Data SGP
Data sgp is a software package designed for the statistical analysis of student assessment data. It uses the open source statistical software environment R. It can be used on computers running Windows, OSX or Linux and is available free of charge with numerous online resources to help new users get started. This tool is not a replacement for existing data systems but can provide a powerful and efficient way to analyze large sets of educational assessment data.
Unlike traditional achievement measures, which only indicate whether students have met or exceeded a specified standard, data sgp shows the extent to which each student has achieved academic growth over time. These growth plots are produced using longitudinal data and utilize a student’s prior test scores as the measurement standard. By comparing each student’s actual performance to that of their academic peers, data sgp demonstrates each student’s academic progress and how far they must still travel in order to meet their educational goals.
These data sgp plots are also useful in measuring the effectiveness of a student’s learning program. Creating SGPs from a student’s standardized test score history requires complex calculations and is fraught with estimation errors. However, by using a student’s progress relative to their academic peers, a data sgp plot allows for a much more accurate measure of a student’s progress and indicates how well the educational system is serving each student.
The sgpdata package contains 4 examplar data sets for use with SGP analyses. The first, sgpData, specifies data in the WIDE format that is used by the lower level SGP functions studentGrowthPercentiles and studentGrowthProjections. The other three data sets, sgptData_LONG, sgpdata_INSTRUCTOR_NUMBER and sgp_data_INSTRUCTOR_NUMBER_LONG, specify long formatted data that is used by higher level wrapper functions like abcSGP, prepareSGP and analyzeSGP. It is recommended that for all but the simplest, one-off analyses that you use the LONG format for your SGP analyses as this offers numerous data preparation and storage benefits over the WIDE format.
In addition to the SGP data sets, sgpdata also contains two important lookup functions that allow districts to connect their student and instructor records. This is particularly important for districts that implement baseline-referenced SGPs as it can be challenging to ensure that students stay with the same instructor throughout the five years necessary for producing a complete set of baseline referenced growth data. The sgpData_INSTRUCTOR_NUMBER lookup function provides districts with a means of connecting students to their instructors through unique identifiers associated with their test results.
The process of data sgp is relatively simple once proper steps are taken to ensure that the data is correctly formatted and prepared for analysis. In almost all cases, any problems that arise while performing SGP analysis revert back to issues with data preparation so it is important to take care of this step carefully. For most users, once the basic steps are learned, the process becomes very straightforward. To learn more about the process and for additional examples, visit the sgpdata page on CRAN.