How do I get by with Excel?
Determine a model that fits observed data as closely as possible

The question of the significance of coefficients is dealt with by statisticians, but is often overlooked. In the linear case, it relies on a Fisher test (see Some common hypothesis tests [FIC 1439] ), which compares the estimated values of the parameters with a priori values, taking into account the associated uncertainties and their covariances. Although not insurmountable, this test is not trivial and requires a few calculations. The bibliography refers to documents dealing with this issue. The CFM guide also deals with this issue from...