Performing Taxometric Analysis to Distinguish Categorical and Dimensional Variables
Author(s) -
John Ruscio,
Ayelet Meron Ruscio,
Lauren Carney
Publication year - 2011
Publication title -
journal of experimental psychopathology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.711
H-Index - 10
ISSN - 2043-8087
DOI - 10.5127/jep.010910
Subject(s) - categorical variable , selection (genetic algorithm) , computer science , psychology , data science , cognitive psychology , artificial intelligence , machine learning
A fundamental question facing clinical scientists is whether the constructs they are studying are categorical or dimensional in nature. The taxometric method was developed expressly to answer this question and is being used by a growing number of investigators to inform theory, research, and practice in psychopathology. The current paper provides a practical introduction to the method, updating earlier tutorials based on the findings of recent methodological studies. We offer revised guidelines for data requirements, indicator selection, parameter estimation, and procedure selection and implementation. We illustrate our recommended approach to taxometric analysis using idealized data sets as well as data sets representative of those found in clinical research. We close with advice to help newcomers get started on their own taxometric analyses.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom