agfh: Agnostic Fay-Herriot Model for Small Area Statistics (original) (raw)

Implements the Agnostic Fay-Herriot model, an extension of the traditional small area model. In place of normal sampling errors, the sampling error distribution is estimated with a Gaussian process to accommodate a broader class of distributions. This flexibility is most useful in the presence of bounded, multi-modal, or heavily skewed sampling errors.

Documentation:

Downloads:

Linking:

Please use the canonical formhttps://CRAN.R-project.org/package=agfhto link to this page.