摘要:"How large a sample size do I need for my study"? Although one of the most commonly-asked questions in statistics, the importance of proper sample size estimation seems to be overlooked by many preclinical researchers. Over the past two decades, numerous reviews of the published literature indicate many studies are too small to answer the research question and results are too unreliable to be trusted. Few published studies present adequate justification of their chosen sample sizes, or even report the total number of animals used. On the other hand, it is not unusual for protocols (usually those involving mouse models) to request preposterous numbers of animals, sometimes in the tens or even hundreds of thousands, "because this is an exploratory study, so it is unknown how many animals we will require."--
