Data.trafo

Applies the Discrete Cosine I transform, data binning and the variance stabilizing transform function to the data.

A nonparametric method to estimate Toeplitz covariance matrices from a sample of n independently and identically distributed p-dimensional vectors with mean zero. The data is preprocessed with the discrete cosine matrix and a variance stabilization transformation to obtain an approximate Gaussian regression setting for the log-spectral density function. Estimates of the spectral density function and the inverse of the covariance matrix are provided as well. Functions for simulating data and a protein data example are included. For details see (Klockmann, Krivobokova; 2023), <arXiv:2303.10018>.

Karolina Klockmann

vstdct

Nonparametric Estimation of Toeplitz Covariance Matrices

Tatyana Krivobokova

Data.trafo function

<dl><dt>y</dt>
<dd><code>nxp</code> dimensional data matrix</dd>
<dt>Te</dt>
<dd>number of bins for data binning. <code>Te</code> should be smaller than the vector length <code>p</code>.</dd>
<dt>dct.out</dt>
<dd>logical. If <code>TRUE</code>, the <code>p</code>-dim. DCT-I matrix is returned. The default is <code>FALSE</code>.</dd></dl>

Arguments

Data Transformation — Data.trafo

<dl>

<dt>y</dt>
<dd><code>nxp</code> dimensional data matrix</dd>


<dt>Te</dt>
<dd>number of bins for data binning. <code>Te</code> should be smaller than the vector length <code>p</code>.</dd>


<dt>dct.out</dt>
<dd>logical. If <code>TRUE</code>, the <code>p</code>-dim. DCT-I matrix is returned. The default is <code>FALSE</code>.</dd>

</dl>

Data.trafo: Data Transformation

Description

Usage

Value

Arguments