mats_trash at hotmail.com (mat) wrote:
>> 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.
>>Did you pluck standard error out of the air? Standard error is only
>introduced when you average results and I see no evidence of that
>here, unless you are collating across yeargroups. Is there supposedly
>a 3% error in the reporting of test results? I find that hard to
>believe as they are likely read by computer and it would mean 3000
>students getting erroneous marks.
My suspicion is that he has glommed onto the 3% error that usually applies to
Gallup poll results based on their sample size, and he thinks that it applies
to every statistic known to man or concocted by nincompoop.
lojbab
