EdSurvey 3.0 is now available on CRAN-R. This latest update provides education researchers with the ability to tap into three new powerful functions that utilize cutting-edge techniques, including latent regression and artificial intelligence (AI), to leverage complex statistical analysis of large-scale assessment data.
Users can now make use of the following functions when using the latest version of EdSurvey:
- The first new function, “mml.sdf,” allows researchers to access the direct estimation functionality of the Dire package directly through EdSurvey. The direct estimation is a latent regression modeling of student proficiency for National Assessment of Educational Progress (NAEP) and Trends in International Mathematics and Science Study (TIMSS) assessment data. Read more about the Dire R package in our previous post.
- The second function, “drawPVs,” enables users to draw plausible values after running the latent regression model through the mml.sdf function. What was once a resource available mainly to those with access to specialized tools from test companies is now an option for all through this new function built into EdSurvey.
- The third function, “suggestWeights,” uses artificial intelligence to suggest appropriate sampling weights based on variables that researchers specify for their analytical models. Currently, this function is available to use with the National Center for Education Statistics (NCES) Early Childhood Longitudinal Study, Kindergarten Class of 2010-11 (ECLS-K:2011) data, but it may be extended to other studies in the future.
The EdSurvey development team is always looking for ways to innovate and improve the efficiency of analyzing NCES data in ways that benefit the education research community through its suite of tools, which are easy to use and available to all.
Let the #EdSurvey team know how it is doing on social media including Twitter and LinkedIn.