Margin of Error:
A margin of error typically refers to a range within which an unknown parameter is estimated to fall, given the variation that can arise from one sample to another. For example, in an opinion survey based on a randomly-drawn sample from a larger population results are usually stated along with a margin of error, also called a confidence interval, that (say) 95% of the time will include the "true" value (i.e. the value you would get by surveying the entire population). It is important to note that most margins of error assume that the sample is drawn randomly; if the sample is not drawn randomly the estimate based on the sample will likely be in error more often than the nominal level of confidence (typically 90%, 95% or 99%).