Power & Sample Size PREP

Study Notes

Core Principles of Mental Health Research - Sample Size

Learning Outcomes:
- Explain the importance of sample size calculations
- Define Type I and Type II errors
- List key factors determining sample size and their impact on study participants
- Calculate sample sizes for studies with continuous and binary outcomes
- Adjust sample sizes to account for loss to follow-up
Approaches to Sample Size:
- Statistical/Scientific:
  - Determine the number of patients needed to reliably detect a treatment effect.
  - Accurately estimate the effect size.
- Economic/Pragmatic:
  - Available patient numbers
  - Time needed to recruit participants
  - Cost of the study
- Ethical:
  - When a trial can be stopped to prevent patients from receiving inferior treatment.
Credibility:
- Small trials are unreliable due to low statistical power.
Small Studies:
- May not detect clinically significant effects
- Produce imprecise estimates
- Less likely to represent the whole population
- More likely to show a false positive (p<0.05) result and be published, skewing findings
- Results may be misleading for clinicians
- Unethical for participants to contribute to a study that does not achieve a robust or meaningful outcome.
Sample Size (Too Small):
- Lack of precision
- Difficult to distinguish real improvement from random chance.
- Ethical considerations
Sample Size (Too Large):
- Waste of resources
- Ethical considerations
- A well-designed study should use the minimum number of participants to answer its research question.
Type I and Type II Errors:
- Type I error (False Positive): Observing an effect that does not exist in the population.
- Type II error (False Negative): Not observing an effect that exists in the population.
- Power: The probability of correctly rejecting a false null hypothesis (1 - Type II error rate).