The reference problem and mapping of coherence: a simulation study

Abstract

Four techniques are applied to record EEG signals: bipolar recording, referential recording, common average reference recording and source derivation. For the interpretation of EEG parameter maps knowledge of the properties of the applied recording technique is essential. Bipolar recordings are not discussed in this paper. The application of reference and common average reference recording has the disadvantage of an unknown reference potential. This disadvantage is much larger with the use of source derivation because every electrode signal has its particular reference signal. This must be taken into consideration when coherence estimations are made. With actual EEG records the influence of the reference cannot be determined unambiguously. However, simulation studies enable some essential conclusions. In this paper by means of autoregressive processes EEG signals with given power and coherence properties were simulated and different recording situations using the same data set were reconstructed. The essential result is that computation and mapping of coherences yield the most reliable results when reference recording is used. However, measures to ensure a low reference signal must be taken.