Comparing Performance II: Parametric and Non-Parametric Analyses

Abstract

In the last chapter we ran a compare-means analysis and produced a scatterplot to investigate test takers’ performances on a reading and a listening test. The results showed that there was some evidence of a positive relationship between the two variables; in other words, as performance on one of the variables increased, so did performance on the other. What we were unable to determine with those two analyses, though, was whether any of the relationships or differences we found were due simply to chance rather than there being a real relationship or difference in the test takers’ performances. This was because the analyses we used simply described the data and could not go any further than that.