Calculating the coverage factor (k)

Hi all.

Wondering if anyone can shed any light on this.
I am trying to find a formula that I can use on our uncertainty budget when there is a single dominant Type B input.
In this case it is for torque when there is course resolution.
I am referring to the UKAS M3003 document appendix C.
There is a table that allows you to work out the new coverage factor but there doesn't appear to be a formula.
In appendix B there is a formula but this doesn't appear to work in this case.
Hoping someone can help.

Cheers.