Parameter and Statistics

A parameter is a numerical value describing the entire population — the population mean, for instance — computed from every single observation in it. A statistic is the analogous value computed from a sample: a subset's mean, standard deviation, or variance, calculated only from the observations actually collected. Convention keeps the two visually distinct — parameters are written with Greek letters ($\mu$ for the mean, $\sigma$ for the standard deviation, $\sigma^2$ for the variance), while statistics use Roman letters ($\bar{x}$, $S$, $S^2$). …