Statistical power and sampling size

A further requirement for economic evaluation is recruitment and retention of a sufficient sample of patients and/or facilities to show statistically significant changes between groups. Many economic evaluations have previously been underpowered, mainly due to the skewed distribution of costs among subjects. To take an example, Gray et al. (19 showed (retrospectively) that at 80 per cent power, their case management study (n = 30) was sufficient to detect between-group differences of approximately 30 per cent for total costs, but to detect a 20 per cent difference in health-care costs alone, over 700 subjects per arm would have been required! This raises a number of questions, including what constitutes a worthwhile difference in costs, and what is the additional research cost of basing sample size estimates on economic (as opposed to clinical) variables. What remains clear, however, is that the uncertainty introduced into economic findings by the variability of costs must be addressed not only by sensitivity analysis but also by statistical power considerations at the design stage.

Break Free From Passive Aggression

Break Free From Passive Aggression

This guide is meant to be of use for anyone who is keen on developing a better understanding of PAB, to help/support concerned people to discover various methods for helping others, also, to serve passive aggressive people as a tool for self-help.

Get My Free Ebook


Post a comment