A relative density model (one fitted by maximising the conditional likelihood) has a zero intercept for density on the default log scale (the intercept is 1.0 for the identity link). The constant k that relates absolute density to relative density \(D^\prime = k^{-1} D\) is obtained as described in Efford (2025).
These functions infer the value of k and use this to construct the predicted density surface (predictDsurface is the equivalent function for full-likelihood models).
The derived method for `secr' objects performs the same calculation as derivedDcoef and also back-transforms the intercept and computes a delta-method estimate of its variance and confidence limits. However that variance estimate is unreliable.
derivedDcoef(object, sessnum = 1, groups = NULL, se = FALSE)derivedDsurface(object, mask = NULL, sessnum = NULL, groups = NULL)
For derivedDcoef --
A dataframe mimicking coef(object) with an initial row for the derived density intercept \(\beta_0\). For an identity link, subsequent density coefficients are scaled by the derived \(\beta_0\).
For derivedDsurface --
Dsurface object with class c("Dsurface", "mask", "data.frame"). Multi-session if object is multi-session and sessnum = NULL.
If groups are defined the result is a list of Dsurfaces.
fitted secr relative density model
new mask for which to compute densities
integer session number
character vector of covariate names to define groups (optional)
logical; if TRUE the variance of beta0 is estimated by the delta method
The theory is provided by Efford in prep.
derivedDcoef(object, se = TRUE) is equivalent to derived(object, Dweight = TRUE), although derivedDcoef returns estimates on the link scale.
Efford, M. G. In prep. SECR models for relative density.
derived
predictDsurface