Premenstrual Hormonal and Affective State Evaluation (PHASE) Project: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Premenstrual Hormonal and Affective State Evaluation (PHASE) Project (NCT03862469), a na na study. The primary outcome is Hormone Analysis.

2. Clinical Question

3. Trial Design

The Premenstrual Hormonal and Affective State Evaluation (PHASE) Project is a completed, single-group study sponsored by the University of Illinois Chicago. The registry records enrollment of 129 and identifies Premenstrual Dysphoric Disorder as the condition. The recorded start date is 2019-09-26, and the primary completion date is 2023-09-01. The study is marked completed. These registration details describe the project and its status; they do not establish how many participants contributed data to the primary outcome.

The study summary describes an evaluation of neuroactive hormone trajectories across the menstrual cycle and of endocrine, autonomic, and subjective responses to psychosocial stress in women suffering from severe PMS, identified there as PMDD. The listed intervention is an individualized laboratory test, classified as a procedure. The arm description names All Participants, with no further description. Masking is recorded as none, and allocation is recorded as NA. The study model is single group.

There is no listed randomized control group or other like-for-like comparator. Accordingly, the design should be read as an assessment within a group, not as a trial estimating a treatment contrast between randomized groups. The registry does not report a detailed protocol, the sequence of laboratory procedures, eligibility criteria, recruitment approach, or the intended sample-size justification. It also does not report how the enrolled population relates to the participants at risk in the safety record.

The registry lists one primary outcome measure and no analysis entries. The outcome is cortisol concentration, with mean and standard deviation specified, at multiple timed assessments during the late luteal phase. However, no numerical outcome results or analysis estimates are included in the record. The design and registration establish what the project set out to assess; they do not, by themselves, show the observed cortisol pattern or the precision of any result.

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

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 Hormone Analysis, measured over -20, +20, +30, +40, +50, +65, +90 minutes in the late luteal phase of the menstrual cycle (one day between -1 to -6 days of the subsequent menstrual cycle).

The primary outcome is titled Hormone Analysis and identifies cortisol as the measure. Concentration is expressed in ng/mL, and the summary measure is a mean with standard deviation. Assessments are scheduled at -20, +20, +30, +40, +50, +65, and +90 minutes in the late luteal phase of the menstrual cycle. The registry describes the timing as one day between -1 to -6 days of the subsequent menstrual cycle. The record does not explain the reference point for the minute labels or give a more detailed collection protocol.

Cortisol is included in the project’s broader assessment of endocrine responses to psychosocial stress. In general, repeated measurements across a stress assessment can describe how a hormone concentration varies over the observed period. A mean describes the central level for a set of measurements, while a standard deviation describes how dispersed participant values are around that mean. Those summaries are useful for characterizing a continuous outcome, but interpretation depends on the actual values, the number of observations contributing at each time, and the analysis approach.

The registry does not report cortisol means, standard deviations, changes over time, or inferential estimates. Nor does it report a defined contrast between time points. Thus, the endpoint description establishes what was measured and when, but the registry record does not provide numerical evidence to characterize the observed trajectory.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies the primary measure as continuous and specifies a mean with standard deviation. These are descriptive summaries. In general, a mean represents the arithmetic center of observed values, and a standard deviation describes the spread of values around that center. They answer different questions: the mean characterizes the typical level in the analyzed observations, while the standard deviation describes variability among observations. Neither tells readers how precisely the mean has been estimated; that requires an uncertainty measure such as a confidence interval.

What can repeated measurements show?

The outcome is scheduled at -20, +20, +30, +40, +50, +65, and +90 minutes in the late luteal phase. In general, repeated measurements can characterize how a continuous measure changes over an assessment period. A statistical analysis might describe values at each time, estimate an overall pattern, or compare selected times. These approaches answer different questions and can rely on different assumptions. The registry specifies timed measurements but does not report a statistical model, a defined time-point contrast, or the results from any such analysis. No particular approach should be assumed.

Repeated observations from the same participant are generally correlated rather than independent. General methods for repeated measures account for that within-person relationship when estimating changes or patterns. Treating correlated observations as independent can misstate uncertainty. The registry does not report whether repeated-measures methods were used, how within-person correlation was handled, or whether the outcome was analyzed separately at each scheduled time. The stated summary measure alone does not reveal the analysis method.

How should variability be understood?

The standard deviation describes dispersion in observed values, but a large or small value cannot be judged without the actual outcome values and context. In general, variability can arise from differences among participants, changes over time, measurement conditions, or other sources. The registry does not separate these sources. It also does not report the distribution of cortisol values or any diagnostics used to evaluate whether a chosen statistical model was suitable.

Some continuous outcomes may show over-dispersion or other departures from a model’s assumptions. In general, over-dispersion means the observed variability exceeds what a model expects. If relevant, this can affect standard errors and confidence intervals, so analysts may consider a model that accommodates the variability. This is a general statistical consideration, not a finding about this study: the registry provides no outcome data or model diagnostics with which to assess dispersion.

What does statistical uncertainty add?

A confidence interval is a general way to express uncertainty around an estimate. Its width depends on the data and the statistical model, among other factors. A narrow interval usually indicates greater precision than a wide interval, but precision is not the same as clinical importance. The registry gives no interval for cortisol. Without an estimate and an interval, readers cannot determine how precisely the primary outcome was characterized.

In general, a hypothesis test evaluates data relative to a specified null hypothesis and model. A p-value does not state the probability that a hypothesis is true, and it does not indicate the size of an effect. Interpretation should consider an estimate and its uncertainty, alongside the design and scientific context. The registry record does not report a hypothesis, test statistic, p-value, or model for the primary measure, so no test-based interpretation is available.

What do the planning assumptions mean?

Sample-size calculations are planning tools, not observations from a completed study. The stated planning assumptions describe a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect defined as a stated fraction of the observed effect. The assumptions also distinguish participants per arm for most outcomes from total events for time-to-event calculations. These are generic planning illustrations and are not the trial’s own design: this study is recorded as single group, with allocation NA, and the registry does not report a trial sample-size justification. Such calculations do not demonstrate observed power, and no planning count or underlying effect estimate is included in the registry record information available for this outcome.

For a valid interpretation of any numerical result, readers would need the outcome estimates, the analysis population, the model and its assumptions, and a measure of uncertainty. The registry record does not report those details for cortisol. The endpoint definition and general statistical principles explain what an analysis could address, but cannot stand in for the absent results or methods.

10. Multiplicity, Missing Data and Analysis Populations

The registry identifies one primary outcome measure, with cortisol assessed at several scheduled times. It does not report how the multiple time points were incorporated into a primary statistical test or whether any time points were designated as primary contrasts. When analyses examine multiple outcomes, time points, or comparisons, the chance of at least one false-positive result can increase. In general, a prespecified analysis plan and an appropriate multiplicity strategy help clarify how such testing is interpreted. The registry record does not report a multiplicity adjustment or a plan for addressing multiple assessments.

Missing-data information is also not reported in the registry record. There is no account of whether cortisol measurements were unavailable at any scheduled time, why any data might be missing, or how incomplete observations were handled. General approaches to missing data rely on assumptions about why observations are absent; those assumptions can influence estimates and uncertainty. Without details about missingness and the analysis method, readers cannot assess whether the reported analysis, if any, would represent all enrolled participants or a subset.

The registry records enrollment of 129, but does not report a primary-outcome analysis population or the number contributing data at each time. The safety record lists a separate denominator of 32 participants at risk; its relationship to enrollment is not reported in the registry record. It should not be treated as the denominator for the cortisol outcome.

The analysis population definitions are not reported in the registry record. The record does not say whether analyses included all enrolled participants, only participants with complete measurements, or another defined group. It also lists no analysis entries. These omissions prevent assessment of attrition, missing-data handling, multiplicity, and alignment between the planned outcome and any analysis population.

11. 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.

The safety record lists a Total group with 32 participants at risk for serious adverse events and 32 at risk for other adverse events. It records 0 serious adverse events, 0 other adverse events, and 0 deaths. These are the posted counts for the listed safety group. They should be read with their stated denominators rather than as counts covering all 129 enrolled participants, because the registry does not explain why the safety denominator differs from enrollment.

In general, an observed count of zero means that no event was recorded in the listed group for the specified category. It does not establish that an event is impossible or that there is no risk. The interpretation of an observed safety count depends on who was monitored, the observation period, event definitions, completeness of reporting, and the size and composition of the safety population. Those details are not reported in the registry record.

The registry lists no serious adverse event terms. The posted figures therefore provide limited descriptive safety information, not a complete characterization of safety for every enrolled participant or a comparison against a control group. The single-group design also offers no like-for-like control comparison of event counts.

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

The registry record is informative about the project’s aim and planned measurement. PHASE is described as evaluating neuroactive hormone trajectories across the menstrual cycle and responses to psychosocial stress in women with severe PMS identified as PMDD. Its primary measure is cortisol, expressed in ng/mL and summarized as a mean with standard deviation at timed assessments in the late luteal phase. The study is recorded as completed, with enrollment of 129.

Those details do not amount to a report of the primary result. Numerical cortisol values, variability estimates, comparisons across time, confidence intervals, and p-values are not reported in the registry record. No statistical analysis entries are listed. Readers therefore cannot determine from this record what cortisol concentrations were observed, how they varied, or how precise any estimated pattern might be.

The single-group design is important to interpretation. In general, observations collected within a group can describe that group’s measured responses, but they do not provide the same evidence as a randomized, like-for-like comparison. The registry lists no comparator and records allocation as NA. As a result, the design does not establish a contrast against a control condition, and the registry cautions that the arms are not a like-for-like control comparison. Any interpretation should remain within the limits of the design.

The enrollment total also should not be mistaken for the number included in the cortisol analysis. The registry does not report the analysis population, the number of available measurements, or missing-data handling. Separately, the safety record lists 32 participants at risk and zero events in the recorded categories; the relationship of that denominator to enrollment is not explained.

In short, the record documents the research question, design, endpoint schedule, and some safety counts. It does not provide the outcome evidence needed to characterize the cortisol response or its statistical uncertainty. The absence of a numerical result in the registry record is not evidence of a particular result in either direction.

13. Why This Trial Matters Statistically

This study raises statistical questions that are useful for clinical researchers because its outcome is a hormone measured repeatedly during a defined phase of the menstrual cycle and a psychosocial-stress assessment. The timing of measurements matters: a concentration at one scheduled time answers a different descriptive question from a pattern across the full assessment. Clear reporting of the time reference, analysis population, and statistical approach is essential for readers to understand what an estimate represents.

The project also illustrates the distinction between a study aim and a reported result. The registry describes interest in endocrine, autonomic, and subjective responses, but the listed primary outcome is cortisol and the registry does not include numerical cortisol results. A scientific rationale or endpoint definition cannot substitute for estimates and uncertainty. Transparent reporting allows readers to separate what was intended from what was observed and analyzed.

The single-group design is another important statistical feature. Without a like-for-like comparator, measurements can describe responses in the assessed group, but do not establish a randomized between-group contrast. That distinction is relevant when claims concern whether a condition, procedure, or exposure caused a difference. The registry itself identifies the absence of a randomized comparison, making the design constraint explicit.

Finally, the record shows why denominators and analysis populations matter. Enrollment is 129, whereas the safety group lists 32 participants at risk, and the connection between them is not reported. The registry also does not say how many participants contributed outcome data. Reporting participant flow and outcome-specific denominators would help readers understand data availability, missingness, and the scope of any estimate. These considerations apply broadly to interpretation of repeated-measures clinical research.

14. Limitations

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

Several limitations specific to interpretation of this registry entry follow from missing detail. The primary outcome is described, but numerical cortisol results and statistical estimates are not reported in the registry record. Without those results, the observed level, variability, and time course cannot be characterized. The registry also lists no analysis entries, so no reported model or inferential procedure can be evaluated.

The design is recorded as single group, with allocation NA and no like-for-like control comparison. This limits the kinds of contrasts the design can support. The registry does not describe a comparator, randomization process, or detailed arm procedures. The only listed intervention is an individualized laboratory test, classified as a procedure, and the arm description contains no further detail.

The registry does not report eligibility criteria, participant characteristics, the number contributing cortisol observations, or the relationship between total enrollment and the outcome analysis population. Missing-data extent, reasons, and handling are also not reported. These omissions prevent assessment of whether the measured participants represent the enrolled group or whether incomplete measurements may affect interpretation.

The timing is given as specified minute labels in the late luteal phase, with a description of one day between -1 to -6 days of the subsequent menstrual cycle. The record does not further clarify the minute reference point or provide a detailed collection protocol. It also does not state how measurements across time were modeled, whether selected contrasts were prespecified, or how multiple assessments were handled.

Finally, no trial-specific sample-size justification or statistical analysis plan is reported in the registry record. The planning assumptions described for sample-size illustrations are not the study design, and they do not replace a documented rationale for the enrolled sample. These limitations concern what can be concluded from the registry entry; they do not establish that additional information is unavailable elsewhere.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Premenstrual Hormonal and Affective State Evaluation (PHASE) Project — NCT03862469.
• Registry record last updated 2025-04-24; status last verified 2025-04.
• Results first posted 2025-04-24.
• 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.

18. Record Summary

The PHASE Project is a completed, single-group study sponsored by the University of Illinois Chicago. The registry records enrollment of 129, a start date of 2019-09-26, and primary completion on 2023-09-01. It describes a project assessing neuroactive hormone trajectories and responses to psychosocial stress in women with severe PMS identified as PMDD. The listed procedure is an individualized laboratory test.

The primary outcome is cortisol concentration in ng/mL, summarized as mean and standard deviation at scheduled times in the late luteal phase. The registry record does not report numerical cortisol results, statistical estimates, analysis methods, missing-data handling, or an outcome analysis population. It lists no analysis entries. The safety record lists 32 participants at risk, with 0 serious adverse events, 0 other adverse events, and 0 deaths; the relationship of that denominator to enrollment is not reported in the registry record.