Progesterone for Cannabis Withdrawal: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Progesterone for Cannabis Withdrawal (NCT03430050), a randomized early/phase 1 study. The primary outcome is Change in Salivary Progesterone Level.

2. Clinical Question

3. Trial Design

This was a randomized, quadruple-masked, parallel-group trial listed as EARLY PHASE1. The sponsor was Medical University of South Carolina. The record identifies progesterone and placebo as the interventions and reports enrollment of 8 participants. The study status is COMPLETED; the start date is 2017-10-16 and the primary completion date is 2018-04-04.

The intervention period lasted 5 days. The progesterone arm received Prometrium 200mg according to a schedule that changed across the period: one pill in the evening on day 1, one pill twice a day on days 2-4, and one pill on the morning of day 5. The placebo arm description gives the same schedule. The record does not describe adherence, dose changes, or treatment discontinuations.

The posted arm counts are 3 for progesterone and 5 for placebo. These are the numbers associated with the reported primary outcome, and they sum to the enrollment of 8. The intended allocation ratio, the randomization sequence method, and whether the posted counts represent all randomized participants or only those with outcome data are not reported in the registry record. The record labels masking as quadruple, but does not identify which roles were masked or describe the procedures used to maintain masking.

The registry lists 2 outcome measures and zero analyses. It does not report a sample-size justification for the trial, planned interim analyses, a statistical analysis plan, or details of analysis populations. The posted results are consequently limited: they give descriptive arm-level primary outcome statistics and safety counts, but no reported inferential comparison.

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 Change in Salivary Progesterone Level, measured over Day 1 and Day 5.

The primary endpoint is titled Change in Salivary Progesterone Level and is measured in pg/ml. Salivary progesterone was measured each day during the 5-day intervention. The change score was defined as the Day 5 level minus the Day 1 level. This makes the endpoint a within-participant difference across the intervention period rather than a single-day measurement.

In general, a change score can describe how an outcome shifts from an initial measurement to a later one. Comparing change scores between randomized groups can help distinguish the pattern in the intervention group from changes observed in the comparison group over the same period. That interpretation depends on an estimable between-group comparison and on the available measurements.

The posted results give a mean change of 237.9 pg/ml in the progesterone arm, with a standard error of 24.21, and a mean change of 97.87 pg/ml in the placebo arm, with a standard error of 14.67. These are descriptive arm-level results. The registry record says values were missing or not estimable for a two-arm comparison, so it does not provide a calculated between-arm estimate or uncertainty interval. The endpoint measures salivary progesterone change; it is not itself a direct measure of cannabis withdrawal symptoms or clinical benefit.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The endpoint is continuous: it records a numerical salivary progesterone change in pg/ml. The registry identifies the reported summary as a mean and its dispersion as a standard error. A mean describes the central value of observations in a group. A standard error describes the statistical uncertainty around an estimated mean under the calculation used; it is not the spread of individual participant measurements. The record does not provide the individual measurements or a fuller account of how the standard errors were calculated.

What would a between-arm estimate represent?

In general, a randomized trial's primary comparison aims to estimate the difference in outcome between assigned groups, using a prespecified method. For this endpoint, the outcome is the Day 5 salivary progesterone level minus the Day 1 level for each participant. An analysis could compare the groups' change scores, but the registry record does not state the planned model or method. It also states that values were missing or not estimable for a two-arm comparison, so no such estimate is posted. A difference should not be recreated from the two reported means when the record identifies the comparison as unavailable.

How should uncertainty be understood?

In general, a confidence interval is a range of estimates compatible with the observed data under a specified statistical procedure. Its width reflects precision: wider intervals indicate less precision, while narrower intervals indicate more precision. No confidence interval for the between-arm comparison is reported in the registry record. The arm-specific standard errors are not substitutes for that interval, because they describe uncertainty in separate group means rather than directly expressing uncertainty in the randomized contrast.

The posted outcome counts are 3 in the progesterone arm and 5 in the placebo arm. Small groups generally provide limited information, and estimates may be sensitive to the values of individual participants. This is a general statistical consideration, not a claim about any particular participant's influence in this trial. Participant-level values are not reported, so that influence cannot be assessed from the registry record.

What can be learned from a change score?

In general, a change score uses measurements taken at two times for the same participant. It can express movement from the starting measurement to a later measurement, and the trial's definition fixes the direction as Day 5 minus Day 1. A positive mean change therefore denotes an increase in the measured level on average within the group; a negative mean change would denote a decrease. The reported arm means are positive. The record does not provide the distribution of participant-level changes, nor does it report a model that adjusts for starting level or other variables.

Over-dispersion is a general concern when observed variability is greater than a statistical model expects. If a model assumes less variation than the data contain, uncertainty can be understated and inferential conclusions can be unreliable. The registry record does not report a dispersion assessment or a model for this trial, and the small posted counts limit the information available to evaluate distributional assumptions. No claim about over-dispersion in these data can be made from the arm summaries alone.

What is reported about planning?

The registry describes a planning illustration based on the observed effect, using a two-sided significance level of 0.05, equal allocation, and a normal approximation; the illustration is described as targeting a stated fraction of the observed effect. The record does not report specific planning sample sizes in the results summarized for the trial. Such a planning illustration is not an observed trial result and is not observed power. It does not establish that the trial was designed around that effect, and the trial's own sample-size justification is not reported in the registry record.

In general, power calculations use assumptions about the effect to be detected, variability, allocation, and the testing approach to estimate a sample size for a future or planned study. They do not measure the probability that a hypothesis is true, and they do not repair missing or non-estimable results after a study. The registry does not report the full assumptions or a trial-specific justification beyond the description of the planning illustration.

What inferential results are available?

The registry lists zero analyses and indicates that a two-arm comparison for the continuous endpoint was not estimable. It gives no test statistic, p-value, confidence interval, or adjusted analysis. The planned statistical approach, handling of repeated daily measurements, covariate adjustment, and approach to missing observations are not reported in the registry record. Without those details and a posted contrast, interpretation should remain descriptive: the arm means and standard errors characterize the reported summaries, but they do not constitute a formal test of a treatment effect.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("Progesterone", "Placebo")
n   <- c(3, 5)
m   <- c(237.86, 97.87)
sp  <- c(24.21, 14.67)
sd  <- sp * sqrt(n)      # standard errors converted to SDs
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Progesterone  3  237.860  41.933  133.693  342.027
CARM  Placebo  5  97.870  32.803  57.140  138.600

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 2 outcome measures, but secondary outcome results are not posted. It reports zero analyses. The record does not identify a family of statistical tests, a primary analysis model, or a procedure for controlling multiplicity. In general, multiplicity arises when several outcomes, time points, or analyses are tested; without a stated testing plan and reported analyses, it is not possible to assess how multiple comparisons were handled in this trial. No multiplicity adjustment is reported in the registry record.

The primary measure involved daily salivary progesterone measurements, while the reported change score uses Day 1 and Day 5. The record does not explain whether intermediate measurements were used in any analysis. It also does not report a missing-data plan, the number of missing measurements, or how any missing observations were handled. The note that values were missing or not estimable for a two-arm comparison signals that the comparison is unavailable, but does not describe the underlying reason or data pattern.

Analysis populations are not defined in the posted record. It is not stated whether results were based on all randomized participants, participants who completed the intervention, or participants with measurements at both endpoint times. Although the posted arm counts total 8, matching the enrollment, the record does not explain the population behind those counts. These omissions limit assessment of whether the analyzed participants differed from those enrolled, how missingness may have affected results, and whether the reported summaries follow an intention-to-treat or another analysis approach.

12. 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 results list 3 participants at risk in the progesterone arm and 5 in the placebo arm. The record reports zero serious adverse events in each arm, zero other adverse events in each arm, and zero deaths in each arm. No serious adverse event terms are listed.

These are counts recorded for the trial, not estimates of the chance of an adverse event in a broader population. The groups are small, and the registry record does not give event definitions, collection procedures, follow-up beyond the stated trial period, or additional detail on the types or timing of events. A reported zero means no events of that category were recorded in the posted results; it does not establish that the risk is absent. The safety counts should be read as descriptive observations from this trial, not as a definitive safety comparison between progesterone and placebo.

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

The registry record documents a randomized comparison of progesterone and placebo over 5 days, with change in salivary progesterone as the primary outcome. The posted mean change was 237.9 pg/ml in the progesterone group and 97.87 pg/ml in the placebo group. The corresponding standard errors were 24.21 and 14.67. These summaries describe the observed arm-level results for the reported endpoint.

The record also states that values were missing or not estimable for a two-arm comparison. It therefore supplies no formal estimate of the between-group effect and no confidence interval or p-value for that contrast. The means alone cannot establish whether the groups differed beyond sampling variation. They also cannot be treated as evidence that progesterone does or does not affect cannabis withdrawal, because the primary outcome is salivary progesterone change rather than a withdrawal symptom measure.

The trial enrolled 8 participants, and the posted outcome counts were 3 and 5. This is a limited amount of data for estimating group-level effects. The registry does not report a trial-specific sample-size justification, analysis plan, missing-data method, or participant-level results that could clarify the precision and robustness of the findings.

The safety record reports no serious adverse events, other adverse events, or deaths in either group. Those counts describe the posted observations and do not establish that adverse events cannot occur or support a definitive safety comparison. Overall, the record provides descriptive biological outcome summaries and safety counts from a small completed study, while leaving the primary between-arm question without an estimable posted result.

14. Why This Trial Matters Statistically

This trial is statistically notable because it combines random assignment and masking with a very small enrolled group and an unavailable primary between-arm comparison. Randomization is intended, in general, to support a fair comparison of assigned groups. But the presence of randomization does not by itself guarantee that a useful contrast can be estimated when the available data do not support the comparison.

The record makes an important distinction between descriptive summaries and inferential results. Arm-specific means and standard errors can describe the recorded outcome, but they do not answer the randomized comparison question on their own. A treatment-group estimate with an uncertainty measure would ordinarily help readers judge both the direction and precision of a contrast. Neither is reported for this endpoint because the comparison was not estimable.

The small arm counts also underline why uncertainty matters. In general, estimates from small groups can be sensitive to a small number of observations, and the data may offer limited ability to characterize variability. The registry's stated planning illustration is not evidence of observed power and is not a substitute for a trial-specific design justification. A planned calculation and an analysis of observed results answer different questions.

Finally, the endpoint is a salivary progesterone measure, while the study background concerns cannabis withdrawal. Keeping the measurement distinct from the broader clinical motivation prevents overinterpretation. The record shows a biological outcome and safety counts, but does not post an estimable group comparison or secondary outcome results. This distinction is useful when evaluating what a small early-phase study can describe versus what it can establish.

15. 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 most direct limitation is that the registry reports the primary continuous outcome as not estimable for a two-arm comparison. No between-group estimate, confidence interval, or p-value is available. The reported means and standard errors therefore support a descriptive reading only.

Enrollment was 8, with posted outcome counts of 3 for progesterone and 5 for placebo. Such small groups offer limited information about the distribution of outcomes and the stability of group summaries. The record does not provide participant-level values or describe whether the outcome counts reflect all randomized participants or a subset with complete measurements.

The endpoint is change in salivary progesterone from Day 1 to Day 5. It is not a direct measure of cannabis withdrawal. Although the record's background motivates the study in relation to withdrawal, no secondary outcome results are posted, and the registry lists zero analyses. The relationship between the primary biological measure and any clinical withdrawal outcome cannot be evaluated from the posted results.

Further limitations are gaps in reporting. The randomization method, masking procedures, analysis plan, missing-data handling, analysis populations, adherence, and trial-specific sample-size justification are not reported in the registry record. These details would help readers assess conduct and analysis choices, but cannot be inferred from the design labels or the arm summaries. The safety counts are also limited by the small enrollment and the lack of additional event detail.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Progesterone for Cannabis Withdrawal — NCT03430050.
• Registry record last updated 2019-05-22; status last verified 2019-04.
• Results first posted 2019-05-22.
• 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.

19. Record Summary

NCT03430050, titled Progesterone for Cannabis Withdrawal, is listed as a completed EARLY PHASE1 randomized, quadruple-masked, parallel-group trial sponsored by Medical University of South Carolina. Enrollment was 8. The listed intervention was Prometrium 200mg for 5 days, compared with placebo on the stated schedule.

The primary endpoint was change in salivary progesterone from Day 1 to Day 5, measured in pg/ml. The reported mean changes were 237.9 for progesterone and 97.87 for placebo, with standard errors of 24.21 and 14.67. A two-arm comparison was not estimable, and no inferential comparison is reported. The safety record lists zero serious adverse events, zero other adverse events, and zero deaths in both groups. Secondary outcome results are not posted.