Trying to Discover Sufficient Condition Causes

Scientific human psychology is ultimately obligated to be able to describe, predict, and causally explain the psychological phenomena of every individual person. If all of this can be done in terms of the interrelations of linear combinations of variables, then our heavy reliance on statistical line...

Full description

Saved in:
Bibliographic Details
Published in:Methodology 2010, Vol.6 (2), p.59-70
Main Author: Krause, Merton S
Format: Article
Language:English
Subjects:
Biological and medical sciences
Fundamental and applied biological sciences. Psychology
Mathematical Modeling
Psychology
Psychology. Psychoanalysis. Psychiatry
Psychology. Psychophysiology
Psychometrics. Statistics. Methodology
Statistical Data
Statistics. Mathematics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Scientific human psychology is ultimately obligated to be able to describe, predict, and causally explain the psychological phenomena of every individual person. If all of this can be done in terms of the interrelations of linear combinations of variables, then our heavy reliance on statistical linear models will have been justified. But can it? The rather imperfect fits of such models to our data do not provide such justification, so perhaps more fundamental forms of data representation would be prudent to look into, given our modern computing capabilities. Such a form is offered in this paper: point-to-point mappings from independent-variable to dependent-variable hyperspaces. Its mathematical relationship to linear models is defined and explains why linear models may often not be capable of fitting psychological data.
ISSN:1614-1881
1614-2241
DOI:10.1027/1614-2241/a000007