- The method has a good intuitive foundation. The underlying concept is that the best estimate of a parameter is that giving the highest probability that the observed set of measurements will be obtained.
- The least-squares method and various approaches to combining errors or calculating weighted averages, etc., can be derived or justified in terms of the maximum likelihood approach.
- The method is of sufficient generality that most problems are amenable to a straightforward application of this method, even in cases where other techniques become difficult. Inelegant but conceptually simple approaches often provide useful results where there is no easy alternative.

- 4.1 Basis
- 4.2 Applications
- 4.2.1 Weighted averages
- 4.2.2 Mean of the Poisson probability distribution function
- 4.2.3 Mean of the binomial probability distribution function
- 4.2.4 An example: Fitting to CCN measurements
- 4.2.5 Maximum-likelihood estimation in cases with correlated errors
- 4.2.6 Estimating exponential-decay time constants
- 4.3 Application to experimental design
- 4.4 Relationship to the method of least squares

To download a Postscript version of Chapter 4, click here. | To download an Adobe Portable Document Format version, click here. |

http://www.asp.ucar.edu