D Vitamin Intervention in VA: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for D Vitamin Intervention in VA (NCT01375660), a randomized na study. The primary outcome is Oral Glucose Insulin Sensitivity (OGIS).

2. Clinical Question

3. Trial Design

This completed trial, listed as NCT01375660, is titled D Vitamin Intervention in VA; its official title is Vitamin D Deficiency and Treatment in Male Veterans at Risk for Diabetes. The US Department of Veterans Affairs is the sponsor. The registry record lists a start date of 2011-05 and primary completion in 2013-10, with enrollment of 205. Phase is listed as NA.

The design is described as randomized, triple-masked, and parallel-group. The two listed arms were placebo and 50K vitamin D2, each taken as one capsule weekly. The registry record does not report the randomization sequence, allocation ratio, masking procedures, or whether any treatment doses beyond those listed were assigned. Equal allocation appears among the assumptions for the planning illustration, but the trial’s original allocation plan is not reported in the registry record.

The study summary describes African American male veterans at risk for diabetes and veterans with newly diagnosed type 2 diabetes, with the work conducted at a Veterans Administration Medical Center in Chicago. The listed conditions include impaired fasting glucose, impaired glucose tolerance, and vitamin D insufficiency. More detailed eligibility criteria and the enrolled participants’ baseline characteristics are not reported in the registry record.

The primary endpoint was change in OGIS at 12 months. The registry lists secondary outcomes that include change in HbA1c, insulin sensitivity by the Matsuda composite, insulinogenic and C-peptidogenic indices, and incident diabetes. The registry record does not give the trial’s original sample-size justification or a detailed statistical 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.

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 Oral Glucose Insulin Sensitivity (OGIS), measured over 12 months.

The primary endpoint is change in oral glucose insulin sensitivity, abbreviated OGIS, from baseline to 12 months. It is defined as the 12-month OGIS value minus the baseline value and expressed in ml/min/m^2 of body surface area. OGIS is an index calculated using glucose and insulin measurements from an oral glucose tolerance test. The registry description states that a higher index means higher insulin sensitivity; it also explains that low insulin sensitivity corresponds to high insulin resistance and high risk of type 2 diabetes mellitus.

A change score expresses how the measure differed from its baseline value over the stated follow-up period. In this trial, the arm means therefore describe average changes, rather than the average OGIS level at the 12-month visit alone. Comparing the arms addresses whether their mean changes differed. A positive between-arm difference in change indicates a higher average change in the vitamin D2 arm than in the placebo arm; interpretation still depends on the endpoint definition, uncertainty, and analysis used.

OGIS is used as a physiological measure of insulin sensitivity. It is not itself a count of diabetes diagnoses. The registry record lists incident diabetes as a secondary outcome, distinct from this primary continuous endpoint. The registry does not report a clinical threshold for a meaningful OGIS change or explain why this endpoint was selected over the other listed measures.

7. Results Posted in the Registry

• 50K Vitamin D2: mean 7.80 versus -16.00 on control; difference 23.80 (95% CI 7.13 to 40.47), standardized effect d = 0.43; z-test p = 0.005.

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 in HbA1c From Baseline at 12 Months

• 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:
  • 50K Vitamin D2: mean -0.01 versus 0.01 on control; difference -0.02 (95% CI -0.08 to 0.04), standardized effect d = -0.10; z-test p = 0.501.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 50K Vitamin D2 and the control. The interval gives the range of effects that remain compatible with the data.

Insulin Sensitivity by Matsuda Composite

• 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:
  • 50K Vitamin D2: mean 0.44 versus 0.13 on control; difference 0.31 (95% CI -0.13 to 0.75), standardized effect d = 0.21; z-test p = 0.166.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 50K Vitamin D2 and the control. The interval gives the range of effects that remain compatible with the data.

Insulinogenic Index-30

• 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:
  • 50K Vitamin D2: mean 0.26 versus -0.03 on control; difference 0.29 (95% CI -0.03 to 0.61), standardized effect d = 0.27; z-test p = 0.074.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between 50K Vitamin D2 and the control. The interval gives the range of effects that remain compatible with the data.

The posted secondary results cover a mix of glycemic and insulin-related measures. Across the reported continuous secondary outcomes, the estimated differences vary in direction and size, and the registry-reported p-values do not show a uniform pattern of statistical evidence. This overall picture is not a consistent repetition of the primary endpoint finding. The registry lists additional secondary outcomes, including the C-peptidogenic index and incident diabetes, but their numerical results are not reported in the registry record.

Secondary measures can add context because they assess related but distinct aspects of glucose regulation. They do not measure the same quantity as OGIS, and a result on one measure does not necessarily imply a similar result on another. The primary result concerns change in an insulin-sensitivity index at 12 months; secondary outcomes include other physiological measures and an event outcome. These endpoints should be interpreted according to their individual definitions and analyses.

Unadjusted secondary results carry less weight when several outcomes are examined because the chance of at least one apparently unusual finding can increase across multiple comparisons. In general, multiplicity procedures can account for a family of tests, but the registry record does not report whether any adjustment was planned or used. It also does not describe which secondary outcome was considered most important or how the outcomes were grouped for testing.

The secondary findings are therefore best treated as additional, exploratory context rather than independent confirmation of the primary result. The registry record does not report enough information about multiplicity or analysis planning to establish how confirmatory each secondary comparison was intended to be.

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

• Change in HbA1c From Baseline at 12 Months
• Insulin Sensitivity by Matsuda Composite
• Insulinogenic Index-30
• C-Peptidogenic Index-30
• Incident Diabetes

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: each participant’s OGIS change is represented by a numerical value, and the registry reports group means and standard deviations. A mean describes the center of a group’s values, while a standard deviation describes their spread. The means alone do not reveal how individual values are distributed, and the standard deviations do not show whether the distribution is symmetric or contains outliers.

What does a difference in means describe?

The recalculated mean difference compares the vitamin D2 group’s mean change with the placebo group’s mean change. Its sign depends on the order of subtraction; the posted calculation is vitamin D2 versus placebo. The positive estimate means the average change was higher in the vitamin D2 group. This is a comparison of group averages, not a statement that each participant experienced that difference.

The reported analysis method is ANOVA. In general, analysis of variance compares group means while accounting for variation within groups. The registry record does not report the precise ANOVA specification, any covariates, transformations, or adjustments. It is therefore not possible to determine from the record whether the reported model differs from a simple comparison of the posted means in any particular way.

What does a p-value convey?

In general, a p-value describes how compatible the observed data are with a specified null hypothesis, assuming the analysis model and its assumptions. A smaller p-value indicates less compatibility with that null under those conditions; it is not the probability that the null hypothesis is true, nor does it measure the size or clinical importance of an effect. The registry’s primary ANOVA result is p = 0.026. The unadjusted recalculation gives p = 0.005. Since these values come from different analyses and the ANOVA details are not reported, they should not be collapsed into one result.

Why do confidence intervals matter?

In general, a confidence interval expresses uncertainty about an estimated effect under a specified statistical procedure. It shows a range of values that are compatible with the data and method, rather than only a single estimate. The recalculated interval for the primary mean difference runs from 7.133 to 40.47. The registry record does not state the interval’s confidence level or report an interval for the sponsor’s ANOVA comparison. As a result, the interval’s reported bounds can be described, but the record does not identify its nominal coverage level.

Why can the summary-statistic recalculation differ?

A recalculation from group means, standard deviations, and sample sizes is a simple unadjusted comparison. It does not reproduce an analysis that may use additional model terms or participant-level information. The record identifies ANOVA but does not supply its full specification or the data used for it. Differences between an unadjusted recalculation and a registry-reported analysis can arise when the analyses use different information or assumptions, but the reason for this particular difference is not reported in the registry record.

Why does variation matter?

The spread of participant outcomes affects how precisely a group mean and a difference between group means can be estimated. When individual outcomes vary widely, averages can be uncertain even when group sizes are substantial. In general, departures from the assumptions used by a simple mean comparison, such as unusually skewed values or unequal variability, may affect its performance. The registry record does not report diagnostic checks or the distributions of OGIS changes, so those features cannot be assessed from the posted summaries.

The posted analyses do not report enough information to establish whether the primary comparison was adjusted for multiple outcomes or whether a particular analysis population was used. The record also does not describe how missing outcome measurements were handled. Those omissions limit reconstruction of the statistical analysis beyond the results and methods explicitly reported.

11. Confidence Intervals and Precision

The recalculated primary difference is 23.8, with reported interval bounds of 7.133 and 40.47. The interval is centered on an estimate of the between-group difference, but it leaves uncertainty about the size of that difference. Its lower and upper bounds both lie above zero, so the interval from this unadjusted calculation does not include no difference. This description applies to the recalculation and does not replace the registry-reported ANOVA result.

In general, confidence intervals combine an estimate and information about its uncertainty. A narrow interval indicates greater precision than a wide interval on the same scale, while an interval that spans a broad range allows more uncertainty about the effect’s magnitude. An interval is not a guarantee that the true effect lies within its bounds. The confidence level for the recalculated interval is not reported in the registry record, so it should not be assigned a level that the record does not specify.

The primary group standard deviations, 55.83 and 56.02, indicate considerable spread in OGIS changes around the group means. This spread helps explain why the precision of an estimated difference depends on both the variability and the number of participants analyzed. The endpoint summaries do not show individual data, and the registry record does not report the distribution of changes or a confidence interval for each arm mean.

The registry’s ANOVA result is reported with a p-value but without an effect estimate or confidence interval. Consequently, its precision cannot be evaluated from a reported interval for that analysis. The recalculated interval provides a precision description for the simple unadjusted comparison only; it should not be presented as the interval for the ANOVA model.

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 figures are participants per arm for the continuous outcomes in this trial. They are not total event counts; the event-count convention applies to time-to-event planning, and these posted outcomes are continuous measures. The assumptions listed for the illustration are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and an effect to detect set to the stated fraction of the observed effect. The trial’s own original sample-size assumptions and justification are not reported in the registry record.

The 80% power column describes the number of participants per arm that the planning calculation estimates would be needed to have an 80% chance of detecting the specified effect, if the assumptions and effect were correct. The 90% column uses a higher target chance of detecting that effect and therefore generally calls for more participants under the same assumptions. These are design-planning concepts, not guarantees about a future study’s result.

Rows for a smaller fraction of the observed effect require more participants per arm. Smaller effects are harder to distinguish from random variation at a fixed sample size, so the planning calculation increases the required size as the target effect shrinks. The illustration uses the observed effect as its reference, but the true effect in another study could differ. The figures are not observed power and do not indicate the probability that the completed trial’s result is true.

Use the figures to understand how sample-size requirements depend on an assumed effect and target power, not as a reconstruction of the trial’s protocol. No original design calculation or rationale is reported in the registry record.

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 = 23.800; pooled standard deviation σ = 55.926.
2. n = 2 × (1.96 + 0.842)² × 55.926² / 23.800² = 86.7, rounded up to 87 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 <- 23.8                      # observed difference in means
sigma <- 55.9256362403584                     # 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(1375660)
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 = 87 (80% power), 117 (90% power)
 75% of observed effect: n per arm = 155 (80% power), 207 (90% power)
 50% of observed effect: n per arm = 347 (80% power), 465 (90% power)
power.t.test: 87.6 
Simulated power at n = 87 per arm: 0.793 (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 registry reports an ANOVA comparison for the primary endpoint with p = 0.026. The simple unadjusted recalculation from the posted arm means, standard deviations, and participant counts gives a mean difference of 23.8, an interval from 7.133 to 40.47, and p = 0.005. The recalculation is not a substitute for the registry-reported analysis; it is a separate comparison based on summary statistics.

The record does not give the ANOVA model specification, covariates, analysis population, or other details needed to reproduce that result. It is therefore not possible to determine why the p-values differ or whether the ANOVA used information not captured in the posted summaries. The registry record does not provide a sponsor-reported estimate and confidence interval for the primary ANOVA comparison, either. The unadjusted interval should not be attributed to the ANOVA.

Both analyses compare the same named groups and outcome, but the method and reported outputs are not identical. The p-values describe evidence under their respective analyses; they do not quantify the effect’s importance. The registry reports no discrepancy flag, but that does not supply the missing model details. Readers should keep the registry-reported ANOVA result distinct from the recalculated summary-statistic result when describing the findings.

15. Multiplicity, Missing Data and Analysis Populations

The registry lists multiple outcomes and analyses, including the primary OGIS endpoint and several secondary measures. When multiple hypotheses are tested, the chance of at least one small p-value can rise even if none of the underlying effects is real. In general, a prespecified multiplicity strategy can control or otherwise address this issue. The registry record does not report whether a multiplicity adjustment was planned or applied, what family of tests it would cover, or how the primary and secondary outcomes were ordered.

The reported primary comparison uses ANOVA, but the detailed statistical plan is not reported in the registry record. Specifics such as model terms, assumptions, handling of baseline values, and the intended analysis population are not described. The registry does not report whether interim analyses were conducted or whether any stopping rules were used. Their absence from the record should not be interpreted as proof that they did or did not occur.

The outcome summaries give analyzed group counts of 86 for placebo and 87 for vitamin D2, while the overall enrollment is 205. The registry record does not explain participant flow, reasons for any difference between enrollment and these outcome counts, or whether all randomized participants contributed data. It does not report the amount or pattern of missing outcome data, the method used to handle missingness, or sensitivity analyses.

Analysis populations such as intention-to-treat or per-protocol are not identified in the registry record. The record also does not state whether the primary analysis followed the randomized assignment regardless of treatment adherence. Without these details, readers cannot assess the role of missing observations, protocol deviations, or analysis-population choices in the reported comparison.

These gaps constrain interpretation of both the nominal p-values and the completeness of the endpoint analysis. They do not establish that a particular bias occurred; they mean the registry record does not provide the information needed to evaluate these issues fully.

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 0% reporting threshold.

The registry reports zero serious adverse events among 86 participants at risk in the placebo group and among 87 participants at risk in the 50K vitamin D2 group. It also reports zero other adverse events among those same at-risk counts. These entries describe the adverse-event counts posted for the registry record.

The registry does not list serious adverse-event terms, and deaths are not reported in the registry record. The zero counts should be read as the entries recorded for this trial, not as evidence that adverse events are impossible or that the intervention has no safety risks. A trial’s ability to identify uncommon events depends on its size, follow-up, and ascertainment; the registry record does not provide enough information to evaluate those features in detail.

These safety figures do not establish a comparison of risk beyond the reported counts. The record does not provide further event descriptions, severity categories, timing, relatedness assessments, or information about how adverse events were collected. They should be interpreted as limited registry summaries rather than a comprehensive safety assessment.

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

The results describe a difference between group averages in change in OGIS over 12 months. The registry-reported ANOVA gives p = 0.026, while a simple unadjusted recalculation from the posted summaries estimates a mean difference of 23.8, with an interval from 7.133 to 40.47 and p = 0.005. The discrepancy between these analysis outputs cannot be resolved from the registry record because the detailed ANOVA model is not reported.

The positive difference in the recalculation means the average OGIS change was higher in the vitamin D2 group than in the placebo group. The endpoint description associates a higher OGIS index with higher insulin sensitivity. This is a statistical description of the measured endpoint, not a conclusion about each participant or a guarantee about any individual outcome. The registry does not report a threshold for a clinically meaningful change.

OGIS is an index derived from glucose and insulin measurements during an oral glucose tolerance test. It is not the same as incident diabetes, which is listed as a secondary outcome. The registry record does not report numerical results for every listed secondary outcome, so the primary endpoint alone cannot answer all questions about diabetes-related outcomes.

Statistical evidence and clinical importance are different questions. A p-value does not show how important an effect is, and an interval does not establish that a result will apply in other populations or settings. The study description concerns male veterans, with African American male veterans specified in the summary. Generalizability beyond that description cannot be established from these results alone.

The record also leaves important analytical details unreported, including missing-data handling, the analysis population, and multiplicity procedures. Those omissions limit how fully the robustness of the findings can be judged. The posted data describe the trial’s reported comparisons; they do not by themselves establish a broader treatment recommendation or certainty about outcomes beyond the measured endpoints and follow-up.

18. Why This Trial Matters Statistically

This trial illustrates why the method attached to a reported result matters. The registry gives an ANOVA p-value for the primary comparison, while a direct unadjusted recalculation from the group summaries produces a different p-value and an interval estimate. Those results answer related questions but arise from analyses that may not use the same information. Since the ANOVA details are not reported, the distinction cannot be fully resolved from the record.

It also illustrates the value of reading effect estimates alongside p-values. The estimated mean difference conveys the direction and scale of the comparison, while an interval conveys uncertainty about its magnitude. A p-value alone cannot describe either the size of a difference or its practical relevance. The registry does not state a clinical threshold for OGIS change, so statistical evidence cannot be translated into a judgment about clinical importance using this record alone.

Variation is another key feature. The group standard deviations indicate substantial spread around the mean changes. In general, an average can conceal considerable differences among participants, making it important not to mistake a group result for a uniform individual response. The registry record does not provide participant-level distributions that would allow a more detailed assessment.

Finally, planning illustrations show how assumptions about effect size and desired power influence required sample sizes. They are not the original trial design calculation and should not be confused with observed power. Taken together, these points make the trial useful for understanding the interpretation of a registry result while also showing why analysis details, endpoint context, and uncertainty are essential.

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 information about the trial’s conduct and statistical plan. It does not report detailed eligibility criteria, baseline characteristics, adherence, protocol deviations, or the randomization and masking procedures. These omissions restrict assessment of how closely the enrolled participants and delivered interventions matched the study description.

For the primary endpoint, the registry reports an ANOVA p-value but does not provide the model specification, an effect estimate from that analysis, or its confidence interval. The unadjusted recalculation is based on group summary statistics and should not be treated as a reconstruction of the ANOVA. The reason for the difference between the reported and recalculated p-values is not reported in the registry record.

The outcome counts are smaller than the total enrollment, but participant flow and reasons for the difference are not reported in the registry record. Missing-data amounts and handling, the analysis population, and sensitivity analyses are also not reported. These gaps make it difficult to determine how complete the endpoint analysis was or how robust it is to assumptions about missing outcomes.

The record does not report a multiplicity strategy, the trial’s original sample-size justification, or whether interim analyses occurred. Some listed secondary outcomes have no numerical results reported in the registry record. The safety summary provides zero serious and other adverse events in the recorded groups, but does not give event descriptions or further ascertainment details. These limitations reflect what is unavailable in the registry record; they do not by themselves show that a particular problem occurred.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: D Vitamin Intervention in VA — NCT01375660.
• Registry record last updated 2015-03-06; status last verified 2015-02.
• Results first posted 2015-02-05.
• 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

NCT01375660 is a completed, randomized, triple-masked, parallel-group trial sponsored by the US Department of Veterans Affairs. The registry lists enrollment of 205 and compares weekly placebo with weekly 50K vitamin D2. The study summary describes African American male veterans at risk for diabetes or with newly diagnosed type 2 diabetes.

The primary outcome was change in OGIS at 12 months. The registry reports an ANOVA p-value of 0.026; an unadjusted recalculation gives a mean difference of 23.8, with an interval from 7.133 to 40.47 and p = 0.005. The ANOVA details needed to explain the difference are not reported in the registry record. The record also leaves important details about missing data, analysis populations, multiplicity, and the original sample-size plan unreported.