"mat" <mats_trash at hotmail.com> wrote in message
news:43525ce3.0207220330.7633e4ae at posting.google.com...
> >
Obviously you were never taught probabilities and statistics.
>> Actually I have very good grades in math
>
Then what is it about this that you're having trouble even accurately
REPEATING what's already been written?
>> So you apply your 'analysis' when it suits the conclusions you wish to
> draw, given that it clearly leads to erroneous results at the
> extremes. Lets say that 10% of questions were answered correctly, this
> means that 90% guess incorrecly and thus, by your method, that 120% of
> people guessed (90 = 0.75x where x is the number of guessers..) God
> knows how many people actually take the test! So you see at any
> percentage below 25, caluclating the 'correct guessers' from the
> number of incorrect answers will surely lead to a number of guessers
> greater than the number taking the test. I hope you will conclude
> that that is idiotic. Given then that 22.8% (<25%) of american girls
> answered correctly, your analysis is meaningless as it will lead to a
> contradiction, namely that more people guessed answers than took the
> test. doh.
>
If students selected more wrong answers than if they'd just guessed, then
you can't use this formula to estimate how many guessed, because this is
evidence that many of them did NOT just guess. It means that many students
had to know enough about the problem in order to consistently get it wrong.
The problem in this event is not how to adjust for guessing--the problem is
how to explain why they scored so much lower than if they'd just guessed.
If it's a 4 choice question, and 25% of them got it right, and if the
responses were evenly distributed across all 4 possible answers, then you
have evidence that 25% just guessed, not that they demonstrated any
knowledge of the problem
The only time you can estimate how many guessed is when the score is real
low, but higher than if they'd just guessed. If 30% got a four choice
multiple choice question correct, only then can you assume:
X = total guesses
.25X = total correct guesses
.75X = total incorrect guesses = 70% (that is, 100% minus 30% correct)
X = 93 1/3%
.25X = 23 1/3%
% who knew problem = % who answered correctly - % who answered correctly
because they guessed = 30% - 23 1/3% = 6 2/3%
So when 30% of students get a four part multiple choice question correct,
you have evidence that 6 2/3% of them understood or could resolve the
problem.
John Knight
