A Study of LY2140023 in Schizophrenia Patients With Prominent Negative Symptoms: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study of LY2140023 in Schizophrenia Patients With Prominent Negative Symptoms (NCT01052103), a randomized phase 2 study. The primary outcome is Change From Baseline in the 16-Item Negative Symptoms Assessment (NSA-16).

2. Clinical Question

3. Trial Design

This was a phase 2, randomized, parallel-group study described in its official title as a 17-week, multicenter, double-blind trial. The registry classifies masking as quadruple. These are both registry descriptions; the record does not explain how the masking labels relate to one another. The study status is completed, and the registry lists enrollment of 167 participants.

Participants were assigned to LY2140023 plus standard of care or placebo plus standard of care. The LY2140023 dose was listed as 40 mg/day orally, administered twice daily as a 20-mg tablet, with adjustment permitted from 10 mg to 40 mg twice daily. Placebo tablets were intended to match the LY2140023 tablets. Standard of care is described as antipsychotic treatment in the study summary, but the specific standard-of-care regimens are not reported in the registry record.

The primary outcome was change from baseline in NSA-16 total score, with the stated timeframe of baseline to randomization treatment Week 16. The primary analysis included randomized participants who received at least one dose and had both a baseline and at least one post-baseline NSA-16 score. The analysis counts posted for the two arms were 81 and 82. These analysis counts need not equal the overall enrollment because the primary analysis population had additional eligibility requirements.

The registry lists 24 secondary outcomes, covering symptom ratings, clinical severity, cognition, functioning, movement-related assessments, and EEG findings. The registry record does not report the original sample-size justification, detailed randomization procedure, or a full protocol-level analysis plan.

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: This study consisted of a 1-week placebo lead-in period and a 16-week randomization treatment period.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All randomized participants who received at least one dose of study drug, had a baseline and at least one post-baseline NSA-16 total score measurement.

5. Baseline Characteristics

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

Population: All randomized participants who received at least one dose of study drug.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in the 16-Item Negative Symptoms Assessment (NSA-16), measured over Baseline, randomization treatment Week 16.

The primary endpoint was change from baseline in the 16-Item Negative Symptoms Assessment, or NSA-16, total score, assessed at randomization treatment Week 16. The NSA-16 is intended to help clinicians rate behaviors commonly associated with negative symptoms of schizophrenia, rather than psychopathology itself. It contains 16 anchors, with each item rated from 1, indicating better, to 6, indicating worse. The total score ranges from 16 to 96, and higher scores indicate greater illness severity.

A change score describes how the assessment differed from the participant's baseline score over the stated follow-up period. The posted values are least-squares means from a mixed model repeated-measures analysis, rather than simple arithmetic averages. In general, adjusted means can account for specified model terms and baseline characteristics, which may make a comparison more informative than a raw difference in group averages. The registry says the model adjusted for visit, pooled investigative site, treatment, standard-of-care type, baseline positive-symptom stratum, treatment by visit, baseline NSA-16 total score, and baseline score by visit.

The endpoint is relevant to the study question because it quantifies behaviors associated with negative symptoms, the focus described in the study summary. The registry record does not report a threshold for a clinically important NSA-16 change, so the numerical size of a difference cannot be classified against such a threshold from this record alone.

7. Results Posted in the Registry

• Placebo + SOC: mean -3.60 versus -2.70 on control; difference -0.90 (95% CI -4.23 to 2.43), standardized effect d = -0.08; z-test p = 0.596.

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 Positive and Negative Syndrome Scale (PANSS) Total Score

• 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:
  • Placebo + SOC: mean -6.60 versus -4.40 on control; difference -2.20 (95% CI -6.59 to 2.19), standardized effect d = -0.15; z-test p = 0.326.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Placebo + SOC and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in Clinical Global Impression Severity (CGI-S) Scale

• 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:
  • Placebo + SOC: mean -0.30 versus -0.40 on control; difference 0.10 (95% CI -0.18 to 0.38), standardized effect d = 0.11; z-test p = 0.480.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Placebo + SOC and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in Measurement and Treatment Research to Improve Cognition in Schizophrenia Consensus Cognitive Battery (MCCB) Overall Composite T-Score

• 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:
  • Placebo + SOC: mean 1.80 versus 3.20 on control; difference -1.40 (95% CI -4.17 to 1.37), standardized effect d = -0.19; z-test p = 0.322.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Placebo + SOC and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists secondary outcomes spanning total symptom burden, clinician-rated severity, cognitive performance, functional skills, movement-related assessments, and EEG findings. The numerical secondary results described in the posted continuous-outcome summaries cover a smaller set of measures than the full outcome list. This means that the broad list of outcome domains should not be mistaken for equal availability of numerical results for every listed measure.

Across the secondary continuous results with posted numerical comparisons, the recalculated confidence intervals include zero. The pattern does not establish a clear separation between the treatment groups across these measures. Nor should similar-looking directions across selected measures be treated as independent confirmation of the primary result: many outcomes assess related or overlapping aspects of illness and functioning, and their estimates may be correlated.

These secondary measures provide context about other domains assessed during the study, but they do not replace the primary NSA-16 comparison. The primary question concerns change in negative-symptom-associated behaviors at Week 16. Secondary results can be useful for describing the broader outcome profile, but their interpretation depends on which outcomes were prespecified, how missing observations were handled, and whether multiplicity was addressed. Those details are not fully reported in the registry record.

Unadjusted secondary p-values carry less weight when many outcomes are tested because, in general, the chance of at least one apparently unusual result increases as more comparisons are made. No multiplicity adjustment or hierarchy for interpreting the secondary outcomes is reported in the registry record. Accordingly, isolated secondary findings, if considered, should be viewed cautiously and should not be taken as conclusive evidence of a treatment difference.

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

• Change From Baseline in Positive and Negative Syndrome Scale (PANSS) Total Score
• Change From Baseline in Clinical Global Impression Severity (CGI-S) Scale
• Change From Baseline in Measurement and Treatment Research to Improve Cognition in Schizophrenia Consensus Cognitive Battery (MCCB) Overall Composite T-Score
• Change From Baseline in University of California at San Diego Performance-Based Skills Assessment-Brief Version (UPSA-B) Total Score
• Change From Baseline in Barnes-Akathisia Scale (BAS) Global Score
• Change From Baseline in Simpson Angus Scale (SAS) Total Score
• Change From Baseline in Abnormal Involuntary Movement Scale (AIMS) Total Score
• Number of Participants With Incidence of Epileptiform Activity Outside of Normal Range in Electroencephalograms (EEGs)

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is continuous: it is a change in a numerical scale score. For such outcomes, an analysis often estimates a group mean change and a contrast between groups. The reported arm values are least-squares means, a model-based form of mean that reflects the covariates and terms included in the analysis. In general, least-squares means are useful when an analysis adjusts for baseline measures or design features, but their interpretation depends on the model specification.

What does the repeated-measures model do?

The registry says a mixed model repeated-measures analysis was used to calculate the primary least-squares means and standard errors. In general, repeated-measures methods analyze measurements collected over time while accounting for the fact that observations from the same participant are related. They can use the pattern of available observations in the model rather than reducing the analysis to a single unadjusted comparison. The particular covariance structure, estimation details, and handling of missing observations are not reported in the registry record.

The stated adjustment terms were visit, pooled investigative site, treatment, standard-of-care type, baseline positive-symptom stratum, treatment by visit, baseline NSA-16 total score, and baseline NSA-16 total score by visit. A treatment-by-visit term allows the modeled treatment contrast to vary across visits. Including baseline score and its interaction with visit allows the relationship between starting score and follow-up score to vary by visit. The registry does not provide further detail about how these terms were coded or how the model was selected.

What does a standard error describe?

A standard error describes the estimated sampling uncertainty of an estimate under the analysis that produced it. It is not the spread of individual participant scores. Smaller standard errors generally correspond to more precise estimates, while larger standard errors indicate more sampling uncertainty. The posted primary standard errors are 1.2 for each arm. The standard errors alone do not show the full uncertainty in the between-group contrast; that is why a contrast estimate and its confidence interval are also informative.

How should the recalculation be read?

The recalculated comparison is a simple unadjusted contrast based on the posted arm summaries, not a recreation of the sponsor's repeated-measures model. The recalculated primary contrast is -0.9, with a 95% confidence interval from -4.226 to 2.426 and an unadjusted p-value of 0.596. The calculation uses an approximate pooled standard deviation inferred from the reported standard errors, as indicated by the calculation notes. It therefore depends on simplifying assumptions and should be considered a secondary check on the posted summaries.

In general, a confidence interval describes a range of values reasonably compatible with the estimate and the statistical model or calculation used. If an interval includes zero for a difference, the data do not distinguish that difference from no difference at the stated confidence level. That does not prove there is no effect. A p-value describes how unusual data at least as incompatible with the null model would be if that model were true; it is not the probability that a treatment works, nor a measure of clinical importance.

The sponsor's result is reported as a Type 3 test of least-squares mean differences, with value 1.0 and p = 0.732. In general, a Type 3 test evaluates a model term while accounting for the other terms in the fitted model. The registry does not provide the sponsor's confidence interval or all details needed to reproduce that test. The sponsor result and the unadjusted recalculation have different analysis bases and should not be treated as duplicate calculations.

What do power and planning illustrations mean?

The sample-size illustrations use the observed effect as a planning reference and then consider stated fractions of that effect. They assume a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. In general, power is the probability that a planned study will reject a specified null hypothesis under an assumed effect and analysis model. The 80% and 90% columns represent different target probabilities of detecting the assumed effect under those planning assumptions. They are planning quantities, not descriptions of the probability that the completed study detected an effect.

Smaller assumed effects require more participants to detect with the same target power, all else held to the stated assumptions. Those calculations are not the original trial's design rationale: the original sample-size assumptions and justification are not reported in the registry record. The listed planning figures are illustrations based on the observed effect, not evidence about the completed trial's power.

General statistical interpretation also depends on the analysis population, missing-data handling, and multiplicity. The primary population is defined in the record, but detailed missing-data procedures and a multiplicity plan are not reported. Those gaps limit how fully the sponsor's inferences can be evaluated from the registry record alone.

11. Confidence Intervals and Precision

The recalculated primary contrast is -0.9, with a 95% confidence interval from -4.226 to 2.426. The interval includes zero. It also covers negative and positive differences, so the summary statistics are compatible with effects favoring either arm as well as a small or absent difference. This is a wide range relative to the point estimate and indicates that the recalculated contrast is not precise enough to settle the direction or size of a between-group difference.

Confidence intervals express uncertainty around an estimate, not the range of individual participant responses. In general, a 95% confidence interval is produced by a procedure that would cover the underlying parameter in 95% of repeated samples if its assumptions held. It is not a 95% probability statement about the true value for this particular trial. The interval belongs to the unadjusted recalculation from posted summaries, not to the sponsor's model-based test.

The sponsor's result is reported as a least-squares mean difference value of 1.0 with p = 0.732, but a confidence interval is not reported in the registry record for that analysis. Without that interval, the precision of the sponsor-reported contrast cannot be described from the registry result in the same way. Its p-value alone does not provide the range of effect sizes compatible with the analysis.

The NSA-16 scale ranges from 16 to 96, but the registry record does not report a threshold for a clinically important difference. Consequently, the statistical interval cannot be used to classify possible values as clinically trivial or important. The study's primary analysis population included 81 participants in the LY2140023 arm and 82 in the placebo arm. Those counts and the reported standard errors provide context for the estimates, but do not remove uncertainty. The registry record also does not report additional precision measures such as participant-level score distributions or a complete model-based interval.

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 a reconstruction of the trial's original design. The planning assumptions listed are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The assumed effect is the stated fraction of the observed effect. The original sample-size justification and assumptions are not reported in the registry record.

For these continuous outcomes, the figures are participants per arm, not total participants. The 80% power column gives the number of participants per arm required under the stated assumptions for an 80% chance of detecting the assumed effect if that effect were the true one. The 90% power column gives the corresponding per-arm planning quantity for a 90% chance. These are planning probabilities under assumptions, not probabilities that the completed trial found an effect. This is not observed power.

Rows that plan for 75% or 50% of the observed effect use smaller assumed effects than the row based on 100% of the observed effect. Smaller effects are harder to distinguish from random variation, so they require more participants per arm to reach the same target power. The sample-size figures therefore illustrate how much the required enrollment can depend on the effect size a future study aims to detect.

The plotted curve should be read as the same planning relationship across assumed effects: as the target effect gets smaller, the participant requirement rises. These calculations use a simplified normal approximation and do not incorporate unreported design features of the completed trial. They are not an enrollment recommendation, and they do not establish that the original study was adequately or inadequately sized.

13. How the Sample Size Is Derived

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

Formula

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

Worked calculation for this trial

1. Observed difference Δ = -0.900; pooled standard deviation σ = 10.833.
2. n = 2 × (1.96 + 0.842)² × 10.833² / -0.900² = 2,274.5, rounded up to 2,275 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 <- -0.9                      # observed difference in means
sigma <- 10.8334884524649                     # 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(1052103)
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 = 2,275 (80% power), 3,045 (90% power)
 75% of observed effect: n per arm = 4,044 (80% power), 5,414 (90% power)
 50% of observed effect: n per arm = 9,099 (80% power), 12,180 (90% power)
power.t.test: 2275.5 
Simulated power at n = 2,275 per arm: 0.797 (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 posted primary analysis is a Type 3 test of least-squares mean differences. The registry reports a value of 1.0 and p = 0.732, with no confidence interval for that result. This is the sponsor's model-based result and should remain the primary registry-reported analysis.

The simple recalculation from the posted arm summaries gives a mean difference of -0.9, with a 95% confidence interval from -4.226 to 2.426 and an unadjusted p-value of 0.596. It is not the same analysis: it is unadjusted and is based on summary statistics, whereas the sponsor's result comes from the reported model framework. The two estimates also use different reported signs. Their values should not be combined or presented as if one directly corrected the other.

The registry record does not provide enough detail to reproduce the sponsor's test fully, including a confidence interval for its reported contrast. The recalculation is useful as a transparent check on the posted arm summaries, but it does not supersede the sponsor's analysis. The record does not flag a discrepancy between the reported sponsor analysis and the recalculated result.

15. Multiplicity, Missing Data and Analysis Populations

The registry reports 24 secondary outcomes, in addition to the primary endpoint. Testing many outcomes creates a multiplicity issue: in general, the more comparisons made, the greater the chance that at least one result will appear statistically notable by chance alone. A prespecified hierarchy, family-wise error adjustment, or other multiplicity strategy can clarify how to interpret multiple tests. Such a strategy is not reported in the registry record.

The primary outcome description does specify an analysis population: randomized participants who received at least one dose of study drug and had a baseline and at least one post-baseline NSA-16 total score measurement. The arm counts posted for the primary outcome are 81 and 82. The registry does not report the number excluded from this population for each reason, or a complete account of participants with missing outcome data.

The primary outcome was analyzed using a mixed model repeated-measures approach. That describes the broad model used, but the registry record does not report the missing-data assumptions, imputation procedures, sensitivity analyses, or covariance structure. A mixed model can use available repeated measurements under its modeling assumptions; it does not by itself demonstrate that missing data could not bias the result.

The record also does not report whether interim analyses were planned or conducted, the original sample-size justification, or a detailed statistical analysis plan. The secondary outcome populations and missing-data procedures are not fully described. These absences do not prove that such procedures were not used; they mean they are not reported in the registry record, limiting independent assessment of those decisions.

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 3% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: psychotic disorder (3.7%), schizophrenia (3.7%), cholangitis (1.2%), cellulitis (1.2%), ischaemic stroke (1.2%).

The registry reports serious adverse events in 8 of 82 participants in the LY2140023 plus standard-of-care group and 4 of 82 participants in the placebo plus standard-of-care group. Other adverse events were reported for 54 of 82 and 51 of 82 participants, respectively. These are counts of participants affected as reported in the record, not a basis for attributing an event to study treatment.

The listed serious-event terms include psychotic disorder and schizophrenia, each reported as 3.7%, and cholangitis, cellulitis, ischaemic stroke, and suicidal ideation, each reported as 1.2%. These listed terms describe reported events; the registry record does not establish causation. The record does not report deaths.

Adverse-event counts should be interpreted alongside the study's size, follow-up period, event definitions, and completeness of reporting. The registry record does not provide enough detail to compare event timing, severity beyond the serious-event classification, or treatment relatedness. The counts alone do not support a conclusion about comparative safety.

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

The posted primary estimates show mean NSA-16 score decreases from baseline in both groups at Week 16. The unadjusted recalculation of the between-group contrast has a 95% confidence interval from -4.226 to 2.426 and p = 0.596. Because the interval includes zero and spans values in both directions, the available summary statistics do not establish a clear difference between LY2140023 plus standard of care and placebo plus standard of care.

This result does not prove that the strategies are identical or equivalent. A nonsignificant result can arise when the underlying difference is small, when estimates are uncertain, or both. The record does not report an equivalence or noninferiority design, a margin for such a conclusion, or a clinically important NSA-16 difference threshold. The findings therefore cannot be interpreted as demonstrating equivalence.

The sponsor's model-based analysis reports p = 0.732 for its Type 3 test. The summary available in the registry does not include a confidence interval for that test. The sponsor analysis remains the reported analysis, while the unadjusted recalculation is supplementary and has different assumptions.

The endpoint measures behaviors associated with negative symptoms, not every aspect of schizophrenia. The secondary outcomes assess other symptom and functioning domains, but multiple comparisons and incompletely reported analysis details limit the weight that can be placed on individual secondary findings. Neither the primary nor secondary statistics alone resolve whether an observed numerical change is clinically important, because the record does not give a clinical-importance threshold.

These are findings from a completed phase 2 study with the stated population, comparison, and assessment period. They do not by themselves establish what would be observed in other populations, under other treatment conditions, or over other follow-up periods. No medical treatment recommendation follows from these registry statistics.

18. Why This Trial Matters Statistically

This trial illustrates why the arm-specific changes and the between-group contrast answer different questions. Both groups had lower posted NSA-16 least-squares mean scores at Week 16 than at baseline, but the clinical question is whether the change differed between the randomized strategies. The contrast and its uncertainty, rather than the direction of change within either arm alone, address that comparison.

It also demonstrates the importance of distinguishing a sponsor's adjusted model-based analysis from a simple recalculation of posted summaries. The sponsor reports a Type 3 test, while the recalculation is an unadjusted contrast with an approximate standard deviation. They are not interchangeable. Clear reporting of the analysis model, contrast direction, confidence interval, and missing-data assumptions would help readers understand how each estimate was obtained.

The sample-size illustrations highlight that planning depends strongly on the effect a study aims to detect. A design aimed at a smaller effect requires more participants under the stated assumptions. Because the original design justification is not reported, the illustrations cannot be used to judge the reasoning behind this trial's enrollment.

Finally, the broad secondary outcome list makes multiplicity relevant. A collection of outcomes can offer a wider view of the study, but unadjusted results across multiple measures are less persuasive than a prespecified primary comparison. The record's limitations in reporting multiplicity, missing-data procedures, and model details matter for interpreting the strength and scope of the statistical evidence.

19. Limitations

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

The registry record contains limited detail for independently assessing the primary model. It identifies the mixed model repeated-measures approach and lists adjustment terms, but does not report the covariance structure, model diagnostics, estimation details, or sensitivity analyses. The sponsor's primary test is reported without a confidence interval, and the full test specification is not available in the registry record.

The recalculated comparison is based on posted summary statistics and uses an approximate pooled standard deviation inferred from standard errors. It is an unadjusted check, not a substitute for participant-level data or the sponsor's adjusted analysis. Its confidence interval and p-value should be interpreted within those limits.

The original sample-size justification, the design assumptions behind enrollment, and any planned interim analyses are not reported in the registry record. The planning illustrations are based on the observed effect and stated simplified assumptions, so they cannot establish whether the original design was adequately sized for a prespecified target effect.

The registry record does not report the missing-data assumptions or procedures, detailed reasons for exclusion from the primary analysis population, or sensitivity analyses for missing outcomes. The primary analysis population requires at least one post-baseline NSA-16 measurement, so its counts are not the same as overall enrollment. A full accounting of outcomes for participants outside that population is not reported.

Multiplicity procedures for the 24 secondary outcomes are not reported. A clinical-importance threshold for NSA-16 change is also not reported, limiting interpretation of the size of possible effects. The safety summary provides counts and selected serious-event terms, but does not report deaths or detailed event attribution in the registry record.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Study of LY2140023 in Schizophrenia Patients With Prominent Negative Symptoms — NCT01052103.
• Registry record last updated 2022-09-07; status last verified 2022-08.
• Results first posted 2021-09-22.
• 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

NCT01052103 is a completed phase 2, randomized, parallel-group study of LY2140023 plus standard of care compared with placebo plus standard of care in participants with schizophrenia and prominent negative symptoms. The official title describes a 17-week, multicenter, double-blind study; the registry classifies masking as quadruple. Enrollment was 167.

The primary outcome was change from baseline in NSA-16 total score at randomization treatment Week 16. The sponsor-reported Type 3 test has p = 0.732. A simple unadjusted recalculation gives a mean difference of -0.9, with a 95% confidence interval from -4.226 to 2.426 and p = 0.596. This recalculation does not establish a clear between-group difference and does not replace the sponsor's model-based analysis.

The registry lists 24 secondary outcomes and reports serious adverse events in 8 of 82 participants in the LY2140023 group and 4 of 82 in the placebo group. Detailed multiplicity, missing-data, and original sample-size procedures are not reported in the registry record.