Search statewide academic performance data

NOTE: Analysis conducted by American University student Thomas Furlong and the Investigative Editing Corps.

METHODOLOGY

Our analysis examined 2018-2019 Maine Department of Education data by school. We used linear regression to examine the relationship between demographic factors and student performance at varying school levels. Using a combination of public enrollment and assessment data we examined multiple factors, such as income, absenteeism and race. The strongest relationship with student performance was the percent of economically disadvantaged students at a school, which the state defines as the percent of students qualifying for free or reduced-price lunch.

The relationship was strongest at the high school level, and in math and English language arts. We did not find as strong a relationship with science. We excluded schools with fewer than 25 students from the analysis.

The analysis allowed us to look at the relationship between the variables. For example, in high school math and ELA, for every 10 percentage point increase in economically disadvantaged students the percent of students exceeding state expectations decreased by 6 points.

Using this analysis, we looked at how schools would perform if we controlled for their proportion of economically disadvantaged students to get a truer estimate of performance. This type of analysis is commonly used to assess school performance and is a way of  putting schools on a demographically “level” playing field.

We used the difference between how schools performed and how they would be predicted to perform to sort schools into three categories: those that performed better than expected, worse than expected or as expected given the percent of poor students. The cut-off was two standard deviations above or two standard deviations below the average difference. Typically about 70% of  schools fall within two standard deviations and would be classified as performing as expected.

The data also includes the number and the percent of economically disadvantaged students in each school district.

Related Stories