Matrix is singular to working precision.

Hi, when downloading some time series the result provided is Matrix is singular to working precision. The data are quite similar, could that be the underlying reason?

Answer 1

[James Tursa]

If a square matrix has rows or columns that are very nearly the same, then yes this would cause the matrix to be singular to working precision.

[economics student]

how can this be treated? if series correspond to real economic data, it should be expected that they remain similar.

[economics student]

would a differentiated weight for each series arrange this?

[James Tursa]

Impossible to advise you without knowing what problem you are trying to solve. I.e., what does the data represent and what are you trying to do with it downstream in your code.

[economics student]

The data corresponds to volatility series from banks. I am trying to calculate pairwise return connectedness and net directional connectedness via the evaluation of the proportions of the variation of the forecast errors in several places due to the shocks that arise elsewhere, via variance decompositions