Understanding the areas involved in language functions not only enables investigators to understand neuroanatomical structures, but may be a promising technique in the presurgical evaluation of epilepsy. The predictive power of various data reduction techniques was tested on language data obtained by magnetoencephalography (MEG) of 16 patients and 12 control subjects. Words were presented aurally in two phases: the study phase and the recognition phase. Subjects were asked to remember words from the study phase and indicate if they remembered those words during the recognition phase. Single equivalent-current dipoles were calculated to determine laterality indices and the neuroanatomical correlates of language function. For all patients, results indicated a concordance, sensitivity, and specificity of 0.75. After consideration of IQ scores and exclusion from the analysis of those patients with scores below the average range, the results indicated a concordance of 0.90, sensitivity of 0.86, and specificity of 1.00. These findings are consistent with previous MEG investigations of language function in comparison with the Wada technique and support the use of MEG language mapping in most patients with an IQ within or above the average range.