An Efficacy, Safety and Tolerability Study of JNJ-42165279 in Participants With Major Depressive Disorder With Anxious Distress: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for An Efficacy, Safety and Tolerability Study of JNJ-42165279 in Participants With Major Depressive Disorder With Anxious Distress (NCT02498392), a randomized phase 2 study. The primary outcome is Double-blind Treatment Period: Change From Baseline in Hamilton Depression Rating Scale (HDRS17) Total Score at Week 6 (eITT Population).

2. Clinical Question

3. Trial Design

NCT02498392 was a completed Phase 2a, randomized, double-blind, placebo-controlled, parallel-group, multi-center study sponsored by Janssen Research & Development, LLC. The registry reports enrollment of 161. The study evaluated efficacy, safety, and tolerability of JNJ-42165279 in participants with major depressive disorder with anxious distress and anxiety symptoms after an inadequate response to an SSRI or SNRI. The listed conditions are depressive disorder and anxiety.

The study included a placebo lead-in and a double-blind treatment period. The arm descriptions distinguish participants who responded during the placebo lead-in from those who did not. In the double-blind period, participants in both lead-in response categories could receive matching placebo or JNJ-42165279. The active treatment was 25 mg orally once daily for 6 weeks. The primary endpoint, however, was defined in the eITT population of placebo lead-in non-responders, rather than across all participants described in the arm structure.

The primary outcome was change from baseline to Week 6 in HDRS17 total score. The registry also lists secondary anxiety and depression rating outcomes, including HAM-A6, HAM-D6, SIGH-A, and the HDRS17 Anxiety/Somatization Factor. There are 25 outcome measures and 2 posted analyses in the record. The reported study start was 2015-10-07 and primary completion was 2019-02-04. The record status is completed.

The registry record does not report the original sample-size justification, the detailed allocation procedure, or further operational details of the lead-in period beyond the arm descriptions. It also does not provide a complete displayed definition of the eITT population. These gaps limit how fully the analysis population and design choices can be reconstructed from the registry record alone.

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: Of the 161 enrolled participants, 1 participant withdrew from study participation prior to dosing. This participant has not been included in the analysis.

Double-blind(DB) Lead-in Period(3 Weeks)

Reasons for not completing this period:

DB Treatment (6 Weeks)+Withdrawal Period

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The enriched intent-to-treat (eITT) analysis set included all enrolled participants who were randomized into double-blind treatment period, who were lead-in placebo non-responder, who received at least one dose of double-blind study medication (either placebo or JNJ-42165279) and had at least one post-baseline HDRS17 assessment in double-blind treatment period. Here 'N' (number of participants analyzed) signifies number of participants who were evaluable for this outcome measure.

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: Baseline population is based on safety analysis set which included all enrolled participants who received at least one dose of study medication in the Lead-in Period and who were lead-in placebo non-responders.

6. Primary Endpoint

The registry lists the primary outcome as Double-blind Treatment Period: Change From Baseline in Hamilton Depression Rating Scale (HDRS17) Total Score at Week 6 (eITT Population), measured over Baseline and Week 6.

The primary endpoint was change from baseline to Week 6 in the total score on the Hamilton Depression Rating Scale, HDRS17, in the eITT population. The scale is clinician-administered and assesses the severity of symptoms in participants diagnosed with depression. It contains 17 items, each rated on either a 3-point or 5-point scale. The total score is formed by adding item scores, and higher total scores indicate more severe symptoms.

Change from baseline is used to describe how the measured score differs at follow-up from its starting value. A negative mean change in this study therefore indicates that the average score at Week 6 was lower than at baseline; because higher HDRS17 scores represent more severe symptoms, a lower score corresponds to a lower measured symptom-severity score. This statistical description does not by itself establish why a change occurred or whether it is clinically important.

The endpoint is useful for comparing average change between randomized groups on a common clinician-rated measure. The eITT restriction makes the primary comparison specific to participants who did not respond during the placebo lead-in and entered the double-blind treatment period. That focus should be kept in mind when considering how broadly the result applies to other participants in the trial or to people outside the study. The registry record does not report a threshold for a clinically meaningful change on HDRS17.

7. Results Posted in the Registry

• JNJ-42165279 25 mg: mean -6.50 versus -6.10 on control; difference -0.40 (95% CI -2.44 to 1.64), standardized effect d = -0.08; z-test p = 0.701.

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.

Double-blind Treatment Period: Change From Baseline in Hamilton Anxiety Rating Subscale (HAM-A6) Score at Week 6 (eITT Population)

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • JNJ-42165279 25 mg: mean -2.90 versus -2.40 on control; difference -0.50 (95% CI -1.64 to 0.64), standardized effect d = -0.18; z-test p = 0.392.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between JNJ-42165279 25 mg and the control. The interval gives the range of effects that remain compatible with the data.

Double-blind Treatment Period: Change From Baseline in HAM-A6 Score at Week 6 (fITT Population)

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • JNJ-42165279 25 mg: mean -2.20 versus -2.10 on control; difference -0.10 (95% CI -1.06 to 0.86), standardized effect d = -0.03; z-test p = 0.838.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between JNJ-42165279 25 mg and the control. The interval gives the range of effects that remain compatible with the data.

Double-blind Treatment Period: Change From Baseline in Hamilton Depression Rating Subscale (HAM-D6) Score at Week 6 (eITT Population)

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • JNJ-42165279 25 mg: mean -3.60 versus -3.10 on control; difference -0.50 (95% CI -1.65 to 0.65), standardized effect d = -0.18; z-test p = 0.392.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between JNJ-42165279 25 mg and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes cover anxiety and depression rating measures, including HAM-A6, HAM-D6, SIGH-A, and the HDRS17 Anxiety/Somatization Factor. The registry record lists 23 secondary outcomes as posted, while detailed numerical summaries are available for a subset. Across the detailed outcomes, mean changes are negative in both treatment groups, and the recalculated between-group contrasts are small relative to their uncertainty. The intervals for the detailed contrasts include zero.

This broad pattern is consistent with the primary result in the limited sense that the posted summaries do not show a clearly separated average change between treatment groups. The secondary outcomes are related measures of symptoms, but they are not interchangeable with the primary HDRS17 total score. They use different scales or score components, and some are reported for fITT rather than eITT. Their results therefore provide supporting context rather than a direct replication of the primary comparison.

The listed recalculated secondary p-values are unadjusted. When many outcomes are examined, the chance of finding an apparently notable result by chance can increase. General practice is to account for multiplicity when making confirmatory claims across multiple comparisons. The registry record does not report a multiplicity adjustment for the displayed secondary results, so individual unadjusted findings deserve less weight than a prespecified primary analysis and should be treated as exploratory rather than as independent confirmation.

The detailed subset should not be mistaken for a complete account of every secondary outcome. The remaining posted secondary results are not described with numerical results in the information available in the registry record. No pattern across the full set can be characterized beyond the information reported. The secondary outcomes also do not alter the interpretation that the primary estimate is uncertain and close to no difference.

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

• Double-blind Treatment Period: Change From Baseline in Hamilton Anxiety Rating Subscale (HAM-A6) Score at Week 6 (eITT Population)
• Double-blind Treatment Period: Change From Baseline in HAM-A6 Score at Week 6 (fITT Population)
• Double-blind Treatment Period: Change From Baseline in Hamilton Depression Rating Subscale (HAM-D6) Score at Week 6 (eITT Population)
• Double-blind Treatment Period: Change From Baseline in HAM-D6 Score at Week 6 (fITT Population)
• Double-blind Treatment Period: Change From Baseline in Structured Interview Guide of the Hamilton Anxiety Scale (SIGH-A) Total Score at Week 6 (eITT Population)
• Double-blind Treatment Period: Change From Baseline in SIGH-A Total Score at Week 6 (fITT Population
• Double-blind Treatment Period: Change From Baseline in the HDRS17 Anxiety/Somatization Factor Total Score at Week 6 (eITT Population)
• Double-blind Treatment Period: Change From Baseline in the HDRS17 Anxiety/Somatization Factor Total Score at Week 6 (fITT Population)

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is continuous: each participant’s HDRS17 score is measured as a numerical scale score, and the registry reports mean change from baseline. For a continuous outcome, group means describe the average observed change, while a measure of spread describes how much participants’ changes vary within each group. The posted group spreads are standard deviations. A standard deviation describes dispersion among individual observations; it is not the uncertainty around the group mean and is not the same as a confidence interval.

What does the unadjusted comparison represent?

The recalculated comparison uses the two posted group means and their summary information to estimate a simple difference in average change. The reported estimate of -0.4 is the JNJ-42165279 group mean minus the placebo group mean. A negative value means the posted average change was more negative in the active-treatment group. Since lower HDRS17 scores represent less symptom severity, that direction is consistent with a larger average score reduction in that group, but the estimate is small relative to its uncertainty. This calculation is unadjusted: it does not account for repeated measurements or any covariates through a model.

The associated confidence interval expresses a range of values compatible with the summary data and the assumptions of the calculation. It is not a range containing a fixed proportion of individual participants’ responses. Because the interval runs from -2.439 to 1.639, it spans zero and includes both negative and positive contrasts. The unadjusted p-value of 0.701 describes how compatible the observed estimate is with a null difference under the calculation’s assumptions; it is not the probability that the null hypothesis is true.

Why does the sponsor analysis use another method?

The sponsor reports a mixed-effects model for repeated measures and a difference of least-square means. In general, repeated-measures models analyze observations collected over time while representing the correlation among measurements from the same participant. Least-square means are model-based estimates of group averages, conditional on the model specification. Such an analysis can use information across scheduled measurements rather than reducing the comparison to a single unadjusted contrast of summary means.

The registry record does not provide the full model specification, the covariance structure, the handling of missing observations, or details of any covariates included. Those choices can affect model-based estimates and their uncertainty. The sponsor result should therefore be described as reported, without attempting to reproduce the model or infer details that are not in the registry record. Its point estimate and interval are not expected to be identical to the simple recalculation because the methods and possibly the information used differ.

What do the analysis populations mean?

The primary endpoint is reported for the enriched intent-to-treat, or eITT, population. The displayed definition says this set included enrolled participants randomized into the double-blind treatment period who were placebo lead-in non-responders and received at least one dose of double-blind study medication; the definition is truncated in the registry display. The fITT population appears in secondary outcomes. The full definition of fITT is not reported in the registry record, so the populations should not be treated as interchangeable or assumed to have identical eligibility rules.

Population choice matters because estimates apply directly to the participants included in each analysis. The primary comparison concerns the eITT subset, while some secondary outcomes use fITT. Differences in population, endpoint, and model can make outcome estimates differ without implying a contradiction. The registry record does not report a complete account of the analysis-population rules or the number of participants contributing measurements at every time point.

Why does over-dispersion matter in general?

For a continuous outcome, greater variation among individual responses generally makes a group mean less precise unless the amount of information also increases. In general, over-dispersion refers to variability greater than a model assumes. If a model understates variability, its standard errors and confidence intervals may be too small, giving an overly precise impression. The primary endpoint is summarized with a standard deviation, but the registry does not report an over-dispersion assessment or a model diagnostic. It would not be appropriate to claim that over-dispersion was present or absent.

These distinctions help separate descriptive results from inference. Group means describe observed averages; standard deviations describe participant-level spread; the estimated difference describes a contrast; confidence intervals describe its precision; and p-values summarize compatibility with a specified null model. None of these measures alone determines clinical importance, and the registry record does not report a clinically meaningful-change threshold for HDRS17.

11. Confidence Intervals and Precision

The recalculated primary contrast is -0.4 points, with a 95% confidence interval from -2.439 to 1.639. The interval is wide enough to include no difference and estimates on either side of zero. It therefore does not pin down the direction of the underlying between-group contrast with precision. The point estimate is only one value within a range of plausible contrasts, not a precise statement of the treatment effect.

A confidence interval is a measure of statistical precision under the assumptions of the analysis. In general, a narrower interval indicates less uncertainty about the estimated contrast, while a wider interval indicates more uncertainty. A confidence interval is not a guarantee that the true effect lies within its endpoints, and it is not a statement about the range of individual participant outcomes.

The sponsor’s mixed-effects model reports a difference of least-square means of -0.2 and an interval from -1.10 to 0.66, with the interval identified as 60%. This is not the same interval as the 95% interval from the unadjusted recalculation. Confidence levels and analysis methods matter when comparing interval widths; the two results should not be treated as if they were produced by identical calculations.

Both the recalculated and sponsor-reported intervals include zero. That means each reported interval is compatible with no between-group difference, as well as with nonzero values on either side. It does not establish that the groups are equivalent, and it does not exclude all potentially important effects. The registry record does not provide a threshold for interpreting the clinical importance of the interval endpoints, so precision can be described statistically but not converted into a clinical judgment from these data alone.

12. Planning a Similar Trial: Sample Size

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

The planning illustrations express participants per arm for 80% power and participants per arm for 90% power. They are based on the observed effect and show how the planning count changes when the effect used for planning is set at 100%, 75%, or 50% of that observed effect. The smaller the effect a future study aims to detect, the more participants per arm are required under the listed assumptions.

The listed planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The target effect is the stated fraction of the observed effect. The registry record’s original design assumptions and sample-size justification are not reported in the registry record; these planning figures are illustrations derived from the observed result, not a reconstruction of the trial’s original design.

In general, 80% power means that a study designed under the stated assumptions has an 80% chance of detecting an effect of the specified size at the stated significance level if that effect is the true one. The 90% column uses a higher detection probability target, which generally requires more participants for the same target effect. These are planning concepts, not guarantees about any particular future result. The displayed estimates also depend on the normal-approximation and equal-allocation assumptions.

These figures are not observed power. Observed power is not a useful substitute for reading the estimated effect and its confidence interval: the relevant uncertainty is already visible in the estimate and interval. The planning counts can be read as conditional illustrations of how study size depends on a target effect and design assumptions, rather than as evidence that the current trial was adequately or inadequately designed.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -0.400; pooled standard deviation σ = 5.044.
2. n = 2 × (1.96 + 0.842)² × 5.044² / -0.400² = 2,496.4, rounded up to 2,497 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -0.4                      # observed difference in means
sigma <- 5.0443086741396                     # 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(2498392)
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 = 2,497 (80% power), 3,343 (90% power)
 75% of observed effect: n per arm = 4,439 (80% power), 5,942 (90% power)
 50% of observed effect: n per arm = 9,986 (80% power), 13,369 (90% power)
power.t.test: 2497.4 
Simulated power at n = 2,497 per arm: 0.800 (20000 replicates)

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

14. Analyses Reported by the Sponsor

The sponsor’s reported primary analysis is a mixed-effects model for repeated measures. It estimates a difference of least-square means of -0.2, with a reported interval from -1.10 to 0.66 and p = 0.416. This is the trial’s reported model-based result. The registry record does not include the full specification needed to independently reproduce that analysis.

The recalculated comparison is a simple unadjusted calculation from the posted group summaries. It estimates a mean difference of -0.4, with a 95% confidence interval from -2.439 to 1.639 and an unadjusted p-value of 0.701. It is not a replacement for the sponsor’s repeated-measures model: the calculations use different methods, and the model may use information and assumptions not represented by the summary-statistic calculation.

The estimates differ in magnitude, but both are close to zero relative to their uncertainty and both reported intervals include zero. The discrepancy flag is false, so the registry record does not identify a discrepancy requiring the sponsor’s analysis to take precedence. The sponsor analysis remains the principal reported trial analysis, while the recalculation is best understood as a transparent, unadjusted check based on the posted summaries. Neither estimate should be interpreted in isolation from its analysis population, model assumptions, and interval.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when a study evaluates several outcomes, time points, populations, or comparisons. In general, making many statistical tests increases the chance that at least one result will appear unusual even when there is no true effect. Methods such as adjustment procedures or a prespecified hierarchy can control how results are interpreted across tests. The registry record does not report a multiplicity strategy for the posted secondary analyses, and the displayed secondary p-values are unadjusted. They should therefore be interpreted cautiously and not treated as a collection of independent confirmatory tests.

The primary endpoint is identifiable in the registry record, but the detailed statistical analysis plan is not reported in the registry record. Specifics such as the planned covariate set, repeated-measures covariance structure, assumptions about missing data, and any sensitivity analyses are also not reported in the registry record. The sponsor’s reported method is named, but the full model details are not available in the record.

Missing-data handling matters because a change score may be unavailable when a participant misses a scheduled assessment or leaves the study. Different assumptions and methods for incomplete observations can affect estimates and uncertainty. Mixed-effects models can use available repeated measurements under model assumptions, but the registry record does not state the missing-data assumptions or provide enough detail to assess whether those assumptions are plausible. No specific missing-data mechanism should be inferred.

Analysis populations also require care. The primary endpoint uses eITT, defined in the displayed text by randomization into the double-blind period, placebo lead-in non-response, and receipt of at least one dose, followed by a truncated additional criterion. Secondary outcomes include both eITT and fITT. The complete fITT definition and the complete eITT definition are not reported in the registry record. These omissions limit the ability to assess how participants were assigned to each analysis set and how missing observations affected each result.

16. Safety Results

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

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: gastroenteritis (1.3%), foot deformity (1.3%).

The registry reports serious adverse event counts separately for the double-blind lead-in placebo period and the double-blind treatment plus withdrawal period. During the lead-in period, 2 of 160 participants at risk were reported with a serious adverse event, and there were 0 deaths. In the treatment plus withdrawal period, the placebo group had 1 of 76 participants at risk with a serious adverse event and 0 deaths; the JNJ-42165279 25 mg group had 1 of 77 participants at risk with a serious adverse event and 0 deaths.

These counts describe events recorded in the registry and the corresponding groups at risk. They do not by themselves establish that a study treatment caused or prevented an event. The treatment-period figures cover a specific period and should not be directly combined with the lead-in figures, which represent a different period and group structure. The registry also lists Gastroenteritis and Foot Deformity among the top serious adverse event terms, each reported as 1.3%.

Adverse-event counts are descriptive safety information, not a complete assessment of safety. The registry record does not provide event timing, participant-level clinical context, exposure-adjusted rates, or a causal assessment for each event. Zero deaths in the listed groups means no deaths were reported in those entries; it does not establish an absence of all safety risks.

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

The primary result describes average HDRS17 change over the double-blind treatment period for the eITT population. The posted means declined in both groups, and the estimated difference between the groups was small in the unadjusted recalculation. The confidence interval includes no difference and leaves uncertainty about the direction and size of the contrast. The sponsor’s repeated-measures analysis also reports an estimate close to zero with an interval spanning zero.

These findings do not prove that the treatments are equivalent. Establishing equivalence would require an appropriate design and prespecified equivalence margin, neither of which is reported in the registry record. The findings also do not prove that JNJ-42165279 has no effect: estimates remain uncertain, and an interval that includes zero can also include nonzero effects. The registry record does not provide a clinical-importance threshold for HDRS17, so the clinical meaning of the interval’s range cannot be determined from these results alone.

The results apply most directly to the analysis population and conditions represented in the trial. The primary endpoint focuses on placebo lead-in non-responders, and the double-blind treatment period lasted 6 weeks. It should not automatically be generalized to participants who responded during the lead-in, people with different treatment histories, or longer-term outcomes. The trial’s randomized, double-blind structure supports a comparative interpretation, but population selection, incomplete reporting of analysis details, and uncertainty in the estimate remain relevant.

Safety counts are also limited to the adverse-event reporting in the registry record and the periods described. They do not establish causality or provide a complete risk profile. Taken together, the posted results describe measured outcomes in this study; they are not medical advice and do not determine what treatment is appropriate for an individual.

18. Why This Trial Matters Statistically

This trial illustrates why a group mean difference should be read alongside its uncertainty. The active-treatment group’s primary mean change was more negative than the placebo group’s, but the estimated contrast was small and its confidence interval included values on both sides of zero. Focusing only on the direction of the point estimate would overstate what the data can establish; focusing only on the p-value would also miss the range of effects compatible with the estimate.

It also shows how analysis choices shape the reported result. The sponsor used a mixed-effects model for repeated measures, while the recalculation uses posted group summaries for an unadjusted comparison. These approaches address the data differently and need not yield identical estimates. Transparent separation of the sponsor analysis from the summary-statistic recalculation helps readers understand that a recalculation is a check, not a substitute for the trial’s reported analysis.

The enriched analysis population is another important statistical feature. The primary result concerns participants who did not respond during the placebo lead-in, not necessarily everyone enrolled or every group described in the study. Population definitions and the timing of assessments define what question an estimate answers. Incomplete population and model details in the registry record constrain how fully those choices can be evaluated.

Finally, the trial offers a useful example of the difference between inference and planning. Planning illustrations based on an observed effect can show how target effect size and power assumptions influence required participants per arm, but they cannot recover the original design rationale or demonstrate observed power. The primary confidence interval, not a retrospective power label, is the more direct description of the uncertainty in the posted comparison.

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 gives a truncated definition of the primary eITT population and does not provide the complete fITT definition. That makes it difficult to determine precisely who contributed to each analysis or to reconcile all analysis populations with the arm descriptions. The primary analysis population is restricted to placebo lead-in non-responders, so its result is not automatically representative of all enrolled participants or of the lead-in responders.

The sponsor’s mixed-effects model is named, but its detailed specification is not reported in the registry record. The record does not report the covariance structure, covariates, missing-data assumptions, or sensitivity analyses. These omissions limit independent assessment of the model-based estimate and its robustness. The simple recalculation is based on posted summary statistics and is not a reconstruction of the sponsor’s analysis.

The primary endpoint is a clinician-rated symptom score measured from baseline to Week 6. The registry does not report a threshold for clinically meaningful change, and the available result does not establish whether the estimated group contrast would be important to participants. The double-blind treatment period’s 6-week duration also limits what can be inferred about longer-term outcomes.

The trial reports numerous outcomes, while a multiplicity adjustment for the secondary results is not reported in the registry record. Detailed numerical information is not available for every posted secondary outcome in the record. The safety information is likewise limited to the event counts and terms listed, without full participant-level context or a causal assessment. These limitations do not invalidate the posted results, but they narrow the conclusions that can be drawn from them.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: An Efficacy, Safety and Tolerability Study of JNJ-42165279 in Participants With Major Depressive Disorder With Anxious Distress — NCT02498392.
• Registry record last updated 2025-04-29; status last verified 2025-04.
• Results first posted 2022-04-07.
• 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

NCT02498392 was a completed Phase 2a randomized, double-blind, placebo-controlled, parallel-group, multi-center study of JNJ-42165279 in major depressive disorder with anxious distress. Enrollment was 161. The primary endpoint was change from baseline to Week 6 in HDRS17 total score for the eITT population of placebo lead-in non-responders.

The posted group means were -6.1 for placebo and -6.5 for JNJ-42165279 25 mg. The unadjusted recalculated mean difference was -0.4, with a 95% confidence interval from -2.439 to 1.639 and p = 0.701. The sponsor’s repeated-measures analysis reported a difference of least-square means of -0.2, an interval from -1.10 to 0.66, and p = 0.416. Both estimates are close to zero relative to their uncertainty, and the registry record does not report evidence establishing a clinically meaningful difference.