Design and Sample Size Issues: How Many Subjects Do I Need for My Study?

• Published in: Quality of Life Outcomes in Clinical Trials and Health‐Care Evaluation pp. 55 - 90
• Format: Book Chapter
• Language: English
• Published: Chichester, UK John Wiley & Sons, Ltd 25.09.2009
• Subjects: Community Postnatal Support Worker (CPSW) study; design and sample size issues; method of statistical analysis and QoL data collected; Natural logarithm of SF‐36 Physical Functioning dimension; QoL outcomes condensed into binary or dichotomous categorical scale; sample size calculations for research protocols; sample size method with quality of life outcomes; significance tests, P‐values and power; standard deviation of QoL outcome; two independent group comparison
• ISBN: 047075382X; 9780470753828
• DOI: 10.1002/9780470840481.ch4

This chapter contains sections titled: Summary Introduction Significance tests, P‐values and power Sample sizes for comparison of two independent groups Choice of sample size method with quality of life outcomes Paired data Equivalence/non‐inferiority studies Unknown standard deviation and effect size Cluster randomized controlled trials Non‐response Unequal groups Multiple outcomes/endpoints Three or more groups What if we are doing a survey, not a clinical trial? Sample sizes for reliability and method comparison studies Post‐hoc sample size calculations Conclusion: Usefulness of sample size calculations Further reading