On computing the fast Fourier transform
Communications of the ACM
Time series: data analysis and theory
Time series: data analysis and theory
Modern Applied Statistics with S
Modern Applied Statistics with S
Hi-index | 0.01 |
In this work, we provide a semi-parametric approach for testing the hypothesis that the spectra of two neural spike trains are equal. Estimates of the spectra are obtained by taking the Fourier transforms of the cumulant functions using convergence factors for smoothing. A quasi-likelihood ratio test for comparing different hypotheses is applied since the estimates are asymptotically Normal with constant variances. An illustrative example is presented where the information transferred to the spinal cord from the muscle spindle, under the influence of two stimuli can be separated into two parts 0-19 and 19-120Hz. The dependence on the frequency in both parts is of a quadratic form.