Table Of Contents
Steepest Ascent With Reset - DRAFT VERSION

Overview

In situations where the steepest ascent algorithm fails to yield a significant improvement in the log likelihood function, the user has the option of specifying that the algorithm reverts to taking a Newton-Raphson step. This optimization method is known as the Steepest Ascent with reset.

References

Cohen, J. (1997). An Overview of AIR’s Direct Estimation Software for Marginal Maximum Likelihood Models. Washington, DC: American Institutes for Research.