Advertisement
Published in:
2016 | OriginalPaper | Chapter
On Things Not Seen
Author : Marek Kimmel
Published in: Challenges in Computational Statistics and Data Mining
Publisher: Springer International Publishing
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
Some statistical observations are frequently dismissed as “marginal” or even “oddities” but are far from such. On the contrary, they provide insights that lead to a better understanding of mechanisms which logically should exist but for which evidence is missing. We consider three case studies of probabilistic models in evolution, genetics and cancer. First, ascertainment bias in evolutionary genetics, arising when comparison between two or more species is based on genetic markers discovered in one of these species. Second, quasistationarity, i.e., probabilistic equilibria arising conditionally on non-absorption. Since evolution is also the history of extinctions (which are absorptions), this is a valid field of study. Third, inference concerning unobservable events in cancer, such as the appearance of the first malignant cell, or the first micrometastasis. The topic is vital for public health of aging societies. We try to adhere to mathematical rigor, but avoid professional jargon, with emphasis on the wider context.