Answers are grounded in this paper and cite their sources.
As part of our longitudinal study of unexposed workers, we drew blood samples and analyzed the individual endocrine profiles for 45 men. The blood collection was between 8 AM and 8 PM, and three blood samples were drawn 20 minutes apart on three occasions during the course of the study (June, October, and February). Serum concentrations of follicle-stimulating hormone, luteinizing hormone, testosterone, and prolactin were determined. A component of variance model was used to estimate variability between the 20-minute blood draws. Statistical power analysis using this component showed that three blood draws provide a marginal improvement over a single blood draw in detecting population shifts. Also, if the prospect of three blood draws reduces subject participation by 10 to 20%, the increase in power would be negated.
No takes yet. Share an insight, caveat, or question.
Schrader et al. (1993) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: