"Jet" <thatjetnospam at yahoo.com> wrote in message
news:3D3A4550.977064EE at yahoo.com...
> > > You still have yet to address the conclusion that if 100% answer
> > > correctly no-one guessed and if 0% answer correctly then something
> > > very strange happens as the population taking the test suddenly
> > > increases by a third but their papers are somehow lost. As you might
> > > see from working with the latter case, your analysis does not hold.
> >
> > It's not clear what you're saying, but the last part of your statement
means
> > that it's obviously wrong--and it's ceretainly not consistent with the
> > original statement. Consider the two extremes:
> >
> > If zero percent get a four part multiple choice question wrong, then
they're
> > scoring 25% lower than if they'd just guessed, in which event might
conclude
> > that there's a high probability that they were taught the wrong thing if
> > everyone selected just one wrong answer. The other extreme is if 50%
get
> > the answer correct, and the rest of the answers are spread evenly over
the
> > other three answers, then this *is* an indication that 50% understood
the
> > problem
>> No, it's not you moron. Try to understand. The scores of those who
> randomly guessed would be spread evenly over all 4 answers, not just the
> incorrect ones.
>> 50/4=12.5. So, 62.5% would choose the correct answer, that is the sum of
> the 50% who understood it, and the 12.5% who made a lucky guess. 12.5%
> would choose each of the 3 remaining (incorrect) answers.
>> [50% guessed wrong, x = total percent who guessed, .25x = the total
> > number who guessed correctly, .75x = the percent who guessed
incorrectly, x
> > = 66.67 percent = total guesses, .25x = 16.7 percent = percent who
guessed
> > correctly, and .75x = 50 percent].
>> Now do you see why this is such bullshit?
>> J
Yup. The more you "think" about this, the worse your "logic" gets.
You didn't even bother to do a sanity check of your STUPID assumptions. It
was a given that 50% had the correct answer, but you inexplicibly changed it
to 62.5%. Why did you do that?
50% = GIVEN = percent of correct answers
X = total guesses
.25X = correct guesses
.75X = incorrect guesses = 50%
X = 66 2/3%
.25X = 16 2/3% = correct guesses
correct answers - correct guesses = knew the problem = 50% - 16 2/3% = 33
1/3%
So if all the guesses were evenly spread over all four answers (50%
incorrect guesses and 16 2/3 correct guesses) then three of them would have
been selected 16 2/3 % and one of them (the correct answer) would have been
selected 50% (16 2/3% who guessed correctly + 33 1/3% who knew the problem).
This is simple. But we already know that your next stab at it will be even
further off the mark, don't we?
John Knight
