Originally posted by erikthewise
[lecture mode]
The results of a survey of this type will have little if any statistical validity due to the strong likelihood of "participation bias". This means that people choose whether or not to participate, and this choice is not likely to be random. In order to draw accurate conclusions about a population from a sample of limited size, the sample must be chosen in an absolutely random way.
For example, people who feel strongly about discounted passes are more likely to respond to this survey, and the responses of those people are probably not representative of all DVC members.
[/lecture mode]
Does this mean the survey is worthless? Of course not. It's just that the results may not be as accurate as you'd like. But if it's the best you can do on a small budget, you may as well go with it.