Associating Variables

The Pearson product moment is a parametric statistic used when both variables are at least approx normally distributed (ie. scale data). when you have ranked data or when other assumptions are markedly violated, one should use a nonparamtric equivalent of the Pearson correlsation coefficient. One such nonparametric, ordinal statistic is Spearman's rho.

Both types of correlations can vary from -1.0 (a perfect negative relationship or association) through 0.0 (no correlation) to +1.0 a perfect positive correlation. Note that +1 and -1 are equally high or strong, but they lead to different interpretations.

- The correlation coefficient tell us the strength with which the two variables are asociated or related.

- r squared signifies the percentage of variance in common between the two variables.

- The Pearson correlations have somewhat higher values than the Spearman correlations, but they have similar sıgnificance/p levels. Usually the Pearson r is somewhat more powerful.

- İf one or both of the variables are clearly ordinal data, we would use the Spearman rho.








Statistical technique for comparing two or more independent groups on the central tendency of the dependent variable is called one-way ANOVA in SPSS, which compares the means of the samples or groups in order to make inferences about the population means. As with the t test, ANOVA assumes that the dependent variable is scale data (ie approx. normally distributed in the population) and the variances of the groups are equal. One-way ANOVA is also called single factor analysis of variance, because there is only one independent variable. the answer to the question - why would one compute a t test when one-way Anova (F) can be used to compare two groups as well as three or more groups? Because F= t 2, provide same with the same information, and the output looks very similar. Thus the choice is the matter of preference. However, t tests can be either one tailed or two tailed, while ANOVAs are always two tailed. Thus, with clear directional hypothesis predicting which group will have the higher mean, one may want to use a t test rather than one-way ANOVA when comparing two groups.



SPSS for Windows, Lawrence Erlbaum Asso, Publishers, New Jersy