Randomised Placebo-controlled Duloxetine-referenced Study of Efficacy and Safety of 5 mg of Vortioxetine (Lu AA21004) in Acute Treatment of Major Depressive Disorder in Elderly Patients: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Randomised Placebo-controlled Duloxetine-referenced Study of Efficacy and Safety of 5 mg of Vortioxetine (Lu AA21004) in Acute Treatment of Major Depressive Disorder in Elderly Patients (NCT00811252), a randomized phase 3 study. The primary outcome is Change From Baseline in HAM-D-24 Total Score After 8 Weeks of Treatment.

2. Clinical Question

3. Trial Design

This was a phase 3, randomized, double-blind, parallel-group, placebo-controlled, duloxetine-referenced study in elderly patients with major depressive disorder. The registry record lists H. Lundbeck A/S as sponsor and marks the study completed. The recorded start was 2009-01 and primary completion was 2010-02. Enrollment was 453.

The intervention groups were placebo, vortioxetine 5 mg, and duloxetine 60 mg. Duloxetine was identified as an active reference. The title and brief summary describe acute treatment, with the primary endpoint assessed after 8 weeks of double-blind treatment. Randomization and double masking are stated in the record; details about the sequence generation, allocation concealment, and how masking was maintained are not reported in the registry record.

The primary outcome was change from baseline in HAM-D-24 total score at Week 8. The record lists 12 secondary outcomes, including HAM-D-24 changes at earlier time points and other depression or clinical-status measures at Week 8. The posted record includes 13 outcome measures and 17 analyses overall. The basis for the planned enrollment, the original sample-size assumptions, and any interim analyses are not reported in the registry record.

For the primary efficacy outcome, the record specifies an ANCOVA analysis in a full-analysis set using last observation carried forward. That analysis population was defined as all patients in the all-patients-treated set who had at least one valid post-baseline assessment of the primary efficacy variable. The registry’s overall enrollment and efficacy-analysis group sizes refer to different record elements, so they should not be treated as interchangeable.

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: The study consisted of a Screening Period; an 8-week Core Treatment Period; a 1-week double-blind down-taper period (Week 9); and a 4-week Safety Follow-up Period after completion/withdrawal (Weeks 8 to 12).

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full-analysis set (FAS) - all patients in the all-patients-treated set (APTS) who had at least one valid post-baseline assessment of the primary efficacy variable; last observation carried forward (LOCF); analysis of covariance (ANCOVA)

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: Full-analysis set (FAS) - all patients in the all-patients-treated set (APTS) who had at least one valid post-baseline assessment of the primary efficacy variable

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in HAM-D-24 Total Score After 8 Weeks of Treatment, measured over Baseline and Week 8.

The primary endpoint was change from baseline in total score on the 24-item Hamilton Depression Scale (HAM-D-24), assessed at Week 8. The scale measures depression severity. According to the registry description, its items are rated from 0, for symptoms not present, to a maximum of 2 to 4, for symptoms described as extremely severe; the total score ranges from 0 to 76. A higher total score indicates more severe symptoms.

Change from baseline expresses how the measured score at follow-up compares with the participant’s baseline score. In the posted results, group mean changes are negative, indicating that average scores at follow-up were lower than baseline scores. A more negative mean change represents a larger decrease in this scale’s score, but it does not by itself explain why scores changed or characterize every participant’s experience.

This endpoint is used to quantify symptom severity in a consistent way and to compare average score changes between randomized groups. The registry specifies Week 8 as the primary assessment, while earlier HAM-D-24 assessments are listed as secondary outcomes. The primary analysis used ANCOVA and the full-analysis set with last observation carried forward; the record’s precise model covariates and other implementation details are not reported in the registry record.

7. Results Posted in the Registry

• Vortioxetine 5 mg: mean -13.70 versus -10.30 on control; difference -3.40 (95% CI -5.48 to -1.32), standardized effect d = -0.37; z-test p = 0.001.
• Duloxetine 60 mg: mean -15.80 versus -10.30 on control; difference -5.50 (95% CI -7.59 to -3.41), standardized effect d = -0.60; 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 HAM-D-24 Total Score After 6 Weeks of Treatment

• 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:
  • Vortioxetine 5 mg: mean -12.30 versus -10.20 on control; difference -2.10 (95% CI -4.04 to -0.16), standardized effect d = -0.25; z-test p = 0.034.
  • Duloxetine 60 mg: mean -14.40 versus -10.20 on control; difference -4.20 (95% CI -6.15 to -2.25), standardized effect d = -0.49; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Vortioxetine 5 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 Duloxetine 60 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in HAM-D-24 Total Score After 4 Weeks of Treatment

• 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:
  • Vortioxetine 5 mg: mean -10.10 versus -8.99 on control; difference -1.11 (95% CI -2.86 to 0.64), standardized effect d = -0.14; z-test p = 0.213.
  • Duloxetine 60 mg: mean -12.30 versus -8.99 on control; difference -3.31 (95% CI -5.07 to -1.55), standardized effect d = -0.43; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Vortioxetine 5 mg and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Duloxetine 60 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in HAM-D-24 Total Score After 2 Weeks of Treatment

• 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:
  • Vortioxetine 5 mg: mean -6.95 versus -6.66 on control; difference -0.29 (95% CI -1.73 to 1.15), standardized effect d = -0.05; z-test p = 0.693.
  • Duloxetine 60 mg: mean -7.91 versus -6.66 on control; difference -1.25 (95% CI -2.71 to 0.21), standardized effect d = -0.20; z-test p = 0.092.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Vortioxetine 5 mg 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 Duloxetine 60 mg and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes span earlier HAM-D-24 assessments and other measures of depression severity or clinical status. Taken together, the posted secondary results show that estimates vary by assessment time and outcome: some comparisons indicate separation from placebo, while others have intervals that include no difference. This variation is a reason to treat the secondary findings as supportive context rather than as a single uniform pattern.

The primary Week 8 HAM-D-24 outcome is the main prespecified question identified in the registry summary. Secondary endpoints can help describe the timing and breadth of measured changes, but they do not replace that primary result. Their relationship to the primary outcome is best considered in terms of consistency and context, not as independent confirmation of the same conclusion.

The record lists 12 secondary outcomes, and the number of posted analyses is greater than the number of listed outcome measures. When many outcomes, comparisons, or time points are examined, the chance of finding apparently notable results by chance can increase. General statistical explanation: multiplicity procedures can control this risk by adjusting the testing strategy, but the registry record does not report whether any adjustment was planned or used for the secondary analyses.

For that reason, unadjusted secondary p-values carry less weight than the primary analysis and should not be interpreted as definitive evidence on their own. The registry record does not describe a hierarchy of secondary hypotheses or identify which secondary results were intended as confirmatory. The overall secondary pattern can inform interpretation of the primary endpoint, but it cannot resolve that missing information or establish how robust the findings are across all possible analyses.

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

• Change From Baseline in HAM-D-24 Total Score After 6 Weeks of Treatment
• Change From Baseline in HAM-D-24 Total Score After 4 Weeks of Treatment
• Change From Baseline in HAM-D-24 Total Score After 2 Weeks of Treatment
• Change From Baseline in HAM-D-24 Total Score After 1 Week of Treatment
• Change From Baseline in MADRS Total Score After 8 Weeks of Treatment
• Change From Baseline in HAM-A Total Score After 8 Weeks of Treatment
• Change From Baseline in CGI-S Score After 8 Weeks of Treatment
• Change in Clinical Status Using CGI-I Score at Week 8

9. Statistical Interpretation

10. Statistical Methods Explained

What does the mean change describe?

The primary endpoint is continuous: each participant has a numerical HAM-D-24 total score, and the reported arm-level values are means of change from baseline. A mean describes the central average of the measured changes; it does not show how scores are distributed among individuals. The standard errors listed alongside the arm means describe the precision of those estimated means. A standard error is not the same thing as the spread of individual participant scores.

General statistical explanation: a mean difference compares the average outcome in one group with the average in another. Here the reported comparisons use placebo as the reference. Since the endpoint is change in a scale where higher scores indicate greater severity, a negative intervention-minus-placebo difference corresponds to a greater average decrease in the intervention group’s score. This interpretation concerns the scale outcome, not a guaranteed change for any individual.

Why does the sponsor use ANCOVA?

The registry identifies ANCOVA as the method for the primary analysis. General statistical explanation: analysis of covariance models an outcome while accounting for selected covariates, often including baseline measurements. This can provide an adjusted comparison between groups rather than a comparison based solely on the unadjusted arm summaries. The exact covariates, model specification, and related diagnostics are not reported in the registry record, so they should not be inferred from the label ANCOVA alone.

The registry’s own reported comparisons are the sponsor’s ANCOVA estimates and inferential results. The recalculated comparisons use the posted arm summaries to make simple, unadjusted comparisons. They are useful as a descriptive cross-check, but they are not a replacement for the trial’s specified analysis. The reported sponsor estimates and p-values should therefore be treated as the trial’s own analysis.

What is the analysis population?

The primary analysis population is described as the full-analysis set: patients in the all-patients-treated set who had at least one valid post-baseline assessment of the primary efficacy variable. The record also states that last observation carried forward (LOCF) was used. General explanation: LOCF substitutes a participant’s last observed value for a later value that is missing, under the analysis approach specified. This choice can affect estimated changes and uncertainty, particularly if reasons for missing observations are related to outcomes or if participants’ measurements would otherwise have changed over time. The registry does not provide enough detail to assess those possibilities or compare this method with alternative missing-data analyses.

The record’s enrollment figure and the counts attached to efficacy and safety analyses are not necessarily the same analytic population. Outcome-specific sets and missing measurements can make those values differ. The record states the primary analysis-set definition but does not report all details about participant flow or missing measurements in the registry record for this analysis.

How should p-values be read?

General statistical explanation: a p-value measures how incompatible the observed data are with a specified null model, under the assumptions of the analysis. It is not the probability that the null hypothesis is true, and it does not measure the size or clinical importance of a difference. The posted unadjusted p-values accompany recalculated comparisons; the sponsor’s ANCOVA p-values accompany its reported analysis. Since the record does not state a multiplicity adjustment, p-values for secondary outcomes should be read cautiously rather than as a set of confirmatory tests.

Confidence intervals complement p-values by showing a range of estimates compatible with the data and method. Their width reflects uncertainty about the estimated comparison. They do not address every source of uncertainty, such as how well the model assumptions hold or how applicable the study is to populations outside the trial.

What does the planning illustration mean?

The planning figures use observed effects as hypothetical inputs and state assumptions of a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The illustration considers the full observed effect and smaller fractions of it. General explanation: planning for a smaller effect generally requires more participants to distinguish that effect from random variation at a chosen power level. The original trial’s own sample-size rationale and planning assumptions are not reported in the registry record. The illustration is not observed power and does not describe the probability that the completed trial “had power” after its results were known.

11. Confidence Intervals and Precision

For vortioxetine 5 mg versus placebo at Week 8, the recalculated mean difference is -3.4, with a 95% confidence interval from -5.479 to -1.321. The sponsor’s ANCOVA estimate is -3.32, with a 95% confidence interval from -5.31 to -1.34. For duloxetine 60 mg versus placebo, the recalculated estimate is -5.5, with a 95% confidence interval from -7.593 to -3.407; the sponsor’s estimate is -5.48, with a 95% confidence interval from -7.50 to -3.46.

General statistical explanation: a confidence interval presents a range of values that are reasonably compatible with the data under the analysis method. A narrower interval indicates greater precision in estimating the group difference, while a wider interval indicates more uncertainty. A confidence interval is not a range containing every individual participant’s change, and it does not mean there is a 95% probability that the true effect lies inside this particular interval.

The posted sponsor intervals and the recalculated intervals are close, reflecting that both describe the same primary group comparisons using different analysis approaches. The sponsor’s ANCOVA results are the trial’s own inferential results; the recalculated intervals are unadjusted estimates derived from summary statistics. Their interpretation depends on the methods and assumptions behind each calculation.

Precision is only one aspect of evidence. The intervals quantify sampling uncertainty under their respective methods, but do not address possible bias, missing-data assumptions, multiplicity, or how meaningful a score difference is to patients. The registry record does not report a threshold for clinical importance on HAM-D-24. Consequently, statistical separation from zero should not be equated with a particular clinical benefit, and the estimate should be understood alongside the endpoint’s definition, analysis population, and study limitations.

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 trial’s original design calculations. For these continuous-outcome comparisons, the listed figures are participants per arm. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set at the stated fraction of the observed effect. The registry record does not report the original sample-size justification or its assumptions.

The 80% power column gives the illustrated number of participants per arm for a hypothetical design targeting an 80% chance of detecting the specified effect under the planning assumptions, if that effect and assumptions were correct. The 90% power column describes the corresponding illustration for a 90% chance. These are design-planning quantities, not statements about what happened in this completed trial.

Rows planning for 75% or 50% of the observed effect represent smaller hypothetical effects than planning for the full observed effect. Smaller effects are harder to distinguish from random variation, so the planning illustration requires more participants per arm. The values depend on the observed estimates, which themselves are uncertain and may not represent the effect that a future study would observe. The figures therefore help illustrate how assumptions about effect size influence planning; they should not be read as a recommendation for a future trial or as proof that any particular sample size would be adequate.

The figures are not observed power. Power is most useful as a prospective planning concept based on a prespecified effect and assumptions, rather than as a post hoc summary of whether a completed study produced a statistically significant result.

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 = -3.400; pooled standard deviation σ = 9.183.
2. n = 2 × (1.96 + 0.842)² × 9.183² / -3.400² = 114.5, rounded up to 115 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 <- -3.4                      # observed difference in means
sigma <- 9.18334866034442                     # 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(811252)
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 = 115 (80% power), 154 (90% power)
 75% of observed effect: n per arm = 204 (80% power), 273 (90% power)
 50% of observed effect: n per arm = 459 (80% power), 614 (90% power)
power.t.test: 115.5 
Simulated power at n = 115 per arm: 0.801 (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 reported ANCOVA comparisons for both active groups versus placebo at the primary Week 8 endpoint. For vortioxetine, the reported mean difference is -3.32, with a 95% confidence interval from -5.31 to -1.34 and p = 0.001. For duloxetine, it is -5.48, with a 95% confidence interval from -7.50 to -3.46 and p < 0.001.

The recalculated comparisons use the posted group means and standard errors to estimate simple, unadjusted mean differences. They produce -3.4 for vortioxetine and -5.5 for duloxetine, with their own 95% confidence intervals and unadjusted p-values. These are not identical to the sponsor’s ANCOVA results because they are based on summary statistics and do not reproduce the adjusted analysis.

The recalculated values are descriptive checks, not a substitute for the sponsor’s analysis. The sponsor’s own analysis takes precedence when describing the trial’s reported inferential results. The record marks no discrepancy between the reported analysis and the recalculated comparison. Agreement in direction does not remove the distinction between an adjusted model-based estimate and a simple unadjusted re-calculation.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when several outcomes, time points, or group comparisons are tested. Each additional test creates another opportunity for a result to appear unusual by chance, even if there is no underlying difference for that test. This matters in this study because the registry lists multiple secondary outcomes and multiple analyses. The registry record does not report a multiplicity adjustment, a testing hierarchy, or which secondary comparisons, if any, were designated as confirmatory. Accordingly, unadjusted secondary results should be treated as exploratory or supportive unless the record establishes otherwise.

The primary efficacy analysis population and missing-data approach are reported: the full-analysis set consisted of patients in the all-patients-treated set with at least one valid post-baseline assessment of the primary efficacy variable, and last observation carried forward was used. This identifies the population and method described for the primary endpoint, but does not show the amount or pattern of missing data, reasons for missingness, or results under alternative assumptions. Those details are not reported in the registry record.

General statistical explanation: missing-data methods rely on assumptions about how absent measurements relate to observed outcomes and participant characteristics. LOCF carries the last observed value forward; when the outcome might continue to change after that observation, this may not represent the unobserved value. The direction and size of any impact cannot be determined from the method label alone. Sensitivity analyses using alternative approaches can help assess how dependent findings are on assumptions, but such analyses are not reported in the registry record.

The record identifies ANCOVA for the primary outcome but does not report the full model specification, covariates, diagnostics, or detailed implementation. Interim analyses and the trial’s original sample-size rationale are also not reported in the registry record. These omissions limit an independent assessment of the analysis plan and its execution. They do not invalidate the posted results, but they constrain how confidently readers can evaluate all potential sources of analytic uncertainty.

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: prostate cancer (2.0%), hip fracture (0.7%), bile duct cancer (0.7%), transient ischaemic attack (0.7%), depression (0.7%).

The safety record lists serious adverse events for placebo, vortioxetine 5 mg, and duloxetine 60 mg. The counts affected were 4 among 145 at risk for placebo, 1 among 156 at risk for vortioxetine, and 1 among 151 at risk for duloxetine. These are group-level counts as recorded, not estimates of whether a treatment caused an event. The record also lists other adverse events, with 63 among 145 at risk for placebo, 72 among 156 at risk for vortioxetine, and 104 among 151 at risk for duloxetine.

The listed serious-event terms include prostate cancer, hip fracture, bile duct cancer, transient ischaemic attack, depression, and major depression, with the percentages shown in the registry record. Those terms and percentages should be read as the registry’s event reporting, not as evidence that an event was caused by a study treatment. The record does not provide death counts in the safety details summarized for this analysis; deaths are not reported in the registry record.

These counts do not alone establish comparative safety. Interpretation depends on event definitions, follow-up, severity, timing, and attribution, as well as the full clinical context. The serious adverse event counts are distinct from the other adverse event counts and should not be combined. The posted safety information should be considered alongside the study design and outcome evidence, without inferring individual risk from group counts.

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

The primary result concerns a measured average change in HAM-D-24 total score during an 8-week trial of elderly patients with major depressive disorder. The posted group means decreased from baseline in all three arms. The sponsor’s ANCOVA comparisons report a difference between vortioxetine and placebo and between duloxetine and placebo in mean change at Week 8. The estimates describe the groups included in the trial analysis, under the reported analysis approach.

This does not mean every participant experienced the average change, or that an individual’s outcome can be predicted from the group estimate. It also does not establish a particular level of clinical importance: the registry record does not report a threshold for interpreting the size of a HAM-D-24 difference as clinically meaningful. Statistical evidence and clinical importance are related but distinct questions.

The result does not establish what would happen in populations unlike those studied, over durations other than the reported acute-treatment period, or under conditions not described in the registry record. The study compared randomized groups, but details of the randomization process and the full model specification are not reported in the registry record. Missing-data assumptions and multiplicity handling also affect how broadly the findings can be interpreted.

Safety counts should not be inferred from the efficacy comparison, nor do the event counts alone establish causality or a complete safety profile. Likewise, secondary outcomes offer context but carry less weight when the record does not report a multiplicity strategy. The most defensible reading is limited to the posted primary score comparison and its uncertainty, supplemented by the listed secondary and safety information with appropriate caution.

These trial results are statistical evidence about measured outcomes in the recorded study. They are not medical advice, do not establish an individual response, and should not be taken as a treatment recommendation.

18. Why This Trial Matters Statistically

This trial is statistically informative because it uses a randomized, double-blind, parallel-group design and includes both a placebo comparison and an active reference group. Its primary endpoint is a defined continuous measure assessed at a stated follow-up time. Those features make the central statistical question concrete: how the mean change in HAM-D-24 score differs between randomized groups under the trial’s analysis.

The record also illustrates why an estimate should be read together with its method. The sponsor’s primary results use ANCOVA, while the recalculated comparisons are simple unadjusted comparisons based on summary statistics. The estimates are similar in direction and magnitude, but they answer the comparison using different statistical procedures. Recognizing that distinction helps prevent a descriptive recalculation from being mistaken for the sponsor’s inferential analysis.

The multiple secondary outcomes demonstrate another common interpretive challenge. Results across time points and measures can help describe patterns, but without a reported multiplicity plan, individual secondary p-values cannot be treated as equally strong confirmation. The missing-data method is stated, yet the registry record does not report enough detail to evaluate the consequences of that method or the robustness of results under alternative assumptions.

Finally, the study’s posted estimates and confidence intervals support a measured account of what the trial found without turning statistical significance into a claim about clinical importance or individual outcomes. Separating endpoint meaning, estimation, uncertainty, analysis choices, multiplicity, and safety is essential to a sound reading of clinical-trial 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.

Several trial-specific limitations constrain interpretation. The registry record specifies an ANCOVA analysis but does not report its full model specification, including the covariates, or provide model diagnostics. It identifies the full-analysis set and LOCF method, but does not report detailed missing-data patterns, reasons for missing observations, or sensitivity analyses using alternative methods. The influence of missing-data assumptions therefore cannot be assessed from the record.

The registry record does not report the original sample-size justification or the assumptions used in the trial’s own planning. The planning illustration based on observed effects is not a substitute for that information. The record also does not report whether interim analyses occurred, or whether a multiplicity adjustment or testing hierarchy was used for secondary analyses. These omissions limit assessment of the prespecified statistical framework, particularly for the multiple secondary endpoints.

Some design details, including the randomization procedure, allocation concealment, and how double masking was maintained, are not reported in the registry record. The available summary also does not establish the clinical importance threshold for HAM-D-24 differences. Consequently, statistical differences should not be translated into claims about clinical importance without further evidence.

Finally, the safety information summarized in the record gives group counts but does not by itself establish causality or offer a complete account of timing, severity, or attribution. These limits are specific to the information reported in the registry record and do not determine whether unreported procedures or analyses were conducted.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Randomised Placebo-controlled Duloxetine-referenced Study of Efficacy and Safety of 5 mg of Vortioxetine (Lu AA21004) in Acute Treatment of Major Depressive Disorder in Elderly Patients — NCT00811252.
• Registry record last updated 2014-01-29; status last verified 2013-12.
• Results first posted 2013-12-18.
• 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

NCT00811252 is a completed phase 3 randomized, double-blind, parallel-group study in elderly patients with major depressive disorder. It compared vortioxetine 5 mg and duloxetine 60 mg with placebo, with duloxetine described as an active reference. The primary outcome was change from baseline in HAM-D-24 total score after 8 weeks.

The sponsor’s ANCOVA results report a Week 8 mean difference of -3.32 for vortioxetine versus placebo and -5.48 for duloxetine versus placebo, with the confidence intervals and p-values described in the statistical interpretation. The primary analysis used the full-analysis set and LOCF. Secondary outcomes covered earlier HAM-D-24 assessments and other measures, while safety results listed serious and other adverse event counts by group.

The record does not report the original sample-size rationale, a multiplicity strategy, or detailed missing-data sensitivity analyses. The results should therefore be read as evidence about the measured group averages under the reported analysis, with those uncertainties in view.