Data SGP is an analysis tool for longitudinal student assessment data. It generates statistical growth plots (SGP) that illustrate a student’s academic progress relative to their peers based on standardised test scores and covariate information. The SGP enables educators to compare students’ current performance levels with their academic peer groups over time, and can predict future progress.
The SGP is a free and open source software application. It runs on computers running the R programming language. There are versions of R available for Windows, OSX and Linux and users can download it from CRAN. The SGP requires a data set, which is a collection of files that contains all the information needed for analysis. There are a number of data sets that can be used with the SGP. The sgpData_LONG data set, which is the preferred choice for most SGP analyses, has 7 required variables: VALID_CASE, CONTENT_AREA, YEAR, ID, SCALE_SCORE, GRADE and ACHIEVEMENT_LEVEL (on required if creating individual level student growth and achievement plots).
Students can use the drop-down menus to select a single school year. Within a school year, the user can then choose a testing window to analyze. To compare a student’s performance with the performance of their peer group over time, the user can also select the comparison year: Fall to Winter or Spring to Summer.
SGPs are calculated by comparing students’ current performance with the performance of their academic peer group in previous MCAS administrations. This means that two students who have the same scaled score history will have the same SGP. However, two students with different score histories will have different SGPs.
The SGP is designed to be as transparent as possible for educational stakeholders. Its algorithms are documented in the SGP documentation. Additionally, the SGP is designed to be extensible by developers. Developers can add new SGP algorithms and create new visualizations using the API.
In order to run SGP analyses, the user must have access to a computer running the R programming language. A copy of the latest version of R can be downloaded for free from the R website. If the user has never used R, there are many resources available to help get started.
The SGP is a free and open-source application for the R language that allows users to create statistical growth plots and percentile growth projections/trajectories for students in Massachusetts. It uses a methodology known as “coefficient matrix estimation” to calculate the growth models for each student. This method is more accurate than a simple percentile score calculation. It is also more flexible than other methods of calculating percentiles, as it accounts for the effects of multiple years of testing on the student’s current performance. This makes the SGP a valuable tool for educators in their efforts to improve student achievement. SGPs can be used for teacher evaluation, curriculum development, and other research activities. The SGP also supports the creation of lookup tables that can be imported into school information systems for additional analysis.