Hilbert space multidimensional modelling of continuous measurements
Abstract
Data fusion problems arise when a researcher needs to analyse results obtained by measuring empirical variables under different measurement contexts. A context is defined by a subset of variables taken from a complete set of variables under investigation. Multiple contexts can be formed from different subsets, which produce a separate distribution of measurements associated with each context. A context effect occurs when the distributions produced by the different contexts cannot be reproduced by marginalizing over a complete joint distribution formed by all the variables. We propose a Hilbert space multidimensional theory that uses a state vector and measurement operators to account for multiple distributions produced by different contexts.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Sep 16, 2019
- Source ID
- 10.1098/rsta.2019.0142
Entities
People
- Jerome Busemeyer
- Zhongbao Wang
Organizations
- Air Force Office of Scientific Research
- Indiana University
- National Science Foundation
- Ohio State University