primary endpoint was change from baseline to Week 26, using last observation carried forward (LOCF). The reported analysis method was ANCOVA, with a least-squares mean difference. Further details of the model, including its covariates and handling of missing observations beyond the stated LOCF approach, are not reported in the registry record. The trial’s original sample-size assumptions and justification are also 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: Participants with diagnosis of Parkinson's disease were enrolled and received one tablet of placebo orally, once daily in a run-in period (Week -2 to 0). After that, the participants who fulfilled the inclusion criteria and did not meet any of the exclusion criteria at Week -2 and Week 0 were randomized in 1:1 to TVP-1012 1 mg or Placebo at Week 0.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set included all randomized participants who received at least 1 dose of the study drug for the treatment period. Here number of participants analyzed are participants evaluable for this outcome measure.

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: Randomized set was defined as all randomized participants.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) Part II + Part III Total Score, measured over From Baseline to Week 26 (LOCF).

The primary endpoint was change from baseline to Week 26 in the combined MDS-UPDRS Part II + Part III total score, analyzed using LOCF. Part II assesses motor experiences of daily living, while Part III assesses motor examination. The registry describes the scale as retaining a four-part structure; its items are rated from 0, normal, to 4, severe, and scores are summed. For the combined Part II + Part III score, the stated range is 0-188, with higher scores reflecting greater severity.

Combining these parts captures both the participant’s motor-related daily experience and the motor examination measure. A change score expresses how the recorded score at follow-up differs from baseline, rather than reporting only a follow-up score. In general, change-from-baseline outcomes can help compare how groups move over the same follow-up period. Because higher scores on this scale indicate greater severity, a negative change represents a decrease in the measured score; that interpretation describes the scale direction, not a treatment recommendation.

The endpoint is reported as a least-squares mean, with standard errors for each group, and the sponsor’s analysis gives an adjusted between-group estimate. The registry record does not report a threshold for interpreting the size of a score change as clinically important. Thus, statistical evidence about a difference and judgments about its clinical importance are distinct questions.

7. Results Posted in the Registry

• TVP-1012 1mg: mean -4.52 versus 1.87 on control; difference -6.39 (95% CI -8.52 to -4.26), standardized effect d = -0.76; z-test p = <0.001.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Change From Baseline in MDS-UPDRS Part I Total 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:
  • TVP-1012 1mg: mean 0.18 versus 0.98 on control; difference -0.80 (95% CI -1.50 to -0.10), standardized effect d = -0.29; z-test p = 0.025.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for TVP-1012 1mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in MDS-UPDRS Part II Total 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:
  • TVP-1012 1mg: mean 0.13 versus 2.32 on control; difference -2.19 (95% CI -3.14 to -1.24), standardized effect d = -0.58; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for TVP-1012 1mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in MDS-UPDRS Part III Total 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:
  • TVP-1012 1mg: mean -4.47 versus -0.48 on control; difference -3.99 (95% CI -5.80 to -2.18), standardized effect d = -0.56; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for TVP-1012 1mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The registry lists secondary outcomes covering MDS-UPDRS Parts I, II, and III, along with safety measures. For the three posted continuous MDS-UPDRS secondary comparisons, the recalculated group contrasts are negative. This direction is broadly aligned with the primary combined Part II + Part III result. The separate components offer related but not identical views of non-motor experiences, motor experiences of daily living, and motor examination; they should not be treated as independent confirmations of the combined endpoint.

The registry record does not include sponsor-reported analyses for these posted secondary comparisons. The recalculated estimates and p-values are unadjusted comparisons derived from summary statistics, rather than the reported ANCOVA analysis available for the primary endpoint. Their p-values do not account for examining multiple secondary outcomes. The registry record does not report a multiplicity adjustment or a testing hierarchy, so these results carry less confirmatory weight than the prespecified primary analysis.

Other listed secondary outcomes concern treatment-emergent adverse events, serious adverse events, markedly abnormal vital signs, and events related to body weight, electrocardiograms, and clinical laboratory tests. The presence of these outcomes in the registry listing does not itself provide evidence about each outcome; counts and definitions must be considered separately. The registry record does not post numerical results for every listed secondary outcome in the registry record for this analysis.

Taken together, the directional pattern of the continuous MDS-UPDRS results is consistent with the primary comparison, but it does not remove the need for caution. Correlation among related scales, multiple testing, unreported sponsor analyses, and the absence of a reported multiplicity plan all limit the strength of conclusions from secondary comparisons. They can add context to the primary result, but they should not be read as separate, definitive proof of the same finding.

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

• Change From Baseline in MDS-UPDRS Part I Total Score
• Change From Baseline in MDS-UPDRS Part II Total Score
• Change From Baseline in MDS-UPDRS Part III Total Score
• Number of Participants Who Experience at Least One Treatment Emergent Adverse Events (TEAEs) and Serious Adverse Events (SAEs)
• Number of Participants With Markedly Abnormal Vital Signs Values
• Number of Participants With TEAE Related to Body Weight
• Number of Participants With TEAE Related to Electrocardiograms (ECG)
• Number of Participants With TEAE Related to Clinical Laboratory Tests

9. Statistical Interpretation

10. Statistical Methods Explained

The registry reports an ANCOVA analysis with a least-squares mean difference for the primary endpoint. In general, analysis of covariance compares groups while accounting for selected covariates in a statistical model. This can produce an adjusted group contrast rather than a simple subtraction of the observed group means. Which covariates were included and how they were specified are not reported in the registry record, so the model cannot be fully reproduced from the posted description.

A least-squares mean is a model-based group mean. The reported primary estimate, -6.39, is the sponsor’s adjusted comparison between the placebo and TVP-1012 groups. The registry also provides group least-squares means: 1.87 for placebo and -4.52 for TVP-1012 1 mg. Standard errors are reported for those group means. A standard error describes the uncertainty in an estimated mean under the analysis; it is not the spread of individual participants’ scores.

The posted recalculation uses the group summaries to form a simple unadjusted comparison. It is not ANCOVA and does not use the sponsor’s model adjustments. The recalculated interval is based on an approximate pooled standard deviation derived from the posted standard errors and group sizes. That approximation is useful for a transparent summary-statistic comparison, but it cannot reproduce model details that are not reported. The sponsor’s own analysis is the primary registry-reported inferential result.

In general, a confidence interval gives a range of estimates compatible with the observed data and the analysis assumptions at the stated confidence level. The primary reported 95% interval is -8.530 to -4.250. Its location below zero indicates that the estimated group contrast is negative throughout that interval. The interval does not incorporate every possible source of uncertainty, such as uncertainty from unreported modeling choices or limitations in generalizing beyond the study population.

The p-value for the reported primary analysis is < 0.001. It is reported as a threshold rather than an exact value. The unadjusted recalculation reports p < 0.001. These values arise from different analyses and should not be treated as if they were interchangeable outputs from one model. In general, a p-value evaluates data against a null comparison under specified assumptions; it does not quantify the probability that the result is due to chance, nor does it measure clinical importance.

The endpoint uses LOCF, or last observation carried forward. In general, LOCF fills a missing later measurement using a participant’s most recent recorded measurement. This approach allows an analysis to retain some participants without a recorded Week 26 value, but it makes assumptions about how the unobserved outcome relates to the last observed one. LOCF does not eliminate uncertainty caused by missing data. The registry record does not report the number of carried-forward values, the reasons for missingness, or sensitivity analyses using other missing-data methods.

The primary analysis population is described as the Full Analysis Set: randomized participants who received at least 1 dose during the treatment period, with the analyzed count limited to those evaluable for the outcome. This definition is not the same as an analysis of every randomized participant regardless of treatment receipt or outcome availability. The registry record does not report a separate intention-to-treat analysis definition or a detailed account of exclusions from the primary analysis.

Several other MDS-UPDRS outcomes are listed as secondary endpoints, alongside safety outcomes. In general, examining multiple outcomes creates a multiplicity issue: the more comparisons considered, the greater the chance that at least one result may appear statistically notable even when no corresponding effect exists. Statistical approaches can account for multiple testing, but the registry record does not report a multiplicity adjustment or a prespecified testing hierarchy. The secondary recalculations should therefore be read as descriptive, unadjusted comparisons rather than as a family of confirmatory tests.

Power describes the probability that a planned study would detect an effect of a stated size under its assumptions if that effect were present. It is a design concept, not a measure of the probability that a particular observed result is true. The planning illustrations use stated assumptions and observed effect estimates; they are not a report of the trial’s original design calculation. The registry record does not report the original sample-size justification, interim analyses, or a complete statistical analysis plan.

General concepts such as adjustment, standard errors, confidence intervals, missing-data assumptions, and multiplicity help interpret the reported statistics, but they do not add information about unreported protocol choices. The posted primary estimate and interval are the available sponsor analysis for the primary outcome; the unadjusted recalculation provides a separate summary-statistic perspective.

11. Confidence Intervals and Precision

The registry-reported primary estimate is -6.39 units, with a 95% confidence interval from -8.530 to -4.250. This interval describes the range of values compatible with the observed data under the sponsor’s ANCOVA model and its assumptions. It lies entirely below zero, indicating that the estimated difference is negative across the interval. The interval’s width conveys uncertainty around the point estimate; it is not a range containing a stated percentage of individual participants’ outcomes.

The unadjusted recalculation gives an estimate of -6.39 and a 95% confidence interval from -8.519 to -4.261. This interval is close to the sponsor-reported interval, but it comes from a different method based on posted summary statistics and an approximate pooled standard deviation. The sponsor’s analysis remains the registry-reported inferential analysis. Neither interval accounts for uncertainty that cannot be evaluated from the registry description, including unreported model details and the assumptions underlying LOCF.

In general, greater precision corresponds to a narrower confidence interval, while less precision corresponds to a wider interval. Precision is not the same as clinical importance: an estimate can be precise without establishing that the magnitude matters to patients. The registry record does not report a threshold for clinical importance for the combined score, so the confidence interval cannot be classified against such a threshold using the registry information alone.

The group standard errors describe uncertainty in the posted least-squares means, not the variability of individual scores. The primary outcome counts were 125 for placebo and 115 for TVP-1012 1 mg. The interval reflects the analysis of those evaluable participants and the LOCF approach; it does not resolve questions about the extent or pattern of missing data. The result is therefore most precisely interpreted as the registry’s estimated between-group difference for this endpoint, population, and analysis.

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 illustrations are stated as participants per arm, not as total events. They use a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. For each illustration, the effect to detect is a stated fraction of the observed effect: 100%, 75%, or 50%. These are planning assumptions for an illustration based on the observed effect, not the original design assumptions for the trial.

The 80% power column gives the number of participants per arm that the illustration estimates would be needed to have an 80% chance of detecting the specified effect under those assumptions. The 90% power column gives the corresponding number per arm for a 90% chance. Higher target power generally calls for more participants when the other assumptions remain fixed. The displayed figures vary with the endpoint and the assumed fraction of the observed effect.

Smaller effects are harder to distinguish from random variation, so the planning illustrations require more participants per arm when the assumed effect is reduced from 100% to 75% or 50% of the observed effect. These figures are not the trial’s observed power and should not be used to infer whether the completed study was adequately powered according to its original plan. The original sample-size justification and planning assumptions are not reported in the registry record.

For continuous outcomes, these illustrations express sample size as participants per arm. The stated general note distinguishes time-to-event calculations, which would report total events, but the primary endpoint in this trial is continuous. The illustrations also depend on the observed effect used as their starting point, which may not represent the effect expected when planning a different study. They are best read as conditional planning examples rather than definitive recommendations.

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 = -6.390; pooled standard deviation σ = 8.408.
2. n = 2 × (1.96 + 0.842)² × 8.408² / -6.390² = 27.2, rounded up to 28 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 <- -6.39                      # observed difference in means
sigma <- 8.4075426720007                     # 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(2337725)
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 = 28 (80% power), 37 (90% power)
 75% of observed effect: n per arm = 49 (80% power), 65 (90% power)
 50% of observed effect: n per arm = 109 (80% power), 146 (90% power)
power.t.test: 28.2 
Simulated power at n = 28 per arm: 0.796 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

14. Analyses Reported by the Sponsor

The registry reports the sponsor’s primary analysis as ANCOVA, with a least-squares mean difference of -6.39, a 95% confidence interval from -8.530 to -4.250, and p < 0.001. This is the primary inferential result recorded for the endpoint.

The separate recalculation uses the posted group summaries and estimates the unadjusted mean difference as -6.39, with a 95% confidence interval from -8.519 to -4.261 and p < 0.001. It is not a reproduction of ANCOVA: the recalculation does not have access to the sponsor model’s covariates or participant-level data. Its role is to provide a simple comparison based on the available summary statistics.

The estimates are similar, and the registry does not flag a discrepancy. The small differences in interval limits and p-value presentation are consistent with the distinction between an adjusted sponsor analysis and an unadjusted summary-statistic calculation. The sponsor’s reported analysis takes precedence as the trial’s stated analysis; the recalculation is supplementary and should not replace it.

15. Multiplicity, Missing Data and Analysis Populations

The primary endpoint is accompanied by multiple secondary outcomes, including three MDS-UPDRS component measures and several safety measures. When many outcomes or comparisons are examined, the chance of at least one apparently notable result can increase. In general, multiplicity methods control or otherwise address this issue by adjusting thresholds, ordering tests, or defining a limited confirmatory family. The registry record does not report a multiplicity adjustment, testing hierarchy, or other plan for interpreting multiple outcomes.

The primary endpoint is the clearest basis for the main statistical interpretation because the registry identifies it as primary and reports an ANCOVA analysis. The secondary continuous comparisons are unadjusted recalculations, and sponsor-reported analyses for them are not reported in the registry record. Their p-values should therefore not be interpreted as if they had been protected against multiple testing or as though each were an independent confirmation.

Missing-data handling is important because the primary outcome is defined from baseline to Week 26 using LOCF. In general, this method carries a participant’s last recorded observation forward when a later measurement is missing. The registry record does not report the number of participants with missing Week 26 measurements, the amount of data carried forward, reasons for missingness, or sensitivity analyses under alternative assumptions. Those omissions limit assessment of how robust the result is to missing-data choices.

The primary population is described as randomized participants who received at least 1 treatment-period dose, with the reported outcome count limited to evaluable participants. This provides a definition of the analysis set, but the registry record does not report a participant-level flow or detailed reasons for exclusion and non-evaluability. It also does not report a separate intention-to-treat analysis description.

The registry record does not report interim analyses, the original sample-size justification, or a complete statistical analysis plan. The posted information supports interpretation of the recorded primary model and results, but not reconstruction of all protocol decisions. These missing details matter when judging prespecification, the treatment of multiple comparisons, and the sensitivity of findings to analysis choices.

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: leukoplakia oral (0.9%), femoral neck fracture (0.9%), spinal compression fracture (0.9%), intracranial aneurysm (0.9%), myocardial infarction (0.8%).

The registry posts serious adverse event counts for 126 participants at risk in the placebo group and 117 at risk in the TVP-1012 1 mg group. The corresponding numbers with serious adverse events were 8 and 4. These are counts within the stated groups; they do not, by themselves, show whether an event was caused by study treatment. The registry record does not report deaths in the posted safety data.

The posted counts for other adverse events are 24 in the placebo group and 23 in the TVP-1012 1 mg group, with 126 and 117 participants at risk, respectively. The registry also lists serious-event terms with percentages: Leukoplakia oral, 0.9%; Femoral neck fracture, 0.9%; Spinal compression fracture, 0.9%; Intracranial aneurysm, 0.9%; Myocardial infarction, 0.8%; and Gastric ulcer, 0.8%. These terms and percentages are not a substitute for participant-level context or an assessment of causality.

Safety counts should be interpreted in light of the number at risk and the registry’s event definitions. The available record does not give enough detail to establish whether differences in counts reflect treatment, chance, or other factors. These figures describe reported events in this trial and should not be used alone to make clinical decisions.

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

The primary result is an estimated difference between randomized groups in change in the combined MDS-UPDRS Part II + Part III score over the stated follow-up. The sponsor-reported ANCOVA estimate is -6.39, with a 95% confidence interval from -8.530 to -4.250 and p < 0.001. The negative direction means the estimated change was lower in the TVP-1012 group than in the placebo group. Given the scale description that higher scores indicate greater severity, the observed contrast is in the direction of a lower score change for the TVP-1012 group.

This statistical result does not establish the clinical importance of the estimated difference. The registry record does not report a threshold for a meaningful change in the combined score. Nor does a small p-value establish that the result is free from bias, missing-data sensitivity, or limitations in generalizability. The confidence interval describes statistical precision under the reported analysis, not certainty about every aspect of the study.

The findings apply to the population, treatment regimen, comparator, endpoint, and follow-up recorded for this study: Japanese patients with early Parkinson’s disease not treated with levodopa, TVP-1012 1 mg or placebo, and the Week 26 LOCF outcome. They do not establish outcomes for different populations, different treatment conditions, longer follow-up, or unmeasured outcomes. The registry record does not report a clinical-importance threshold or enough missing-data detail to resolve those broader questions.

Safety counts also require a separate interpretation. The serious adverse event figures describe events recorded among participants at risk, but they do not establish causation or provide a complete benefit-risk assessment. The primary efficacy comparison and the safety summaries answer different questions and should not be collapsed into a single conclusion.

18. Why This Trial Matters Statistically

Statistically, this trial illustrates the distinction between a sponsor-reported adjusted analysis and a simple recalculation from group summaries. The reported ANCOVA estimate and the unadjusted estimate are close, but they are produced by different methods. Keeping that distinction clear prevents a summary-statistic calculation from being mistaken for a reconstruction of the trial’s model.

It also illustrates why endpoint definition and analysis population matter. The primary outcome combines two related MDS-UPDRS parts, uses change from baseline, and applies LOCF through Week 26. Its evaluable counts are lower than the overall enrollment figure. Each choice shapes the question answered by the reported estimate and the people whose data contribute to it.

The secondary results provide related context, but multiple outcomes and the absence of a reported multiplicity plan limit how strongly they can be treated as confirmatory. The record also does not report the original sample-size justification, interim analyses, or detailed missing-data sensitivity analyses. These gaps do not erase the primary result; they define what can be assessed from the registry record.

Finally, statistical evidence and clinical importance are not interchangeable. The reported interval and p-value characterize the comparison under the stated analysis, while the record does not specify a threshold for meaningful change. Reading the result with its model, endpoint, population, and uncertainty in view is essential to a sound statistical 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 record gives limited detail for reproducing the primary ANCOVA. It reports the method and adjusted estimate, but the model covariates and other specifications are not reported in the registry record. The recalculation therefore provides only an unadjusted summary-statistic comparison and cannot verify every aspect of the sponsor’s analysis.

The primary endpoint uses LOCF, but the amount and pattern of missing data are not reported in the registry record. Reasons for missing outcomes and sensitivity analyses under other missing-data assumptions are also not reported. The primary analysis counts include participants evaluable for the outcome, and a detailed account of who was not evaluable is not reported.

The record does not report the original sample-size justification, interim analyses, or a multiplicity plan. Consequently, the planning illustrations based on the observed effect do not establish the design assumptions of the completed trial, and the unadjusted secondary p-values should not be regarded as multiplicity-controlled evidence.

The registry record does not report a clinical-importance threshold for the primary scale. Although the score direction and range are described, the record alone does not establish whether the estimated difference corresponds to a meaningful change for participants. Follow-up for the primary endpoint is stated as Week 26; longer-term outcomes are not reported in the registry record used. The safety summaries provide counts, but the registry record does not provide enough detail to infer causality or a comprehensive safety profile.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Phase 3 Study of TVP-1012 (1 mg) in Early Parkinson's Disease Patients — NCT02337725.
• Registry record last updated 2022-03-02; status last verified 2022-02.
• Results first posted 2018-12-31.
• 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, randomized, quadruple-masked, parallel-group Phase 3 study compared TVP-1012 1 mg with placebo in Japanese patients with early Parkinson’s disease. The registry lists enrollment of 244 and a primary completion date of 2016-09-15. Participants followed a 2-week placebo run-in, then a 26-week treatment period.

The primary outcome was change from baseline to Week 26 in the combined MDS-UPDRS Part II + Part III score, analyzed with LOCF. The sponsor-reported ANCOVA estimate was -6.39, with a 95% confidence interval from -8.530 to -4.250 and p < 0.001. The result describes a lower estimated score change in the TVP-1012 group than in the placebo group.

Interpretation is limited by unreported details about model specification, missing data, multiplicity, and the trial’s original sample-size assumptions. The registry record does not report a threshold for clinical importance. The safety counts describe recorded events but do not establish causation.