This study explores using transfer learning in machine learning for natural language processing (NLP) to create generic automated essay scoring (AES) models, providing instant online scoring for statewide writing assessments in K-12 education. The goal is to develop an instant online scorer that is generalizable to any prompt, addressing the…

The purpose of this research is to first estimate the item and ability parameters and the standard error values related to those parameters obtained from Unidimensional Item Response Theory (UIRT), bifactor (BIF) and Testlet Response Theory models (TRT) in the tests including testlets, when the number of testlets, number of independent items, and…

Since the beginning of the federal Race To The Top grant competition, Value-Added Measurement (VAM) has captured the attention of the American public through high-profile media representations of the tool and the controversy that surrounds it. In this paper, we build upon investigations of constructions of VAM in the media and present a discourse…

When conducting item reviews, analysts evaluate an array of statistical and graphical information to assess the fit of a field test (FT) item to an item response theory model. The process can be tedious, particularly when the number of human reviews (HR) to be completed is large. Furthermore, such a process leads to decisions that are susceptible…

We present an inference algorithm for perturbation models based on Poisson regression. The algorithm is designed to handle unclassified input with multiple errors described by independent mal-rules. This knowledge representation provides an intelligent tutoring system with local and global information about a student, such as error classification…

Theoretical perspectives on spelling characterize development as a progression through qualitatively different phases or as a process of more or less continuous growth. This study investigated the potential utility of a different perspective, the overlapping-wave model, for characterizing spelling development (Rittle-Johnson & Siegler, 1999). In…

We report a study of 10-14 year old children's use of additive strategies while solving ratio and proportion tasks. Rasch methodology was used to develop a diagnostic instrument that reveals children's misconceptions. Two versions of this instrument, one with "models" thought to facilitate proportional reasoning and one without were…

Inappropriate assessment procedures result in the misdiagnosis, misidentification, and misplacement of many African American students in special education. This article discusses poor teacher judgment, lack of cultural awareness among teachers, cultural discontinuity between home and school, and bias inherent in current tests used in special…