This occurs due to the constitutional heterogeneity of the material (the fact that gold particles are different from quartz particles). Engineers use statistics to determine the minimum sample mass required to keep this error within acceptable limits.
$$ (X - \hatX)^T V^-1 (X - \hatX) $$
This is the specific branch of statistics developed for the mining industry to estimate reserves based on sparse drill hole data. Statistical Methods For Mineral Engineers
Recovery is a proportion between 0 and 1. Linear regression can predict values outside this range ($>100%$). models the log-odds of recovery: This occurs due to the constitutional heterogeneity of
Statistical Methods for Mineral Engineers is the title of a highly regarded book by Professor Tim Napier-Munn , published through the Julius Kruttschnitt Mineral Research Centre (JKMRC) Statistical Methods For Mineral Engineers