Experimental Design: A Bayesian Perspective

Abstract

Introduction Experimentation plays an integral part in the scientific method. Conjectures and hypotheses are put forth based on the current state of knowledge. Experimental data may be collected to address unknown aspects of the problem. Int. Encyc. Social and Behavioral Sciences 4 April 2001 2 Finally, analysis of experimental results may lead to one hypothesis being favored over others or may lead to new questions and investigations, so that the process is repeated, with the accumulation of additional knowledge about the scientific process under investigation. In some fields of scientific inquiry, physical models can be used to describe the outcome of an experiment given certain inputs with complete certainty. In the majority of applications, one cannot describe the scientific phenomena perfectly, leading to a distribution on possible outcomes, which can be described by probability models. For example, in comparing a new therapy to an existing treatment, ind

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 34 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.