incomplete knowledge in a domain. In this study, the foundations of a combinatorial algorithm that will provide the universal set of states of knowledge will be introduced. Each state of knowledge is represented by a list of “can/cannot” cognitive tasks and processes (called cognitively relevant attributes or latent variables) which are usually unobservable. A Boolean descriptive function will be introduced as a mapping between the attribute space spanned by latent attribute variables and the item response space spanned by item score variables. The Boolean descriptive function plays the role of uncovering the unobservable content of a black box. Once all the possible classes are retrieved explicitly and expressed by a set of ideal item response patterns which are described by a “can/cannot” list of latent attributes, the notion of bug distributions and statistical pattern classification techniques will enable us to diagnose students' states of knowledge accurately. Moreover, investigations on algebraic properties of these logically-derived ideal-response patterns will provide an insight into the structures of the test and dataset.
Diagnosing cognitive errors possessed by examinees can be considered as a pattern classification problem which is designed to classify a sequential input of stimuli into one of several predetermined groups. The sequential inputs in our context are item responses and the predetermined groups are various states of knowledge resulting from misconceptions or different degrees of incomplete knowledge in a domain. In this study, the foundations of a combinatorial algorithm that will provide the universal set of states of knowledge will be introduced. Each state of knowledge is represented by a list of “can/cannot” cognitive tasks and processes (called cognitively relevant attributes or latent variables) which are usually unobservable. A Boolean descriptive function will be introduced as a mapping between the attribute space spanned by latent attribute variables and the item response space spanned by item score variables. The Boolean descriptive function plays the role of uncovering the unobservable content of a black box. Once all the possible classes are retrieved explicitly and expressed by a set of ideal item response patterns which are described by a “can/cannot” list of latent attributes, the notion of bug distributions and statistical pattern classification techniques will enable us to diagnose students' states of knowledge accurately. Moreover, investigations on algebraic properties of these logically-derived-ideal-response patterns will provide an insight into the structures of the test and dataset.
[1]
G. Masters.
A rasch model for partial credit scoring
,
1982
.
[2]
F. Samejima.
Estimation of latent ability using a response pattern of graded scores
,
1969
.
[3]
K. Tatsuoka.
RULE SPACE: AN APPROACH FOR DEALING WITH MISCONCEPTIONS BASED ON ITEM RESPONSE THEORY
,
1983
.
[4]
Christine E. DeMars,et al.
Item Response Theory
,
2010,
Assessing Measurement Invariance for Applied Research.
[5]
R. Darrell Bock,et al.
Estimating item parameters and latent ability when responses are scored in two or more nominal categories
,
1972
.
[6]
Kikumi K. Tatsuoka,et al.
Analysis of Errors in Fraction Addition and Subtraction Problems. Final Report.
,
1984
.
[7]
K. Tatsuoka.
Toward an Integration of Item-Response Theory and Cognitive Error Diagnosis.
,
1987
.
[8]
Kikumi K. Tatsuoka,et al.
Bug Distribution and Pattern Classification.
,
1985
.
[9]
Kikumi K. Tatsuoka,et al.
Bug distribution and statistical pattern classification
,
1987
.
[10]
Kikumi K. Tatsuoka,et al.
A Probabilistic Model for Diagnosing Misconceptions By The Pattern Classification Approach
,
1985
.