What question did this study set out to answer?

The aim is to provide a numerical solution for likelihood equations when working with incomplete data from exponential families.

An iterative method for solution of the likelihood equations for incomplete data from exponential families

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates an iterative solution for likelihood equations in incomplete data, implying better statistical analysis.

The aim is to provide a numerical solution for likelihood equations when working with incomplete data from exponential families.
Proposed a simple iterative method to solve likelihood equations.
Studied grouped and censored normal samples as illustrative examples.
Analyzed convergence properties of the iterative sequence.
Convergence of the iterates to a relative maximum of the likelihood function was achieved.
Convergence is geometric with a factor related to Fisher information loss.
Practical applications showed effectiveness of the proposed method.

Rolf Sundberg (1976) studied this question.

View Full Paper

Ask AI

Bookmark