Abstract
Many commentators have discussed misinterpretations of null hypothesis significance tests. Although probability levels are often misinterpreted, there is a valid interpretation that is not well-known. With the wide access to statistical programs it has become possible to use the exact probability levels of tests of statistical significance to estimate the probability that replications of completed studies would be statistically significant. It is shown that the difference between an observed value of t and the critical value of t can provide such estimates. The method is applied to tests of the statistical significance of correlation coefficients also. Both a graphical and a tabular method of converting a probability level of an initial study into the probability of a statistically significant replication are provided.
