Estimation (or estimate) is the process of finding an approximation about a measure, that which is to be valued for some purpose is usable even if the input data may be incomplete, uncertain, or unstable. In the field of statistics, estimation implies »using the value of a statistic derived from a sample to estimate the value of a parameter corresponding to the population»; the sample establishes that the information can be projected through various factors, formally or informally, they are processes to determine a most likely range and discover the missing information. When an estimate turns out to be incorrect, it is called an “overestimate” if the estimate exceeded the actual result and an underestimate if the estimate fell short of the actual result.

The estimation is done by frequency sampling, (which is counting on a rather small number of examples), and projecting that number onto a larger population.

Estimates can similarly be generated by projecting the results of polls or surveys onto the total population; when making an estimate, it is more often than not that the goal is useful in generating a range of possible outcomes, and that quality is sufficient to be useful, but it is not necessary that it is likely to be wrong.

For example, when trying to guess the number of candies contained in a jar if fifty percent were visible and the overall volume of the jar about appeared to be twenty times as large as the volume container containing the visible candies, then a simple project measures that there were a thousand candies in the jar; such a projection, intended to collect the single value believed to be closest to the true value, is called a point estimate.

However the point estimate is likely to be wrong, because the sample size (in this case, the number of candies are visible), is too small a number to be sure that it does not contain anomalies that differ from the population as a whole; this concept corresponds to an interval estimate that captures a much wider range of possibilities, but is too wide to be useful.