A very crude approach would be to say “of all the women I’ve met, what proportion were caned at school”, with perhaps various caveats about age ranges, and use that to estimate the proportion of the population and therefore come up with a numerical answer.
Of course, there’s a great deal of uncertainty, but you could try to construct (say) a 95% confidence interval.
In any event, I could say for sure that at least three English women had been caned at school! And of course, it was pretty unlikely that the number was as few as three.
I can’t remember what my crude estimate was (and at the moment I can’t be bothered to look it up) but I have a feeling that it would have been tens of thousands.
Of course, this has no direct bearing on the question of whether the punishment was effective.