Can children with language impairment be accurately identified using temporal processing measures? A simulation study

Three simulation experiments were conducted to determine the basis of the h igh predictive accuracy (98%) of temporal processing variables for the iden tification of language impairment obtained by Tallal, Stark, and Mellits (1 985). In the first two experiments, the stepwise discriminant analysis usin g a set of 160 arrays of random numbers to predict a dichotomous language s tatus (either normal or disordered) resulted in an average accuracy rate of 86.3% in contrast with the 98% rate obtained by Tallal, Stark, and Mellits . The third experiment showed that a 95% accuracy rate could be obtained fr om an array of 160 variables that each may only account for about 1.5% vari ance in the language ability. These results emphasize the need for confirma tory studies when large data sets are used to identify a small set of predi ctor variables. (C) 1998 Academic Press.