Nomograms for obtaining a necessary, minimum sample size. I. When distribution of data is normal.

Abstract

Four different nomograms were devised to obtain a necessary, minimum sample size at a 95% confidence rate when data were distributed normally. They corresponded to four different cases, the population of which was either infinite or finite and the permitted error of which was either mu--m or mu--m/s, where mu was population mean, m sample mean and s sample standard deviation. They could also be used for obtaining the confidence limits of the population mean from the data after having carried out a work.