Kathleen E Sheehan

US Patent:

6484010, Nov 19, 2002

Filed:

Jul 31, 2000

Appl. No.:

09/629374

Inventors:

Kathleen M. Sheehan - Skillman NJ

Assignee:

Educational Testing Service - Princeton NJ

International Classification:

G09B 700

US Classification:

434362, 434118, 434322, 434350

Abstract:

A method for diagnostic assessment and proficiency scaling of test results is provided. The method uses as input a vector of item difficulty estimates for each of n items and a matrix of hypothesized skill classifications for each of said n items on each of skills. The method includes using a tree-based regression analysis based on the vector and matrix to model ways in which required skills interact with different item features to produce differences in item difficulty. This analysis identifies combinations of skills required to solve each item, and forms a plurality of clusters by grouping the items according to a predefined prediction rule based on skill classifications. A nonparametric smoothing technique is used to summarize student performance on the combinations of skills identified in the tree-based analysis. The smoothing technique results in cluster characteristic curves that provide a probability of responding correctly to items with specified skill requirements. The probability is expressed as a function of underlying test score.

US Patent:

8517738, Aug 27, 2013

Filed:

Jan 30, 2009

Appl. No.:

12/363243

Inventors:

Kathleen Marie Sheehan - Skillman NJ, US
Irene Kostin - Princeton NJ, US
Yoko Futagi - Lawrenceville NJ, US

Assignee:

Educational Testing Service - Princeton NJ

International Classification:

G09B 5/00

US Classification:

434169, 434156, 434167, 434178

Abstract:

A computer-implemented method, system, and computer program product for automatically assessing text difficulty. Text reading difficulty predictions are expressed on a scale that is aligned with published reading standards. Two distinct difficulty models are provided for informational and literary texts. A principal components analysis implemented on a large collection of texts is used to develop independent variables accounting for strong intercorrelations exhibited by many important linguistic features. Multiple dimensions of text variation are addressed, including new dimensions beyond syntactic complexity and semantic difficulty. Feedback about text difficulty is provided in a hierarchically structured format designed to support successful text adaptation efforts. The invention ensures that resulting text difficulty estimates are unbiased with respect to genre, are highly correlated with estimates provided by human experts, and are based on a more realistic model of the aspects of text variation that contribute to observed difficulty variation.

US Patent:

20120150534, Jun 14, 2012

Filed:

Dec 7, 2011

Appl. No.:

13/313372

Inventors:

Kathleen Marie Sheehan - Skillman NJ, US
Irene Kostin - Princeton NJ, US
Yoko Futagi - Lawrenceville NJ, US

Assignee:

EDUCATIONAL TESTING SERVICE - Princeton NJ

International Classification:

G06F 17/27

US Classification:

704 9, 704E11001

Abstract:

Systems and methods are provided for determining a difficulty level of a text. A determination is made as to a number of cohesive devices present in a text. A further determination is made as to a number of cohesive devices expected in the text. A cohesiveness metric is calculated based on the number of cohesive devices present in the text and the number of cohesive devices expected in the text, where the cohesiveness metric is used to identify a difficulty level of the text.

US Patent:

61448389, Nov 7, 2000

Filed:

Dec 18, 1998

Appl. No.:

9/215685

Inventors:

Kathleen M. Sheehan - Skillman NJ

Assignee:

Educational Testing Services - Princeton NJ

International Classification:

G09B 700

US Classification:

434362

Abstract:

A method for diagnostic assessment and proficiency scaling of test results is provided. The method uses as input a vector of item difficulty estimates for each of n items and a matrix of hypothesized skill classifications for each of said n items on each of k skills. The method includes using a tree-based regression analysis based on the vector and matrix to model ways in which required skills interact with different item features to produce differences in item difficulty. This analysis identifies combinations of skills required to solve each item, and forms a plurality of clusters by grouping the items according to a predefined prediction rule based on skill classifications. A nonparametric smoothing technique is used to summarize student performance on the combinations of skills identified in the tree-based analysis. The smoothing technique results in cluster characteristic curves that provide a probability of responding correctly to items with specified skill requirements. The probability is expressed as a function of underlying test score.