Data SGP is a tool that allows districts to quickly access and analyze their students’ growth information. Using student-level data, SGP compares a student’s growth to that of his or her academic peers nationwide – those who are in the same grade and have a similar achievement history on Star assessments. It can be used to identify areas of strength and weakness in a student’s academic progress, and can inform classroom instruction. It can also help educators develop SLOs and district-wide initiatives.

SGP analyses typically utilize statistical methods such as least squares regression modeling and Bayesian inference to estimate latent achievement trait models for a student. These models are then compared against growth standards established through teacher evaluation criteria and student covariates to minimize estimation errors (Akram, Erickson & Meyer 2013; Lockwood & Castellano 2015). SGP analyses can be conducted at both the classroom and school-wide level, but they are most often performed on an individual student basis to help inform classroom practice.

As a result, the data is very sensitive and requires careful handling. To ensure its security, it must be accessed only by authorized personnel and only on a secure network. The tool’s underlying software, R, is open source and available for Windows, OSX, and Linux. It is recommended that users spend some time familiarizing themselves with the software before diving into SGP analyses. Any errors that come up during analyses will likely revert back to data preparation issues and thus should be corrected as soon as possible.

While it is important to have access to comprehensive and accurate SGP data, it is equally vital to have the tools to make it usable. For example, the Macomb and Clare-Gladwin ISDs have made their SGP data publicly accessible in formats compatible with operational SGP analyses. This makes it easy for districts to use their data to support classroom instruction and guide SLO development. It also enables districts to easily connect instructors with their students through the sgpData_INSTRUCTOR_NUMBER lookup table.

In addition, the sgpData package includes an exemplar WIDE and LONG formatted data set to assist users in setting up their data. The lower level functions (studentGrowthPercentiles and studentGrowthProjections) require WIDE formatted data whereas higher level functions (wrappers for the lower level functions) require the LONG formatted data. If you intend to run anything but the most basic of analyses we strongly recommend setting up your data in the long format as much of the package’s capability is built around using this. It is also the format required for SGP state level meta-data. For more details see the SGPdata documentation.