Leveraging Kindergarten and First-Grade Literacy Behaviors to Predict Third-Grade Reading Failure

<a href="https://embed.stanford.edu/iframe/?url=https%3A%2F%2Fpurl.stanford.edu%2Fgv633xg5647" class="su-underline">Show Content</a>

Abstract/Contents

Abstract: Early identification of students at-risk is an essential component of effective reading interventions. While Informal Reading Inventories (IRI) are used in districts across the country to identify students who need additional support, they have been shown to have poor psychometric properties and low diagnostic accuracy. The current longitudinal study serves as a “proof of concept” to show that utilizing more data-driven classification measures can significantly increase the accuracy of IRIs. Classification accuracies from three statistical learning models trained on Reading Inventory data were compared to the accuracy of classifications based on predefined cut-off scores for 1,928 students attending public schools in a large metropolitan district. Using binary classifiers significantly improved the overall accuracy of predicting third grade Reading achievement based on first grade Reading Levels, with an average increase of 27%. Results indicated that incorporating kindergarten Reading Skills (i.e. phonemic awareness, letter knowledge, etc.) to the training data significantly increased classification accuracy for the Logistic Regression Model and Support Vector Machine, but not for the Random Forest Classifier. The findings also showed that letter knowledge variables were more important than phonemic awareness skills in predicting third grade reading outcomes. Implications for practice and future research are discussed.

Type of resource	text
Date created	May 2018

Author	Zhang, Stephanie
Advisor	McCandliss, Bruce

Subject	Informal Reading Inventories
Subject	Fountas and Pinnell Benchmark Assessment System
Subject	Statistical Learning Models
Subject	Diagnostic Accuracy
Subject	Phonemic Awareness
Subject	Letter Knowledge
Subject	Graduate School of Education
Subject	Stanford
Genre	Thesis

Location	https://purl.stanford.edu/gv633xg5647

Use and reproduction: User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
License: This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).

Preferred Citation: Zhang, Stephanie. (2018). Leveraging Kindergarten and First-Grade Literacy Behaviors to Predict Third-Grade Reading Failure. Unpublished Honors Thesis. Stanford University, Stanford CA.

Undergraduate Honors Theses, Graduate School of Education

Loading usage metrics...