iCare Stress Management e-Training for Dementia Family Caregivers: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for iCare Stress Management e-Training for Dementia Family Caregivers (NCT01378195), a randomized phase 2 study. The primary outcome is Perceived Stress Scale.

2. Clinical Question

The registry record identifies this as a phase 2 randomized study with a parallel design and no masking. The central statistical comparison is the difference in the mean Perceived Stress Scale score between the two assigned groups at the stated assessment time. The posted summary reports a mean of 15.83 for the CBT-based group and 16.41 for the educational/resource group, with a mean difference of 0.58 for educational/resource materials relative to CBT-based treatment. The confidence interval extends from -1.785 to 2.945, and the unadjusted p-value is 0.631. Since higher scores indicate worse stress, the positive point estimate indicates a higher average score in the educational/resource group, while the interval also includes differences in the opposite direction. These data describe the observed comparison; the registry record does not report an adjusted or otherwise sponsor-reported analysis.

3. Trial Design

This was a completed phase 2 randomized, parallel-group trial with no masking. The registry record lists enrollment of 150. The study began in 2011-05 and reached primary completion in 2012-07. The record describes a home-based program and says participants could live anywhere in the United States; it does not describe face-to-face meetings.

The two behavioral interventions were a CBT-based program and an educational/resource materials program. Both arm descriptions refer to a video, workbook, and website. The broader program description includes a free DVD, printed materials, a resource website, and free access to final online resources for 1 year after program completion. The registry record describes program development by Photozig and Stanford University, with funding from the National Institute on Aging.

The primary outcome was caregiver perceived stress assessed at 3 months. The posted primary outcome summaries include 46 participants in the CBT-based group and 57 in the educational/resource group. The registry record does not explain the relationship between those outcome counts and the enrollment figure. It also does not report the original sample-size rationale, planned analysis population, missing-data approach, allocation sequence procedure, or details of how adherence was assessed. The record states that masking was absent but does not provide further detail about who knew assignments.

Two additional outcomes are listed: the Revised Memory and Behavior Problems Checklist and Perceived Quality of Life. Both are described as continuous measures assessed at 3 months. The registry record has no reported analyses for these outcomes, so the posted arm summaries and simple unadjusted comparisons should not be mistaken for a complete account of the trial's prespecified 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: Participant assignment to group was random.

Overall Study

Reasons for not completing this period:

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 Perceived Stress Scale, measured over 3 months.

The primary endpoint is the Perceived Stress Scale score at 3 months. The registry description says the instrument contains 10 items assessing overall appraisals of stress during the past month and refers to the caregiver. It is measured in units on a scale, with a minimum score of 0 representing the best value and a maximum score of 40 representing the worst value. Higher values therefore indicate worse stress.

A continuous score can retain information across the scale rather than reducing each caregiver's experience to a yes-or-no category. Comparing group means provides a summary of average scores in the randomized groups. The standard deviation describes how spread out individual scores are around each group mean; it is not a confidence interval for the mean and does not show the range of every participant's score.

Perceived stress is the outcome identified as primary in the registry record, making it the central reported comparison for this analysis. The measure's timeframe is the past month, while the assessment is specified at 3 months. The registry record does not report a threshold defining a clinically important difference, nor does it explain how the score was selected as the primary outcome. The results should therefore be read in the scale's stated direction and units, without assuming a particular threshold for importance.

7. Results Posted in the Registry

• Educational/Resources Materials: mean 16.41 versus 15.83 on control; difference 0.58 (95% CI -1.78 to 2.94), standardized effect d = 0.09; z-test p = 0.631.

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.

Revised Memory and Behavior Problems Checklist

• 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:
  • Educational/Resources Materials: mean 0.91 versus 0.83 on control; difference 0.08 (95% CI -0.19 to 0.35), standardized effect d = 0.11; z-test p = 0.556.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Educational/Resources Materials and the control. The interval gives the range of effects that remain compatible with the data.

Perceived Quality of Life

• 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:
  • Educational/Resources Materials: mean 6.31 versus 6.34 on control; difference -0.03 (95% CI -0.68 to 0.62), standardized effect d = -0.02; z-test p = 0.928.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Educational/Resources Materials and the control. The interval gives the range of effects that remain compatible with the data.

The two secondary outcomes are the Revised Memory and Behavior Problems Checklist and Perceived Quality of Life, both assessed at 3 months. Across these outcomes, the posted comparisons do not show a clear separation between the randomized groups: each unadjusted confidence interval includes zero. The pattern is broadly consistent with the uncertainty in the primary comparison, rather than providing a distinct, precise contrast between the programs.

These secondary results can add context by showing whether the observed pattern is confined to the primary measure or appears across other reported measures. They do not independently resolve the primary result's uncertainty. The registry record reports no sponsor analyses for either secondary outcome, and the simple comparisons are unadjusted calculations from the posted group summaries.

Multiple outcomes create a multiplicity concern: when several hypotheses are examined, interpreting each unadjusted result as if it were the sole planned test can overstate the strength of evidence. The registry record does not state whether the secondary outcomes were confirmatory, exploratory, or part of a prespecified testing hierarchy. It also does not report a multiplicity adjustment. For that reason, secondary comparisons should generally carry less weight than the designated primary outcome and should be treated as descriptive rather than conclusive.

The direction and apparent size of a mean difference should also be interpreted according to each measure's scoring conventions. The registry description does not provide comparable detail about the direction or scale interpretation of the secondary measures. This makes it especially important not to infer that a difference is favorable solely from whether its numerical value is higher or lower. Taken together, the secondary results add limited evidence beyond the primary comparison and leave important interpretive questions unresolved.

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

• Revised Memory and Behavior Problems Checklist
• Perceived Quality of Life

9. Statistical Interpretation

10. Statistical Methods Explained

The primary result compares a continuous score between two randomized groups. The summary uses the mean in each group and reports their mean difference, with the educational/resource group compared against the CBT-based group. The group means are 15.83 and 16.41, respectively, and the mean difference is 0.58. The direction matters: a positive difference means a higher mean in the educational/resource group, and the endpoint description says higher scores represent worse stress.

What the means and standard deviations describe

A mean is the arithmetic average of participant scores in a group. It gives a compact description of the group's center, but it does not show the distribution of all scores. The standard deviations, 5.07 for the CBT-based group and 7.15 for the educational/resource group, describe how much scores vary around those averages. A larger standard deviation indicates greater spread in the observed scores. Standard deviation is distinct from the standard error, which describes the uncertainty of an estimated mean.

The posted summaries report 46 participants for the CBT-based primary outcome and 57 for the educational/resource primary outcome. Group counts matter because estimates based on different amounts of information can have different precision. The registry record does not explain why these outcome counts differ from the stated enrollment or whether all randomized participants were included in an analysis.

Mean difference and confidence interval

The mean difference is the estimated separation between the group averages, expressed in the outcome's units. Here the stated comparison is educational/resource materials relative to CBT-based treatment. A confidence interval describes uncertainty around that estimate under the statistical method used. In general, a wider interval indicates less precision, while a narrower interval indicates more precision. The primary interval extends from -1.785 to 2.945. Because it crosses zero, it includes the possibility of no mean difference and values favoring either direction of the comparison.

A confidence interval is not a range containing a fixed proportion of individual participant scores. Nor does it mean that every value in the interval is equally plausible. It is an interval estimate whose interpretation depends on the method and assumptions used. The registry record does not report a sponsor-conducted confidence-interval analysis; the posted comparison is a simple unadjusted recalculation from group summaries.

How to read the p-value

The unadjusted p-value for the primary comparison is 0.631. In general, a p-value describes how unusual data at least as incompatible with a null hypothesis would be if that hypothesis and the statistical model's assumptions were true. It is not the probability that the null hypothesis is true, and it does not measure the size or clinical importance of a difference. A p-value should be considered alongside the estimate, interval, study design, and analysis details.

The word unadjusted is important because the registry lists more than one outcome. The reported p-value is not identified as accounting for multiple comparisons. The record does not report whether a multiplicity procedure was planned or applied. The p-value also does not resolve uncertainty about outcome availability, the analysis population, or the original analysis plan.

What the planning calculations represent

The sample-size illustrations use the observed effect as a reference and consider stated fractions of that effect. Their assumptions are a two-sided significance level of 0.05, equal allocation between groups, and a normal approximation. Such calculations illustrate how sample size can depend on the effect a future study aims to detect and on the chosen power target. They are not a report of the original trial's design calculation; the original design assumptions and sample-size justification are not reported in the registry record.

These illustrations are separate from the observed comparison. They do not tell how likely the completed trial was to find a result, and they do not change the uncertainty in the posted estimate. The registry record provides no sponsor-reported statistical analyses, and it does not supply details of adjustment, missing-data handling, or analysis populations. Those limitations should remain explicit when interpreting the means, interval, p-value, and planning illustrations.

11. Confidence Intervals and Precision

The primary mean difference is 0.58 units, with a confidence interval from -1.785 to 2.945. The interval crosses zero and covers both negative and positive differences. With educational/resource materials as the first group in the stated subtraction, negative values would indicate a lower average score in that group, while positive values indicate a higher average score. Since higher scores represent worse stress, the interval does not isolate one direction of difference.

The interval is more informative than the point estimate alone: the estimate of 0.58 is not known with certainty, and the posted data remain compatible with a range of effects. The interval's width indicates that the comparison is not precise enough to sharply distinguish a small difference from no difference or from a difference favoring the other group. The registry record gives no clinically important difference threshold, so the interval cannot be classified against a stated clinical margin.

In general, confidence intervals quantify uncertainty in an estimated effect under a statistical method and its assumptions. They do not describe the spread of individual scores, which is represented by the standard deviations, and they do not establish equivalence merely because they contain zero. The posted interval is an unadjusted recalculation from summary statistics, rather than a sponsor-reported adjusted interval. The registry record does not report the original analysis method, missing-data strategy, or analysis population, all of which would help contextualize precision.

The outcome summaries include 46 participants in the CBT-based group and 57 in the educational/resource group. The registry record does not explain how those counts arose from the stated enrollment of 150. That reporting gap limits assessment of how representative the analyzed participants are of the randomized groups and whether missing outcomes could affect the estimate.

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 entries are participants per arm, not total events. They use the observed effect as a reference, considering planning for 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. The stated assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The registry record does not report the original trial's sample-size justification or design assumptions, so these illustrations should not be mistaken for the enrollment target's rationale.

The 80% power column gives the estimated participants per arm for a future study to have an 80% probability of detecting the selected effect under the stated assumptions, if that effect is the true one. The 90% power column gives the corresponding planning estimate for a 90% probability. These are planning targets, not guarantees: actual study results also depend on the true effect, variability, data availability, and whether the assumptions hold.

Smaller effects require more participants to detect with the same power and significance level. Thus the planning scenario for 50% of the observed effect requires more participants per arm than planning for the full observed effect. The posted calculations vary substantially by outcome because the observed effects and variability differ. They are not observed power, and they do not indicate whether the completed trial's result is true or important. The registry record does not report the study's original sample-size calculation, so the illustrations cannot establish whether the trial was planned to detect a particular clinically meaningful difference.

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 = 0.580; pooled standard deviation σ = 6.309.
2. n = 2 × (1.96 + 0.842)² × 6.309² / 0.580² = 1,857.1, rounded up to 1,858 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 <- 0.58                      # observed difference in means
sigma <- 6.30855187286855                     # 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(1378195)
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 = 1,858 (80% power), 2,487 (90% power)
 75% of observed effect: n per arm = 3,302 (80% power), 4,420 (90% power)
 50% of observed effect: n per arm = 7,429 (80% power), 9,945 (90% power)
power.t.test: 1858.1 
Simulated power at n = 1,858 per arm: 0.804 (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. Multiplicity, Missing Data and Analysis Populations

The registry record identifies one primary outcome and two secondary outcomes. It does not report a statistical analysis plan, a hierarchy for testing outcomes, or a method for controlling multiplicity. No reported analyses are listed for the secondary outcomes. The posted comparisons are unadjusted, so their p-values should not be interpreted as if they account for all outcomes or analyses that may have been considered.

The registry record also does not report how missing outcome data were handled, the number of participants with missing scores, or whether any imputation or sensitivity analysis was conducted. It does not identify an intention-to-treat, per-protocol, or other analysis population. Without those details, the outcome summaries cannot be assumed to represent every randomized participant or a particular prespecified population.

Enrollment is listed as 150, while the primary outcome summaries include 46 participants in the CBT-based group and 57 in the educational/resource group. The record does not explain this difference or describe participant flow between assignment, follow-up, and analysis. Safety information lists 75 participants at risk in each group, which is a separate reported denominator; the registry record does not reconcile it with the outcome-specific counts. These denominators should not be combined or treated as evidence about attrition without further information.

The registry record does not report whether baseline outcome values were available or used, whether analyses adjusted for baseline measures, or how protocol deviations were handled. It also does not state whether the reported summaries follow a prespecified plan. These omissions do not establish that any particular method was or was not used; they mean that the analysis details are not reported in the registry record. Consequently, the unadjusted comparisons are best read as descriptive summaries with limited information about the full analysis process.

15. 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 5% reporting threshold.

The safety record lists 75 participants at risk in each group and zero participants affected by serious adverse events in each group. These figures should be read as the registry's reported serious-event counts, not as proof that no serious events occurred outside the recorded definitions, observation period, or reporting process. The registry record does not provide serious adverse event terms for either group.

Death counts are not reported in the registry record. The serious adverse event denominators differ from the participant counts in the primary outcome summaries, and the registry record does not explain the relationship between them. No inference about follow-up completeness or comparability of safety and outcome populations can be made from those counts alone.

Zero affected participants in the recorded serious-event category is a descriptive safety result. It does not establish that the interventions are free of risk, and it does not address events not captured or reported in this registry entry. The registry record also lists zero participants affected by other adverse events in the safety groups; interpretation remains subject to the same limits of the reported safety information.

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

The posted primary outcome summaries describe mean caregiver perceived stress at the 3-month assessment. The estimated difference is 0.58 scale units, with a confidence interval that includes zero and extends in both directions. The observed group averages therefore do not provide a precise separation between the CBT-based and educational/resource groups. The unadjusted p-value of 0.631 is consistent with substantial uncertainty about the comparison; it is not proof that the programs are equivalent.

The measure's direction gives context to the estimate: higher Perceived Stress Scale scores are worse, so a positive difference for educational/resource materials indicates a higher average score in that group. But the interval includes negative values as well, and the registry record supplies no clinical-importance threshold. The data do not establish that either program reduces stress, that the programs have the same effect, or that any observed difference is meaningful to caregivers.

The study is described as randomized, which is relevant to how group comparisons may be interpreted, but the registry record does not report important details of allocation, missing data, or analysis populations. The posted summaries include fewer participants per group than the total enrollment, and the record does not explain why. The simple comparisons are recalculated from summary statistics and are not sponsor-reported analyses.

The findings also should not be generalized beyond the population and program information recorded without considering the limits of the entry. The registry record does not report detailed participant characteristics, adherence, or the original sample-size justification. Secondary comparisons are unadjusted and carry less weight because a multiplicity plan is not reported. The most defensible conclusion is descriptive: the registry's group summaries show similar average scores in this sample, with uncertainty that does not rule out differences in either direction.

17. Why This Trial Matters Statistically

This trial illustrates why an estimate should be read together with its uncertainty. The primary mean difference is straightforward to state, but its confidence interval includes no difference and extends toward effects in either direction. Looking only at the point estimate or only at the p-value would leave out important information about precision and the range of effects compatible with the posted data.

It also illustrates the distinction between an outcome's standard deviation and the uncertainty around a group comparison. Standard deviations describe the spread of participant scores; the confidence interval addresses uncertainty in the estimated mean difference. Those quantities answer different questions and should not be used interchangeably.

The registry entry shows another practical issue: enrollment, outcome, and safety denominators are not always presented as a single reconciled participant flow. The primary outcome counts and safety risk counts are different, and the record does not explain why. Without information on missingness and analysis populations, readers cannot determine how those discrepancies relate to follow-up or analysis choices.

Finally, planning calculations based on an observed effect are not the same as the original trial's design justification. The registry record does not report the original assumptions. The illustrations can demonstrate how required sample size depends on the target effect and power, but they cannot establish whether the completed trial was adequately planned for a meaningful target. These are general lessons about interpretation, not claims about undocumented choices in this trial.

18. 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 trial-specific limitations constrain interpretation. The registry record states enrollment of 150, but the primary outcome summaries include 46 participants in the CBT-based group and 57 in the educational/resource group. Safety information separately lists 75 at risk in each group. No participant-flow account explains these counts, so the relationship between enrollment, outcome availability, and safety reporting is unclear.

The record does not report the original sample-size justification, missing-data methods, analysis population, or a sponsor-reported statistical analysis. The recalculated comparisons are unadjusted summaries and may not reflect any planned adjustment. The registry also does not report whether baseline scores or other characteristics were incorporated into analyses, or whether the posted comparisons were specified before results were known.

The primary scale is described, including its range and direction, but no clinically important difference threshold is reported. Consequently, the statistical estimate cannot be directly classified as clinically important or unimportant from the registry entry alone. The intervention descriptions identify shared materials, but the record does not report adherence or exposure details that would help explain how participants engaged with the programs.

The trial is described as unmasked, but the registry record does not specify who was aware of assignments or how outcome assessments were conducted. The two secondary outcomes have unadjusted comparisons, with no reported multiplicity plan or analysis hierarchy. These limitations do not show that the results are biased; they identify information absent from the registry record that would be needed for a fuller assessment.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: iCare Stress Management e-Training for Dementia Family Caregivers — NCT01378195.
• Registry record last updated 2013-02-28; status last verified 2013-02.
• Results first posted 2013-01-08.
• 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.

22. Record Summary

The registry record describes a completed phase 2 randomized, parallel-group trial with no masking and enrollment of 150. It compares a CBT-based program with educational/resource materials for dementia family caregivers. The primary outcome is caregiver Perceived Stress Scale score at 3 months, where higher values represent worse stress.

The posted primary group means are 15.83 and 16.41, and the unadjusted mean difference for educational/resource materials relative to CBT-based treatment is 0.58. Its confidence interval includes zero, and the unadjusted p-value is 0.631. The registry also lists two secondary outcomes, but no sponsor-reported analyses are listed. Sample-size illustrations use stated planning assumptions and are not the trial's original design justification. Missing-data handling, analysis populations, multiplicity procedures, and the explanation for differing outcome and safety counts are not reported in the registry record.