On the trasductive arguments in statistics

TL;DR

This paper critiques current statistical arguments, highlighting issues in foundational assumptions related to prediction, semi-supervised learning, and causality inference from observational data.

Contribution

It challenges prevailing statistical reasoning by analyzing the foundational aspects of prediction, semi-supervised classification, and observational causality.

Findings

Identifies gaps in the theoretical basis of certain statistical methods

Highlights issues in applying standard foundations to prediction and causality

Calls for a reassessment of foundational principles in statistics

Abstract

The paper argues that a part of the current statistical discussion is not based on the standard firm foundations of the field. Among the examples we consider are prediction into the future, semi-supervised classification, and causality inference based on observational data.