Safety and Efficacy of SPD503 in Treating ADHD in Children and Adolescents Aged 6-17: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety and Efficacy of SPD503 in Treating ADHD in Children and Adolescents Aged 6-17 (NCT00150618), a randomized phase 3 study. The primary outcome is Change From Baseline in Attention Deficit Hyperactivity Disorder Rating Scale (ADHD-RS-IV) Score at 6 Weeks.

2. Clinical Question

3. Trial Design

The registry describes a Phase III, randomized, double-blind, multicenter, parallel-group, placebo-controlled study of SPD503 in children and adolescents aged 6-17 with ADHD. Enrollment is listed as 324. The study status is completed. The recorded start date is 2004-03-30, and the primary completion date is 2004-10-07. Shire is named as sponsor.

Five arms are listed: SPD503 at 1 mg, 2 mg, 3 mg, and 4 mg, and placebo. The primary outcome was assessed at baseline and 6 weeks. The primary analysis population was the intent-to-treat population as defined in the record: randomized subjects who had baseline and at least one post-randomization primary efficacy measurement. The outcome-specific arm counts are not identical across endpoints, so the results should be read with the population and count shown for each outcome rather than assumed to use the same participants throughout.

The record lists four secondary outcomes concerning parent symptom ratings, clinical global improvement, parent global assessment, and child health-related quality of life. It reports analyses for the primary endpoint and some secondary outcomes. The registry record does not report the original sample-size justification, the detailed randomization procedure, dose administration instructions, study-site details, or a full statistical analysis plan. It also does not report the specific approach used to handle missing outcome data. Those omissions limit how completely the design and analysis can be reconstructed from the registry.

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: Although 324 subjects were randomized, 2 never received drug and therefore were not included in the Baseline Characteristics. Subjects received either 1, 2, 3, or 4 mg of SPD503 (Guanfacine hydrochloride) or placebo once daily.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Intent to treat (ITT) defined as all subjects who were randomized to treatment and had the Baseline and at least one post-randomization primary efficacy measurement.

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in Attention Deficit Hyperactivity Disorder Rating Scale (ADHD-RS-IV) Score at 6 Weeks, measured over Baseline and 6 weeks.

The primary endpoint is change from baseline in the Attention Deficit Hyperactivity Disorder Rating Scale-fourth edition total score at 6 weeks. The registry describes the measure as 18 items scored on a 4-point scale, with a total score from 0 to 54; higher item scores indicate more severe symptoms. The endpoint therefore records change in symptom-rating score over the study period, rather than a count of events or a time-to-event measure.

The posted arm results are least-squares mean changes, accompanied by standard errors. A negative change means the follow-up score is lower than baseline. In this context, a more negative mean change indicates a larger reduction in the recorded score. The dose-versus-placebo estimates are differences between mean changes, with confidence intervals conveying uncertainty around those estimates.

Using a standardized rating scale gives the study a defined outcome for comparing groups over the same follow-up period. It also gives a quantitative measure that can capture changes that are not summarized by a simple event count. The registry does not report a threshold for deciding what size of score change would be clinically important, nor does it provide a minimal clinically important difference. Statistical separation from placebo should therefore be distinguished from the importance of the size of the change to patients or families.

7. Results Posted in the Registry

• SPD503 (1 mg): mean -19.44 versus -12.69 on control; difference -6.75 (95% CI -11.31 to -2.19), standardized effect d = -0.53; z-test p = 0.004.
• SPD503 (2 mg): mean -18.09 versus -12.69 on control; difference -5.40 (95% CI -9.83 to -0.97), standardized effect d = -0.43; z-test p = 0.017.
• SPD503 (3 mg): mean -20.00 versus -12.69 on control; difference -7.31 (95% CI -11.80 to -2.82), standardized effect d = -0.58; z-test p = 0.001.
• SPD503 (4 mg): mean -20.57 versus -12.69 on control; difference -7.88 (95% CI -12.31 to -3.45), standardized effect d = -0.62; 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 Conner's Parent Rating Scale-revised Short Version (CPRS-R) Score at 6 Weeks

• 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:
  • SPD503 (1 mg): mean -19.50 versus -8.41 on control; difference -11.09 (95% CI -17.60 to -4.58), standardized effect d = -0.65; z-test p = <0.001.
  • SPD503 (2 mg): mean -14.96 versus -8.41 on control; difference -6.55 (95% CI -12.97 to -0.13), standardized effect d = -0.39; z-test p = 0.045.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for SPD503 (1 mg) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for SPD503 (2 mg) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Number of Participants With Improvement in Clinical Global Impression-Improvement (CGI-I)

• 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:
  • SPD503 (1 mg): 54.4% (31/57) versus 30.2% (19/63) on control; risk difference 24.2 percentage points (95% CI 7.0 to 41.4), risk ratio 1.80 (1.16–2.81); unadjusted two-proportion z-test p = 0.007.
  • SPD503 (2 mg): 42.9% (27/63) versus 30.2% (19/63) on control; risk difference 12.7 percentage points (95% CI -4.0 to 29.4), risk ratio 1.42 (0.89–2.28); unadjusted two-proportion z-test p = 0.139.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for SPD503 (1 mg) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between SPD503 (2 mg) and the control. The interval gives the range of effects that remain compatible with the data.

Number of Participants With Improvement in Parent Global Assessment (PGA)

• 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:
  • SPD503 (1 mg): 50.9% (27/53) versus 30.2% (16/53) on control; risk difference 20.8 percentage points (95% CI 2.5 to 39.0), risk ratio 1.69 (1.04–2.75); unadjusted two-proportion z-test p = 0.030.
  • SPD503 (2 mg): 36.4% (20/55) versus 30.2% (16/53) on control; risk difference 6.2 percentage points (95% CI -11.6 to 23.9), risk ratio 1.20 (0.70–2.06); unadjusted two-proportion z-test p = 0.496.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for SPD503 (1 mg) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between SPD503 (2 mg) and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes broaden the assessment beyond the primary symptom-rating score. They include another parent symptom scale, two global-improvement assessments, and a child health-related quality-of-life measure. Together, these outcomes offer perspectives from different assessment instruments and respondents, but they are not interchangeable with the primary endpoint.

The posted secondary results do not form a uniform pattern across measures and doses. Some recalculated comparisons have confidence intervals that do not include zero, while others span zero; the outcome and dose matter to the interpretation. The overall pattern therefore should not be reduced to a single claim that all secondary assessments agree or disagree with the primary result. These outcomes can provide context, but do not independently settle the primary question.

The registry lists 5 outcome measures and 20 analyses, while secondary results are posted for 4 outcomes. The record does not report a multiplicity adjustment for the secondary comparisons, nor does it state which secondary analyses were designated confirmatory. When many outcomes and group comparisons are examined, the chance of at least one apparently notable result due to random variation increases. For that reason, unadjusted secondary p-values generally carry less evidential weight than a clearly prespecified primary analysis, particularly when considered one at a time.

These secondary findings are best read as supportive or exploratory context rather than as a collection of independent confirmations. Their relationship to the primary result depends on the differences in measurement, assessment population, and analysis. The registry record does not provide enough detail about missingness or the analysis plan to determine how those issues may have affected the secondary results.

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

• Change From Baseline in Conner's Parent Rating Scale-revised Short Version (CPRS-R) Score at 6 Weeks
• Number of Participants With Improvement in Clinical Global Impression-Improvement (CGI-I)
• Number of Participants With Improvement in Parent Global Assessment (PGA)
• Change From Baseline in Child Health Questionnaire-Parent Form (CHQ-PF50) Score at 6 Weeks

9. Statistical Interpretation

10. Statistical Methods Explained

The registry reports the primary outcome as a least-squares mean change from baseline. The arm-level standard errors describe the estimated uncertainty around those means. The sponsor's listed analysis method for each primary comparison is ANCOVA, or analysis of covariance. The record does not specify the covariates included, the precise model specification, or other details needed to reproduce that analysis.

What does a mean difference represent?

In general, a mean difference compares the average outcome in one group with the average outcome in another. Here, the recalculated estimate subtracts the placebo mean change from the SPD503 mean change. Because all four estimates are negative, the posted arm summaries show a larger average decrease in score in the SPD503 group for each comparison. The estimate is expressed in ADHD-RS-IV score units, not as a percentage or a risk.

The posted arm means and standard errors allow a simple unadjusted comparison to be reconstructed. The recalculation uses an approximate pooled standard deviation inferred from the standard errors and group counts, as noted in the posted comparison data. That approximation is not the same as access to participant-level observations. It cannot incorporate model details that are absent from the arm summaries, and it does not recreate the sponsor's ANCOVA.

Why are confidence intervals useful?

In general, a confidence interval gives a range of values compatible with the data and the method used to calculate it. A narrower interval indicates greater precision under that method; a wider interval indicates more uncertainty about the estimate. For the primary comparisons, the 95% intervals around the recalculated mean differences are below zero. The interval width still matters: it shows that the data do not identify a single exact difference. A confidence interval is not a guarantee that the true value lies within its endpoints, nor does it measure clinical importance.

How should p-values be read?

A p-value describes how unusual data at least as incompatible with a stated null hypothesis would be if that hypothesis and the analysis assumptions held. It is not the probability that the null hypothesis is true, and it does not measure the size or importance of an effect. The registry gives sponsor p-values from ANCOVA and the recalculated unadjusted p-values. Because the sponsor's own analysis is the reported trial analysis and a discrepancy is flagged, the sponsor's values take precedence.

For the binary secondary outcomes, the recalculated comparisons use risk differences. In general, a risk difference is the difference between the proportions with an outcome in two groups. For the continuous secondary outcome, the comparison is a mean difference. The registry lists Cochran-Mantel-Haenszel analyses for the binary outcomes and ANCOVA for the continuous CPRS-R outcome. It does not describe the stratification or adjustment details for those methods. The recalculated estimates are not adjusted for those unreported details.

Why does over-dispersion matter?

In general, over-dispersion occurs when observed variability is greater than a model assumes. If a model understates variability, standard errors can be too small and confidence intervals too narrow, making results appear more precise than they are. This issue is especially relevant for count or clustered data. The primary endpoint is continuous, and the posted summaries do not report an over-dispersion assessment. The registry record does not report whether over-dispersion was evaluated for any analysis; it should not be assumed to have been a feature of the primary model.

The interpretation depends on the outcome definition, analysis population, model, and missing-data handling as well as the numerical results. The registry identifies the primary ITT definition and analysis methods, but does not report a complete analysis plan. The distinction between sponsor analyses and summary-statistic recalculations is therefore important: the latter help readers inspect the posted summaries but do not supersede the sponsor's analysis.

11. Confidence Intervals and Precision

The primary comparisons have 95% confidence intervals for the mean difference. For SPD503 (1 mg), the recalculated difference is -6.75, with an interval from -11.31 to -2.189. For 2 mg, it is -5.4, with an interval from -9.835 to -0.965. For 3 mg, it is -7.31, with an interval from -11.8 to -2.819. For 4 mg, it is -7.88, with an interval from -12.31 to -3.445. All four intervals are on the negative side of zero, consistent with larger average decreases in score in the SPD503 arms than in placebo under this unadjusted calculation.

The interval endpoints also show that the estimates are not exact. For example, the 1 mg interval allows a range of mean differences from -11.31 to -2.189 under the calculation used. The width of an interval reflects both the observed variability and the amount of information available for that comparison. A confidence interval is a measure of statistical uncertainty, not a range containing every participant's response. It also does not state whether any particular difference is clinically meaningful.

The posted estimates are recalculated from arm-level summary statistics, with approximate pooled variability. Their precision should therefore be understood as conditional on that reconstruction. The sponsor's ANCOVA results are the trial's own reported analysis and take precedence because the record flags a discrepancy. The sponsor results include 95% confidence interval levels, but numeric confidence limits are not reported in the registry record. The unadjusted recalculated intervals should not be presented as though they were the sponsor's model-based intervals.

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 illustrations are planning calculations based on observed effects, not the trial's original design assumptions. The figures are participants per arm for the two-arm comparison; they are not total participants across all study groups. The assumptions listed are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each planning scenario uses the stated fraction of the observed effect as the effect to detect. The original trial's sample-size assumptions and justification are not reported in the registry record.

The 80% power column indicates the illustrative number of participants per arm for a design with an 80% chance of detecting the specified effect under the stated assumptions, if that effect were the true effect. The 90% power column gives the corresponding planning figure for a 90% chance. These are design calculations, not a measure of what the completed study achieved. This is not observed power.

The rows that plan for 75% or 50% of the observed effect assume a smaller difference to detect than the row based on the full observed effect. Smaller effects are harder to distinguish from random variation, so the corresponding planning figures require more participants per arm. The calculations are illustrations rather than a recommendation for a future study: they use the observed effect, which may be uncertain, and do not account for design features or analysis details that are not reported in the registry. Read them as conditional planning scenarios, not as evidence that the trial was adequately or inadequately sized.

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 = -6.750; pooled standard deviation σ = 12.728.
2. n = 2 × (1.96 + 0.842)² × 12.728² / -6.750² = 55.8, rounded up to 56 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 <- -6.75                      # observed difference in means
sigma <- 12.7279324482329                     # 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(150618)
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 = 56 (80% power), 75 (90% power)
 75% of observed effect: n per arm = 100 (80% power), 133 (90% power)
 50% of observed effect: n per arm = 224 (80% power), 299 (90% power)
power.t.test: 56.8 
Simulated power at n = 56 per arm: 0.798 (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 sponsor analyses using ANCOVA for the primary endpoint. The reported p-values are 0.004 for SPD503 (1 mg), 0.018 for 2 mg, 0.002 for 3 mg, and 0.001 for 4 mg, each versus placebo. These are the sponsor's own results and should take precedence over the simple unadjusted recalculations from the posted arm summaries.

The recalculated p-values are 0.004, 0.017, 0.001, and <0.001, respectively. The recalculated mean differences and confidence intervals are based on posted group means, standard errors, and an approximate pooled standard deviation. They are useful for a transparent summary-statistic comparison, but they are not a reproduction of ANCOVA. The registry record does not report enough information about the sponsor's model specification to explain the exact numerical differences between the two sets of p-values.

The direction of the primary comparisons is consistent across the sponsor analyses and recalculations: the reported mean changes are more negative in each SPD503 arm than in placebo. The discrepancy flag means that the recalculated values should not be substituted for the sponsor's reported analyses or described as the trial's definitive inferential results.

15. Multiplicity, Missing Data and Analysis Populations

The registry reports multiple outcomes and analyses, but it does not report whether the statistical plan adjusted for multiple comparisons. It lists 5 outcome measures and 20 analyses, including the primary outcome and secondary outcomes. The absence of a stated adjustment matters because interpreting many unadjusted tests as though each were the only test can overstate the strength of evidence. The record also does not identify which secondary analyses, if any, were intended as confirmatory.

The primary outcome population is described as intent to treat, but the registry's definition is specific: randomized subjects with baseline and at least one post-randomization primary efficacy measurement. This is not a description of every randomized participant regardless of outcome availability. The record does not report how missing measurements were handled, whether participants with incomplete follow-up were excluded from particular outcomes, or whether sensitivity analyses assessed alternative missing-data assumptions.

The arm counts vary across outcomes, as expected when outcome-specific analysis populations or available measurements differ. The registry does not explain those count differences. It also does not report the number or reasons for withdrawals, protocol deviations, or the imputation approach, if any. These details are important because incomplete outcome data can affect both the estimated group means and their uncertainty.

The registry identifies ANCOVA for the primary comparisons and the CPRS-R secondary outcome, and Cochran-Mantel-Haenszel for the posted binary secondary comparisons. Further model details, covariates, stratification factors, and diagnostic checks are not reported in the registry record. Thus the sponsor's stated methods can be named, but their full implementation cannot be independently reconstructed from the registry entry.

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: concussion (1.5%), convulsion (1.5%), lower limb fracture (1.5%).

The registry lists serious adverse events by arm using the number at risk and the number affected. The serious-event counts are 0 for SPD503 (1 mg), 0 for SPD503 (2 mg), 1 for SPD503 (3 mg), 0 for SPD503 (4 mg), and 1 for placebo. The corresponding numbers at risk are 61, 65, 65, 65, and 66, respectively. These are arm-level registry counts and should be read with their listed denominators, not as a comparison adjusted for exposure or other factors.

The listed serious-event terms include concussion, convulsion, and lower limb fracture, each reported as 1.5%. The record does not provide further details in the registry record about timing, severity beyond the serious classification, relatedness to study intervention, or participant-level overlap among terms. The death counts are not reported in the registry record.

Other adverse events affected 49 participants in the 1 mg arm, 40 in the 2 mg arm, 45 in the 3 mg arm, 55 in the 4 mg arm, and 45 in the placebo arm. These counts are distinct from the serious adverse event counts. Such descriptive safety summaries do not establish causation or provide a complete assessment of comparative risk; details about event definitions and exposure-adjusted analyses are not reported in the registry record.

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

The posted primary outcome data show decreases in ADHD-RS-IV score from baseline in all arms at 6 weeks. The mean decreases in the SPD503 arms were larger than the placebo mean decrease, and each unadjusted recalculated mean difference was negative with a 95% confidence interval below zero. The registry also reports sponsor ANCOVA p-values for the four dose-versus-placebo comparisons. Those analyses are the sponsor's own inferential results and take precedence over the recalculations because the registry flags a discrepancy.

These findings describe average changes and group comparisons. They do not mean that every participant improved, that all participants had similar experiences, or that the difference was important to every child or family. The record does not provide a threshold for clinical importance, participant-level response distributions, or information sufficient to evaluate individual variation in outcomes.

The results also do not establish that one SPD503 dose is better than another. The primary comparisons are each against placebo; the registry does not report a formal comparison among active doses or a formal dose-trend analysis. Nor do the results establish that the same pattern would occur in other populations, settings, or follow-up periods. The posted primary endpoint is measured through 6 weeks, and longer-term results are not reported in this record.

Statistical evidence should be interpreted alongside uncertainty, design, analysis choices, secondary outcomes, and safety reporting. The registry does not report the original sample-size justification, detailed missing-data procedures, full multiplicity plan, or numeric sponsor confidence limits. These limits constrain how broadly or precisely the findings can be characterized. The results are a statistical account of the posted trial data, not medical advice or a guarantee of outcome for an individual.

18. Why This Trial Matters Statistically

This trial is statistically instructive because it compares several active dose groups with a shared placebo group and reports a continuous primary endpoint as least-squares mean change. Readers can see how the arm-level changes relate to dose-versus-placebo mean differences, while also distinguishing the sponsor's ANCOVA analyses from simple recalculations based on posted summaries.

The record illustrates why uncertainty is not conveyed by a point estimate alone. Each recalculated mean difference has a confidence interval, and the interval width helps show the range of values compatible with the calculation. The differences among the observed dose estimates also raise a common interpretive issue: separate comparisons with placebo do not constitute a formal comparison among active doses or establish a dose-response pattern.

The trial also highlights the importance of analysis populations and outcome availability. The primary ITT definition requires baseline and at least one post-randomization measurement, and the arm counts vary across the outcomes. Without further reporting about missing data, readers cannot fully evaluate how incomplete measurements may have affected estimates.

Finally, secondary measures and multiple analyses require careful weighting. A collection of unadjusted comparisons should not be treated as though each had been the only planned test. The record's missing detail about multiplicity and original planning assumptions reinforces a broader lesson: registry statistics are most informative when read alongside the protocol and full analysis report, while avoiding conclusions that exceed the methods and results actually documented.

19. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The registry record does not provide the original sample-size calculation or its assumptions. The planning illustrations based on observed effects are not evidence about the assumptions used to design the trial. The record also does not report a complete statistical analysis plan, including covariates in ANCOVA, any stratification factors, or the handling of missing observations.

Although the primary endpoint is defined and the ITT population is described, the record does not give reasons for outcome-specific differences in arm counts, participant flow, or withdrawal information. This limits assessment of whether available-case populations differed from the intended analysis population and how missingness might influence results. No details are reported about protocol deviations or sensitivity analyses.

The primary recalculations use summary statistics and approximate pooled variability rather than individual participant data. They cannot reproduce the sponsor's ANCOVA, whose numeric confidence limits are not reported in the registry record. The discrepancy flag makes it especially important to treat these recalculations as supplementary and to rely on the sponsor's reported analysis for the trial's own inferential results.

The registry does not report a multiplicity strategy despite listing several outcomes and analyses. Nor does it provide a clinical-importance threshold for the ADHD-RS-IV score. The posted follow-up for the primary endpoint is 6 weeks; longer-term outcomes are not reported in this record. Safety information is also limited: event counts are provided, but the record does not report detailed event narratives, relatedness assessments, or death counts. These gaps do not invalidate the posted statistics, but they limit the conclusions that can be drawn from them.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Safety and Efficacy of SPD503 in Treating ADHD in Children and Adolescents Aged 6-17 — NCT00150618.
• Registry record last updated 2021-06-10; status last verified 2021-05.
• Results first posted 2009-10-15.
• 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

NCT00150618 is a completed Phase III randomized, double-blind, parallel-group, placebo-controlled study of SPD503 in children and adolescents aged 6-17 with ADHD. The registry lists enrollment of 324 and five arms: SPD503 at 1 mg, 2 mg, 3 mg, and 4 mg, and placebo. The primary endpoint was change from baseline in ADHD-RS-IV total score at 6 weeks.

The posted arm means show negative score changes in every group. The recalculated dose-versus-placebo differences are negative, with 95% confidence intervals below zero. The registry also reports sponsor ANCOVA analyses; because a discrepancy is flagged, the sponsor's results take precedence over the summary-statistic recalculations. Secondary outcomes and adverse-event counts provide additional context, while multiplicity, missing-data handling, and several design and analysis details are not reported in the registry record.