I'm bad at probability and statistics, please understand. Suppose we are writing a multiple choice test, with say 100 questions. Now each question have 4 options to choose from, out of which only 1 is correct. Now we guess on each question, a complete guess. I mean we don't even read the question or look at any of its answers. What is the best way to go, mark the same option for each question (all A's for example) or randomly pick each option?

  • $\begingroup$ There is no best strategy with these information. You need more information: for example if you know that your professor has a fetishism for first options, maybe the best thing to do is choosing always the first option. $\endgroup$ – Crostul Apr 7 '16 at 10:15
  • $\begingroup$ lol, thats what I thought, but it's good to be sure $\endgroup$ – Rockstar5645 Apr 7 '16 at 10:17

If the distribution of answers (A, B, C & D) is uniform (which is generally the case in tests), then both options (marking the same, or randomly) will give the same result :

for each question, you have a probabilty of 0.25 to find the correct answer. Thus you will have 25 overall points in average to the test.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.