In multiple choice, question 2, what did a larger sample size in an experiment improve? Validity, reliability, precision or uncertainty?
This is an interesting one - I would say that the correct answer is uncertainty, and here's why:
1. A larger sample size can improve validity - but if your larger selection still has the same sampling bias as your smaller sample size, then the experiment is just as invalid.
2. Reliability. See above. If you're still sampling the wrong kind of people, your results are just unreliable
3. Precision, is where it gets interesting... You see, in some sense, precision and uncertainty go hand in hand. I've opted for precision to be incorrect because past, individual experiments can be just as imprecise.
4. Uncertainty, however, is kind of an average of the precision - and uncertainty HAS to go down if you increase the number of experiments, even if the new tests are just as imprecise as the previous ones, because that's the nature of uncertainty - repeat results give you more confidence for them to keep repeating.
But this is a tricky one, and I wouldn't be surprised if VCAA has a different stance - I could reasonably see all of these being improved by an increase in sample size, so we'll just have to wait and see what VCAA says. And who knows, maybe they'll decide in hindsight that this was too ambiguous, and give multiple answers a mark (this has been done in the past, though I don't remember the exact question - just that it was in my specialist exam, back when I took the subject)