This distribution was very skewed, and it was decided that bootstrapping would be a more appropriate method to calculate CIs rather than relying on large sample assumptions.
The calculation of CIQs has traditionally been based on the large-sample assumption that the quantile estimators are normally distributed, but with small samples commonly available, this assumption is shown to be quite crude.
Our models indicate that the 'random paleogeographic sampling' assumption used in the previous studies is not valid due primarily to the lack of an adequate sample size and temporal distribution.
Under general sampling assumption, we also derive the special structure of the SS-1 kernel (e.g. its tridiagonal inverse and factorization have closed form expression), also giving to it a maximum entropy covariance completion interpretation.
Second, to address violation of the assumption of representative training samples (Assumption 3, Table 1) we used "pseudo-presence data"—points randomly sampled from across the range of the focal species rather than actual occurrence localities from museums, herbaria, or field surveys.
Length bias is expected under a uniform sampling assumption.
Three issues are addressed: First, what is a tenable sampling model for Ames test data, and how does one best test the adequacy of the Poisson sampling assumption?
