I have corrected my alpha level using Šidák correction to take into account the experiment-wise error rate, as I am doing multiple correlation tests using the same data set.

My new alpha is 0.00056.

I tried using SPSS but the p threshold (alpha) seems to be either 0.01 or 0.05 and the p value of the correlation is given only in three decimal places.

For example, SPSS returns the p value of one of my correlations as 0.000 and indicated it is significant at 0.01. However, my p threhold is not 0.01 but 0.00056.

How do I determine if this correlation is significant? How do I work out the extact p value at 4 decimal points, which will then enable me to compare it with 0.00056. Is there an easy to use but reliable online calculator, or is this adjustment possible in SPSS?


Double-click the output table. Select the cells containing p-values. Right-click...Cell Properties...and adjust the number of decimal places.

  • 1
    $\begingroup$ Also, if memory serves, when SPSS does post-hocs it reports the p-values /after/ the adjustment has already been performed. $\endgroup$ – russellpierce Sep 6 '11 at 1:14

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.