VEC-162 Study in Adult Patients With Primary Insomnia: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for VEC-162 Study in Adult Patients With Primary Insomnia (NCT00548340), a randomized phase 3 study. The primary outcome is Average Change From Baseline - Latency to Persistent Sleep (LPS).

2. Clinical Question

3. Trial Design

This was a Phase 3, randomized, double-blind, placebo-controlled, parallel-group study in adults with primary insomnia. The study title describes it as multicenter. It compared daily oral VEC-162 at 20 mg and 50 mg with daily oral placebo over five weeks. The registry lists Vanda Pharmaceuticals as sponsor and reports the study as completed. Enrollment was 322. The start is recorded as 2007-11 and primary completion as 2008-02.

The primary endpoint was average change from baseline in latency to persistent sleep, measured in minutes. The endpoint description defines latency to persistent sleep as the time from lights off until the beginning of 10 minutes of uninterrupted sleep, determined using polysomnography. The change measure compares baseline with the average of nights 1 and 8. A secondary outcome is listed for average change from baseline in wake after sleep onset and total sleep time. Four outcome measures are recorded, but only one secondary outcome description is listed in the registry summary.

The reported primary endpoint arms include 108 participants for VEC-162 20 mg, 109 for VEC-162 50 mg, and 104 for placebo. The registry notes that one participant assigned to 20 mg had no post-baseline polysomnography data and was excluded from the Full Analysis Population. How the remaining analysis populations were defined, and how other missing observations were handled, are not reported in the registry record.

Randomization, double masking, and a parallel design describe broad features of the comparison, but they do not specify the detailed conduct of the study. The allocation method, masking procedures, protocol deviations, adherence, and the trial’s original statistical design assumptions are not reported in the registry record. The posted effect-based sample-size calculations are planning illustrations, not the study’s original design rationale.

4. Participant Flow and Accounting

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

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: One subject randomized to VEC-162 20 mg did not have any post-baseline PSG data and was excluded from the Full Analysis Population.

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 Average Change From Baseline - Latency to Persistent Sleep (LPS), measured over Baseline, Night 1, and Night 8 measurement.

The primary endpoint is average change from baseline in latency to persistent sleep, expressed in minutes. Latency to persistent sleep captures the interval between lights off and the point at which 10 minutes of uninterrupted sleep has begun, with sleep onset determined by polysomnography. The registry defines the change as the difference between baseline and the average measurement from nights 1 and 8.

This measure is used to quantify the time taken to reach a defined period of uninterrupted sleep, rather than relying only on a general report of sleep quality. Polysomnography is the measurement method specified in the registry. In general, a continuous endpoint retains information about the magnitude of a measured value, allowing results to be summarized as means and compared using mean differences. The clinical interpretation of a change depends on the scale’s direction, the chosen timepoints, and what magnitude is meaningful in the study context; a threshold for clinical importance is not reported in the registry record.

The registry labels the arm summaries as means and their accompanying spread as standard errors. The posted comparison estimates are mean differences versus placebo. They quantify differences between group averages, not the experience of every participant. The registry does not report the individual-level distribution of changes or additional primary-endpoint measurement details beyond the stated definition and timepoints.

7. Results Posted in the Registry

• VEC-162 20 mg: mean 45.00 versus 28.30 on control; difference 16.70 (95% CI 8.41 to 24.99), standardized effect d = 0.54; z-test p = <0.001.
• VEC-162 50 mg: mean 46.40 versus 28.30 on control; difference 18.10 (95% CI 9.82 to 26.38), standardized effect d = 0.59; z-test p = <0.001.

8. Statistical Interpretation

9. Statistical Methods Explained

The endpoint is continuous, so its arm summaries are reported as means. A mean is the arithmetic average of measured values in a group; it describes the group’s central level but does not show how values vary among individuals. The registry reports standard errors alongside the three arm means. In general, a standard error describes the precision of an estimated mean, whereas a standard deviation describes dispersion among individual observations. They answer different questions and should not be treated as interchangeable.

What does the mean difference represent?

The posted mean difference compares each VEC-162 arm with placebo. It is a contrast between average changes from baseline, measured in minutes. The estimates are 16.7 for VEC-162 20 mg versus placebo and 18.1 for VEC-162 50 mg versus placebo. These are unadjusted comparisons. The registry does not describe covariate adjustment or other details of the sponsor’s analysis model. A mean difference is not a statement that every participant’s measure changed by that amount; individual values may vary around the group averages.

How should the p-values be understood?

Each posted unadjusted p-value is <0.001. In general, a p-value evaluates how compatible observed data are with a specified null hypothesis under the assumptions of a statistical test. It is not the probability that the null hypothesis is true, and it does not measure the size or clinical importance of an effect. The exact test, model, and testing assumptions used for the posted p-values are not reported in the registry record. The designation “unadjusted” also means that the p-values should not be mistaken for results corrected for multiple comparisons.

The study has two dose comparisons for the primary measure, and the registry also lists a secondary outcome. Multiple testing can increase the chance of obtaining at least one small p-value when many hypotheses are examined. In general, a prespecified multiplicity strategy can address that issue, but the registry record does not report whether a strategy was planned or used. The posted p-values can therefore be described as unadjusted without assuming how the trial’s original statistical plan handled multiple testing.

What do the confidence intervals add?

The posted intervals are 8.405 to 24.99 for the 20 mg comparison and 9.82 to 26.38 for the 50 mg comparison. In general, a confidence interval presents a range of values compatible with an estimate under a statistical procedure and its assumptions. It conveys precision as well as direction: narrower intervals indicate greater precision than wider intervals on the same scale. The registry does not state the confidence level or the method used to construct these intervals. Their bounds are positive, but the intervals do not answer whether the estimated differences meet a clinical-importance threshold, which is not reported.

Why can over-dispersion matter?

General statistical context: for count outcomes, over-dispersion means that variation exceeds what a simple model assumes. It can make standard errors too small if the model does not accommodate the extra variability. That issue is not the main modeling concern for this reported continuous primary endpoint, and no count-outcome model is described for it. The registry does not report enough detail to assess model diagnostics or alternative variance assumptions for the endpoint analysis.

The comparisons also include pooled standard deviations of 30.81 and 30.82. In general, a pooled standard deviation combines information about variability across two groups and can be used in standardized effect calculations. The registry does not provide the method or model details needed to determine how these values relate to the sponsor’s primary analysis. They do not replace the endpoint’s mean difference in minutes, which remains the direct scale for describing the posted contrast.

What can be said about the analysis population?

The registry reports that one participant assigned to VEC-162 20 mg had no post-baseline polysomnography data and was excluded from the Full Analysis Population. This identifies one specific exclusion, but does not give a complete accounting of participants included in every endpoint comparison. In general, missing outcome data can affect estimates when the people with missing measurements differ systematically from those with observed measurements. The registry does not report the missing-data assumptions, imputation methods, sensitivity analyses, or definitions of other analysis populations. Those details cannot be inferred from the posted means and intervals.

The posted results include group summaries and pairwise comparisons, while the registry does not include analysis entries. The detailed statistical analysis plan, including the prespecified model, covariates, handling of repeated measurements, and decision rules, is not reported in the registry record. The statistical descriptions therefore distinguish the posted unadjusted results from general explanations of how common methods work; they do not reconstruct an unreported analysis plan.

10. Confidence Intervals and Precision

The two posted mean-difference estimates are 16.7 minutes for VEC-162 20 mg versus placebo and 18.1 minutes for VEC-162 50 mg versus placebo. Their corresponding intervals extend from 8.405 to 24.99 minutes and from 9.82 to 26.38 minutes. Each interval gives a range around its point estimate, expressing uncertainty in the estimated group contrast. The registry does not report the confidence level or construction method, so those details should not be assumed.

In general, a confidence interval is a way to communicate precision: a narrower interval indicates a more precise estimate than a wider interval on the same scale, given the same method. The posted intervals span values above zero, consistent with positive estimated differences in average change versus placebo. They do not imply that the true difference is known exactly, nor do they convey the distribution of participant-level results. They also cannot establish clinical importance without a meaningful threshold, which is not reported in the registry record.

Arm sizes for the primary endpoint were 108 for 20 mg, 109 for 50 mg, and 104 for placebo. The registry reports standard errors for the arm means, but these are not individual-level standard deviations. Precision depends on sample size, variability, and analysis methods; the registry does not provide sufficient analysis detail to evaluate every factor. The intervals and p-values should consequently be read as summaries of the posted unadjusted comparisons, not as a complete account of statistical uncertainty or clinical relevance.

11. 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 mean differences, not the study’s original design assumptions. They report participants per arm for the two-arm comparison. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and an effect to detect set to a stated fraction of the observed effect. These are planning assumptions for the illustration; the trial’s original sample-size justification is not reported in the registry record.

The 80% power column gives the estimated number of participants per arm for a planning scenario with 80% power under those assumptions. In plain terms, power is the probability that the planned test would reject its null hypothesis if the effect used for planning were the true effect and the assumptions held. The 90% power column gives the corresponding per-arm planning count for 90% power. Neither column is a count of participants who actually experienced an outcome.

The rows vary the effect used for planning: the full observed effect, 75% of the observed effect, and 50% of the observed effect. Smaller effects need more participants to achieve the same target power under the same assumptions. The curve presents that planning relationship visually; it should be read as an illustration that depends on the chosen effect and assumptions, not as a forecast of what a future study will observe.

These values are not observed power. They are hypothetical sample-size calculations based on the observed estimates, and smaller or larger true effects, different variability, or different design choices would change the planning requirements. For the serious-event counts, the relevant figures are numbers of participants with events, not sample-size planning totals. No time-to-event planning totals are reported for this continuous endpoint.

12. 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 = 16.700; pooled standard deviation σ = 30.806.
2. n = 2 × (1.96 + 0.842)² × 30.806² / 16.700² = 53.4, rounded up to 54 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 <- 16.7                      # observed difference in means
sigma <- 30.8057756566772                     # 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(548340)
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 = 54 (80% power), 72 (90% power)
 75% of observed effect: n per arm = 95 (80% power), 128 (90% power)
 50% of observed effect: n per arm = 214 (80% power), 287 (90% power)
power.t.test: 54.4 
Simulated power at n = 54 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.

13. Multiplicity, Missing Data and Analysis Populations

The primary endpoint has two posted dose-versus-placebo comparisons, and the registry lists a secondary outcome concerning wake after sleep onset and total sleep time. Four outcome measures are recorded overall. The posted p-values for the two primary endpoint comparisons are unadjusted. The registry does not report whether the trial’s statistical plan included a multiplicity procedure, how outcomes were ordered, or whether any result was designated as confirmatory after accounting for the number of comparisons. A reader should therefore interpret the posted p-values as unadjusted rather than presume a correction was made.

Some analysis details are absent from the registry record. The original statistical analysis plan, model specification, covariates, interim analyses, and stopping rules are not reported. The registry also does not report the confidence level for the intervals. It does not explain the relationship between the outcome-measure count and the listed analyses; no analysis entries are listed even though pairwise comparison results are posted.

The primary endpoint description identifies one participant assigned to VEC-162 20 mg with no post-baseline polysomnography data, excluded from the Full Analysis Population. It does not describe all exclusions or define all analysis populations. Missing-data handling, including any imputation or sensitivity analysis, is not reported. The number of participants included in each specific comparison is listed, but those counts do not establish how all missing data or protocol deviations were handled.

In general, multiplicity concerns the increased chance of a false-positive finding when multiple hypotheses are tested, while missing-data methods address the consequences of incomplete outcome observations. Neither issue can be resolved by the observed mean differences alone. The registry record supports reporting the comparisons as posted, with their unadjusted status and the stated single exclusion, but does not support reconstructing the unreported statistical plan or analysis population rules.

14. 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 3% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: hypertensive emergency (1.0%), blood pressure increased (0.9%).

The serious adverse event figures are counts of participants affected and counts at risk, not estimates of treatment effect. The registry reports 1 participant with a serious adverse event among 109 at risk in the VEC-162 20 mg group, 0 among 109 at risk in the VEC-162 50 mg group, and 1 among 104 at risk in the placebo group. These are the posted group counts; they do not by themselves establish whether events were caused by study treatment.

The registry lists hypertensive emergency at 1.0% and blood pressure increased at 0.9% among the top serious-event terms, but does not provide group attribution for those terms in the summary. The death counts are not reported in the registry record. For other adverse events, the posted affected counts are 15 for 20 mg, 13 for 50 mg, and 11 for placebo. The recorded at-risk count for other adverse events is 109 in each VEC-162 group and 109 for placebo, while the serious-event at-risk count for placebo is 104. These differing registry counts should be retained as reported rather than reconciled by assumption.

In general, rare-event counts can be imprecise, and raw counts do not account for differences in exposure or event definitions. The registry summary does not provide enough detail to assess event timing, duration, severity beyond the serious classification, or causal assessment.

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

The posted results describe a difference between group averages in the primary measure of change from baseline in latency to persistent sleep. The mean change values are 45.0 minutes for 20 mg, 46.4 minutes for 50 mg, and 28.3 minutes for placebo. The unadjusted comparisons report mean differences of 16.7 and 18.1 minutes, respectively, with both p-values <0.001. These findings characterize the registry’s reported endpoint summaries for this study.

They do not show how much any individual participant changed, how many participants had a particular response, or whether a difference met a threshold that patients or clinicians would consider important. The registry does not report a clinical-importance threshold. Nor do the posted summaries establish how results would generalize to people outside the study population or to different treatment durations. The study description concerns adults with primary insomnia and a five-week treatment period.

The registry also does not report a complete statistical analysis plan, multiplicity handling, or detailed missing-data methods. The comparisons are unadjusted, and one participant assigned to 20 mg without post-baseline polysomnography was excluded from the Full Analysis Population. These details limit how fully the statistical evidence can be reconstructed from the record. A p-value is not a measure of clinical benefit, and a confidence interval is not a guarantee that its range contains the true effect; both are statistical summaries whose interpretation depends on their methods and assumptions.

The safety figures are similarly descriptive: they give counts of participants with serious and other adverse events, but do not establish causation or provide a complete account of event characteristics. The registry’s posted results can therefore be used to describe the observed group-level summaries and their reported precision, while conclusions about individual outcomes, clinical importance, or broader application require information not reported in the registry record.

16. Why This Trial Matters Statistically

This study illustrates why a statistically clear group contrast and a complete clinical interpretation are not the same thing. The registry reports continuous primary-endpoint means, unadjusted mean differences, intervals, and p-values for two dose comparisons. That combination allows the estimated differences and their precision to be described on the original minutes scale. At the same time, the clinical meaning of a positive difference depends on how change is coded and what magnitude matters; the record does not report a clinical-importance threshold.

The example also highlights the need to distinguish standard errors from standard deviations. Standard errors accompany the arm means and describe their estimation precision, while the pooled standard deviations describe another aspect of variation. Mixing these quantities can lead to mistaken conclusions about individual variability or uncertainty. The reported intervals help communicate uncertainty in the contrasts, but the registry does not state their confidence level or construction method.

Two dose comparisons and a listed secondary outcome make multiplicity an important interpretive consideration. Because the posted p-values are unadjusted and the original testing strategy is not reported, the results cannot be treated as if a particular multiplicity plan were documented. The record also identifies one missing post-baseline polysomnography observation but does not describe broader missing-data procedures or all analysis populations.

Finally, the effect-based sample-size figures are useful for understanding how planning requirements depend on the assumed effect size, but they are not evidence of achieved power and are not the original trial justification. Taken together, these features show how registry results can support a transparent account of estimates while leaving important design and analysis details unresolved.

17. Limitations

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

The registry record does not report the detailed statistical analysis plan, including the model used for the primary endpoint, any covariate adjustments, the confidence level for intervals, or the method used to calculate them. It also does not state how the trial handled multiple comparisons across the two dose groups and listed outcomes. The p-values are unadjusted, and no original sample-size justification is reported.

For the primary endpoint, the record notes one participant assigned to VEC-162 20 mg who lacked post-baseline polysomnography and was excluded from the Full Analysis Population. It does not give a complete account of missing measurements, other exclusions, protocol deviations, or the rules defining every analysis population. The posted group sizes therefore do not resolve all questions about which observations contributed to every result.

The endpoint is defined using baseline and the average of nights 1 and 8, but other measurement timing details and the clinical-importance threshold are not reported. The registry does not provide individual-level distributions or response counts for the primary outcome. The safety summary gives event counts but limited context about timing, duration, severity details, or causal assessment. Death counts are not reported in the registry record.

These limitations do not change the reported summaries, but they constrain interpretation. In particular, the posted comparisons cannot establish a prespecified multiplicity strategy, a missing-data assumption, or clinical importance that the registry does not describe. The effect-based planning illustrations should also be kept separate from the trial’s original design rationale, which is not reported.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: VEC-162 Study in Adult Patients With Primary Insomnia — NCT00548340.
• Registry record last updated 2014-10-15; status last verified 2014-10.
• Results first posted 2014-10-15.
• 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.

21. Record Summary

NCT00548340 is a completed Phase 3 randomized, double-blind, parallel-group, placebo-controlled study of VEC-162 in adults with primary insomnia. The registry reports 322 enrolled participants and a five-week daily oral treatment period, comparing 20 mg and 50 mg with placebo. The primary endpoint was average change from baseline in latency to persistent sleep, measured in minutes using the average of nights 1 and 8.

Posted arm means were 45.0 for 20 mg, 46.4 for 50 mg, and 28.3 for placebo. Unadjusted mean differences versus placebo were 16.7 and 18.1, with p-values <0.001 for both comparisons. The record reports one participant assigned to 20 mg without post-baseline polysomnography, excluded from the Full Analysis Population. Detailed multiplicity, missing-data, and original sample-size methods are not reported in the registry record.