1. ## p vs. r

Sorry if this is a naive question, but its all a crash course for me...
I am running a bivariate correlation in SPSS on some data. The Pearson correlation comes out low (<.1) but p = 0.00. From what I know of r, less than .3 basically means no correlation, but a p < 0.05 means there is a relationship.
Where am I off?

2. ## Re: p vs. r

Your comments are generally correct. There is a discernible correlation, though you need to remember the pvalue does not tell you the size or direction of the correlation. Also with a large enough sample, small correlations can have small pvalues because sample sizes are usually in the denominator of the test statistic calculation.

3. ## Re: p vs. r

Originally Posted by leejones15
Sorry if this is a naive question, but its all a crash course for me...
I am running a bivariate correlation in SPSS on some data. The Pearson correlation comes out low (<.1) but p = 0.00. From what I know of r, less than .3 basically means no correlation, but a p < 0.05 means there is a relationship.
Where am I off?
It's simply a matter of practical significance verses statistical significance: For example see Roger Kirk's (widely cited) article published in Psychological Methods (1996): http://journals.sagepub.com/doi/abs/...64496056005002

4. ## The Following User Says Thank You to Dragan For This Useful Post:

bugman (04-08-2017)

 Tweet

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts