Testing of Coarsening Mechanisms: Coarsening at Random Versus Subgroup Independence

Julia Plass, Marco E. G. V. Cattaneo, Georg Schollmeyer, Thomas Augustin

Abstract

Since coarse(ned) data naturally induce set-valued estimators , analysts often assume coarsening at random (CAR) to force them to be single-valued. Using the PASS data as an example, we re-illustrate the impossibility to test CAR and contrast it to another type of uninformative coarsening called subgroup independence (SI). It turns out that SI is testable here.
BibTeX
@inproceedings{plass2016testing,
  author = {Julia Plass and Marco E. G. V. Cattaneo and Georg Schollmeyer and Thomas Augustin},
  title = {{Testing of Coarsening Mechanisms: Coarsening at Random Versus Subgroup Independence}},
  booktitle = {SMPS},
  year = {2016},
  doi = {10.1007/978-3-319-42972-4\_51},
}

Loading related content...

Figure