Computing Correlations Within Respondents

The default methods in Q for computing Correlations are designed to compute the correlations between variables. It is possible to compute the correlations between sets of data within respondents using JavaScript Variables.

Two methods are available:

• Computing Correlations Within Respondents - Pearson's Correlation measures the strength of the straight-line relationship between the two sets of values. Use this when the values are numeric and evenly scaled.
• Computing Correlations Within Respondents - Spearman's Correlation compares the rank order of the two sets instead of the values themselves. Use this when the data is ordinal, or when outliers would distort a Pearson's correlation.

Example

Both correlations are illustrated in File:CorrelationJavaScript.QPack.