GraphPad Statistics Guide

Asterisks

Asterisks

Previous topic Next topic No expanding text in this topic  

Asterisks

Previous topic Next topic JavaScript is required for expanding text JavaScript is required for the print function Mail us feedback on this topic!  

Once you have set a threshold significance level (usually 0.05), every result leads to a conclusion of either "statistically significant" or not "statistically significant". Some statisticians feel very strongly that the only acceptable conclusion is significant or 'not significant', and oppose use of adjectives or asterisks to describe values levels of statistical significance.

Many scientists are not so rigid, and so prefer to use adjectives such as “very significant” or “extremely significant”. Prism uses this approach as shown in the tables below. These definitions are not entirely standard. If you report the results in this way, you should define the symbols in your figure legend.

Prior to Prism 7,  the scheme below was always used. Now it is used if you choose GP formatting or if you ask for four or more digits after the decimal point.

P value

Wording

Summary

< 0.0001

Extremely significant

****

0.0001 to 0.001

Extremely significant

***

0.001 to 0.01

Very significant

**

0.01 to 0.05

Significant

*

≥ 0.05

Not significant

ns

If you choose APA or NEJM formatting for P values, Prism uses this scheme (note the absence of ****).

P value

Wording

Summary

< 0.001

Very significant

***

0.001 to 0.01

Very significant

**

0.01 to 0.05

Significant

*

≥ 0.05

Not significant

ns

Prism stores the P values in double precision (about 12 digits of precision), and uses that value (not the value you see displayed) when it decides how many asterisks to show. So if the P value equals 0.05000001, Prism will display "0.0500" and label that comparison as "ns".

Decimal formatting of P values.