District Administration - March 2012 - (Page 68)

A CrystAl BAll for student AChievement Avoid Pitfalls of Predictive Analysis There are plenty of lessons in predictive analysis models, according to a 2011 white paper, “Worst Practices in Predictive Analysis,” by Information Builders, a company that focuses on enterprise business intelligence and Web reporting software solutions. Here is how to avoid them: • Determine the ROI. When planning to implement predictive analysis, consider the total cost and the anticipated return to ensure the maximum value is achieved. • Focus on bottom-line initiatives. Create models that provide forward-looking information to help solve specific problems, like a very low graduation rate, or to help achieve certain goals, like improving math performance in at-risk students. • Prepare the data correctly. Guarantee the most accurate possible results by ensuring all the data are properly accessed before the models are created and applied. • Evaluate the model without overevaluating. The model must be tested to ensure that it provides better decision-making capabilities over current analysis methods. • Share the results. The insights that result from the predictive analysis must be shared with everyone across the district, including teachers, counselors and parents. more affordable and accessible to people, San Jose Unified began developing its own rigorous predictive model to identify students at risk of failing. Developing this predictive model, named RAMP for Risk Assessment Management Protocol, was possible given the data warehouse. The warehouse was created by Follett Software Company’s TetraData. It now contains over 33 million records spanning 15 years of San Jose student history. Using a graduating cohort of seniors, the district’s warehouse expert worked with local statisticians to employ “logistic regression analyses” to determine which early data indicators at grades 8-10 predicted the likelihood of timely high school graduation, according to Assistant Superintendent Willis. The predictive model will enable administrators to monitor student progress and to identify students who appear to be at elevated risk of failing to graduate on time. The long-term objective is to significantly raise high school graduation and college completion rates. “These predictive models provide the distinct advantage of acting on data to prevent” students from failing, Willis says. “As school district budgets continue to be scaled back, particularly in California, our system must find a better way to distribute resources in a way that will dramatically improve student performance. We believe that predictive analytics may be a path to attaining that outcome.” SC RTIFIED HO OL R I S K MA NAGERS Online and classroom risk management courses for schools and universities Reduce Losses Protect Assets Protect Budgets Save Jobs $149 Online courses $179 Classroom courses 3809 0112 CE Learn more at www.TheNationalAlliance.com or call 800-633-2165 68 March 2012 District Administration http://www.TheNationalAlliance.com

Table of Contents for the Digital Edition of District Administration - March 2012

District Administration - March 2012
Contents
From the Editor
Letters
News Update
Inside the Law
District Profile
Administrator Profile
Research Center
CIO News
Building an Ed Tech Dream Team
Are you Ready for Common Core Math?
A Crystal Ball for Student Achievement
The Single Largest Education Donor Comes With Controversy
Models of Education Reform
Noteworthy Books
New Products
Going Mobile
Professional Opinion

District Administration - March 2012