> These elections in Russia that we analysed using this method were fraudulent - as proved by the method.

Not "as proved by the method", but "as proved by the science of statistics". So let me fix it for you:

a) This method can identify fraudulent elections, because it's scientifically correct.

b) These elections in Russia that we analysed using this method were fraudulent - as proved by the science of statistics.

FYI, the paper was published in "Annals of Applied Statistics", which is a peer-reviewed journal.