ENVX1002 Lecture Notes - Lecture 11: Standard Deviation
Document Summary
No matter how carefully any measurement is made, it could have turned out differently. Individual measurement = exact value + chance error. The best way to estimate the chance error is to replicate the measurement under the same conditions, and calculate the standard deviation. In any large enough series of careful replicated measurements, we expect to see a small percentage of extreme measurements called outliers. One common convention to define outliers as measurements more than 3. Bias is a constant amount added to or subtracted from each measurement. Bias cannot be estimated by replicating the measurements. Individual measurement = exact value + chance error + bias. Any measurement could have turned out differently due to chance error, and any bias.