A Study Comparing Two Types of Supportive Interventions for Caregivers of Patients With Cancer: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study Comparing Two Types of Supportive Interventions for Caregivers of Patients With Cancer (NCT04802720), a randomized na study. The primary outcome is Changes in Anxiety Symptoms.

2. Clinical Question

3. Trial Design

The registry describes a randomized, parallel-group trial with no masking. The interventions are ERT-C and CBT-C, both directed to caregivers of cancer patients. The listed enrollment is 348. The registry status is active, not recruiting. The recorded study start is 2021-02-26, and the primary completion date is 2025-02-24. These are registry dates, not results about when individual participants entered or completed treatment.

The intervention arms are intended to compare two supportive therapy approaches. A training case group is also listed; its description says it would receive ERT-C only and would not complete questionnaires. The primary outcome record states that no participants accrued to that group. A patient group is listed as well, reflecting the study’s interest in patient quality of life, stress, and healthcare service use in connection with caregiver participation. The primary outcome record says that the patient group was not assessed at 6 months.

The trial is randomized, but the registry record does not report the randomization sequence method, allocation concealment procedures, or the method used to assign participants to groups. Masking is listed as none. The registry also does not report the trial’s original sample-size justification or original statistical analysis plan. These details should not be inferred from the posted results or from the separate planning illustration.

The primary outcome is changes in anxiety symptoms, expressed as a mean score on a scale. The registry lists two outcome measures, but no secondary results are posted in this record. The randomized design supports a comparison between the intervention groups, while interpretation still depends on outcome availability, the analysis population, and the methods used to handle missing assessments. Those details are not reported in the registry record.

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

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: no participants accrued to Training case group. Patient group not assessed at 6 months

5. Baseline Characteristics

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

Population: No participants accrued to the Training case group

6. Primary Endpoint

The registry lists the primary outcome as Changes in Anxiety Symptoms, measured over up to 6 months.

The primary endpoint is change in anxiety symptoms, assessed with the anxiety subscale of the Hospital Anxiety and Depression Scale (HADS-A), through up to 6 months. HADS has separate anxiety and depression subscales. The registry describes each subscale as ranging from 0 to 21, with higher scores indicating higher distress. Individual items use a five-point severity scale, from 0 to 4.

A change score is intended to describe how anxiety scores shift over the assessment period. The posted means are negative in both groups: -3.42 for ERT-C and -3.45 for CBT-C. Given that higher scores indicate greater distress, a negative change is consistent with a decrease in the measured score. These group summaries alone do not describe the experience of every caregiver, and the registry record does not provide the individual-level distribution of changes.

Anxiety is relevant to the trial’s stated focus on caregiver distress. HADS also measures depression, but the primary result is for anxiety symptoms; it should not be treated as a result for depression or for overall quality of life. The registry record lists other planned areas of interest, including caregiver outcomes, patient outcomes, and saliva hormone and stress levels, but secondary results are not posted. The primary endpoint record does not report the exact assessment schedule within the period of up to 6 months.

7. Results Posted in the Registry

• CBT-C: Cognitive Behavioral Therapy for Cancer Caregivers: mean -3.45 versus -3.42 on control; difference -0.03 (95% CI -1.14 to 1.08), standardized effect d = -0.01; z-test p = 0.958.

8. Statistical Interpretation

9. Statistical Methods Explained

The posted comparison is based on group means for a continuous outcome. A continuous measure can take a range of numerical values rather than falling into categories such as event or no event. The primary endpoint is a mean change in HADS-A score. The registry describes the group summaries as means with standard errors. The mean represents the group’s average observed change; it does not imply that every participant changed by that amount.

What does the mean difference represent?

The reported comparison is a mean difference of -0.03, with CBT-C compared against ERT-C. The negative sign indicates that the CBT-C mean is lower than the ERT-C mean on the change-score scale by the estimated amount. The group means themselves are -3.42 for ERT-C and -3.45 for CBT-C. A difference between group averages is not the same as a comparison of each participant’s response, and it does not show the spread of individual responses.

What does the standard error describe?

The standard error (SE) describes the uncertainty in an estimated mean, rather than the variability of individual participants’ scores. The posted SE is 0.4 in each group. As general statistical context, a smaller SE usually indicates a more precise estimate of a group mean, while a larger SE indicates more sampling uncertainty. The SE is affected by the variability in the data and the amount of information available. The registry does not post the raw score distributions, so individual variability cannot be read from the SE alone.

How should the confidence interval be read?

The reported 95% confidence interval for the mean difference runs from -1.139 to 1.079. As general statistical context, a confidence interval is a range of values produced by a method that, over repeated samples under its assumptions, would cover the underlying parameter at its stated rate. It is not a range containing a specified proportion of individual scores, and it is not a probability statement about this particular interval after it has been calculated. Its width conveys how precisely the difference has been estimated.

What does the p-value add?

The unadjusted p-value is 0.958. As general statistical context, a p-value measures how compatible the observed data are with a specified null model, assuming that model and the analysis assumptions hold. It is not the probability that the treatments are equal, nor does it quantify the clinical importance of a difference. A p-value should be read alongside the effect estimate and confidence interval. Here, the interval is important because it shows a range of group differences that remain compatible with the estimate.

What analysis details remain uncertain?

The registry record does not report whether the comparison was adjusted for baseline score or other variables, the exact model used, or how missing observations were handled. The record does not specify whether the posted means are model-based estimates or direct summaries beyond identifying the parameter as a mean. It also does not report the original statistical analysis plan. Therefore, the numerical comparison can be described as posted, but its full analytic implementation cannot be reconstructed from the registry record.

Randomization is intended to make intervention groups comparable in expectation, but a randomized design does not itself identify the analysis population or resolve missing outcome data. General statistical practice distinguishes an intention-to-treat analysis, which retains participants according to randomized assignment, from analyses limited to those who received or completed treatment. The registry record does not name the population used for this primary result, so neither approach should be assumed.

The sample-size illustration uses a normal approximation, equal allocation between two arms, a two-sided significance level of 0.05, and effect sizes expressed as fractions of the observed effect. These are the assumptions of the posted planning illustration, not a report of the trial’s original design assumptions. The trial’s own sample-size justification and statistical plan are not reported in the registry record. General caution is warranted when planning from an observed effect: such an estimate can be unstable, particularly when the observed difference is small.

10. Confidence Intervals and Precision

The estimated mean difference is -0.03, and its 95% confidence interval ranges from -1.139 to 1.079. The interval includes zero, so the posted results do not identify a clear direction of difference between the group means. It also extends in both directions far beyond the point estimate. Thus, the estimate is close to zero, but the interval does not restrict plausible differences to values very close to zero.

Precision refers to how narrowly an estimate locates the quantity of interest. A confidence interval is a useful measure of that precision: a narrower interval generally conveys greater precision than a wider one, under the same analysis and assumptions. Here, the interval spans values that could represent a lower mean change for either group. The registry record does not provide a threshold for a difference considered important, so the clinical importance of the endpoints of the interval cannot be assessed from this record alone.

The standard error for each group mean is 0.4. This is uncertainty in the estimated mean, not a description of how much scores vary from caregiver to caregiver. The registry does not post standard deviations or individual-level data for the primary result. The pooled standard deviation included in the comparison information is 3.81, but it does not replace the missing distributional detail or reveal the range of individual changes.

The unadjusted p-value of 0.958 is consistent with the confidence interval including zero, but it should not be used as a measure of precision on its own. The interval gives more direct information about the magnitude and direction of differences that are compatible with the estimate. Since the analysis method and missing-data handling are not reported, the interval’s interpretation remains conditional on the method used to calculate it.

11. 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 illustration gives participants per arm, not total participants and not total events. It assumes a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to be detected is set at the stated fraction of the observed effect. The trial’s original sample-size assumptions and justification are not reported in the registry record. The illustration is a planning aid, not observed power.

The 80% power column gives the participants per arm estimated to provide an 80% chance of detecting the specified effect under those assumptions if that effect is the true one. The 90% power column uses a higher target chance of detection, so its participant requirements are larger. These are planning probabilities under a model, not guarantees about the result of a future study.

For planning for 100% of the observed effect, the illustration gives 253,171 participants per arm for 80% power and 338,925 participants per arm for 90% power. For planning for 75% of the observed effect, the corresponding figures are 450,082 and 602,532 participants per arm. For planning for 50% of the observed effect, they are 1,012,684 and 1,355,697 participants per arm. Smaller effects require more participants to detect under the same assumptions.

The very large figures arise in an illustration based on the observed mean difference, which is close to zero. They should not be read as the trial’s planned enrollment or as evidence about the actual ability of the completed trial to detect an effect. They also do not account for design details that are not included in the stated planning assumptions.

12. 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 = -0.030; pooled standard deviation σ = 3.810.
2. n = 2 × (1.96 + 0.842)² × 3.810² / -0.030² = 253,171.0, rounded up to 253,171 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 <- -0.0300000000000002                      # observed difference in means
sigma <- 3.80986301325589                     # 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(4802720)
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 = 253,171 (80% power), 338,925 (90% power)
 75% of observed effect: n per arm = 450,082 (80% power), 602,532 (90% power)
 50% of observed effect: n per arm = 1,012,684 (80% power), 1,355,697 (90% power)
power.t.test: 253171.9 
Simulated power at n = 253,171 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.

13. Multiplicity, Missing Data and Analysis Populations

The registry lists two outcome measures, but no secondary results are posted. The primary result concerns changes in anxiety symptoms. The study description also mentions anxiety, depression, quality of life, saliva hormone and stress levels, and patient outcomes such as quality of life, stress, and healthcare service use. Results for these additional areas are not reported in the registry record.

When a study examines multiple outcomes, time points, or comparisons, the chance of at least one apparently unusual result can increase. As general statistical context, multiplicity procedures or a prespecified hierarchy can be used to address that issue. The registry record does not report whether a multiplicity adjustment or outcome hierarchy was planned or used. The posted p-value is identified as unadjusted, so it should not be interpreted as accounting for multiple testing.

The primary outcome timeframe is up to 6 months, but the exact measurement schedule and the method for defining change are not reported. The record says the patient group was not assessed at 6 months and that no participants accrued to the training case group. It does not state how many caregivers had missing primary outcome observations, why any observations may be missing, or how missing data were handled.

Missing outcome information can affect both the estimated mean and the uncertainty around it, especially when the likelihood of missingness is related to participants’ scores or circumstances. As general statistical context, complete-case analyses, imputation approaches, and models using available repeated measurements rely on different assumptions. The registry record does not identify which approach was used, so the effect of missing data cannot be evaluated from the posted results alone.

The analysis population is also not named. The registry reports outcome group sizes of 82 for ERT-C and 98 for CBT-C, but does not say whether these represent everyone randomized, everyone treated, or participants with outcome data. The record does not report a sensitivity analysis addressing missing outcomes or departures from the main analysis assumptions. These limitations make it difficult to assess how robust the primary comparison is to analytic choices.

14. 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 0% reporting threshold.

The adverse event record lists 124 caregivers at risk in the ERT-C group and 120 in the CBT-C group. It reports zero serious adverse events and zero other adverse events in each caregiver group. The training case group has zero participants at risk and zero events reported. These safety counts are distinct from the primary outcome group sizes, and the registry record does not explain the different denominators or define the event collection period in the information.

The patient group lists 95 at risk, zero serious adverse events, zero other adverse events, and 13 deaths. The death count is reported separately from the serious and other adverse event counts. The registry record does not give details about the causes of death or whether the deaths were considered related to study participation. No serious adverse event terms are listed.

Zero reported events means that none were recorded in these categories for the groups and denominators shown; it does not establish that no events occurred outside the registry’s reporting definitions or observation period. The counts also do not, by themselves, establish a causal relationship between an intervention and an event. The registry record does not provide event narratives, severity details beyond the serious-event category, or a comparative safety analysis.

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

The posted outcome describes average change in caregiver anxiety symptoms through up to 6 months. The group means are -3.42 for ERT-C and -3.45 for CBT-C, and the estimated mean difference is -0.03. The 95% confidence interval, from -1.139 to 1.079, shows substantial uncertainty about the exact between-group difference and includes values on both sides of zero. The unadjusted p-value is 0.958.

These results do not establish equivalence, nor do they show that the groups had identical outcomes. A failure to find a statistically clear difference is not proof of no difference. Equivalence requires a prespecified range of differences considered sufficiently small, together with an analysis designed to test that question. Such a margin is not reported in the registry record.

The result is specific to the posted measure, group comparison, and outcome sample. It does not describe every caregiver’s experience, identify individual responders, or establish whether either intervention changes depression, quality of life, patient stress, healthcare use, or saliva measures. Secondary results are not posted in this record. The patient group was not assessed at 6 months for this primary outcome, and no participants accrued to the training case group.

The registry record does not report the analysis population, missing-data methods, model details, or original statistical plan. These omissions matter because they limit assessment of the assumptions behind the estimate and its confidence interval. The appropriate reading is therefore descriptive and statistical: the posted mean changes are close, but the uncertainty interval does not precisely rule out differences in either direction. This is not medical advice and does not determine which therapy is appropriate for an individual.

16. Why This Trial Matters Statistically

This trial poses a useful statistical comparison because both groups receive an active caregiver-focused therapy. The question is not simply whether scores change within a group, but whether the average change differs between ERT-C and CBT-C. A between-group estimate is important because changes over time within either group do not, by themselves, separate intervention effects from other influences on scores.

The posted effect estimate is close to zero, while the confidence interval remains broad enough to include differences in either direction. This distinction between the point estimate and its precision is central to interpreting a comparative trial. A small estimate alone is not enough to establish similarity, and a non-significant p-value does not establish equivalence. The result illustrates why confidence intervals and prespecified decision thresholds matter alongside tests of statistical significance.

The study also spans caregiver and patient outcomes, multiple forms of distress, and biological measures. That breadth may raise questions about how outcomes and analyses were prioritized and how multiple comparisons were handled. The registry record lists two outcome measures but posts no secondary results, and does not report a multiplicity strategy. Clear reporting of the analysis population, assessment schedule, missing-data methods, and outcome hierarchy would help readers judge how much weight to place on the primary finding and how it relates to the broader research questions.

Finally, the planning illustration shows how strongly sample-size requirements can depend on the effect selected for detection. Its figures are based on the observed effect rather than the trial’s original design assumptions, which are not reported. This makes the illustration useful for understanding the mechanics of planning, but not a substitute for a transparent original design rationale.

17. 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 posted primary comparison has limited reporting detail. The registry record does not identify the analysis population, the model used to estimate the means, whether the analysis adjusted for baseline anxiety, or the method used to address missing data. The reported outcome group sizes are 82 for ERT-C and 98 for CBT-C, but their relationship to the listed enrollment is not explained.

The primary endpoint is described as change in anxiety symptoms through up to 6 months, without a more detailed assessment schedule in the posted record. The record also does not report a prespecified threshold for a meaningful difference, so the importance of the confidence interval limits cannot be judged against such a threshold. A confidence interval that includes zero should not be treated as evidence of equivalence.

The trial record lists two outcome measures, but no secondary results are posted. It therefore cannot answer the broader questions about depression, quality of life, saliva hormone and stress levels, or patient quality of life, stress, and healthcare service use. The record notes that the patient group was not assessed at 6 months for the primary outcome and that no participants accrued to the training case group.

The registry does not report the original sample-size justification, the original statistical analysis plan, missingness patterns, or sensitivity analyses. The planning illustration uses the observed effect and stated assumptions, so it should not be interpreted as the trial’s original design calculation. The adverse event record also lacks event narratives and information about the circumstances of the 13 deaths reported in the patient group. These reporting gaps limit independent assessment of the results and their generalizability.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: A Study Comparing Two Types of Supportive Interventions for Caregivers of Patients With Cancer — NCT04802720.
• Registry record last updated 2026-06-10; status last verified 2026-05.
• Results first posted 2026-06-10.
• 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.

21. Record Summary

NCT04802720 is a randomized, parallel-group trial with no masking, comparing ERT-C with CBT-C for caregivers of patients with cancer. The registry lists enrollment of 348 and a status of active, not recruiting. The primary outcome is change in anxiety symptoms measured with HADS-A through up to 6 months.

The posted means are -3.42 for ERT-C and -3.45 for CBT-C. The mean difference, comparing CBT-C with ERT-C, is -0.03, with a 95% confidence interval from -1.139 to 1.079 and an unadjusted p-value of 0.958. The record does not post secondary results or report the analysis population and missing-data methods.

The registry lists zero serious and zero other adverse events in both caregiver intervention groups. It separately reports 13 deaths in the patient group, without further details about their circumstances or relationship to study participation.