The method of quasilikelihood

Abstract

The methods of “ Maximum Likelihood ” (ML) and “ Least Squares” (LS) are two central methods in the theory of inference. They have being developed and studied for a long time, and they still play an important role in statistics. However, as time goes on, more and more understanding of natural phenomena has been obtained and more diverse requirements have been introduced into statistical practice. Sometimes those phenomena and requirements cause some difficulties in the use of the ML and LS methods. Therefore statisticians have to look in detail into the advantages and weaknesses of each of the methods.