The EEG is a valuable tool because it reflects cerebral physiology, it is a continuous and non-invasive measure, and it changes markedly on the administration of anesthetic drugs. The objective of this project is to find the excellent features to discriminate between different anesthesia states. Spectral Edge Frequency (SEF), spectral entropy and bicoherence can be used to differentiate different states. Analysis of EEG is typically performed using Fourier analysis, which is useful for detecting frequency components that correspond to the mental state of a patient. The parameters are calculated from power spectral density using appropriate formulas. From power spectrum of EEG, it’s observed that, the awake state active frequency range is 1.5-11 Hz. During the induction state the active frequency range is 1.5-9 Hz and during the deep state the active frequency range is around 1.5-7 Hz. Also, it’s observed that there is a decrease in EEG entropy as the anesthesia progresses. For the different stages of anesthesia no specific bicoherence values could be calculated. The awake state indicates the activity of α, β, δ and θ waves and later on during the deep state there occurs the presence of δ and θ waves. EEG entropies measure the uncertainty, or regularity, of a signal and correlate with cortical activity. With increasing concentrations of an anesthetic drug that depresses cortical activity there is a decrease in EEG entropy. The bicoherence measures the proportion of the signal energy at any bifrequency that is quadratically phase coupled. It was observed that, the magnitude of the coherence or coupling varies for all the cases. No specific pattern was observed, when different cases were observed.