Full Length Research Paper
Abstract
This study investigated the influences of district-related variables on a district’s academic performance. Arkansas augmented benchmark examination scores were used to measure a district’s scholastic achievement. Spatial analysis fit each district’s performance to its geographical location; spatial autocorrelation measured the amount of influence one district’s scores has on its neighbours. Regression, both ordinary least squares regression (OLS) and spatial auto regression (SAR), quantified how much a district’s academic scores were accounted for by the proportion of white students enrolled, the appraised value of property within a district, and the proportion of students receiving federally assisted lunches. The OLS model was able to account for 30% to 60% of the variation in scores. When ethnicity was predominately white, the district’s scores were higher; the more federally assisted lunches a district’s enrolment received, the lower scores tended to be. Spatial analysis indicated that a district’s performance was highly influenced by the surrounding districts. Major findings showed that, for 2008 data, once fit to an OLS regression model, the spatial dependency completely disappears for mathematics responses, but not literacy. Similar results were seen in 2009 and 2010, though they were not as systematically patterned.
Keywords: Arkansas education, regression, spatial analysis and spatial autocorrelation.
Copyright © 2024 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0