At 11:54 AM 2/4/2003, Simon, Steve, PhD wrote:
but, stability of tests scores is NOT like balancing a table ...Think of a table with the legs close to the center. It is unstable. Push the legs out a bit and it becomes more stable.
stability in a measurement sense means that for EACH score ... we have greater "faith" that it is close(er) to the true score ... that certainly canNOT be the case when you have no middle ... in fact, you have lost ANY information about the stability of the mid scores
hmmm ... unfortunately, a person thin as a rail can eat pasta alfredo ... and, a person who is very heavy can eat tofu ...I visualize fat consumption fairly easily. The top quintile eats things like pasta alfredo and the bottom quintile eats things like tofu.
of course, why ANYbody would eat tofu is beyond me!
For the sake of argument, let's say that the top quintile consumes 45% or
more of calories from fat and the bottom quintile consumes 15% or less of
calories from fat. I am interested in the probability of a heart attack in a
five year period. When we compare the top and bottom quintile and get an
odds ratio of 2.4, which tells us that people who consume 45% of the
calories from fat are much more likely to have a heart attack than people
who consume 15% or less of calories from fat.
i guess i am fussing about the use of the term ... "visualize" ... i am not sure what the visual IS in this context ...Compare that to the odds ratio computed on a continuous scale. It would probably be around 1.03, which tells us that each extra percentage of calories from fat in the diet will be associated with an increase of about 3% in the odds of a heart attack. Both interpretations are reasonable, but I find the first one a bit easier to visualize.
if you are saying that people can understand that 15% is more than 3% ... sure ... i think on the other hand they can just as easily see that there is not as much difference between 5% and 3% ... so, in the context you are raising it ... eliminating the middle ... i don't really see the point you are trying to make
depends on how you categorize the data and which side you happen to be onSuppose someone reports their fat consumption as 50% and it is actually 55%. If you categorize the responses, the measurement error disappears entirely for that person. A few people who are close to the boundary are misclassified, so dichotomization doesn't completely solve the problem.
what if you report 53% when you are really 49% and ... the cut point is 50% between good and bad ... we have maximum error ... reducing categories will NOT improve the precision
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
. http://jse.stat.ncsu.edu/ .
=================================================================
