Informally this refers to personal fairness, but within statistics it also has a more formal meaning. We say an estimate is unbiased if the long term or theoretical average of the estimate is the true value of the real world thing it is trying to measure. For example, if we want to know the average height of someone in Malaysia, we might randomly sample 1000 people from Malaysia and then take the arithmetic mean (μ) of the measured heights. It turns out that the sample mean is an unbiased estimator of the population mean. For any given sample of 1000 people this might be slightly more, or slightly less than the true national average, but if one were to take many such samples the average value of the sample average would be the true average!

Used on pages 29, 30, 36, 37