Data sgp is a software package for the R programming environment that provides classes, functions and data for performing SGP analyses. It is important to note that this software, like all programs used for statistical analysis, requires careful attention to data preparation and, as a result, almost all errors that arise during SGP analyses are due to problems with the input data.
SGP uses large scale longitudinal education assessment data to estimate student growth percentiles and student growth projections/trajectories using quantile regression. The results of these analyses provide insights into the progress that students are making towards their educational goals as well as what additional supports may be needed to help them reach those targets.
The data sgp package is currently being developed for the new, longitudinal Star assessments in Oregon. It will be expanded to include previous Star tests as the project continues. It is also possible that the SGP package will be adapted to other longitudinal assessment datasets for which it is appropriate.
The primary goal of data sgp is to create a unique and valuable research resource for the geochemical community. We believe that this resource will become a critical component of the growing effort to collect, curate and analyze large geochemical datasets. Unlike the popular concept of ‘big data’ that is being used to refer to datasets too large for traditional database management applications, our SGP project is not trying to assemble an unprecedented amount of information but rather is focused on answering specific research questions. We have designed our system to be as straightforward and easy to use as possible given the scope of the task at hand.
Data sgp is currently being utilized by researchers in several fields including geology, environmental science and education. The ability to access a large set of data and analytical tools from one source is enabling researchers to quickly develop and test new hypothesis in a more efficient manner than would be possible with data distributed across multiple sites and software applications. The SGP database will also be a valuable resource for accessing metadata, legacy data and unpublished analyses that are often difficult to locate.
Using data sgp
The main requirement for using the data sgp package is that it be installed on your computer. The SGP package relies on the R software environment which is available for Windows, OSX and Linux. We recommend that you take a look at the R documentation on CRAN for more information.
The SGP package will use a file called sgpData to perform its analyses. This file contains the student identifier, 5 years of Star assessment results (mean and median SGP) and 5 years of covariate data. The first column, ID, provides the unique student identifier and the next 5 columns, GRADE_2013, GRADE_2014, GRADE_2015, GRADE_2016 and GRADE_2017, provide the grade level of the test taken for each year. The final 5 columns, SS_2013, SS_2014, SS_2015, SS_2016 and SS_2017, contain the scale scores of the test.