"Bob LeChevalier" <lojbab at lojban.org> wrote in message
news:t0jnjusa3s0ndrh1cnq9jtq4im8rgmfasb at 4ax.com...
> "John Knight" <johnknight at usa.com> wrote:
> >> What part of "less than zero percent of American girls got the correct
> >> answer" did you NOT intend, and how does it make any sense, so matter
how
> >> much you "adjust it for guesses"?
> >>
> >
> >Let's try to break this down into real simple pieces so American 12th
grade
> >girls may be able understand it.
> >
> >If you have a red straw, a green straw, a blue straw, and a white straw,
and
> >you ask a student to pick one at random, then if they pick it randomly,
the
> >probability of picking the red one is 0.25, and the green one is 0.25,
and
> >the blue one is 0.25, and the White one is 0.25.
> >
> >If you put all four straws back in your hand and ask them to pick them
> >randomly again, the probability is the same thing again. If you do it
two
> >more times, then the overall probability of picking each color is 1.0: a
> >red one = 1.0, a green on = 1.0, a blue one = 1.0, and a white one = 1.0.
>> Let's break this down in real simple pieces so a 1st grader could
understand.
>> NO! YOU ARE WRONG! BAD JOHNNY! Go sit in the corner with the pointy hat!
>> You don't know what you are talking about. You don't know how to
calculate
> probability. One is tempted to think that you don't know what probability
> means.
>> Lest you need an example, the probability when flipping a coin randomly is
.5
> for heads and .5 for tails. It is NOT the case that if you flip a coin
twice
> that the probability is 1.0 that you will get heads once. If you doubt
this,
> then try flipping coins twice several times. If the probability is indeed
> 1.0 that you will get heads once, then that means that in EACH pair of
flips,
> EXACTLY one of the two flips will be heads.
>> This will NOT happen, unless you have truly exceptional luck. Sometimes
you
> will get two tails and NO heads, sometimes you will get TWO heads and no
> tails, and sometimes indeed you will get 1 head. Roughly half the time in
> fact.
>> >This doesn't mean that this is exactly what you'll get on the first
set--but
> >if you were to do this a million times, you would have 250,000 red,
250,000
> >green, 250,000 blue, and 250,000 white, IF the student actually picked
the
> >straws at random.
>> If the probability was 1.0 for each color in 4 drawings, then that means
that
> EVERY time, without fail, you drew 4 straws at random, you would get
exactly
> one of each color. That is what a probability of 1.0 means.
>> My best guess it that you are confusing "probability" with some perversion
of
> the concept called "expected value". But you'd have to learn the
difference
> before it would be worthwhile exploring whether that was what you were
> talking about. I don't propose to teach you basic probability theory. Go
> back to school or read a book (or even a good internet site if you don't
know
> what a book is).
>> >What bias do American 12th grade girls have against so many correct
answers?
>> What bias do you have against learning something about what you are
talking
> about? Like basic probability theory. Like maybe the answer to H04 and
how
> those girls (and boys) were supposed to figure it out. Right now you are
> demonstrably dumber than a 12th grade girl.
>> lojbab
Now we know what's wrong with "liberals", don't we? You "think" you're so
smart, but you're stupider than door knobs. You are DEAD WRONG, and maybe
now you know why--you don't have a clue about what "probability" even means.
So let's make it REAL simple. Let's define a simple statement of the
problem.
If you have 100,000 students *randomly guessing* at one multiple choice
question which has four possible answers (A., B., C., and D.), one of which
must be selected, then there is only ONE possible outcome:
A. gets selected 25,000 times.
B. gets selected 25,000 times.
C. gets selected 25,000 times.
D. gets selected 25,000 times.
Unless the correct answers are not distributed evenly across A., B., C. and
D. (i.e., unless the test designers didn't assign the correct answers
randomly), then there is NO other possible outcome (except for an initial
minor variation from these figures which would eventually even out over
time).
If the correct answer is B., and this answer is selected by 25,000 girls,
then you have zero evidence that they properly applied the theories to
resolving the problem. If they selected this answer 25,750 times, you still
have no evidence that they understood the principles, or could apply them,
because such a score would be lower than the 3% standard error. If they
selected this answer 30,000 times, you are just barely higher than the
combination of the 25% multiple choice guesses and the 3% standard error,
which starts to make the score meaningful.
BUT--if they selected this answer only 20,000 times, then you have evidence
that some of them were *misled*, somehow, somewhere, along the way.
If you *dispute* this statement of the problem, then post what you believe
to be the *correct* statement, and quit confusing yourself with probability
theory which you could never hope to grasp.
John Knight
