Latent property diagnosing procedure

• US 7,457,581 B2
• Filed: 12/08/2004
• Issued: 11/25/2008
• Est. Priority Date: 04/20/2001
• Status: Expired due to Fees

• Current Assignee: Educational Testing Service
• Original Assignee: Educational Testing Service
• Inventors: Hartz, Sarah M., Stout, William F.
• Primary Examiner(s): Fernstrom; Kurt
• Application Number:
  US10/970,795
• Publication Number:
  US 20050123893A1
• Time in Patent Office: 1,448 Days
• Field of Search: 434/156, 434/167, 434/178, 434/322, 434/323, 434/327, 434/335, 434/336, 434/350, 434/351, 434/353, 434/354, 434/362
• US Class Current: 434/353
• CPC Class Codes: G09B 23/02 for mathematics for statics or dynamics G09B23/08
• CPC Class Codes: G09B 7/00 Electrically-operated teaching apparatus or devices working with questions and answers mechanically operated G09B3/00; computing arrangements G06F

Abstract

The present invention provides a method of doing cognitive diagnosis of mental skills, medical and psychiatric diagnosis of diseases and disorders, and in general the diagnosing of latent properties of a set of objects, usually people, for which multiple pieces of binary (dichotomous) information about the objects are available, for example testing examinees using right/wrong scored test questions. Settings where the present invention can be applied but are not limited to include classrooms at all levels, web-based instruction, corporate in-house training, large scale standardized tests, and medical and psychiatric settings. Uses include but are not limited to individual learner feedback, learner remediation, group level educational assessment, and medical and psychiatric treatment.

Claims

1. A computer implemented method for providing remedial instruction to a student, the method comprising:

receiving a response from a student for each of a plurality of items;

determining an item/attribute incidence matrix, including reparameterizing and calibrating an underlying model as a Bayesian model with an assumed positive correlational attribute structure;

determining a mastery value for each attribute based on the item responses and the item/attribute incidence matrix; and

providing instruction to the student based on the determined mastery value.

2. The method of claim 1 wherein the item/attribute incidence matrix includes a first value for each entry corresponding to an attribute that is needed to correctly answer an item, wherein the item/attribute incidence matrix includes a second value for each entry corresponding to an attribute that is not needed to correctly answer an item.

3. The method of claim 1 wherein providing instruction to the student comprises:

instructing the student in a subject pertaining to the attribute having a smallest mastery value.

4. The method of claim 1 wherein providing instruction to the student comprises:

instructing the student in each subject pertaining to an attribute having a mastery value below a threshold.

5. The method of claim 1 wherein providing instruction to the student comprises:

selecting a subject for instruction based on a pattern of mastery values across all attributes; and

instructing the student in the subject for instruction.

6. A computer implemented method for providing remedial instruction to a plurality of students, the method comprising:

receiving a response from each of one or more students for each of a plurality of items;

determining an item/attribute incidence matrix, including reparameterizing and calibrating an underlying model as a Bayesian model with an assumed positive correlational attribute structure;

for each student, determining a mastery value for each attribute based on the item responses received from the student and the item/attribute incidence matrix; and

providing instruction based on the determined mastery values.

7. The method of claim 6 wherein the item/attribute incidence matrix includes a first value for each entry corresponding to an attribute that is needed to correctly answer an item, wherein the item/attribute incidence matrix includes a second value for each entry corresponding to an attribute that is not needed to correctly answer an item.

8. The method of claim 6 wherein providing instruction based on the determined mastery values comprises:

for each attribute, determining the average mastery value for the attribute for a plurality of students; and

instructing the plurality of students in a subject pertaining to the attribute having a smallest average mastery value.

9. The method of claim 6 wherein providing instruction based on the determined mastery values comprises:

for each attribute, determining an average mastery value for the attribute for a plurality of students; and

instructing the plurality of students in a subject pertaining to each attribute having an average mastery value below a threshold.

10. The method of claim 6 wherein providing instruction based on the determined mastery values comprises:

selecting a subject for instruction based on a pattern of mastery values across all attributes; and

instructing the plurality of students in the subject for instruction.

11. The method of claim 6, further comprising:

for each student, placing the student into one of a plurality of groups based on a pattern of mastery values across all attributes.

12. The method of claim 11, further comprising, for each group:

selecting a subject for instruction based on the pattern of mastery values for the group; and

instructing the group in the subject for instruction.

13. The method of claim 11, further comprising:

placing each group in an instructional module based on the pattern of mastery values for the group.

14. A computer implemented method for assessing instructional effectiveness, the method comprising:

receiving a response from each of a plurality of students for each of a plurality of items;

determining an item/attribute incidence matrix, including reparameterizing and calibrating an underlying model as a Bayesian model with an assumed positive correlational attribute structure;

for each student, determining a mastery value for each attribute based on the item responses received from the student and the item/attribute incidence matrix;

for each attribute, determining an average mastery value for all students; and

for each attribute, determining an effectiveness for instruction based on the average mastery value.