Safety and Efficacy Study of NBI-98854 in Children and Adolescents With Tourette Syndrome: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety and Efficacy Study of NBI-98854 in Children and Adolescents With Tourette Syndrome (NCT02679079), a randomized phase 2 study. The primary outcome is Change From Baseline to Week 6 in the Yale Global Tic Severity Scale (YGTSS) Total Tic Score (TTS).

2. Clinical Question

3. Trial Design

This was a randomized, parallel-group phase 2 study with placebo control and quadruple masking. The registry title describes the study as assessing safety and efficacy in children and adolescents with Tourette syndrome. The brief summary describes once-daily treatment over 6 weeks and an intended enrollment of approximately 90 male and female pediatric participants. The reported enrollment was 98.

The three posted groups were placebo, NBI-98854 low dose, and NBI-98854 high dose. Each group’s treatment description specifies once-daily administration for 6 weeks. The actual dose amounts and details of allocation procedures are not reported in the registry record. The study is marked completed. Its recorded start date is 2016-03-23, and its primary completion date is 2017-04-14.

The primary endpoint analysis used least-squares means and standard errors for the change from baseline to Week 6 in YGTSS Total Tic Score. The primary analysis population is described as an intent-to-treat analysis set, with eligibility conditions including randomization, receipt of at least one dose, postbaseline safety data, and a baseline plus at least one postrandomization score. The registry description ends partway through its account of the visit window, so further details of that definition are not reported in the registry record.

The registry lists 9 outcome measures and 18 analyses. It identifies 8 secondary outcomes, including ratings of global improvement and severity, responder measures, impairment, tic severity, video-based tic ratings, and premonitory urges. The original sample-size justification, planned analysis details beyond the posted information, and any interim-analysis arrangements are not reported in the registry record.

4. Participant Flow and Accounting

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

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The intent-to-treat (ITT) analysis set included all randomized participants who received at least one dose of study drug, had postbaseline safety data, and had a baseline (Day -1) and at least one postrandomization TTS value reported at a scheduled or mapped early termination (ET) visit during the 6-week treatment period. Dose levels based on age group were prespecified to be combined within each dose arm.

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: The intent-to-treat (ITT) analysis set included all randomized participants who received at least one dose of study drug, had postbaseline safety data, and had a baseline (Day -1) and at least one postrandomization Total Tic Score (TTS) value reported at a scheduled or mapped early termination (ET) visit during the 6 week treatment period.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline to Week 6 in the Yale Global Tic Severity Scale (YGTSS) Total Tic Score (TTS), measured over Baseline, Week 6.

The primary endpoint was change from baseline to Week 6 in the Yale Global Tic Severity Scale (YGTSS) Total Tic Score (TTS). The registry describes the YGTSS as an investigator-administered, computer-based structured clinical interview designed to rate motor and phonic tic symptoms across dimensions that include number, frequency, intensity, complexity, and interference.

The TTS combines the five motor tic items and five phonic, or vocal, tic items. It ranges from 0 to 50, with higher scores representing greater severity. A change score describes how the measure differed between baseline and the later assessment; a negative change in the posted results represents a decrease in the score. The group results are least-squares means with standard errors, rather than raw individual measurements.

This type of scale provides a structured way to quantify symptom severity and compare average changes between randomized groups. The trial’s main statistical comparison asks whether the estimated change in either dose group differs from placebo. The score is a clinical rating measure, not a direct count of every tic or a measure of every aspect of a participant’s experience. The registry record does not report a threshold for a clinically meaningful change on this endpoint.

7. Results Posted in the Registry

• NBI-98854 Low Dose: mean -7.30 versus -8.80 on control; difference 1.50 (95% CI -2.52 to 5.52), standardized effect d = 0.18; z-test p = 0.465.
• NBI-98854 High Dose: mean -9.10 versus -8.80 on control; difference -0.30 (95% CI -4.32 to 3.72), standardized effect d = -0.04; z-test p = 0.884.

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 Global Impression of Tourette Syndrome (CGI-TS) - Improvement Score at Week 6

• 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:
  • NBI-98854 Low Dose: mean 3.50 versus 3.40 on control; difference 0.10 (95% CI -0.45 to 0.65), standardized effect d = 0.09; z-test p = 0.724.
  • NBI-98854 High Dose: mean 3.00 versus 3.40 on control; difference -0.40 (95% CI -0.95 to 0.15), standardized effect d = -0.36; z-test p = 0.157.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NBI-98854 Low Dose and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NBI-98854 High Dose and the control. The interval gives the range of effects that remain compatible with the data.

Participants Who Are a YGTSS TTS Responder at Week 6

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • NBI-98854 Low Dose: 30.0% (9/30) versus 34.5% (10/29) on control; risk difference -4.5 percentage points (95% CI -28.3 to 19.4), risk ratio 0.87 (0.41–1.83); unadjusted two-proportion z-test p = 0.713.
  • NBI-98854 High Dose: 48.4% (15/31) versus 34.5% (10/29) on control; risk difference 13.9 percentage points (95% CI -10.8 to 38.6), risk ratio 1.40 (0.76–2.61); unadjusted two-proportion z-test p = 0.275.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NBI-98854 Low Dose and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NBI-98854 High Dose and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline to Week 6 in the YGTSS Impairment 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:
  • NBI-98854 Low Dose: mean -7.10 versus -8.50 on control; difference 1.40 (95% CI -4.42 to 7.22), standardized effect d = 0.12; z-test p = 0.637.
  • NBI-98854 High Dose: mean -10.40 versus -8.50 on control; difference -1.90 (95% CI -7.58 to 3.78), standardized effect d = -0.17; z-test p = 0.512.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NBI-98854 Low Dose and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between NBI-98854 High Dose and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes examine complementary aspects of Tourette syndrome, including global ratings, impairment, tic severity, video-based ratings, premonitory urges, and responder status. The posted results include both continuous scores and a binary responder outcome. Across the available secondary results, estimates vary in direction and precision; they do not form a clear, consistent pattern that changes the reading of the primary endpoint.

These measures can help describe whether the primary result is accompanied by similar patterns in related assessments. They are not interchangeable with the primary YGTSS Total Tic Score, and differences in scale, outcome type, and analysis mean that their estimates should not be combined informally. The registry has 8 secondary outcomes, and the posted record includes analyses across multiple outcomes and comparisons.

Unadjusted secondary findings carry less weight because testing multiple outcomes can make an apparently notable result more likely by chance. The registry record does not report whether a multiplicity adjustment or a hierarchy for interpreting secondary endpoints was planned. Secondary results can therefore be viewed as context or hypothesis-generating information, rather than as separate confirmation of efficacy. The primary comparisons remain the central evidence for the trial’s main question, and their confidence intervals include zero.

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

• Clinical Global Impression of Tourette Syndrome (CGI-TS) - Improvement Score at Week 6
• Participants Who Are a YGTSS TTS Responder at Week 6
• Change From Baseline to Week 6 in the YGTSS Impairment Score
• Change From Baseline to Week 6 in the YGTSS Global Tic Severity Score
• Change From Baseline to Week 6 in the Rush Video-based Tic Rating Scale (RTRS) Total Score
• Change From Baseline to Week 6 in the Premonitory Urge for Tics Scale (PUTS) Total Score
• Change From Baseline to Week 6 in the Clinical Global Impression of Tics (CGI-Tics) - Severity Score
• Participants Who Are a CGI-TS-Improvement Responder at Week 6

9. Statistical Interpretation

10. Statistical Methods Explained

General statistical explanation: A randomized comparison estimates how an outcome differs between groups assigned to different study conditions. In this trial, the primary measure is continuous, so the reported group summaries are least-squares mean changes and the between-group contrasts are mean differences. A mean difference is expressed in the score’s units; it is not a percentage change.

The primary endpoint reports a least-squares mean and standard error for each group. A least-squares mean is a model-based estimate of the group mean under the analysis used. A standard error describes the statistical uncertainty in an estimated mean; it is not the spread of individual participant scores. The registry does not provide enough detail to reconstruct the sponsor’s model specification, including all covariates, handling of repeated measurements, or other modeling choices. Those details are not reported in the registry record.

The sponsor reports a mixed models analysis of mean difference (net) for each active group versus placebo. The posted analysis is marked as a superiority comparison. The estimates are -0.3 for high dose and 1.5 for low dose, with p-values of 0.89 and 0.47. A p-value describes how unusual data at least as incompatible with a specified null hypothesis would be if that hypothesis and the analysis assumptions were correct. It is not the probability that the null hypothesis is true, and it does not quantify the size or clinical importance of an effect.

General statistical explanation: Confidence intervals show a range of effect values compatible with the data and the model at a stated confidence level. They help communicate precision and direction, not certainty that the true effect lies within a particular observed interval. In the sponsor results, both 95% intervals include zero, and each extends to values on both sides of zero. The interval therefore does not distinguish a difference in one direction from no difference or a difference in the other direction.

The registry also supports a simple unadjusted comparison based on posted summary statistics. Those recalculations produce mean differences of 1.5 for low dose and -0.3 for high dose. The recalculated intervals and p-values are approximate and are not the sponsor’s mixed-model results. In particular, the calculations use standard errors to approximate variability; they do not account for unreported features of the sponsor’s model. Because the discrepancy flag is false and the estimates are close, the appropriate interpretation is still to give precedence to the sponsor’s reported analysis.

For the responder endpoint, the outcome is a count of participants meeting the registry’s responder definition. The posted record gives group counts and reports a Cochran-Mantel-Haenszel comparison as a risk difference. A risk difference expresses the difference between the proportions meeting the definition in the two groups. The responder threshold and additional details of the stratification or adjustment are not reported in the registry record. The registry’s reported comparisons are -4.5 for low dose versus placebo, p = 0.71, and 13.9 for high dose versus placebo, p = 0.24; confidence limits are not posted for these analyses.

General statistical explanation: Over-dispersion occurs when binary outcome variability is greater than a model assumes. If present and ignored, uncertainty may be understated. The registry record does not report whether over-dispersion was assessed or how it was handled, so no conclusion about that issue can be drawn for these analyses. More broadly, the analysis details needed to evaluate model assumptions, missing-data handling, and any sensitivity analyses are not reported in the registry record.

The secondary continuous outcomes use least-squares means and standard errors, while the responder outcome is binary. These different outcome types require different summaries and comparison methods. A continuous mean difference and a risk difference are not directly interchangeable. No single summary across all outcomes is therefore appropriate. The posted analyses should be read endpoint by endpoint, with attention to the prespecified primary endpoint and the uncertainty around each estimate.

General statistical explanation: Multiplicity arises when several outcomes, groups, time points, or hypotheses are tested. With many tests, the chance of at least one apparently unusual result can increase, even if there is no underlying effect. The registry lists numerous outcomes and analyses, but whether a formal multiplicity procedure was planned or applied is not reported in the registry record. For that reason, unadjusted secondary p-values should be interpreted as exploratory rather than as standalone confirmatory evidence.

11. Confidence Intervals and Precision

The sponsor’s primary 95% confidence interval for high dose versus placebo ranges from -4.4 to 3.8, around a mean difference of -0.3. The low-dose interval ranges from -2.6 to 5.6, around a mean difference of 1.5. Both intervals include zero and allow differences on either side of it. This means the estimates are not precise enough to rule out no between-group difference or a range of potentially relevant differences in either direction.

Confidence intervals are more informative than a single point estimate because they display uncertainty around the estimated contrast. They do not show the range of individual participant responses. Nor do they establish that every value within the interval is equally plausible. Their interpretation depends on the model and assumptions used to calculate them.

The recalculated intervals are similar in broad interpretation but are not identical to the sponsor’s intervals: -4.322 to 3.722 for high dose and -2.522 to 5.522 for low dose. These are unadjusted calculations from posted summary statistics, not replacements for the sponsor’s mixed models analysis. The sponsor’s results are the principal inferential results to use.

The observed standard errors and the widths of the intervals reflect uncertainty in these group comparisons. The registry record does not report a prespecified clinically meaningful difference for the primary scale, so the intervals cannot be classified against such a threshold. They do, however, make clear that the posted data do not narrowly pin down the size or direction of the between-group effect.

12. Planning a Similar Trial: Sample Size

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

The planning illustrations show participants per arm for the non-time-to-event outcomes in this trial; they do not show total events. The stated calculation assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and an effect to detect set to a stated fraction of the observed effect. The original trial’s own sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the planned number of participants per arm under those assumptions for an 80% chance of detecting the specified effect if that effect were the true one and the assumptions held. The 90% power column gives the corresponding number per arm for a 90% chance. These are planning illustrations based on the observed effect, not observed power.

Each illustration uses a different target effect: 100%, 75%, or 50% of the observed effect. A smaller target effect is harder to distinguish from random variation, so the illustration requires more participants per arm. The figures are not evidence that the study was designed around those effects, and they do not revise the trial’s actual design. They are sensitive to the observed effect, which is itself uncertain, especially in a study with estimates whose confidence intervals include zero.

The sample-size values should therefore be treated as conditional planning scenarios, not as a retrospective judgment that the study was adequately or inadequately powered. No conclusions about the trial’s original power can be made from these illustrations because its original design assumptions are not reported.

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 = 1.500; pooled standard deviation σ = 8.135.
2. n = 2 × (1.96 + 0.842)² × 8.135² / 1.500² = 461.7, rounded up to 462 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 <- 1.5                      # observed difference in means
sigma <- 8.1349478823887                     # 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(2679079)
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 = 462 (80% power), 619 (90% power)
 75% of observed effect: n per arm = 821 (80% power), 1,099 (90% power)
 50% of observed effect: n per arm = 1,847 (80% power), 2,473 (90% power)
power.t.test: 462.7 
Simulated power at n = 462 per arm: 0.794 (20000 replicates)

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

14. Analyses Reported by the Sponsor

The sponsor’s own primary analyses use mixed models and report a mean difference (net) of -0.3 for high dose versus placebo and 1.5 for low dose versus placebo. The respective 95% confidence intervals are -4.4 to 3.8 and -2.6 to 5.6, with p-values of 0.89 and 0.47. These are the registry’s reported inferential results.

The unadjusted recalculations from the posted summary statistics yield estimates of -0.3 and 1.5, with intervals of -4.322 to 3.722 and -2.522 to 5.522. The broad conclusions are similar, but the recalculations are not an independent replication of the sponsor’s modeling. They use summary statistics and approximate variability and cannot recover the full mixed-model analysis.

Because the sponsor’s analysis is the study’s reported analysis, it takes precedence. The discrepancy flag is false, and the small differences between the posted sponsor results and recalculated values do not change the interpretation that both primary comparisons are uncertain and their reported intervals include zero. The unadjusted recalculated p-values are not substitutes for the sponsor’s p-values.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity is relevant because the record lists 9 outcome measures and 18 analyses, including a primary outcome, several secondary measures, and comparisons involving two dose groups. When many hypotheses are tested, individual p-values can appear small by chance more often than when only one hypothesis is tested. This is why prespecified testing order or an adjustment for multiple comparisons can matter when interpreting secondary findings.

The registry record does not report a multiplicity-control procedure, a testing hierarchy, or whether secondary comparisons were intended to be confirmatory. The posted p-values for secondary analyses should therefore be treated as unadjusted evidence, not as a familywise-confirmed set of findings. The record also does not report whether the primary endpoint itself was subject to any multiplicity procedure.

The primary endpoint description identifies an intent-to-treat analysis set with specified participation and measurement conditions. However, the complete definition is truncated in the registry record. Further details of the analysis population, including how participants with incomplete outcome data were handled, are not reported in the registry record.

The registry does not report the missing-data method, assumptions about missing outcomes, sensitivity analyses, or the extent and pattern of missing primary endpoint data. It also does not report sufficient detail to evaluate the sponsor’s model specification or all analysis assumptions. These omissions limit independent assessment of the robustness of the estimates. They do not justify assuming that a particular method was or was not used.

For these reasons, the primary sponsor analysis is the best available basis for interpreting the main comparison, while the secondary analyses warrant additional caution. Complete protocol and analysis-plan details would be needed to determine the planned multiplicity strategy, the full analysis populations, and the handling of missing observations.

16. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

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: conversion disorder (3.1%).

The registry reports serious adverse event figures by group: 1 participant affected in placebo, 0 in NBI-98854 low dose, and 0 in NBI-98854 high dose. The corresponding numbers at risk were 32, 32, and 33. Deaths were reported as 0 in each group. The listed serious term Conversion disorder is reported as 3.1%.

These figures describe the posted safety record; they do not by themselves establish whether an event was caused by study treatment. Zero reported serious adverse events in an arm does not prove that a risk is absent. The number of participants at risk differs from the primary endpoint analysis group sizes, so the safety figures should be interpreted using their stated denominators rather than assuming the populations are identical.

The record also lists other adverse events affecting 9 participants in placebo, 15 in low dose, and 19 in high dose, with the respective at-risk counts shown alongside the serious-event figures. These are descriptive counts and are not adjusted comparisons. Further detail on event definitions, severity, relatedness, and statistical safety comparisons is not reported in the registry record.

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

The primary results describe estimated average changes in YGTSS Total Tic Score over the 6-week treatment period and estimated differences between each NBI-98854 dose group and placebo. Both sponsor-reported 95% confidence intervals include zero. The estimates therefore do not establish a difference from placebo in either direction, and the intervals leave room for a range of possible effects.

This is not the same as proving that the groups are equivalent or that no effect exists. A result that is not statistically conclusive may reflect uncertainty, and the confidence intervals are essential for seeing how broad that uncertainty is. The registry record does not report an equivalence margin or a clinically meaningful threshold for the primary score, so equivalence or clinical importance cannot be inferred from these comparisons.

The negative within-group changes show that average scores decreased from baseline in all three groups. Those descriptive changes alone do not establish that the study treatment caused improvement: the comparison with placebo is the relevant randomized contrast, and the sponsor’s primary contrasts remain uncertain. The data also do not support a claim that either dose works or does not work.

The study is a phase 2 trial with a 6-week treatment period and a pediatric Tourette syndrome population. Its findings should be understood within that setting and on the measures reported. The registry does not provide enough information to infer effects beyond the recorded outcomes or period, to determine longer-term safety, or to make claims about individual participants.

The secondary outcomes and safety counts add context but do not remove the uncertainty in the primary comparison. The registry record is a report of trial results, not a substitute for a complete analysis plan, full publication, or broader evidence base. Those materials and details are not reported in the registry record.

18. Why This Trial Matters Statistically

This trial illustrates why changes within treatment groups and differences between randomized groups answer different questions. All three groups had negative estimated changes in the primary score, but the treatment comparison depends on the difference relative to placebo, not on whether an individual group’s score moved from baseline. The sponsor’s estimated between-group differences are close to zero relative to their uncertainty.

It also shows the importance of reporting confidence intervals alongside point estimates and p-values. The estimates alone have a direction, but the intervals include zero and span values in both directions. Precision, rather than just the sign of an estimate, is central to interpreting what the study can establish.

The record also gives an opportunity to distinguish a sponsor’s model-based analysis from simple recalculations based on summary statistics. The latter can serve as a check on the scale and broad direction of posted estimates, but they do not reproduce a mixed-model analysis or supersede the sponsor’s results. This distinction matters whenever the trial’s full model details are unavailable.

Finally, the trial includes multiple secondary outcomes and comparisons. Their breadth may offer descriptive context, but without reported multiplicity procedures, individual unadjusted results require restraint. The case demonstrates how to keep the primary question central while recognizing the limits of secondary analyses and planning illustrations.

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 report the dose amounts, full randomization procedures, or the original sample-size justification. The analysis description for the primary population is incomplete, and the model specification is not detailed enough to reproduce the sponsor’s mixed models analysis. These gaps limit independent evaluation of the analysis choices.

Missing-data methods, sensitivity analyses, and the extent and pattern of missing primary endpoint data are not reported in the registry record. Multiplicity procedures and a testing hierarchy for secondary outcomes are also not reported. This is important because the record includes numerous outcome measures and analyses.

The primary endpoint is a clinical rating scale, and the registry does not report a clinically meaningful threshold for interpreting its change. The short treatment period is 6 weeks; longer-term outcomes are not established by these results. The record does not report enough detail to assess generalizability beyond the enrolled pediatric study population.

The recalculated contrasts use summary statistics and approximate standard deviations derived from the reported standard errors. They are unadjusted and cannot account for the sponsor model’s details. They should not be mistaken for the study’s prespecified analysis. The sponsor’s results remain the main inferential results, and their confidence intervals are broad enough to include zero and effects in either direction.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Safety and Efficacy Study of NBI-98854 in Children and Adolescents With Tourette Syndrome — NCT02679079.
• Registry record last updated 2021-01-15; status last verified 2020-12.
• Results first posted 2021-01-15.
• 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

NCT02679079 was a completed phase 2 randomized, parallel-group, quadruple-masked, placebo-controlled study of once-daily NBI-98854 in pediatric participants with Tourette syndrome. Treatment was described as lasting 6 weeks, and reported enrollment was 98.

The primary endpoint was change from baseline to Week 6 in YGTSS Total Tic Score. The sponsor’s mixed models comparisons versus placebo were -0.3 for high dose and 1.5 for low dose; both 95% confidence intervals included zero. The registry lists 8 secondary outcomes and safety counts by group. Original design assumptions, several analysis details, multiplicity methods, and missing-data methods are not reported in the registry record.