"Parse Tree" <parsetree at hotmail.com> wrote in message
news:gj529.2150$9g7.421107 at news20.bellglobal.com...
> "Bob LeChevalier" <lojbab at lojban.org> wrote in message
> news:i1mhkugkvkveqhjlbsfjr5bo4jaduimbqh at 4ax.com...> > "Parse Tree" <parsetree at hotmail.com> wrote:
> > >> The larger the sample size, the smaller the deviation from 25%.
TIMSS
> was
> > >a
> > >> large enough sample size that a 3% standard error is conservative.
> > >
> > >I don't know the size of the sample. Was it 10 000?
> >
> > For the 12th grade math questions, N for the US was 2795. Only 2
> > other countries had a sample size over 2000, and Cyprus had the
> > smallest sample at N=190.
>> Ha ha ha!! That's not really big enough to get an accurate picture.
>> I assumed that it was simply given to every student in the country that
was
> of the required grade.
>>
You "assumed" what?
Not only are your assumptions dead wrong, but so are your conclusions, and
analysis, and for that matter, your entire participation in this forum.
2,795 is MORE than enough American students to get a plus or minus 3%
standard error, which means that you just proved that you know less than
nothing about probability and statistics.
With the difference between us and Singapore being 143 points, the minimum
difference, even if both countries were at the tail ends of that 3%, is
still more than 120 points. And the probability that this happened is
essentially zero. The only ranking that might be questioned is with the
countries which scored within plus or minus 3% of us at the 8th grade level,
except that most of those who participated in the 12th grade test scored
MUCH higher at that level
http://christianparty.net/timss8thv12thmechanics.gif
This study is as objective and fair as it can be. It's not easy for entire
countries to cheat on a study like this, because there are so many ways for
them to get caught if they even try, just as Israel got caught. We ranked
just as low on the 1999 TIMSS study as we did on the 1995 study, and as we
did on IAEP http://christianparty.net/iaep.htm
John Knight
