6.2.2. Pearson-Spearman-Kendall Correlations Matrix

This procedure computes the three most commonly used Correlation Coefficients (i.e. Pearson, Spearman, Kendall) for all combinations of column pairs selected from the Variables Available list. The output is in the form of a matrix in each cell of which up to three Correlation Coefficients, the number of cases and the probability values are reported. It is possible to display one- or two-tailed probabilities.

Columns to be analysed are selected from the Variables Available list by clicking on [Variable]. Selected columns do not need to have equal length. The program will consider each column pair separately and calculate the coefficients for only those pairs with equal number of cases. Matrix cells for columns with unequal lengths will be left blank. Also, the program will handle missing values for each pair of columns separately and omit the missing values pairwise.

An Output Options Dialogue will allow you to select which correlations to be displayed in the output.

Note that computing the rank Correlation Coefficients can be time consuming. When k columns are chosen from the data matrix, this procedure will compute 3k(k - 1)/2 Correlation Coefficients together with their tail probability values.

Example

Open CORRCOEF and select Statistics 1 → Correlation Coefficients → Pearson-Spearman-Kendall Correlations Matrix. Select Introversion, Attitude and Score (C5 to C7) as [Variable]s ad click [Finish].

Pearson-Spearman-Kendall Matrix