Bayesian Networks In Educational Testing

@article{Vomlel2002BayesianNI,
  title={Bayesian Networks In Educational Testing},
  author={Jir{\'i} Vomlel},
  journal={Int. J. Uncertain. Fuzziness Knowl. Based Syst.},
  year={2002},
  volume={12},
  pages={83-100}
}
  • J. Vomlel
  • Published 2002
  • Computer Science
  • Int. J. Uncertain. Fuzziness Knowl. Based Syst.
In this paper we discuss applications of Bayesian networks to educational testing. Namely, we deal with the diagnosis of person's skills. We show that when modeling dependence between skills we can get better diagnosis faster. We present results of experiments with basic operations that use fractions. The experiments suggest that the test design can benefit from a Bayesian network that models relations between skills, not only in the case of an adaptive test but also when designing a fixed (non… 
Bayesian Network Models for Adaptive Testing
TLDR
This research uses Bayesian networks to create a model of tested humans, which was tested and compared by cross-validation and brought a clearer view on the model selection problem.
Student Skill Models in Adaptive Testing
TLDR
This paper provides a common framework, a generic model, for Computerized Adaptive Testing (CAT) for different model types, using three different types of models, Item Response Theory, Bayesian Networks, and Neural Networks, that instantiate the generic model.
Using Bayesian Networks in Computerized Tests 1
TLDR
The integration and evaluation of an existing generic Bayesian student model (GBSM) into an existing computerized testing system within the Mathematics Education Project (PmatE Projecto Matemática Ensino) of the University of Aveiro and results show a high degree of agreement among the scores given by the experts and also among the diagnosis provided by the BSM in the written exam and the experts average.
Item-based Bayesian Student Models
TLDR
By relying on graph models with observable nodes, learned student models can be built from small data sets with standard Bayesian Network techniques and Naı̈ve Bayesian models and shown how to feed a concept assessment model from a learned observable nodes model.
Bayesian Networks in Educational Assessment
TLDR
This critical review outlines the existing research on BN in educational assessment, providing an introduction to the ITS literature for the psychometric community, and points out several promising research paths.
Dynamic versus Static Student Models Based on Bayesian Networks: An Empirical Study
TLDR
An empirical study with simulated students that allows to compare the accuracy of two models based on Bayesian networks in the context of student modelling: a dynamic model versus an static model shows that the performance of both models is very similar.
Probabilistic Models for Computerized Adaptive Testing: Experiments
TLDR
This paper presents models using Item Response Theory (IRT - standard CAT method), Bayesian networks, and neural networks for CAT, and conducted simulated CAT tests on empirical data.
Using Bayesian Networks for Modeling Students' Learning Bugs and Sub-skills
TLDR
The results show that using Bayesian networks to diagnose the existence of bugs and sub-skills of students can get good performance.
Bayesian Network Approach to Computerized Adaptive Testing
TLDR
A novel testing method, Bayesian network-based approach to Computerized Adaptive Testing (CAT), which can estimate proficiency of the examinee effectively and efficiently and can improve accuracy and speed of estimating examinee’s proficiency.
Probabilistic Models for Computerized Adaptive Testing
TLDR
This paper presents three different methods for CAT, one of them, the item response theory, is a well established method, while the other two, Bayesian and neural networks, are new in the area of educational testing.
...
...

References

SHOWING 1-10 OF 34 REFERENCES
A Bayesian Diagnostic Algorithm for Student Modeling and its Evaluation
TLDR
A new approach to diagnosis in student modeling based on the use of Bayesian Networks and Computer Adaptive Tests is presented and a new integrated Bayesian student model is defined and then combined with an Adaptive Testing algorithm.
Bayes Nets in Educational Assessment: Where the Numbers Come From
TLDR
Details for the special cases of item response theory (IRT) and multivariate latent class modeling are given, with a numerical example of the latter.
Bayes Nets in Educational Assessment: Where Do the Numbers Come from? CSE Technical Report.
TLDR
Details for the special cases of item response theory (IRT) and multivariate latent class modeling are given, with a numerical example of the latter.
Models for Conditional Probability Tables in Educational Assessment
TLDR
The method described here combines judgements about the structure of the conditional probabilities table with Item Response Theory methods for partial credit scoring to produce a conditional probability table or a prior distribution for a learning algorithm.
On-Line Student Modeling for Coached Problem Solving Using Bayesian Networks
TLDR
The knowledge structures represented in the student model are described and the implementation of the Bayesian network assessor is discussed, and a preliminary evaluation of the time performance of stochastic sampling algorithms to update the network is presented.
Computerized Adaptive Testing: Overview and Introduction
TLDR
The elements of CAT discussed here include item selection procedures, estimation of the latent trait, item exposure, measurement precision, and item bank development.
Controlling Item Exposure Conditional on Ability in Computerized Adaptive Testing
TLDR
A new method of controlling the exposure rate of items conditional on ability level is presented in the continuous testing environment made possible by the computerized admin-istration of a test.
Causation, prediction, and search
TLDR
The authors axiomatize the connection between causal structure and probabilistic independence, explore several varieties of causal indistinguishability, formulate a theory of manipulation, and develop asymptotically reliable procedures for searching over equivalence classes of causal models.
Comparing Bayesian Network Classifiers
TLDR
Experimental results show the obtained classifiers are competitive with (or superior to) the best known classifiers, based on both Bayesian networks and other formalisms; and that the computational time for learning and using these classifiers is relatively small.
On Test Selection Strategies for Belief Networks
TLDR
Value-of-information analyses provide a formal strategy for selecting the next test(s) and the complete decision-theoretic approach is impractical and researchers have sought approximations.
...
...