INTERNAL function. Distribution families provide derivatives of the deviance and link w.r.t. mu = inv_link(eta).
This routine converts these to the required derivatives of the deviance w.r.t. eta, the linear predictor.
dDeta(y, mu, wt, theta, fam, deriv = 0)vector of observations.
if eta is the linear predictor, mu = inv_link(eta). In a traditional GAM mu=E(y).
vector of weights.
vector of family parameters that are not regression coefficients (e.g. scale parameters).
the family object.
the order of derivative of the smoothing parameter score required.
A list of derivatives.