Bayesian model determination for multivariate ordinal and binary data

Abstract. The aim of the present study was to examine the construct and cross-cultural validity of the Beck Hopelessness Scale (BHS; Beck, Weissman, Lester, & Trexler, 1974 ). Beck et al. applied exploratory Principal Components Analysis and argued that the scale measured three specific components (affective, motivational, and cognitive). Subsequent studies identified one, two, three, or more factors, highlighting a lack of clarity regarding the scale’s construct validity. In a large clinical sample, we tested the original three-factor model and explored alternative models using both confirmatory and exploratory factor analytical techniques appropriate for analyzing binary data. In doing so, we investigated whether method variance needs to be taken into account in understanding the structure of the BHS. Our findings supported a bifactor model that explicitly included method effects. We concluded that the BHS measures a single underlying construct of hopelessness, and that an incorporation of method effects consolidates previous findings where positively and negatively worded items loaded on separate factors. Our study further contributes to establishing the cross-cultural validity of this instrument by showing that BHS scores differentiate between depressed, anxious, and nonclinical groups in a Hungarian population.

Download Full-text

Evaluating the Validity of a Bayesian Program for Predicting Stage in Hodgkin’s Disease

Methods of Information in Medicine ◽

10.1055/s-0038-1635305 ◽

1981 ◽

Vol 20 (03) ◽

pp. 174-178 ◽

Cited By ~ 2

Author(s):

A. I. Barnett ◽

J. Cynthia ◽

F. Jane ◽

Nancy Gutensohn ◽

B. Davies

Keyword(s):

New England ◽

Hodgkin's Disease ◽

Bayesian Model ◽

Medical Center ◽

Hodgkin’S Disease ◽

Test Procedure ◽

Disease Patient ◽

Probabilistic Information ◽

Probabilistic Forecasts ◽

England Medical

A Bayesian model that provides probabilistic information about the spread of malignancy in a Hodgkin’s disease patient has been developed at the Tufts New England Medical Center. In assessing the model’s reliability, it seemed important to use it to make predictions about patients other than those relevant to its construction. The accuracy of these predictions could then be tested statistically. This paper describes such a test, based on 243 Hodgkin’s disease patients of known pathologic stage. The results obtained were supportive of the model, and the test procedure might interest those wishing to determine whether the imperfections that attend any attempt to make probabilistic forecasts have gravely damaged their accuracy.

Download Full-text

Machine Learning of Motor Vehicle Accident Categories from Narrative Data

Methods of Information in Medicine ◽

10.1055/s-0038-1634680 ◽

1996 ◽

Vol 35 (04/05) ◽

pp. 309-316 ◽

Cited By ~ 4

Author(s):

M. R. Lehto ◽

G. S. Sorock

Keyword(s):

Machine Learning ◽

Bayesian Model ◽

Keyword Search ◽

Motor Vehicle ◽

Motor Vehicle Accident ◽

Computer Search ◽

Vehicle Accident ◽

Learning Technique ◽

Expert Ratings ◽

Keyword Searches

Abstract:Bayesian inferencing as a machine learning technique was evaluated for identifying pre-crash activity and crash type from accident narratives describing 3,686 motor vehicle crashes. It was hypothesized that a Bayesian model could learn from a computer search for 63 keywords related to accident categories. Learning was described in terms of the ability to accurately classify previously unclassifiable narratives not containing the original keywords. When narratives contained keywords, the results obtained using both the Bayesian model and keyword search corresponded closely to expert ratings (P(detection)≥0.9, and P(false positive)≤0.05). For narratives not containing keywords, when the threshold used by the Bayesian model was varied between p>0.5 and p>0.9, the overall probability of detecting a category assigned by the expert varied between 67% and 12%. False positives correspondingly varied between 32% and 3%. These latter results demonstrated that the Bayesian system learned from the results of the keyword searches.

Download Full-text