Data SGP – How to Interpret Student Growth Percentiles and Growth Projections

Data sgp is an R package for calculating student growth percentiles and growth projections/trajectories. The package uses large scale, longitudinal education assessment data to compare students and their academic peer groups across time.

A student’s growth percentageile is a relative measure of how much they have grown in their academic skills from one year to the next. It is meant to be considered in conjunction with their scaled score and achievement level to gain a more complete picture of their learning. SGPs are intended to be used in an instructional context to help teachers identify which skills their students are struggling with and to inform instruction.

Typically, a high SGP indicates that a student has demonstrated greater relative growth than their peers. However, there are times that a student’s SGP will indicate less growth than expected or even negative growth (i.e., a negative SGP indicates that a student’s performance has declined from one assessment to the next). SGP scores are not static and can be influenced by many factors, including state and national trends in test results, the timing of assessments, and changes in the makeup of student cohorts from one year to the next.

SGPs are also useful for analyzing overall student growth at the district and school level. Because they are based on averages, district and school SGPs can fluctuate from year to year as a result of a variety of factors, including fluctuations in the mix of students tested and in the overall statewide performance level of students.

An individual’s SGP can be interpreted using two different formats: window specific and current. Window Specific SGPs are compared to a prior, window specific, SGP and reflect the amount of growth that a student has achieved during that timeframe. Current SGPs are a summary of the student’s most recent SGP and reflect the amount of growth that the student has experienced since their last SGP.

The sgpdata exemplar data set, included with the data sgp package when it is installed, models the format of data needed for running the lower level studentGrowthPercentiles and studentGrowthProjections functions. It is recommended that you review this exemplar data set before attempting to use these functions.

To run the sgpdata functions you will need to have the open source program R installed on your computer. This program is available for Windows, OSX and Linux and can be downloaded from CRAN. If you are new to R, we recommend that you familiarize yourself with the basic commands before attempting to run any analyses using this package.

To get started with using the data sgp package, visit our guide for administrators, educators and families or one of our three vignettes that provide detailed instructions for using the various data sgp functions. If you have questions or suggestions for future vignettes, please contact us via GitHub. We would love to hear from you!