In the present study, inter-electrode hemispheric dependency has been estimated by using frequency, time and phase domain methods (Fourier Correlation, Wavelet Correlation (WC), Hilbert Correlation) for eight individual brain lobes (pre-frontal, anterio-frontal, central, occipital, parietal, posterio-frontal, anterio-temporal, posterio-temporal) in five frequency band activities (Delta (0.5 - 4 Hz), Theta (4 - 8 Hz), Alpha (8-16 Hz), Beta (16-32 Hz) and, Gamma (32-64 Hz)) for detection of obsessive compulsive disorder (OCD). For this purpose, patients and controls are classified by using non-linear Least-Squares Support-Vector-Machine with 10-fold cross validation for both eight features in each sub-band and single ban-specific feature at each lobe. The best classification performance (87, 15% and 96, 65% in Beta and Gamma) is obtained for eight features estimated by using WC. In particular, single feature through WC has provided the relatively lower but useful classification performance in Beta (72, 34% at prefrontal, (72, 59% at occipital, 76, 39% at posterio-frontal, 70, 89% at anterio-temporal, 71, 14% at posterio-temporal) and Gamma (71, 84% at prefrontal, 76, 39% at occipital, 76, 39% at posterio-frontal, 70, 89% at anterio-temporal, 71, 77% at posterio-temporal). In detail, OCD is found to be characterized by low hemispheric dependency in Gamma over cortex. In conclusion, OCD causes abnormalities at almost every hemispheric lobe. WC provides the best estimations to compute band specific asymmetry levels due to non-linear and non-stationary nature of EEG.