# Computing Significance of Cumulative Improvement Between Test Variants

Given a test with two variants ($$A$$ and $$B$$), entrants of the test are randomly assigned into a variant with equal probability. A function exists to compute the score of any entrant $$i$$.

How can one compute the confidence that: the total scores of entrants in $$A$$ being greater than or equal to the total score for $$B$$ is significant?

• can you elaborate a bit more on this ... not entirely sure what the question is Nov 20 '20 at 14:59