Events and Meetings of Italian Statistical Society, Advances in Latent Variables - Methods, Models and Applications

Font Size: 
The Generalised Autocovariance Function
Tommaso Proietti, Alessandra Luati

Last modified: 2013-06-16


The generalised autocovariance function is defined for a stationary stochastic process as the inverse Fourier transform of the power transformation of the spectral density function. Depending on the value of the transformation parameter, this function nests the inverse and the traditional autocovariance functions. A frequency domain non-parametric estimator based on the power transformation of the pooled periodogram is considered and its asymptotic distribution is derived. The results are employed to construct a novel feature matching estimator of the spectrum, that is applied for latent component estimation.

Full Text: PDF