Getting Started With Data SGP

Data sgp is an analysis tool used to calculate student growth percentiles (SGP) and student growth projections/trajectories using large scale, longitudinal education assessment data. It uses quantitativeile regression to estimate conditional density associated with student achievement history and then produces a number, called the SGP, that represents the relative performance of the student in comparison to others with similar score histories. The SGP can be reported at the school, district and subgroup level.

A SGP tells you how much more a student learned from one year to the next on state assessments compared with the average student in their grade and content area. It is a number on a scale of 1 to 99, and it provides insight into how well students are learning in relation to their peers. If a student has an SGP of 85, we know that the student has made more growth than about 85 percent of all other students who have the same starting point on their state assessment.

SGPs are normalized so that they can be compared across different assessments and grades. This is done by making the scale scores from each assessment normalized to the same scale of 0-100. Then the percentiles are recalculated to take into account the relative differences in the starting points of the students. For example, a sixth grade student with an assessment score of 350 would have a SGP of 85 on the ELA statewide SGP, while a fifth grade student with an assessment score of 300 would have a SGP of 50 on that same statewide SGP.

While SGPs can be compared to one another, it is important to remember that the results do not indicate if a particular level of growth is deemed adequate by stakeholders. That is why DPI also relies on value-added measures in its accountability system.

Getting Started with Data SGP

In order to use data sgp, you will need a computer that has R installed. This is a free and open source software program available for Windows, OSX and Linux. There are many resources on the CRAN website to get you started with R. Running SGP analyses also assumes familiarity with the concepts of data governance. This is a set of practices that ensures that data is being managed appropriately and in accordance with policy and regulations.

Data sgp requires the data set sgpData in LONG format with 7 required variables: VALID_CASE, CONTENT_AREA, YEAR, ID, SCALE_SCORE, GRADE and ACHIEVEMENT_LEVEL. In addition, sgpData must have the embedded SGPstateData meta-data present in each record for analysis. For more information on how to use these data see the SGP data analysis vignette for more detailed documentation on how to utilize sgpData with SGP functions.