ABSTRACT
Problems with small samples In dealing with the situation in which we wished to ascertain whether a sample mean was significantly different from the population mean, we - in previous chapters - used a type of Z-score. That is, we divided the difference between m and X by the standard error of the mean and used the Z-table (Appendix A) to work out the probabilities. However, all of this assumes not only that the population from which the sample might have been drawn was normally distributed, but that the sample itself was in excess of 30 scores in size.
