A researcher computes sample correlation coefficients r1, r2, r3 and r4 from four different samples and obtains 0.97, 0.95, 0.10 and 0.03 respectively as their p-values. The correlation coefficient significant at the 5% level is:

A correlation is significant at the 5% level when its p-value is below 0.05, which only r4 with 0.03 satisfies.

The p-value gives the probability of the observed result under the null hypothesis of no correlation.

r1 with p equal to 0.97 is far above 0.05, so its correlation is statistically non-significant.

r2 with p equal to 0.95 likewise fails to reject the null hypothesis.

r3 with p equal to 0.10 stays above the 0.05 cut-off and remains non-significant.

A smaller p-value, not a larger correlation value, marks stronger evidence against the null.