Girls want iPhones, Boys want PS4 this holiday

[fatslob-:O]

famousringo said:

fatslob-:O said:
The thing about making surveys more accurate are the amount of samples. If you have too little samples your poll is inaccurate and therefore can not be used to represent statistical evidence. When you start to have over 10000 samples and maybe even 50000 a survey will start to become more accurate and will converge to the correct statistics.

Actually a sample size of merely 1,000 people can draw pretty accurate conclusions for a population of almost any size. The biggest challenge in stats isn't getting a bigger sample, but in getting a more representative one. Did you only survey people with a landline phone? An internet connection? All urban dwellers? You wanted kids 12-17, but were most of them 15 and up?

This page does a nice job of explaining it:

http://www.dfrank.com/samplesize.htm

Generally, samples of 1,000 are well regarded for national surveys. (The layman, however, might be critical of samples of 1,000 or 2,000 considering an adult population of 180 million or so – particularly when their favorite TV show is threatened with cancellation because of poor ratings.) The key to good research, however, is not sample size so much as it is getting representative samples. Even if we survey 100,000 people and they are not representative of our target market (let's say they are all university students and we are investigating washing detergent purchases) then sample size means nothing. Therefore, in research investigations, whenever possible, use random sampling procedures with controls in place to insure our target market is properly represented.

You learn something everyday then. To add I had also thought it would have needed a demographic constraints. Thanks for sharing me more info.