Data sgp is the collective of aggregated student performance data collected over time that teachers and administrators use to make decisions about instruction and assessment. It includes individual-level measures like test scores and growth percentiles, as well as aggregated measures at the school/district/classroom level such as class size, attendance rates, and graduation rates. Data sgp provides valuable information about student learning that can help identify areas for improvement, inform classroom practices, evaluate schools/districts, and support broader research initiatives.
In SGP analyses, student raw scores are converted to scaled scores for comparison with an average of scaled scores from students with similar prior test scores (their academic peers). The resulting percentages indicate how far a student’s score has progressed in relation to his or her academic peers. This is a more meaningful measure of student progress than merely reporting the score, as it provides a sense of whether the student’s current score is below, above or at the same level as his or her academic peers.
SGP also provides a range of projected outcomes for each student based on his or her historical growth trajectories. These projections show the likelihood that a student will attain proficiency and what his or her score might be in future years, provided that the student continues along the same growth trajectory. This is a useful tool for planning instructional interventions to ensure that every student has an opportunity to succeed.
Using SGP to determine student needs is most effective when the data is collected over a large period of time, in order to capture the full range of student growth. This is why it is important to use multiple measures, including both the standardized tests and the student growth percentiles, to obtain the most complete picture of student learning. The results from both measures should be reported to teachers, parents, and the community, as they provide a complete description of how each student is performing in the classroom.
A key challenge in analyzing SGP is making sure that the data are free from bias. Bias can occur when the raw student scores are correlated with other variables, such as the teacher’s or school’s characteristics or the design of the baseline cohort. Bias can also be introduced when student data are analyzed using techniques that assume a linear relationship between the student’s initial assessment score and his or her future growth.
The SGPdata package provides 4 example data sets for use in SGP analyses. The first of these, sgpData, specifies data in the WIDE format that’s used with the lower level SGP functions studentGrowthPercentiles and studentGrowthProjections. The other three examples, sgpData_LONG, sgptData_LONG and sgpData_INSTRUCTOR_NUMBER, specify data in the LONG data format that’s used by higher level SGP functions such as abcSGP, prepareSGP, and analyzeSGP. For all but the simplest, one-off analyses, it’s generally best to use LONG data formats whenever possible as they offer many preparation and storage benefits over WIDE data. To learn more about how to use these example data sets, please consult the SGPdata vignette.
