Reliability Explorer
Comparing children by their accuracy within a window only works if that measure is reliable, and reliability depends on the window chosen. For a grid of analysis windows, your browser computes split-half reliability. Each child’s trials are split at random into two halves, the half means are correlated across children, and the result is Spearman-Brown corrected.
Loading data…
The grid covers windows starting from −500 to 1500 ms and ending from 1000 to 4000 ms. Cells with too few children (< 8 usable) are blank. The × marks the grid cell nearest your window.