Please register to participate in our discussions with 2 million other members - it's free and quick! Some forums can only be seen by registered members. After you create your account, you'll be able to customize options and access all our 15,000 new posts/day with fewer ads.
I think this is great data---but am wondering, are the results statistically skewed if the size of the population of students is different?
For example, if school A has 100 seniors but school B has 500---how is that taken into account to ensure the "view" is accurate? I ask because I looked at the same data, but got that argument back from somebody else......
it's an average. so the school that has 100 seniors adds up each individual student's score and divides the total by 100 while the total score of the larger school would be divided by 500.
I'm a numbers guy and I still think this is the fairest way to compare schools. All the other formulas and what not are flawed. The NJ Monthly list is ridiculous and simply a ploy to sell magazine, increase web traffic, and give boards like this something to argue over, further spreading their brand as reliable source for ranking things. SATs have been, and will continue to be, the biggest thing colleges look at when deciding whether to accept a student. Thanks for compiling.
Last edited by Goldendoodle1969; 12-08-2011 at 08:24 AM..
it's an average. so the school that has 100 seniors adds up each individual student's score and divides the total by 100 while the total score of the larger school would be divided by 500.
I totally get that it's an average.....
However, comparing averages against other averages are only statistically valid if the sample sizes are around the same. That's one of the uses of weighted averages--which is to attempt to create a true comparison.
My understanding --and it makes sense to me--is that the wider the gap between sample sizes, the less reliable the comparative results can be because the error margin increases to unacceptable levels. I will try and research this further....
Having said that, I did look at SAT averages and I found it to be a useful data point....not to rank schools, necessarily, but rather as a predictor of what the school is churning out. It is still useful data to have--however, I would not rely on these "rankings" because, statistically speaking, I believe the methodology is flawed. I think that's the crazy rationale behind the NJ Monthly, US Weekly methodologies. Of course--I don't find their formulas much better. In the end, the best thing to do is think about what kind of kid you have and try to match the data to their need. Certainly a high SAT average is a useful thing to know.
Let me see if I can research the point further and get back to you.
"A Word About Comparing States and Schools
Media and others often rank states, districts and schools on the basis of SAT scores despite repeated warnings that such rankings are invalid. The SAT is a strong indicator of trends in the college-bound population, but it should never be used alone for such comparisons because demographics and other nonschool factors can have a strong effect on scores. If ranked, schools and states that encourage students to apply to college may be penalized because scores tend to decline with a rise in percentage of test-takers."
To Tahiti's point: there are demographic and other factors that influence aggregate and average SAT scores in particular districts. Additionally, the scores tend to decline with a rise in percentage of test-takers......
I don't know if that addresses my point or if this means I was right, by the way. They don't say anything about it being statistically unsound to compare different sample sizes. Instead, they point out that there is a difference in the percentage of students who may opt to take the test--and that is the significant wrench in the comparison because you are not comparing apples to apples.
I still don't know if comparing 100 to 1000000 on an average alone is a proper survey method--and I think I want to take a class in stastics. Most fascinated by the subject.... :-)
"A Word About Comparing States and Schools
Media and others often rank states, districts and schools on the basis of SAT scores despite repeated warnings that such rankings are invalid. The SAT is a strong indicator of trends in the college-bound population, but it should never be used alone for such comparisons because demographics and other nonschool factors can have a strong effect on scores. If ranked, schools and states that encourage students to apply to college may be penalized because scores tend to decline with a rise in percentage of test-takers."
To Tahiti's point: there are demographic and other factors that influence aggregate and average SAT scores in particular districts. Additionally, the scores tend to decline with a rise in percentage of test-takers......
I don't know if that addresses my point or if this means I was right, by the way. They don't say anything about it being statistically unsound to compare different sample sizes. Instead, they point out that there is a difference in the percentage of students who may opt to take the test--and that is the significant wrench in the comparison because you are not comparing apples to apples.
I still don't know if comparing 100 to 1000000 on an average alone is a proper survey method--and I think I want to take a class in stastics. Most fascinated by the subject.... :-)
I agree that it is difficult to compare between schools on the basis of percentage of students who take the SAT which could skew the results a little bit but I don't think it would make too much of a difference but it would be interesting to see what percentage of kids take the SATs at each school nevertheless.
However, I think this is a better ranking than what NJ Monthly has..even if it was mostly due to plugging in the wrong number for % of kids going on to college for Princeton.
I'm a numbers guy and I still think this is the fairest way to compare schools. All the other formulas and what not are flawed. The NJ Monthly list is ridiculous and simply a ploy to sell magazine, increase web traffic, and give boards like this something to argue over, further spreading their brand as reliable source for ranking things. SATs have been, and will continue to be, the biggest thing colleges look at when deciding whether to accept a student. Thanks for compiling.
SAT scores is the best way to compare schools? I guess that might be true - but it's still a horrible way to measure schools. The college my sister went to doesn't even require students take the SAT or ACT, and it's a highly regarded liberal arts school.
there are so many other factors that you need to understand about a school beyond average SAT scores.
it's an average. so the school that has 100 seniors adds up each individual student's score and divides the total by 100 while the total score of the larger school would be divided by 500.
yeah, so the average of the population of 500 is statistically more significant than the average of the population of 100. but - there's not really a better way to do it without getting very complicated. in any statistical measure, the larger the population you're counting, the more meaningful the number would be.
Please register to post and access all features of our very popular forum. It is free and quick. Over $68,000 in prizes has already been given out to active posters on our forum. Additional giveaways are planned.
Detailed information about all U.S. cities, counties, and zip codes on our site: City-data.com.
Please register to participate in our discussions with 2 million other members - it's free and quick! Some forums can only be seen by registered members. After you create your account, you'll be able to customize options and access all our 15,000 new posts/day with fewer ads.
