Data SGP

Data sgp is an analysis package for the R software environment. R is free and open source and has versions for Window, OSX and Linux. Like any statistical analyses, SGP requires proper data preparation. However, once data is prepared correctly, SGP analyses are designed to be simple and straightforward. Any errors that arise in SGP analysis usually revert back to data preparation issues. As a result, any new users of SGP should spend some time familiarizing themselves with the basics of R and the data preparation process before trying to run SGP analyses.

SGP measures student growth by comparing current year scores with the scores of students with comparable score histories on a given subject-matter test. Individual SGPs can be aggregated to summarise the performance of subgroups, classes, schools and districts. Since the introduction of student growth as an accountability metric, median SGPs have been the primary summary tool used for these aggregates. This article presents a rationale for moving away from median SGPs and toward using means as the primary summary statistic.

While SGPs can be used to estimate student average scale scores, they are more commonly employed to calculate the distribution of those scores. In the case of an accelerated class, for example, SGPs can be aggregated to define the class median and prevent the results from being distorted by the few students that cannot keep up with their peers. Similarly, in the case of a state-wide program, SGPs can be aggregated to provide an indication of whether a program is working or not by examining the number of students whose growth falls below the class median.

A key component of the SGP methodology is the creation of knots and boundaries for the distribution of scale score scores. These knots and boundaries are calculated using a distribution from several years of compiled data so that any anomalies in the single year data are smoothed out.

The SGP packages provides a convenient way to manage this distribution and to run SGP analyses for each of the states in the United States. It is important that the users of this software be familiar with the data sgp formats used in each state as differences in the format can lead to problems with the calculations.

For more information on the SGP packages and how to use them, refer to the SGP documentation. If you have questions, please feel free to contact us. We are available to answer any questions or assist with running SGP analyses for your school. We look forward to hearing from you.