By entering the data (-yi, -xi) followed by (-yi-xi), one can obtain an intercept-free regression Y = Xβ + ε from a program package that normally uses an intercept term. There is no bias in the resultant regression coefficients, but a minor postanalysis adjustment is needed to the residual variance and standard errors.
Bibliographical noteFunding Information:
If X" ... , X n are identically and independently distributed, then as n --> 00, there exists under suitable regularity conditions a sequence of solutions of the likelihood equation that is consistent and asymptotically efficient. However, this consistent solution is not necessarily the maximum likelihood estimate. Likelihood estimation should therefore emphasize the determination of a consistent sequence of * ~.L. Lehmann is Professor of Statistics, University of California, Berkeley, CA 94720. This article was prepared with the support of National Science Foundation Grant MCS76-1-238 and Office of Naval Research Contract No. N-14-75-C-0444/Nr 042-036.
- Multiple regression
- Program packages