Sense and Nonsense about Generalizing to a Language Population

Abstract

Certain researchers have been advocating the use of special research designs so as to be able to apply tests of statistical significance when attempting to generalize beyond the particular language samples used in an experiment. It makes a great deal of sense to attempt to design research so as to be able to generalize beyond the particular reading passages used in an experiment but the suggestion that tests of statistical significance are a necessary part of making valid generalizations is nonsense. The nonsensical aspects of the “generalizing to a language population” position are discussed in detail and illustrated by reference to a particular reading research study. An important, but usually unnoticed, form of replication is also discussed.