Document Detail


Stepwise variable selection and maximum likelihood estimation of smoothing factors of kernel functions for nonparametric discriminant functions evaluated by different criteria.
MedLine Citation:
PMID:  3971705     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Kernel functions are used to estimate the probability density functions of variables for nonparametric discriminant analysis. In connection with stepwise variable identification a stepwise maximum likelihood estimation procedure for the estimation of smoothing factors of the kernel functions is developed. This procedure allows a step-by-step estimation of smoothing factors for every variable which is considered to be added to the model or which is examined to substitute a variable in a model. Different criteria for model evaluation in stepwise discriminant analysis are discussed. Beside criteria, like distance and dependence functions and the error and nonerror rate, a criterion which considers the ratio of probability densities of different classes at point x is proposed for stepwise variable identification. An application of the procedures described in this study to a medical decision problem shows the importance of stepwise parameter estimation of kernel functions for nonparametric discriminant analysis and the role of different model evaluation criteria for the selection of the best subset of variables.
Authors:
K P Pfeiffer
Related Documents :
24018525 - Data governance for health care providers.
24292145 - Current trends in the development of the electrochemiluminescent immunosensors.
11878225 - Estimating distributions with increasing failure rate in an imperfect repair model.
11315015 - Estimating equations for a latent transition model with multiple discrete indicators.
17825015 - Sampling for conditional inference on case-control data.
18943755 - Identifying risk factors for european stone fruit yellows from a survey.
Publication Detail:
Type:  Comparative Study; Journal Article    
Journal Detail:
Title:  Computers and biomedical research, an international journal     Volume:  18     ISSN:  0010-4809     ISO Abbreviation:  Comput. Biomed. Res.     Publication Date:  1985 Feb 
Date Detail:
Created Date:  1985-04-19     Completed Date:  1985-04-19     Revised Date:  2006-11-15    
Medline Journal Info:
Nlm Unique ID:  0100331     Medline TA:  Comput Biomed Res     Country:  UNITED STATES    
Other Details:
Languages:  eng     Pagination:  46-61     Citation Subset:  IM    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Biometry*
Cerebrovascular Disorders / etiology
Computers
Humans
Probability
Risk

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Cross-correlation technique for arrhythmia detection using PR and PP intervals.
Next Document:  Virtual leads for the ambulatory ECG monitoring: remarks on the persistency of their direction.