1
$\begingroup$

In one of the articles I found such a statement:

The significance of the correlation coefficient was then verified using Student's t test for independent variables

Is this incorrect or did I miss something?

$\endgroup$
  • 1
    $\begingroup$ We'd need some context to understand what the author meant. $\endgroup$ – Harvey Motulsky Nov 3 '14 at 13:42
1
$\begingroup$

If I understood your question correctly, the author in question was testing for a significant difference of $r$ from 0. Given $r$ as the Pearson product-moment correlation coefficient, you can then use a $t$ distribution with $N-2$ degrees of freedom for small samples, or a $Z$ distribution for large sample sizes to asses the claim that $r$ is significantly different than 0. For this, $H_0$ is that $r=0$, and $H_1$ is that $r\ne0$. Hope that helps a little.

Further reading:

Correlation Analysis and Regression - York U

Correlation - Arizona State

Penn State

| cite | improve this answer | |
$\endgroup$
1
$\begingroup$

It is badly worded. Obviously, you can test the significance of the correlation coefficient using a t-test. And the null hypothesis of this test is normally that the correlation coefficient is zero, i.e, the two variables are independent. But it is of course not the t-test for the equality of means with independent variables.

| cite | improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.