Botulinum Toxin A to Treat Arm Tremor: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Botulinum Toxin A to Treat Arm Tremor (NCT02207946), a randomized phase 2 study. The primary outcome is Change From Baseline to Week 4 in Maximum Angular Tremor Amplitude of the Wrist (Injected Limb).

2. Clinical Question

3. Trial Design

The study was a randomized, double-blind, parallel-group, placebo-controlled Phase 2 trial. Its official title describes prospective assessment of the efficacy and safety of NT 201 for unilateral treatment of essential tremor of the upper limb. The registry identifies the sponsor as Merz Pharmaceuticals GmbH and records the study status as completed. Enrollment was 30.

The treatment was a single injection cycle of incobotulinumtoxinA, with a total dose of up to 200 Units, or placebo. In both arms, wrist muscle injection was mandatory, while shoulder and/or elbow muscle injection was optional. The treatment description says the injections were intramuscular. The study summary describes the injection approach as based on kinematic analysis. Further details about how doses or injection sites were selected are not reported in the registry record.

Randomization means participants were assigned to groups by an allocation process intended to reduce systematic differences between groups. Double masking means the registry identifies the study as masked for two parties, but which parties were masked and how masking was maintained are not reported in the registry record. A parallel-group design assigns participants to a group that is compared with another group rather than describing a crossover between treatments.

The posted efficacy results include 18 participants in the incobotulinumtoxinA group and 11 in the placebo group for the wrist-amplitude outcome. The full analysis set was defined as participants who received study medication at least once and had a post-baseline efficacy measurement. Safety risk groups include 19 participants receiving incobotulinumtoxinA and 11 receiving placebo. The reason the reported group counts differ across these records is not reported in the registry record. Details of the allocation sequence, concealment, study locations, and original sample-size 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: A total of 52 participants were screened, out of which 30 participants were randomized and treated.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The full analysis set (FAS) was defined as the subset of participants who received study medication (incobotulinumtoxinA or placebo) at least once, and for whom a post-baseline value of any efficacy variable was measured.

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 safety evaluation set (SES) was the subset of all participants who received study medication (incobotulinumtoxinA or placebo) at least once.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline to Week 4 in Maximum Angular Tremor Amplitude of the Wrist (Injected Limb), measured over Baseline up to Week 4.

The registered measure is the change from baseline to Week 4 in maximum angular tremor amplitude at the wrist of the injected limb. The measure is expressed in degrees and is identified as a mean with standard deviation. The registry describes TremorTek as a tremor kinematic analytics investigational device used to measure the maximum angular tremor amplitude at the injected wrist. It also states that angular tremor amplitude measures tremor severity and that a reduction in amplitude represents tremor improvement.

In practical terms, the outcome compares a participant’s wrist-amplitude measurement after treatment with the baseline measurement. A negative change indicates a lower measured amplitude at Week 4 than at baseline; the registry’s description links a reduction to improvement in the measured tremor. This is a measurement of a specific limb and a specific time point, not a direct measure of every aspect of essential tremor or daily functioning.

The registry explicitly notes that no primary efficacy variables were defined for the study. The wrist-amplitude outcome was a secondary outcome used for registry protocol registration and results reporting. That distinction matters when interpreting the result: the outcome is presented as the registered measure for this statistical analysis, but the record does not identify it as the study’s formally defined primary efficacy endpoint. Further details about validation or clinical importance thresholds for this measure are not reported in the registry record.

7. Results Posted in the Registry

• IncobotulinumtoxinA 30 to 200 U: mean -0.47 versus 0.07 on control; difference -0.54 (95% CI -1.14 to 0.06), standardized effect d = -0.74; z-test p = 0.076.

8. Secondary Efficacy Endpoints

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

Change From Baseline to Week 4 in Maximum Log-transformed Accelerometric Tremor Amplitude at Wrist Level (Injected Limb)

• 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 deviations.
• Result:
  • IncobotulinumtoxinA 30 to 200 U: mean -0.73 versus 0.05 on control; difference -0.78 (95% CI -1.15 to -0.41), standardized effect d = -1.42; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for IncobotulinumtoxinA 30 to 200 U than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline to Week 4 in Fahn-Tolosa-Marin (FTM) Tremor Score in Injected Limb (Item 5 [Right Upper Extremity] or 6 [Left Upper Extremity])

• 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 deviations.
• Result:
  • IncobotulinumtoxinA 30 to 200 U: mean -1.90 versus -0.50 on control; difference -1.40 (95% CI -2.78 to -0.02), standardized effect d = -0.75; z-test p = 0.047.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for IncobotulinumtoxinA 30 to 200 U than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline to Week 4 in FTM Motor Performance Score (Items 11-15)

• 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 deviations.
• Result:
  • IncobotulinumtoxinA 30 to 200 U: mean -2.80 versus -0.80 on control; difference -2.00 (95% CI -3.39 to -0.61), standardized effect d = -1.14; z-test p = 0.005.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for IncobotulinumtoxinA 30 to 200 U than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcome results add measures of tremor amplitude, limb tremor score, and motor performance to the wrist-amplitude result. For the three secondary measures with numerical group comparisons posted, the unadjusted mean differences are negative, with p-values ranging from < 0.001 to 0.047. These directions are consistent with greater reductions in the treatment group on those reported change measures, but they do not replace or redefine the registered wrist-amplitude analysis. The registry describes the wrist-amplitude result as a secondary measure used for registration and reporting, and says no primary efficacy variables were defined.

The remaining named secondary measures are participant and investigator global impressions at Week 4. Their numerical results are not reported in the registry record. Thus, the full set of secondary outcomes does not have a complete numerical account in the posted results. The registry lists six outcome measures overall and five secondary outcomes; results are posted for three of those secondary measures, while the other two global-impression outcomes are not reported in the registry record.

Unadjusted secondary findings carry less weight because examining several outcomes creates more opportunities for a seemingly notable result to occur by chance. A multiplicity adjustment can address this issue, but the registry does not report an adjustment or a prespecified hierarchy for these outcomes. The absence of that information means the secondary p-values should be considered exploratory rather than treated as independent confirmation of the wrist-amplitude finding. The registry’s statement that no primary efficacy variables were defined makes it especially important not to promote one secondary result as a definitive primary conclusion.

Secondary outcomes can still be useful: they show whether different measurement approaches appear to tell a broadly similar or different story and can help identify questions for later studies. Here, the available secondary comparisons generally point in a negative direction, but their interpretation is limited by the small groups, multiple comparisons, and lack of reported multiplicity handling. They should be considered alongside the sponsor’s registered-outcome analysis and its confidence interval, not as a substitute for it.

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

• Change From Baseline to Week 4 in Maximum Log-transformed Accelerometric Tremor Amplitude at Wrist Level (Injected Limb)
• Change From Baseline to Week 4 in Fahn-Tolosa-Marin (FTM) Tremor Score in Injected Limb (Item 5 [Right Upper Extremity] or 6 [Left Upper Extremity])
• Change From Baseline to Week 4 in FTM Motor Performance Score (Items 11-15)
• Participant's Global Impression of Change Scale (GICS) at Week 4
• Investigator's Global Impression of Change Scale (GICS) at Week 4

9. Statistical Interpretation

10. Statistical Methods Explained

The primary comparison is between mean changes in a continuous measure. A continuous outcome can take values across a scale, rather than being limited to categories such as yes or no. Here, the measured quantity is angular tremor amplitude at the injected wrist, and the reported change is the Week 4 measurement relative to baseline. The mean describes the average change within each arm. The standard deviation describes how much individual participant measurements varied around that group mean; it is not the uncertainty of the mean itself.

What does the unadjusted comparison estimate?

The recalculated mean difference compares the two posted group means directly. For the wrist-amplitude measure, the incobotulinumtoxinA mean change was -0.47 degrees and the placebo mean change was 0.07 degrees. The unadjusted recalculation reports a mean difference of -0.54 degrees. This is a simple comparison based on the posted summary statistics, not an adjustment for baseline values or other covariates. It is useful as a transparent descriptive check, but it is not a replacement for the sponsor’s reported analysis.

The recalculation’s standard error represents the estimated sampling uncertainty of the mean difference under its assumptions. A confidence interval is formed around the estimate to express a range of values compatible with the data and method. The 95% interval for the unadjusted estimate extends from -1.136 to 0.056. Since the interval includes zero, the data do not rule out a zero difference under this calculation. The interval also spans values on both sides of zero, so the estimate is not precise enough to determine the direction of the difference with confidence.

What does the sponsor’s ANCOVA add?

The sponsor reported an analysis of covariance, or ANCOVA, with a least-squares mean difference of -0.43 degrees, a 95% confidence interval from -1.02 to 0.16, and p = 0.144. ANCOVA compares groups while accounting for variables included in the model. In clinical trials, such models can adjust for baseline outcome values or other prespecified covariates, but the covariates used in this analysis are not reported in the registry record. A least-squares mean difference is therefore a model-based estimate, not simply the subtraction of the two posted group means.

The sponsor’s interval also includes zero. Its estimate is in the same negative direction as the unadjusted recalculation, but the two point estimates and intervals are not identical. Such differences can arise because the model and the unadjusted calculation use different estimation approaches; the registry does not report enough detail to identify the exact reasons. The sponsor analysis is the reported trial analysis, while the unadjusted calculation is a separate summary-statistic-based recalculation.

How should p-values be understood?

A p-value assesses how incompatible the observed data are with a specified null model, assuming that model and the statistical assumptions are correct. The unadjusted recalculation gives p = 0.076, while the sponsor’s ANCOVA gives p = 0.144. Neither p-value should be interpreted as the probability that treatment has no effect or as a measure of clinical importance. A p-value also does not measure the probability that a result will be replicated. The estimate and its confidence interval provide essential context, especially when the interval covers both zero and nonzero values.

These calculations depend on assumptions about the data and analysis. General statistical considerations include the suitability of the model, the independence of participant observations, and the adequacy of the uncertainty estimates. The registry record does not report diagnostic checks or enough detail to assess all model assumptions. Because the efficacy groups are small, estimates can be sensitive to the observations included and may be imprecise.

Why might over-dispersion matter?

General statistical explanation: over-dispersion occurs when observed variability is greater than a model expects. When that happens, a model that assumes less variability can understate uncertainty and make intervals too narrow or p-values too small. It is most often discussed for count outcomes, while this registered outcome is continuous and is reported with a standard deviation. The registry record does not report an over-dispersion assessment or identify over-dispersion as an issue for this analysis.

The endpoint is a change score, so its interpretation depends on the baseline and follow-up measurements and their variability. The registry reports group means and standard deviations for change but does not provide participant-level data, baseline and follow-up distributions separately, or correlations between repeated measurements. Those omissions prevent an independent assessment of how the change-score variability arose. They do not invalidate the reported calculations, but they limit what can be checked from the registry record.

11. Confidence Intervals and Precision

Precision concerns how narrowly an analysis estimates the between-group difference. The unadjusted recalculation for maximum angular wrist tremor amplitude gives a mean difference of -0.54 degrees and a 95% confidence interval from -1.136 to 0.056. The interval includes zero. It therefore allows for no mean difference and for differences in either direction, while its point estimate lies in the negative direction. The breadth of this interval relative to the point estimate indicates appreciable uncertainty in the size and direction of the unadjusted difference.

The sponsor’s ANCOVA estimate is -0.43 degrees, with a 95% confidence interval from -1.02 to 0.16. This interval also includes zero and spans both negative and positive differences. The adjusted and unadjusted estimates are not identical, and the record does not report the ANCOVA covariates or further modeling details needed to explain the difference. Each interval should be interpreted as belonging to its own analysis rather than combined into a new estimate.

In general, a 95% confidence interval is a procedure that, under repeated use and its assumptions, would cover the true value at the stated rate. It is not a statement that there is a 95% probability that this particular interval contains the true effect. The interval conveys a range of estimates compatible with the data and model; it does not show which values within that range are more likely, nor does it establish clinical importance.

The observed efficacy groups are small: 18 participants for incobotulinumtoxinA and 11 for placebo. Small groups commonly produce less precise estimates because the data contain limited information about the underlying group means and variability. The registry record does not report a clinically meaningful threshold for this outcome, so the intervals cannot be classified against such a threshold. The uncertainty is relevant when reading both the point estimate and the p-value: neither alone communicates the range of plausible effects.

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 figures are planning illustrations based on the observed effect, not the original design assumptions for the trial. The displayed figures are participants per arm, not total participants and not total events. The calculation assumes a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It considers the stated fraction of the observed effect as the effect to detect. The trial’s own original sample-size justification and design assumptions are not reported in the registry record.

The 80% power column gives the illustrative number of participants per arm for a design with an 80% chance of detecting the specified effect under the calculation’s assumptions, if that effect is the true one. The 90% power column applies the same idea with a 90% chance. These are planning targets for a hypothetical study, not descriptions of how many participants were actually needed to reach a conclusion in this trial.

Rows for 100%, 75%, and 50% of the observed effect illustrate how the planning estimate changes when the target effect is varied. A smaller effect is harder to distinguish from random variation, so detecting it generally requires more participants. The numerical examples are consequently conditional on the observed effect and the assumptions used for the planning calculation; they do not establish that the observed effect is a reliable estimate of the effect a future study would see.

This is not observed power. Observed power is sometimes calculated after a study using its observed estimate, but it does not provide a useful substitute for interpreting the estimate and confidence interval. The planning figures are better read as conditional illustrations of how sample-size requirements respond to effect size and desired power, rather than as evidence that this completed trial had adequate or inadequate power.

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 = -0.540; pooled standard deviation σ = 0.733.
2. n = 2 × (1.96 + 0.842)² × 0.733² / -0.540² = 28.9, rounded up to 29 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 <- -0.54                      # observed difference in means
sigma <- 0.73260822737314                     # 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(2207946)
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 = 29 (80% power), 39 (90% power)
 75% of observed effect: n per arm = 52 (80% power), 69 (90% power)
 50% of observed effect: n per arm = 116 (80% power), 155 (90% power)
power.t.test: 29.9 
Simulated power at n = 29 per arm: 0.787 (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 reported comparison is an ANCOVA estimate of the least-squares mean difference: -0.43 degrees, with a 95% confidence interval from -1.02 to 0.16 and p = 0.144. The interval includes zero. This is the trial’s own reported inferential analysis for the registered wrist-amplitude outcome.

The unadjusted recalculation uses only the posted group means and standard deviations. It estimates a mean difference of -0.54 degrees, with a 95% confidence interval from -1.136 to 0.056 and p = 0.076. This is not the same analysis as ANCOVA. The two estimates point in the same negative direction, but their numerical values and p-values differ. The registry record does not identify the ANCOVA covariates or provide further detail that would explain the difference.

The sponsor analysis should be distinguished from the recalculation rather than treated as interchangeable with it. The recalculation is a simple unadjusted comparison from summary statistics; the ANCOVA is the sponsor’s model-based result. Both intervals include zero, and neither analysis by itself demonstrates equivalence. The record does not flag a discrepancy between the posted summary statistics and the sponsor analysis. The sponsor’s p-value and interval remain the reported trial results, while the recalculation offers a separate view of the group summaries.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when a study assesses several outcomes, comparisons, time points, or subgroups. The more statistical tests performed, the greater the chance that at least one result will appear notable by chance alone, even if no corresponding effect exists. One approach is to define a primary outcome and analysis in advance and apply a prespecified strategy for secondary tests. The registry record states that no primary efficacy variables were defined. It identifies the wrist-amplitude measure as a secondary outcome used for registry registration and reporting, and lists several additional secondary outcomes.

Whether the trial had a prespecified multiplicity strategy, such as an adjustment or testing hierarchy, is not reported in the registry record. The posted secondary comparisons therefore should not be read as if each were the sole confirmatory test. Their unadjusted p-values can describe the observed data under their individual analyses, but they do not account for the family of outcomes considered. Protocol details about planned analyses beyond those summarized in the registry are not reported in the registry record.

The full analysis set is defined as participants who received study medication at least once and had a post-baseline value for any efficacy variable. That definition is reported, but the registry does not provide a participant-level account of who was excluded from each outcome analysis or why. The registered wrist-amplitude outcome has 18 participants in the incobotulinumtoxinA group and 11 in placebo. Whether all eligible participants contributed to every secondary outcome, and how missing measurements were handled, is not reported in the registry record.

Missing data can affect an estimate if the participants without measurements differ systematically from those with measurements. General statistical methods for addressing missing values include analyses based on available observations and model-based approaches, but the method used for this study is not reported in the registry record. The record also does not report sensitivity analyses that assess how results might change under different assumptions about missing data. No assumptions about reasons for missingness or imputation should therefore be inferred from the posted group counts.

These gaps limit assessment of the analysis plan and robustness. They do not establish that the trial used an inappropriate approach; they mean the registry record does not report enough detail to determine the approach. The small analysis groups, multiple outcomes, and unreported missing-data handling are relevant context for the uncertainty in the estimates.

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 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: influenza like illness (9.1%), chest discomfort (9.1%).

For serious adverse events, the registry lists 0 affected participants among 19 at risk in the incobotulinumtoxinA group and 2 among 11 at risk in the placebo group. Deaths are listed as 0 in each group. These are counts of participants, not a comparison adjusted for follow-up time or other characteristics. With groups of this size, the counts provide a limited description of the events recorded in the registry and do not establish that risks are equal or different.

The registry lists influenza like illness and chest discomfort among the top serious adverse event terms, each at 9.1%. The record does not give additional detail in the listed terms about event timing, severity beyond the serious classification, relatedness to treatment, or whether an individual had more than one event. Those details are not reported in the registry record.

For other adverse events, 9 of 19 participants in the incobotulinumtoxinA group and 6 of 11 in the placebo group are listed as affected. These figures are separate from the serious adverse event counts. Adverse event counts describe what was recorded during the study; they are not, on their own, proof that an event was caused by the assigned intervention. The registry record does not provide enough detail to assess comparative safety beyond these posted counts and terms.

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

The posted results describe a small randomized comparison of one injection cycle of incobotulinumtoxinA with placebo, with wrist tremor amplitude measured through Week 4. For the registered measure, the mean change was -0.47 degrees in the incobotulinumtoxinA group and 0.07 degrees in the placebo group. The unadjusted recalculation and the sponsor’s ANCOVA both estimate a difference in the negative direction, but both 95% confidence intervals include zero. The data therefore leave substantial uncertainty about the size and direction of the between-group difference.

This is not evidence that the treatments are equivalent. Showing equivalence requires a design and analysis that specify an acceptable range of differences and assess whether the confidence interval lies within that range. Such a margin and analysis are not reported in the registry record. Nor does a p-value above a conventional threshold prove that there is no effect; it indicates that the observed data do not provide strong evidence against the tested null model under the analysis assumptions.

The endpoint is a kinematic measurement of the injected wrist. It is not a direct summary of all symptoms, overall function, or longer-term outcomes. The registry reports Week 4 changes and lists other outcomes, but the two global-impression outcomes have no numerical results in the record. Longer-term effects and broader consequences are not established by this short-term outcome report.

Secondary results offer additional observations, but they are unadjusted and come from several outcomes. Their p-values require caution because of multiplicity, and the record does not report a multiplicity strategy. The safety counts likewise describe recorded events in small groups and cannot establish comparative risks. The evidence is best understood as estimates from this particular study with meaningful uncertainty, rather than as a universal conclusion about the intervention or all people with essential tremor.

18. Why This Trial Matters Statistically

This trial is statistically instructive because the registry uses a secondary outcome for its registered results while explicitly stating that no primary efficacy variables were defined. A formal primary outcome ordinarily provides a clear focal test and can guide interpretation when several measures are assessed. Without one, the reader should be careful not to elevate a favorable-looking secondary result into a definitive conclusion after seeing the results.

The example also distinguishes a sponsor’s model-based estimate from an unadjusted recalculation based on group summaries. ANCOVA can account for variables included in the model, while a simple recalculation compares the posted means directly. The two estimates have the same direction but different values and p-values. Knowing which estimate answers which question helps prevent confusion between a reported trial analysis and a separate descriptive check.

Precision is central to the interpretation. The sponsor’s interval and the unadjusted interval both include zero, and the observed outcome groups are small. This illustrates why the point estimate alone is not enough: uncertainty encompasses a range of effects, and the p-value does not specify the effect’s clinical importance. Planning illustrations based on the observed effect also cannot repair the uncertainty in a completed small trial or reveal the original design rationale.

Finally, the record illustrates the limits of registry results as a standalone statistical account. It defines the full analysis set but does not report the missing-data method, the ANCOVA covariates, or a multiplicity strategy. These omissions do not imply that no such plans existed; they limit what can be assessed from the registry record. Transparent reporting of those elements is important for evaluating robustness and interpreting the evidence.

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 has several trial-specific limitations for statistical interpretation. It states that no primary efficacy variables were defined, although the wrist-amplitude outcome is used for results reporting. This leaves uncertainty about the outcome’s role in the original analysis plan and makes the multiple secondary results harder to frame as confirmatory evidence. The original protocol and statistical analysis plan are not reported in the registry record.

The sponsor reports ANCOVA, but the covariates and model details are not reported in the registry record. It is therefore not possible to assess how the adjusted estimate was constructed or to reproduce it from the posted group summaries. The unadjusted recalculation offers a direct summary-statistic comparison, but it cannot substitute for unavailable model specifications or participant-level data.

The efficacy outcome group counts are 18 and 11, while enrollment is 30 and safety groups include 19 and 11. The record does not explain these differences. It defines the full analysis set but does not report outcome-specific missingness, the handling of missing measurements, or sensitivity analyses. These gaps limit assessment of how the analysis population and missing data may affect the estimates.

The study reports multiple secondary outcomes, but a multiplicity adjustment or testing hierarchy is not reported in the registry record. Numerical results are also absent for the participant and investigator global-impression outcomes. Finally, the registered endpoint is measured through Week 4 and concerns the injected wrist. The posted results do not establish persistence beyond that time point or represent all dimensions of tremor. The registry does not report a clinically meaningful threshold for the angular-amplitude measure, which limits interpretation of the magnitude in practical terms.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Botulinum Toxin A to Treat Arm Tremor — NCT02207946.
• Registry record last updated 2021-02-18; status last verified 2021-02.
• Results first posted 2021-02-18.
• 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

The registry describes a completed Phase 2 randomized, double-blind, parallel-group comparison of a single incobotulinumtoxinA injection cycle with placebo for essential tremor of the upper limb. Enrollment was 30. The registered wrist-amplitude outcome measures change from baseline to Week 4; the registry notes that no primary efficacy variables were defined and that this measure was used as a secondary outcome for registration and reporting.

The sponsor’s ANCOVA reports a least-squares mean difference of -0.43 degrees, with a 95% confidence interval from -1.02 to 0.16 and p = 0.144. The unadjusted recalculation is -0.54 degrees, with a 95% confidence interval from -1.136 to 0.056 and p = 0.076. Both intervals include zero. Secondary outcomes provide additional but unadjusted comparisons, and numerical global-impression results are not reported in the registry record. Safety counts and analysis details should be interpreted in light of the small groups and the registry’s unreported multiplicity and missing-data methods.