We consider two types of problems in maximum likelihood estimation of parameters of linear functions subject to certain restraints. One is a family of lines with equal slopes or intercepts; the other is a pair of lines constrained to meet at a predetermined point. In the case of normally distributed errors with equal variances within each set, the solutions are identical with least squares solutions. In addition to linear functions, non-linear functions which are transformable to linearity may be treated under these methods.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License
Minton, Paul D. and Crofts, Alfred E. Jr.
"The Estimation of Parameters in Regression Functions Subject to Certain Restraints,"
Journal of the Graduate Research Center: Vol. 29:
1, Article 2.
Available at: https://scholar.smu.edu/journal_grc/vol29/iss1/2