Does anyone know how the validity of a linear extrapolation is determined? I mean is there a standard way of measuring an extrapolation, like sigma? The only way I can think of is to take the ratio of the sample with the population. For instance, if sample = 24 and population = 200 billion, their ratio is 0.00000012. How do we know if this is a valid linear extrapolation? In this case, sample is the number of galaxies Hubble observed in 1929 for his famous paper and the population is the number of known galaxies. Is there a rigorous way to evaluate an extrapolation in statistics?