Data SGP is an open source software package for calculating student growth percentiles (SGP). The package utilizes a least squares model to estimate the latent achievement trait and compare it to growth standards established on teacher evaluation criteria and student covariates. The SGP process is iterative and requires a large number of tests to be run in order to produce a sufficiently accurate estimate of the latent achievement trait. This iterative process can be time consuming and computationally expensive, which makes it impractical for many school districts to use the SGP method.
SGP analyses are intended to be as simple as possible, but they do require some computer skills and programming knowledge in order to be properly conducted. The bulk of the time involved in SGP analysis is spent on the initial data preparation and it is critical that this be done correctly. Once the data is prepared properly, running SGP calculations is relatively quick and straightforward.
To use data sgp, you will need to have access to a computer running the R statistical software program. R is available for Window, OSX, and Linux and is free to download and install. It is recommended that you spend some time familiarizing yourself with R before diving into conducting SGP analyses.
Using the sgpData package to prepare and analyze SGP data is relatively straight forward. Please refer to the sgpData vignette for more detailed information on how to use the sgpData package and wide format data sets in general.
The first column in sgpData, ID, provides the unique student identifier and the next five columns, GRADE_2013, GRADE_2014, GRADE_2015, GRADE_2016, and GRADE_2017, provide the test scores for each of the students across the five years of their assessment history. The test score is a scaled score that represents a students performance on a specific test.
A scaled score is a number that is created by multiplying a raw test score by a conversion factor and dividing it by the total number of test scores in the dataset. This results in a decimal value that is used to calculate the student growth percentile.
A student’s growth percentile is the percentage of students in her grade who have a higher or lower SGP than the student. In other words, if a student’s test score in her most recent year is higher than 85 percent of her academic peers she has a high SGP. Conversely, if her test score is lower than 85 percent of her academic peers she has low SGP.
SGP can be a powerful tool for understanding student learning and growth. However, it can be difficult to interpret if you are not familiar with the concept or how to use the SGP calculator. This article aims to help introduce the basic concepts of SGP and how to use the data sgp calculator. We hope this will make it easier for educators to incorporate SGP into their classrooms. Thanks for reading!