𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Science without (parametric) models: the case of bootstrap resampling

✍ Scribed by Jan Sprenger

Publisher
Springer Netherlands
Year
2009
Tongue
English
Weight
160 KB
Volume
180
Category
Article
ISSN
0039-7857

No coin nor oath required. For personal study only.

πŸ“œ SIMILAR VOLUMES

Assessing the quality of bootstrap sampl
Assessing the quality of bootstrap samples and of the bootstrap estimates obtained with finite resampling
✍ Yannis Yatracos πŸ“‚ Article πŸ“… 2002 πŸ› Elsevier Science 🌐 English βš– 182 KB

It is seen in simulations and conΓΏrmed theoretically that: (i) the loss in accuracy of the Monte Carlo approximation of the bootstrap estimate can be inΓΏnite, due to the additional uncertainty introduced by ΓΏnite resampling, and (ii) the dimension of the data or the estimate of interest a ect drasti

Parametric models as thin subsets of the
Parametric models as thin subsets of the space of distributions
✍ Mario Antonio Gneri πŸ“‚ Article πŸ“… 1999 πŸ› Elsevier Science 🌐 English βš– 67 KB

Hampel [1986, Robust Statistics. The Approach Based on In uence Functions. Wiley, New York], pointed out that: "Classical parametric statistics allows only a (very thin) low dimensional subset of all probability distributions -the parametric model". In this paper we give a formal support to this ass