"The study of federal education initiatives that take place over multiple years in multiple settings often calls fror aggregating and comparing data -- in particular, student achievement data -- across a broad set of schools, districts, and states. The need to track the trends over time is complicated by the fact that the data from the different schools, districts, and states also may have been based on different measures of achievement. This paper suggests one approach for defining a common metric: calculating the standardized slope of a time-series of datapoints. The standardized slope can then serve as an "effect size statistic," student acheivement test results from different states can be considered equivalent to the findings from different "studies," and meta-analytic techniques can be employed."
PDFs can be opened with the free Adobe Acrobat Reader.
Comments