Data Analysis and Modeling
Data Analysis and Modeling
This chapter provides a guidebook to the basic issues in quantitative data analysis and modeling. It shows how we test the quality of a model and fit the model to observed data. The quality of a model or theory includes qualitative assessments related to internal consistency, breadth of application, and the ability to make new and useful predictions. Another assessment of the quality of a model is its ability to predict or fit the observed behavioral data in relevant domains quantitatively. Two criteria for fitting a model to data are considered, a least-squared error criterion and a maximum likelihood criterion, along with methods of estimating the best-fitting parameters of the models. Bootstrap methods are used to estimate the variability of derived data and model parameters. Several methods of comparing and selecting between models are considered. The chapter uses typical psychophysical testing situations to illustrate several standard applications of these methods of data analysis and modeling.
Keywords: Modeling visual functions, Model applicability, Model fitting criteria, Error function, Least-squared error, Maximum likelihood, Parameter estimation, Parameter variability, Bootstrap methods, Model selection
MIT Press Scholarship Online requires a subscription or purchase to access the full text of books within the service. Public users can however freely search the site and view the abstracts and keywords for each book and chapter.
Please, subscribe or login to access full text content.
If you think you should have access to this title, please contact your librarian.
To troubleshoot, please check our FAQs, and if you can't find the answer there, please contact us.