ARMA spectral density

[seabbs]

As suggested by @SamuelBrand1 ARMA models have a spectral density (https://en.wikipedia.org/wiki/Autoregressive_moving-average_model) this means we should be able to implement approximate AMRA models within our GP framework.

This builds off discussions in #757.

[SamuelBrand1]

Might need a bit of thought about whether there are any considerations around using a discrete time process. Although I think the GPs in general being used in a discrete sense here, the forward epi process might depend on the GP $f$ only at a discrete set of points: e.g. $\log R_{t_i}$ $= f_i = f(t_i)$ for $i=1,...$ so it might not be a big deal.

[seabbs]

Noting I am keen to see this in but have no real idea where to start.

[seabbs]

I think we should close this and instead steal the new ARIMA module from epinowcast so closing