Grant: Discovery Grants Program - Individual
University of Saskatchewan
$11,000.00
Information Geometry of Imprecise Inference
EF 2015-16
Résumé
Traditional statistical inference depends on specifying precise probabilities, which requires that one can, for every conceivable pair of alternatives, indicate which of the two is believed to be more likely. It may be more realistic, however, to acknowledge that in many situations one lacks sufficient knowledge to make such a judgment until more data are collected. This concession to prior ignorance is the cornerstone of imprecise probability. The methodology for making inferences from data using imprecise probabilities is known as imprecise inference.
Traditional geometry studies spatial relationship in terms of distances between objects. Other kinds of
relationships can be similarly studied using analogues of distance. In particular, relationships between states of knowledge (represented by probabilities) can be studied by quantifying the difference of information between any two such states. This metaphorical use of geometric ideas to understand the relationship among states of knowledge is known as information geometry.
Combining these two ideas allows one to visualize the evolution of knowledge about a system as data are acquired. These principles allow one to make predictions and decisions that take into one's lack of knowledge and to avoid the quagmire of spurious precision.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Saskatchewan, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
36817-2013
Name nom
Bickis, Mikelis
Department département
Mathematics and Statistics
Organization id
16
Institution établissement
University of Saskatchewan
Province en
Saskatchewan
Province fr
Saskatchewan
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2015
Competition year année de concours
2013
Award amount
11000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1508
Committee name en
Mathematics and Statistics
Committee name fr
Mathématiques et statistique
Area of application code
1200
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Advancement of knowledge
Area of application fr
Avancement des connaissances
Research subject code
3001
Research subject group en
Statistics and probability
Research subject group fr
Statistique et probabilité
Research subject en
Statistical theory
Research subject fr
Théorie de statistique
Partie
3
Nb partie
5
Application title
Information Geometry of Imprecise Inference
Keyword
NSERC
Application summary
Traditional statistical inference depends on specifying precise probabilities, which requires that one can, for every conceivable pair of alternatives, indicate which of the two is believed to be more likely. It may be more realistic, however, to acknowledge that in many situations one lacks sufficient knowledge to make such a judgment until more data are collected. This concession to prior ignorance is the cornerstone of imprecise probability. The methodology for making inferences from data using imprecise probabilities is known as imprecise inference.
Traditional geometry studies spatial relationship in terms of distances between objects. Other kinds of
relationships can be similarly studied using analogues of distance. In particular, relationships between states of knowledge (represented by probabilities) can be studied by quantifying the difference of information between any two such states. This metaphorical use of geometric ideas to understand the relationship among states of knowledge is known as information geometry.
Combining these two ideas allows one to visualize the evolution of knowledge about a system as data are acquired. These principles allow one to make predictions and decisions that take into one's lack of knowledge and to avoid the quagmire of spurious precision.