1. |
|
|
2. |
- Arnborg, Stefan, et al.
(author)
-
Bayes rules!
- 2000
-
Conference paper (peer-reviewed)abstract
- Of the many justifications of Bayesianism, most imply some assumption that is not very compelling, like the differentiability or continuity of some auxiliary function. We show how such assumptions can be replaced by weaker assumptions for finite domains. The new assumptions are a non-informative refinement principle and a concept of information independence. These assumptions are weaker than those used in alternative justifications, which is shown by their inadequacy for infinite domains. They are also more compelling. 1 Introduction The normative claim of Bayesianism is that every type of uncertainty should be described as probability. Bayesianism has been quite controversial in both the statistics and the uncertainty management communities. It developed as subjective Bayesianism, in [5, 11]. Recently, the information based family of justifications, initiated in [3] and continued in [1] have been discussed in [12, 6, 13]. We will try to find assumptions that are strong enough to s...
|
|
3. |
- Arnborg, Stefan, et al.
(author)
-
Bayes rules in finite models
- 2000. - 1
-
In: Proceedings of the European Conference on Artificial Intelligence, 20-25 Aug 2000, Berlin, Germany. - 1586030132 ; , s. 571-575
-
Conference paper (peer-reviewed)
|
|
4. |
- Arnborg, Stefan
(author)
-
Data Mining : Opportunities and Challenges chapter 1: A Survey of Bayesian Data Mining.
- 2003
-
In: Data Mining. - : Idea Group Publishing.
-
Book chapter (peer-reviewed)abstract
- Data Mining: Opportunities and Challenges presents an overview of the state of the art approaches in this new and multidisciplinary field of data mining. The primary objective of this book is to explore the myriad issues regarding data mining, specifically focusing on those areas that explore new methodologies or examine case studies. This book contains numerous chapters written by an international team of forty-four experts representing leading scientists and talented young scholars from seven different countries.
|
|
5. |
- Arnborg, Stefan, et al.
(author)
-
Data Mining in Schizophrenia Research - preliminary analysis
- 2002
-
Conference paper (peer-reviewed)abstract
- We describe methods used and some results in a study of schizophrenia in a population of affected and unaffected participants, called patients and controls. The subjects are characterized by diagnosis, genotype, brain anatomy (MRI), laboratory tests on blood samples, and basic demographic data. The long term goal is to identify the causal chains of processes leading to disease. We describe a number of preliminary findings, which confirm earlier results on deviations of brain tissue volumes in schizophrenia patients, and also indicate new effects that are presently under further investigation. More importantly, we discuss a number of issues in selection of methods from the very large set of tools in data mining and statistics.
|
|
6. |
|
|
7. |
- Arnborg, Stefan, 1945-
(author)
-
Från observationer till kunskap
- 2008. - 1
-
In: Människor och matematik. - Göterborg : Nationellt Centrum för Matematikutbildning. - 9789185143085 ; , s. 367-389
-
Book chapter (pop. science, debate, etc.)
|
|
8. |
- Arnborg, Stefan, et al.
(author)
-
Information awareness in command and control : precision, quality, utility
- 2000
-
In: FUSION 2000. - 2725700000 ; , s. THB1/25-THB1/32 vol.2
-
Conference paper (peer-reviewed)abstract
- In current command and control system design, the concept of information plays a central role. In order to find architectures for situation and threat databases making full use of all dimensions of information, the concept of information awareness must be understood. We consider and define some information attributes: measures of precision, quality and usability, and suggest some uses of these concepts. The analysis is Bayesian. A critical point is where subjective Bayesian probabilities of decision makers meet the objective sensor related Bayesian assessments of the system. This interface must be designed to avoid credibility problems.
|
|
9. |
- Arnborg, Stefan, et al.
(author)
-
On the foundations of Bayesianism
- 2000
-
Conference paper (peer-reviewed)abstract
- We discuss precise assumptions entailing Bayesianism in the line of investigations started by Cox, and relate them to a recent critique by Halpern. We show that every nite model which cannot be rescaled to probability violates a natural and simple re nability principle. A new condition, separability, was found sufficient and necessary for rescalability of in nite models. We nally characterize the acceptable ways to handle uncertainty in in nite models based on Cox's assumptions. Certain closure properties must be assumed before all the axioms of ordered elds are satis ed. Once this is done, a proper plausibility model can be embedded in an ordered eld containing the reals, namely either standard probability ( eld of reals) for a real valued plausibility model, or extended probability ( eld of reals and in nitesimals) for an ordered plausibility model. The end result is that if our assumptions are accepted, all reasonable uncertainty management schemes must be based on sets of extended probability distributions and Bayes conditioning.
|
|
10. |
|
|